diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a446482603dfabcc56082e9b28446dcb3be42f05 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/conftest.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/conftest.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8cb99433fb19d8f2870e95018ff5b0cdbc95cbf5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/conftest.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_any_index.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_any_index.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..45ec69d8ff8c59ee9b027100eed71695fe533603 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_any_index.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_base.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_base.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d9367b830055fc703d4052c47cada22b61d00e2c Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_base.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_common.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_common.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9921b79f49da157ef4c3f0eaf04e8a933fcf8cfc Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_common.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_datetimelike.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_datetimelike.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6f8f65ca4fb493fc6305114afed0d165d9b86cf6 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_datetimelike.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_engines.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_engines.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eb18aa961e458dc0daecd04784d0e9ce27ce6831 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_engines.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_frozen.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_frozen.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1accbcdde0c81d2bd727fa869effb68987afc8b1 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_frozen.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_index_new.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_index_new.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4c51261a84fd56a45e2bf23196426020822e6a28 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_index_new.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8523aee3641c79daa34c60102812e5c938b0ac8d Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_numpy_compat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_numpy_compat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..96fae06f9a0e728c9f521496cf124827c0c76ed1 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_numpy_compat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_old_base.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_old_base.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..424e42688692a714cb1e40ee6145f1e997dafc04 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_old_base.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a45448a65f6f6d927932fc68633ab17dc4793968 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_subclass.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_subclass.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b9a8eb3d72d1e13808c3c38c39e8bc03903a25b5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/__pycache__/test_subclass.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..946dc9c252cbca9098feee34e29fb4cdae21b8cc Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c9a0e9ac26da3104fb37b23a0fbc2b05ec318e6e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_formats.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_formats.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bd1ef7374f945ff52c9a6104acad49493e242cb5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_formats.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eda07b693765a4497bf45ba80d28e0634336751e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_pickle.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_pickle.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..32fd1cfad5dd178b4af5961b412227fa07271471 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_pickle.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_reshape.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_reshape.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6ec04d5bf7f44e76c7727b7cf0b395c6aae21a9f Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_reshape.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f611c13f0aac62ed7da3b0269162b7ef7ef51d77 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_where.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_where.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..53682f69b2e72a065f21dc6e686ae5cc2ead261a Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/__pycache__/test_where.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..338509dd239e63f7fde17fe377a697429f1405e2 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_constructors.py @@ -0,0 +1,80 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + MultiIndex, + Series, +) +import pandas._testing as tm + + +class TestIndexConstructor: + # Tests for the Index constructor, specifically for cases that do + # not return a subclass + + @pytest.mark.parametrize("value", [1, np.int64(1)]) + def test_constructor_corner(self, value): + # corner case + msg = ( + r"Index\(\.\.\.\) must be called with a collection of some " + f"kind, {value} was passed" + ) + with pytest.raises(TypeError, match=msg): + Index(value) + + @pytest.mark.parametrize("index_vals", [[("A", 1), "B"], ["B", ("A", 1)]]) + def test_construction_list_mixed_tuples(self, index_vals): + # see gh-10697: if we are constructing from a mixed list of tuples, + # make sure that we are independent of the sorting order. + index = Index(index_vals) + assert isinstance(index, Index) + assert not isinstance(index, MultiIndex) + + def test_constructor_cast(self): + msg = "could not convert string to float" + with pytest.raises(ValueError, match=msg): + Index(["a", "b", "c"], dtype=float) + + @pytest.mark.parametrize("tuple_list", [[()], [(), ()]]) + def test_construct_empty_tuples(self, tuple_list): + # GH #45608 + result = Index(tuple_list) + expected = MultiIndex.from_tuples(tuple_list) + + tm.assert_index_equal(result, expected) + + def test_index_string_inference(self): + # GH#54430 + pytest.importorskip("pyarrow") + dtype = "string[pyarrow_numpy]" + expected = Index(["a", "b"], dtype=dtype) + with pd.option_context("future.infer_string", True): + ser = Index(["a", "b"]) + tm.assert_index_equal(ser, expected) + + expected = Index(["a", 1], dtype="object") + with pd.option_context("future.infer_string", True): + ser = Index(["a", 1]) + tm.assert_index_equal(ser, expected) + + def test_inference_on_pandas_objects(self): + # GH#56012 + idx = Index([pd.Timestamp("2019-12-31")], dtype=object) + with tm.assert_produces_warning(FutureWarning, match="Dtype inference"): + result = Index(idx) + assert result.dtype != np.object_ + + ser = Series([pd.Timestamp("2019-12-31")], dtype=object) + + with tm.assert_produces_warning(FutureWarning, match="Dtype inference"): + result = Index(ser) + assert result.dtype != np.object_ + + def test_constructor_not_read_only(self): + # GH#57130 + ser = Series([1, 2], dtype=object) + with pd.option_context("mode.copy_on_write", True): + idx = Index(ser) + assert idx._values.flags.writeable diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_formats.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_formats.py new file mode 100644 index 0000000000000000000000000000000000000000..f30b578cfcf566ac577d15a1bc15880bea5d7af0 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_formats.py @@ -0,0 +1,163 @@ +import numpy as np +import pytest + +from pandas._config import using_pyarrow_string_dtype +import pandas._config.config as cf + +from pandas import Index +import pandas._testing as tm + + +class TestIndexRendering: + def test_repr_is_valid_construction_code(self): + # for the case of Index, where the repr is traditional rather than + # stylized + idx = Index(["a", "b"]) + res = eval(repr(idx)) + tm.assert_index_equal(res, idx) + + @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="repr different") + @pytest.mark.parametrize( + "index,expected", + [ + # ASCII + # short + ( + Index(["a", "bb", "ccc"]), + """Index(['a', 'bb', 'ccc'], dtype='object')""", + ), + # multiple lines + ( + Index(["a", "bb", "ccc"] * 10), + "Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', " + "'bb', 'ccc', 'a', 'bb', 'ccc',\n" + " 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', " + "'bb', 'ccc', 'a', 'bb', 'ccc',\n" + " 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],\n" + " dtype='object')", + ), + # truncated + ( + Index(["a", "bb", "ccc"] * 100), + "Index(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',\n" + " ...\n" + " 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],\n" + " dtype='object', length=300)", + ), + # Non-ASCII + # short + ( + Index(["あ", "いい", "ううう"]), + """Index(['あ', 'いい', 'ううう'], dtype='object')""", + ), + # multiple lines + ( + Index(["あ", "いい", "ううう"] * 10), + ( + "Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', " + "'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', " + "'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう'],\n" + " dtype='object')" + ), + ), + # truncated + ( + Index(["あ", "いい", "ううう"] * 100), + ( + "Index(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', " + "'あ', 'いい', 'ううう', 'あ',\n" + " ...\n" + " 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう', 'あ', 'いい', 'ううう'],\n" + " dtype='object', length=300)" + ), + ), + ], + ) + def test_string_index_repr(self, index, expected): + result = repr(index) + assert result == expected + + @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="repr different") + @pytest.mark.parametrize( + "index,expected", + [ + # short + ( + Index(["あ", "いい", "ううう"]), + ("Index(['あ', 'いい', 'ううう'], dtype='object')"), + ), + # multiple lines + ( + Index(["あ", "いい", "ううう"] * 10), + ( + "Index(['あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ', 'いい', 'ううう'],\n" + " dtype='object')" + "" + ), + ), + # truncated + ( + Index(["あ", "いい", "ううう"] * 100), + ( + "Index(['あ', 'いい', 'ううう', 'あ', 'いい', " + "'ううう', 'あ', 'いい', 'ううう',\n" + " 'あ',\n" + " ...\n" + " 'ううう', 'あ', 'いい', 'ううう', 'あ', " + "'いい', 'ううう', 'あ', 'いい',\n" + " 'ううう'],\n" + " dtype='object', length=300)" + ), + ), + ], + ) + def test_string_index_repr_with_unicode_option(self, index, expected): + # Enable Unicode option ----------------------------------------- + with cf.option_context("display.unicode.east_asian_width", True): + result = repr(index) + assert result == expected + + def test_repr_summary(self): + with cf.option_context("display.max_seq_items", 10): + result = repr(Index(np.arange(1000))) + assert len(result) < 200 + assert "..." in result + + def test_summary_bug(self): + # GH#3869 + ind = Index(["{other}%s", "~:{range}:0"], name="A") + result = ind._summary() + # shouldn't be formatted accidentally. + assert "~:{range}:0" in result + assert "{other}%s" in result + + def test_index_repr_bool_nan(self): + # GH32146 + arr = Index([True, False, np.nan], dtype=object) + msg = "Index.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + exp1 = arr.format() + out1 = ["True", "False", "NaN"] + assert out1 == exp1 + + exp2 = repr(arr) + out2 = "Index([True, False, nan], dtype='object')" + assert out2 == exp2 + + def test_format_different_scalar_lengths(self): + # GH#35439 + idx = Index(["aaaaaaaaa", "b"]) + expected = ["aaaaaaaaa", "b"] + msg = r"Index\.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + assert idx.format() == expected diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..2988fa7d1baa1e0bc0f6cc4b6dc32e5d12f332cf --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_indexing.py @@ -0,0 +1,104 @@ +import numpy as np +import pytest + +from pandas._libs import index as libindex + +import pandas as pd +from pandas import ( + Index, + NaT, +) +import pandas._testing as tm + + +class TestGetSliceBounds: + @pytest.mark.parametrize("side, expected", [("left", 4), ("right", 5)]) + def test_get_slice_bounds_within(self, side, expected): + index = Index(list("abcdef")) + result = index.get_slice_bound("e", side=side) + assert result == expected + + @pytest.mark.parametrize("side", ["left", "right"]) + @pytest.mark.parametrize( + "data, bound, expected", [(list("abcdef"), "x", 6), (list("bcdefg"), "a", 0)] + ) + def test_get_slice_bounds_outside(self, side, expected, data, bound): + index = Index(data) + result = index.get_slice_bound(bound, side=side) + assert result == expected + + def test_get_slice_bounds_invalid_side(self): + with pytest.raises(ValueError, match="Invalid value for side kwarg"): + Index([]).get_slice_bound("a", side="middle") + + +class TestGetIndexerNonUnique: + def test_get_indexer_non_unique_dtype_mismatch(self): + # GH#25459 + indexes, missing = Index(["A", "B"]).get_indexer_non_unique(Index([0])) + tm.assert_numpy_array_equal(np.array([-1], dtype=np.intp), indexes) + tm.assert_numpy_array_equal(np.array([0], dtype=np.intp), missing) + + @pytest.mark.parametrize( + "idx_values,idx_non_unique", + [ + ([np.nan, 100, 200, 100], [np.nan, 100]), + ([np.nan, 100.0, 200.0, 100.0], [np.nan, 100.0]), + ], + ) + def test_get_indexer_non_unique_int_index(self, idx_values, idx_non_unique): + indexes, missing = Index(idx_values).get_indexer_non_unique(Index([np.nan])) + tm.assert_numpy_array_equal(np.array([0], dtype=np.intp), indexes) + tm.assert_numpy_array_equal(np.array([], dtype=np.intp), missing) + + indexes, missing = Index(idx_values).get_indexer_non_unique( + Index(idx_non_unique) + ) + tm.assert_numpy_array_equal(np.array([0, 1, 3], dtype=np.intp), indexes) + tm.assert_numpy_array_equal(np.array([], dtype=np.intp), missing) + + +class TestGetLoc: + @pytest.mark.slow # to_flat_index takes a while + def test_get_loc_tuple_monotonic_above_size_cutoff(self, monkeypatch): + # Go through the libindex path for which using + # _bin_search vs ndarray.searchsorted makes a difference + + with monkeypatch.context(): + monkeypatch.setattr(libindex, "_SIZE_CUTOFF", 100) + lev = list("ABCD") + dti = pd.date_range("2016-01-01", periods=10) + + mi = pd.MultiIndex.from_product([lev, range(5), dti]) + oidx = mi.to_flat_index() + + loc = len(oidx) // 2 + tup = oidx[loc] + + res = oidx.get_loc(tup) + assert res == loc + + def test_get_loc_nan_object_dtype_nonmonotonic_nonunique(self): + # case that goes through _maybe_get_bool_indexer + idx = Index(["foo", np.nan, None, "foo", 1.0, None], dtype=object) + + # we dont raise KeyError on nan + res = idx.get_loc(np.nan) + assert res == 1 + + # we only match on None, not on np.nan + res = idx.get_loc(None) + expected = np.array([False, False, True, False, False, True]) + tm.assert_numpy_array_equal(res, expected) + + # we don't match at all on mismatched NA + with pytest.raises(KeyError, match="NaT"): + idx.get_loc(NaT) + + +def test_getitem_boolean_ea_indexer(): + # GH#45806 + ser = pd.Series([True, False, pd.NA], dtype="boolean") + result = ser.index[ser] + expected = Index([0]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_pickle.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_pickle.py new file mode 100644 index 0000000000000000000000000000000000000000..c670921decb78808fa54a35c45e3d2d15ab57a67 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_pickle.py @@ -0,0 +1,11 @@ +from pandas import Index +import pandas._testing as tm + + +def test_pickle_preserves_object_dtype(): + # GH#43188, GH#43155 don't infer numeric dtype + index = Index([1, 2, 3], dtype=object) + + result = tm.round_trip_pickle(index) + assert result.dtype == object + tm.assert_index_equal(index, result) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_reshape.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_reshape.py new file mode 100644 index 0000000000000000000000000000000000000000..814a6a516904b6c31d3ef38fa91f23f69fa6ed7e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_reshape.py @@ -0,0 +1,95 @@ +""" +Tests for ndarray-like method on the base Index class +""" +import numpy as np +import pytest + +from pandas import Index +import pandas._testing as tm + + +class TestReshape: + def test_repeat(self): + repeats = 2 + index = Index([1, 2, 3]) + expected = Index([1, 1, 2, 2, 3, 3]) + + result = index.repeat(repeats) + tm.assert_index_equal(result, expected) + + def test_insert(self): + # GH 7256 + # validate neg/pos inserts + result = Index(["b", "c", "d"]) + + # test 0th element + tm.assert_index_equal(Index(["a", "b", "c", "d"]), result.insert(0, "a")) + + # test Nth element that follows Python list behavior + tm.assert_index_equal(Index(["b", "c", "e", "d"]), result.insert(-1, "e")) + + # test loc +/- neq (0, -1) + tm.assert_index_equal(result.insert(1, "z"), result.insert(-2, "z")) + + # test empty + null_index = Index([]) + tm.assert_index_equal(Index(["a"], dtype=object), null_index.insert(0, "a")) + + def test_insert_missing(self, nulls_fixture, using_infer_string): + # GH#22295 + # test there is no mangling of NA values + expected = Index(["a", nulls_fixture, "b", "c"], dtype=object) + result = Index(list("abc"), dtype=object).insert( + 1, Index([nulls_fixture], dtype=object) + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "val", [(1, 2), np.datetime64("2019-12-31"), np.timedelta64(1, "D")] + ) + @pytest.mark.parametrize("loc", [-1, 2]) + def test_insert_datetime_into_object(self, loc, val): + # GH#44509 + idx = Index(["1", "2", "3"]) + result = idx.insert(loc, val) + expected = Index(["1", "2", val, "3"]) + tm.assert_index_equal(result, expected) + assert type(expected[2]) is type(val) + + def test_insert_none_into_string_numpy(self): + # GH#55365 + pytest.importorskip("pyarrow") + index = Index(["a", "b", "c"], dtype="string[pyarrow_numpy]") + result = index.insert(-1, None) + expected = Index(["a", "b", None, "c"], dtype="string[pyarrow_numpy]") + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "pos,expected", + [ + (0, Index(["b", "c", "d"], name="index")), + (-1, Index(["a", "b", "c"], name="index")), + ], + ) + def test_delete(self, pos, expected): + index = Index(["a", "b", "c", "d"], name="index") + result = index.delete(pos) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + + def test_delete_raises(self): + index = Index(["a", "b", "c", "d"], name="index") + msg = "index 5 is out of bounds for axis 0 with size 4" + with pytest.raises(IndexError, match=msg): + index.delete(5) + + def test_append_multiple(self): + index = Index(["a", "b", "c", "d", "e", "f"]) + + foos = [index[:2], index[2:4], index[4:]] + result = foos[0].append(foos[1:]) + tm.assert_index_equal(result, index) + + # empty + result = index.append([]) + tm.assert_index_equal(result, index) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..3ef3f3ad4d3a20bd2e6303d781590396cbc00ae0 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_setops.py @@ -0,0 +1,266 @@ +from datetime import datetime + +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + Series, +) +import pandas._testing as tm +from pandas.core.algorithms import safe_sort + + +def equal_contents(arr1, arr2) -> bool: + """ + Checks if the set of unique elements of arr1 and arr2 are equivalent. + """ + return frozenset(arr1) == frozenset(arr2) + + +class TestIndexSetOps: + @pytest.mark.parametrize( + "method", ["union", "intersection", "difference", "symmetric_difference"] + ) + def test_setops_sort_validation(self, method): + idx1 = Index(["a", "b"]) + idx2 = Index(["b", "c"]) + + with pytest.raises(ValueError, match="The 'sort' keyword only takes"): + getattr(idx1, method)(idx2, sort=2) + + # sort=True is supported as of GH#?? + getattr(idx1, method)(idx2, sort=True) + + def test_setops_preserve_object_dtype(self): + idx = Index([1, 2, 3], dtype=object) + result = idx.intersection(idx[1:]) + expected = idx[1:] + tm.assert_index_equal(result, expected) + + # if other is not monotonic increasing, intersection goes through + # a different route + result = idx.intersection(idx[1:][::-1]) + tm.assert_index_equal(result, expected) + + result = idx._union(idx[1:], sort=None) + expected = idx + tm.assert_numpy_array_equal(result, expected.values) + + result = idx.union(idx[1:], sort=None) + tm.assert_index_equal(result, expected) + + # if other is not monotonic increasing, _union goes through + # a different route + result = idx._union(idx[1:][::-1], sort=None) + tm.assert_numpy_array_equal(result, expected.values) + + result = idx.union(idx[1:][::-1], sort=None) + tm.assert_index_equal(result, expected) + + def test_union_base(self): + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[3:] + second = index[:5] + + result = first.union(second) + + expected = Index([0, 1, 2, "a", "b", "c"]) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("klass", [np.array, Series, list]) + def test_union_different_type_base(self, klass): + # GH 10149 + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[3:] + second = index[:5] + + result = first.union(klass(second.values)) + + assert equal_contents(result, index) + + def test_union_sort_other_incomparable(self): + # https://github.com/pandas-dev/pandas/issues/24959 + idx = Index([1, pd.Timestamp("2000")]) + # default (sort=None) + with tm.assert_produces_warning(RuntimeWarning): + result = idx.union(idx[:1]) + + tm.assert_index_equal(result, idx) + + # sort=None + with tm.assert_produces_warning(RuntimeWarning): + result = idx.union(idx[:1], sort=None) + tm.assert_index_equal(result, idx) + + # sort=False + result = idx.union(idx[:1], sort=False) + tm.assert_index_equal(result, idx) + + def test_union_sort_other_incomparable_true(self): + idx = Index([1, pd.Timestamp("2000")]) + with pytest.raises(TypeError, match=".*"): + idx.union(idx[:1], sort=True) + + def test_intersection_equal_sort_true(self): + idx = Index(["c", "a", "b"]) + sorted_ = Index(["a", "b", "c"]) + tm.assert_index_equal(idx.intersection(idx, sort=True), sorted_) + + def test_intersection_base(self, sort): + # (same results for py2 and py3 but sortedness not tested elsewhere) + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[:5] + second = index[:3] + + expected = Index([0, 1, "a"]) if sort is None else Index([0, "a", 1]) + result = first.intersection(second, sort=sort) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("klass", [np.array, Series, list]) + def test_intersection_different_type_base(self, klass, sort): + # GH 10149 + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[:5] + second = index[:3] + + result = first.intersection(klass(second.values), sort=sort) + assert equal_contents(result, second) + + def test_intersection_nosort(self): + result = Index(["c", "b", "a"]).intersection(["b", "a"]) + expected = Index(["b", "a"]) + tm.assert_index_equal(result, expected) + + def test_intersection_equal_sort(self): + idx = Index(["c", "a", "b"]) + tm.assert_index_equal(idx.intersection(idx, sort=False), idx) + tm.assert_index_equal(idx.intersection(idx, sort=None), idx) + + def test_intersection_str_dates(self, sort): + dt_dates = [datetime(2012, 2, 9), datetime(2012, 2, 22)] + + i1 = Index(dt_dates, dtype=object) + i2 = Index(["aa"], dtype=object) + result = i2.intersection(i1, sort=sort) + + assert len(result) == 0 + + @pytest.mark.parametrize( + "index2,expected_arr", + [(Index(["B", "D"]), ["B"]), (Index(["B", "D", "A"]), ["A", "B"])], + ) + def test_intersection_non_monotonic_non_unique(self, index2, expected_arr, sort): + # non-monotonic non-unique + index1 = Index(["A", "B", "A", "C"]) + expected = Index(expected_arr) + result = index1.intersection(index2, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + + def test_difference_base(self, sort): + # (same results for py2 and py3 but sortedness not tested elsewhere) + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[:4] + second = index[3:] + + result = first.difference(second, sort) + expected = Index([0, "a", 1]) + if sort is None: + expected = Index(safe_sort(expected)) + tm.assert_index_equal(result, expected) + + def test_symmetric_difference(self): + # (same results for py2 and py3 but sortedness not tested elsewhere) + index = Index([0, "a", 1, "b", 2, "c"]) + first = index[:4] + second = index[3:] + + result = first.symmetric_difference(second) + expected = Index([0, 1, 2, "a", "c"]) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "method,expected,sort", + [ + ( + "intersection", + np.array( + [(1, "A"), (2, "A"), (1, "B"), (2, "B")], + dtype=[("num", int), ("let", "S1")], + ), + False, + ), + ( + "intersection", + np.array( + [(1, "A"), (1, "B"), (2, "A"), (2, "B")], + dtype=[("num", int), ("let", "S1")], + ), + None, + ), + ( + "union", + np.array( + [(1, "A"), (1, "B"), (1, "C"), (2, "A"), (2, "B"), (2, "C")], + dtype=[("num", int), ("let", "S1")], + ), + None, + ), + ], + ) + def test_tuple_union_bug(self, method, expected, sort): + index1 = Index( + np.array( + [(1, "A"), (2, "A"), (1, "B"), (2, "B")], + dtype=[("num", int), ("let", "S1")], + ) + ) + index2 = Index( + np.array( + [(1, "A"), (2, "A"), (1, "B"), (2, "B"), (1, "C"), (2, "C")], + dtype=[("num", int), ("let", "S1")], + ) + ) + + result = getattr(index1, method)(index2, sort=sort) + assert result.ndim == 1 + + expected = Index(expected) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("first_list", [["b", "a"], []]) + @pytest.mark.parametrize("second_list", [["a", "b"], []]) + @pytest.mark.parametrize( + "first_name, second_name, expected_name", + [("A", "B", None), (None, "B", None), ("A", None, None)], + ) + def test_union_name_preservation( + self, first_list, second_list, first_name, second_name, expected_name, sort + ): + first = Index(first_list, name=first_name) + second = Index(second_list, name=second_name) + union = first.union(second, sort=sort) + + vals = set(first_list).union(second_list) + + if sort is None and len(first_list) > 0 and len(second_list) > 0: + expected = Index(sorted(vals), name=expected_name) + tm.assert_index_equal(union, expected) + else: + expected = Index(vals, name=expected_name) + tm.assert_index_equal(union.sort_values(), expected.sort_values()) + + @pytest.mark.parametrize( + "diff_type, expected", + [["difference", [1, "B"]], ["symmetric_difference", [1, 2, "B", "C"]]], + ) + def test_difference_object_type(self, diff_type, expected): + # GH 13432 + idx1 = Index([0, 1, "A", "B"]) + idx2 = Index([0, 2, "A", "C"]) + result = getattr(idx1, diff_type)(idx2) + expected = Index(expected) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_where.py b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_where.py new file mode 100644 index 0000000000000000000000000000000000000000..0c8969735e14e2741bc029b499024af3ec378a92 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/base_class/test_where.py @@ -0,0 +1,13 @@ +import numpy as np + +from pandas import Index +import pandas._testing as tm + + +class TestWhere: + def test_where_intlike_str_doesnt_cast_ints(self): + idx = Index(range(3)) + mask = np.array([True, False, True]) + res = idx.where(mask, "2") + expected = Index([0, "2", 2]) + tm.assert_index_equal(res, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dc87daa7f36fb20208138cfee992be5caa8b4d47 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_drop_duplicates.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_drop_duplicates.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..34847f18339699b399ba1374aebfc0e80023f69e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_drop_duplicates.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_equals.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_equals.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..89a1624faae7775812bbbb0375e29de07b51ef70 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_equals.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad9db5f4c9d54dfe49ee679857145a8e5c9578db Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_is_monotonic.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_is_monotonic.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9043ad0cb83a12ee84abf8e3aafc02da0f87f824 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_is_monotonic.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_nat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_nat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dc58f0c513b95d323a171ff320b6b750b4e9d5a4 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_nat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_sort_values.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_sort_values.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8faac07de13f0409f79389651166294bdae31a11 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_sort_values.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_value_counts.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_value_counts.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7366d08584c977298f65249a5a480d9ee65bef41 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/__pycache__/test_value_counts.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_drop_duplicates.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_drop_duplicates.py new file mode 100644 index 0000000000000000000000000000000000000000..61a79c4ceabf9d68aab73ffd69e0f15ad842ff74 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_drop_duplicates.py @@ -0,0 +1,89 @@ +import numpy as np +import pytest + +from pandas import ( + PeriodIndex, + Series, + date_range, + period_range, + timedelta_range, +) +import pandas._testing as tm + + +class DropDuplicates: + def test_drop_duplicates_metadata(self, idx): + # GH#10115 + result = idx.drop_duplicates() + tm.assert_index_equal(idx, result) + assert idx.freq == result.freq + + idx_dup = idx.append(idx) + result = idx_dup.drop_duplicates() + + expected = idx + if not isinstance(idx, PeriodIndex): + # freq is reset except for PeriodIndex + assert idx_dup.freq is None + assert result.freq is None + expected = idx._with_freq(None) + else: + assert result.freq == expected.freq + + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "keep, expected, index", + [ + ( + "first", + np.concatenate(([False] * 10, [True] * 5)), + np.arange(0, 10, dtype=np.int64), + ), + ( + "last", + np.concatenate(([True] * 5, [False] * 10)), + np.arange(5, 15, dtype=np.int64), + ), + ( + False, + np.concatenate(([True] * 5, [False] * 5, [True] * 5)), + np.arange(5, 10, dtype=np.int64), + ), + ], + ) + def test_drop_duplicates(self, keep, expected, index, idx): + # to check Index/Series compat + idx = idx.append(idx[:5]) + + tm.assert_numpy_array_equal(idx.duplicated(keep=keep), expected) + expected = idx[~expected] + + result = idx.drop_duplicates(keep=keep) + tm.assert_index_equal(result, expected) + + result = Series(idx).drop_duplicates(keep=keep) + expected = Series(expected, index=index) + tm.assert_series_equal(result, expected) + + +class TestDropDuplicatesPeriodIndex(DropDuplicates): + @pytest.fixture(params=["D", "3D", "h", "2h", "min", "2min", "s", "3s"]) + def freq(self, request): + return request.param + + @pytest.fixture + def idx(self, freq): + return period_range("2011-01-01", periods=10, freq=freq, name="idx") + + +class TestDropDuplicatesDatetimeIndex(DropDuplicates): + @pytest.fixture + def idx(self, freq_sample): + return date_range("2011-01-01", freq=freq_sample, periods=10, name="idx") + + +class TestDropDuplicatesTimedeltaIndex(DropDuplicates): + @pytest.fixture + def idx(self, freq_sample): + return timedelta_range("1 day", periods=10, freq=freq_sample, name="idx") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_equals.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_equals.py new file mode 100644 index 0000000000000000000000000000000000000000..fc9fbd33d0d285fe7635c23c598318208bb58561 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_equals.py @@ -0,0 +1,181 @@ +""" +Tests shared for DatetimeIndex/TimedeltaIndex/PeriodIndex +""" +from datetime import ( + datetime, + timedelta, +) + +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + CategoricalIndex, + DatetimeIndex, + Index, + PeriodIndex, + TimedeltaIndex, + date_range, + period_range, + timedelta_range, +) +import pandas._testing as tm + + +class EqualsTests: + def test_not_equals_numeric(self, index): + assert not index.equals(Index(index.asi8)) + assert not index.equals(Index(index.asi8.astype("u8"))) + assert not index.equals(Index(index.asi8).astype("f8")) + + def test_equals(self, index): + assert index.equals(index) + assert index.equals(index.astype(object)) + assert index.equals(CategoricalIndex(index)) + assert index.equals(CategoricalIndex(index.astype(object))) + + def test_not_equals_non_arraylike(self, index): + assert not index.equals(list(index)) + + def test_not_equals_strings(self, index): + other = Index([str(x) for x in index], dtype=object) + assert not index.equals(other) + assert not index.equals(CategoricalIndex(other)) + + def test_not_equals_misc_strs(self, index): + other = Index(list("abc")) + assert not index.equals(other) + + +class TestPeriodIndexEquals(EqualsTests): + @pytest.fixture + def index(self): + return period_range("2013-01-01", periods=5, freq="D") + + # TODO: de-duplicate with other test_equals2 methods + @pytest.mark.parametrize("freq", ["D", "M"]) + def test_equals2(self, freq): + # GH#13107 + idx = PeriodIndex(["2011-01-01", "2011-01-02", "NaT"], freq=freq) + assert idx.equals(idx) + assert idx.equals(idx.copy()) + assert idx.equals(idx.astype(object)) + assert idx.astype(object).equals(idx) + assert idx.astype(object).equals(idx.astype(object)) + assert not idx.equals(list(idx)) + assert not idx.equals(pd.Series(idx)) + + idx2 = PeriodIndex(["2011-01-01", "2011-01-02", "NaT"], freq="h") + assert not idx.equals(idx2) + assert not idx.equals(idx2.copy()) + assert not idx.equals(idx2.astype(object)) + assert not idx.astype(object).equals(idx2) + assert not idx.equals(list(idx2)) + assert not idx.equals(pd.Series(idx2)) + + # same internal, different tz + idx3 = PeriodIndex._simple_new( + idx._values._simple_new(idx._values.asi8, dtype=pd.PeriodDtype("h")) + ) + tm.assert_numpy_array_equal(idx.asi8, idx3.asi8) + assert not idx.equals(idx3) + assert not idx.equals(idx3.copy()) + assert not idx.equals(idx3.astype(object)) + assert not idx.astype(object).equals(idx3) + assert not idx.equals(list(idx3)) + assert not idx.equals(pd.Series(idx3)) + + +class TestDatetimeIndexEquals(EqualsTests): + @pytest.fixture + def index(self): + return date_range("2013-01-01", periods=5) + + def test_equals2(self): + # GH#13107 + idx = DatetimeIndex(["2011-01-01", "2011-01-02", "NaT"]) + assert idx.equals(idx) + assert idx.equals(idx.copy()) + assert idx.equals(idx.astype(object)) + assert idx.astype(object).equals(idx) + assert idx.astype(object).equals(idx.astype(object)) + assert not idx.equals(list(idx)) + assert not idx.equals(pd.Series(idx)) + + idx2 = DatetimeIndex(["2011-01-01", "2011-01-02", "NaT"], tz="US/Pacific") + assert not idx.equals(idx2) + assert not idx.equals(idx2.copy()) + assert not idx.equals(idx2.astype(object)) + assert not idx.astype(object).equals(idx2) + assert not idx.equals(list(idx2)) + assert not idx.equals(pd.Series(idx2)) + + # same internal, different tz + idx3 = DatetimeIndex(idx.asi8, tz="US/Pacific") + tm.assert_numpy_array_equal(idx.asi8, idx3.asi8) + assert not idx.equals(idx3) + assert not idx.equals(idx3.copy()) + assert not idx.equals(idx3.astype(object)) + assert not idx.astype(object).equals(idx3) + assert not idx.equals(list(idx3)) + assert not idx.equals(pd.Series(idx3)) + + # check that we do not raise when comparing with OutOfBounds objects + oob = Index([datetime(2500, 1, 1)] * 3, dtype=object) + assert not idx.equals(oob) + assert not idx2.equals(oob) + assert not idx3.equals(oob) + + # check that we do not raise when comparing with OutOfBounds dt64 + oob2 = oob.map(np.datetime64) + assert not idx.equals(oob2) + assert not idx2.equals(oob2) + assert not idx3.equals(oob2) + + @pytest.mark.parametrize("freq", ["B", "C"]) + def test_not_equals_bday(self, freq): + rng = date_range("2009-01-01", "2010-01-01", freq=freq) + assert not rng.equals(list(rng)) + + +class TestTimedeltaIndexEquals(EqualsTests): + @pytest.fixture + def index(self): + return timedelta_range("1 day", periods=10) + + def test_equals2(self): + # GH#13107 + idx = TimedeltaIndex(["1 days", "2 days", "NaT"]) + assert idx.equals(idx) + assert idx.equals(idx.copy()) + assert idx.equals(idx.astype(object)) + assert idx.astype(object).equals(idx) + assert idx.astype(object).equals(idx.astype(object)) + assert not idx.equals(list(idx)) + assert not idx.equals(pd.Series(idx)) + + idx2 = TimedeltaIndex(["2 days", "1 days", "NaT"]) + assert not idx.equals(idx2) + assert not idx.equals(idx2.copy()) + assert not idx.equals(idx2.astype(object)) + assert not idx.astype(object).equals(idx2) + assert not idx.astype(object).equals(idx2.astype(object)) + assert not idx.equals(list(idx2)) + assert not idx.equals(pd.Series(idx2)) + + # Check that we dont raise OverflowError on comparisons outside the + # implementation range GH#28532 + oob = Index([timedelta(days=10**6)] * 3, dtype=object) + assert not idx.equals(oob) + assert not idx2.equals(oob) + + oob2 = Index([np.timedelta64(x) for x in oob], dtype=object) + assert (oob == oob2).all() + assert not idx.equals(oob2) + assert not idx2.equals(oob2) + + oob3 = oob.map(np.timedelta64) + assert (oob3 == oob).all() + assert not idx.equals(oob3) + assert not idx2.equals(oob3) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..7b2c81aaf17de3785e62a2d989394259b2496085 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_indexing.py @@ -0,0 +1,45 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + DatetimeIndex, + Index, +) +import pandas._testing as tm + +dtlike_dtypes = [ + np.dtype("timedelta64[ns]"), + np.dtype("datetime64[ns]"), + pd.DatetimeTZDtype("ns", "Asia/Tokyo"), + pd.PeriodDtype("ns"), +] + + +@pytest.mark.parametrize("ldtype", dtlike_dtypes) +@pytest.mark.parametrize("rdtype", dtlike_dtypes) +def test_get_indexer_non_unique_wrong_dtype(ldtype, rdtype): + vals = np.tile(3600 * 10**9 * np.arange(3, dtype=np.int64), 2) + + def construct(dtype): + if dtype is dtlike_dtypes[-1]: + # PeriodArray will try to cast ints to strings + return DatetimeIndex(vals).astype(dtype) + return Index(vals, dtype=dtype) + + left = construct(ldtype) + right = construct(rdtype) + + result = left.get_indexer_non_unique(right) + + if ldtype is rdtype: + ex1 = np.array([0, 3, 1, 4, 2, 5] * 2, dtype=np.intp) + ex2 = np.array([], dtype=np.intp) + tm.assert_numpy_array_equal(result[0], ex1) + tm.assert_numpy_array_equal(result[1], ex2) + + else: + no_matches = np.array([-1] * 6, dtype=np.intp) + missing = np.arange(6, dtype=np.intp) + tm.assert_numpy_array_equal(result[0], no_matches) + tm.assert_numpy_array_equal(result[1], missing) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_is_monotonic.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_is_monotonic.py new file mode 100644 index 0000000000000000000000000000000000000000..b0e42e660b751cddaca74c4574e9588e8ac8c782 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_is_monotonic.py @@ -0,0 +1,46 @@ +from pandas import ( + Index, + NaT, + date_range, +) + + +def test_is_monotonic_with_nat(): + # GH#31437 + # PeriodIndex.is_monotonic_increasing should behave analogously to DatetimeIndex, + # in particular never be monotonic when we have NaT + dti = date_range("2016-01-01", periods=3) + pi = dti.to_period("D") + tdi = Index(dti.view("timedelta64[ns]")) + + for obj in [pi, pi._engine, dti, dti._engine, tdi, tdi._engine]: + if isinstance(obj, Index): + # i.e. not Engines + assert obj.is_monotonic_increasing + assert obj.is_monotonic_increasing + assert not obj.is_monotonic_decreasing + assert obj.is_unique + + dti1 = dti.insert(0, NaT) + pi1 = dti1.to_period("D") + tdi1 = Index(dti1.view("timedelta64[ns]")) + + for obj in [pi1, pi1._engine, dti1, dti1._engine, tdi1, tdi1._engine]: + if isinstance(obj, Index): + # i.e. not Engines + assert not obj.is_monotonic_increasing + assert not obj.is_monotonic_increasing + assert not obj.is_monotonic_decreasing + assert obj.is_unique + + dti2 = dti.insert(3, NaT) + pi2 = dti2.to_period("h") + tdi2 = Index(dti2.view("timedelta64[ns]")) + + for obj in [pi2, pi2._engine, dti2, dti2._engine, tdi2, tdi2._engine]: + if isinstance(obj, Index): + # i.e. not Engines + assert not obj.is_monotonic_increasing + assert not obj.is_monotonic_increasing + assert not obj.is_monotonic_decreasing + assert obj.is_unique diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_nat.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_nat.py new file mode 100644 index 0000000000000000000000000000000000000000..50cf29d0163555876eb7b1914bbd4ee45bc2285e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_nat.py @@ -0,0 +1,53 @@ +import numpy as np +import pytest + +from pandas import ( + DatetimeIndex, + NaT, + PeriodIndex, + TimedeltaIndex, +) +import pandas._testing as tm + + +class NATests: + def test_nat(self, index_without_na): + empty_index = index_without_na[:0] + + index_with_na = index_without_na.copy(deep=True) + index_with_na._data[1] = NaT + + assert empty_index._na_value is NaT + assert index_with_na._na_value is NaT + assert index_without_na._na_value is NaT + + idx = index_without_na + assert idx._can_hold_na + + tm.assert_numpy_array_equal(idx._isnan, np.array([False, False])) + assert idx.hasnans is False + + idx = index_with_na + assert idx._can_hold_na + + tm.assert_numpy_array_equal(idx._isnan, np.array([False, True])) + assert idx.hasnans is True + + +class TestDatetimeIndexNA(NATests): + @pytest.fixture + def index_without_na(self, tz_naive_fixture): + tz = tz_naive_fixture + return DatetimeIndex(["2011-01-01", "2011-01-02"], tz=tz) + + +class TestTimedeltaIndexNA(NATests): + @pytest.fixture + def index_without_na(self): + return TimedeltaIndex(["1 days", "2 days"]) + + +class TestPeriodIndexNA(NATests): + @pytest.fixture + def index_without_na(self): + return PeriodIndex(["2011-01-01", "2011-01-02"], freq="D") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_sort_values.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_sort_values.py new file mode 100644 index 0000000000000000000000000000000000000000..a2c349c8b0ef679b9d32411efd8a0d393b9d5e9d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_sort_values.py @@ -0,0 +1,315 @@ +import numpy as np +import pytest + +from pandas import ( + DatetimeIndex, + Index, + NaT, + PeriodIndex, + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +def check_freq_ascending(ordered, orig, ascending): + """ + Check the expected freq on a PeriodIndex/DatetimeIndex/TimedeltaIndex + when the original index is generated (or generate-able) with + period_range/date_range/timedelta_range. + """ + if isinstance(ordered, PeriodIndex): + assert ordered.freq == orig.freq + elif isinstance(ordered, (DatetimeIndex, TimedeltaIndex)): + if ascending: + assert ordered.freq.n == orig.freq.n + else: + assert ordered.freq.n == -1 * orig.freq.n + + +def check_freq_nonmonotonic(ordered, orig): + """ + Check the expected freq on a PeriodIndex/DatetimeIndex/TimedeltaIndex + when the original index is _not_ generated (or generate-able) with + period_range/date_range//timedelta_range. + """ + if isinstance(ordered, PeriodIndex): + assert ordered.freq == orig.freq + elif isinstance(ordered, (DatetimeIndex, TimedeltaIndex)): + assert ordered.freq is None + + +class TestSortValues: + @pytest.fixture(params=[DatetimeIndex, TimedeltaIndex, PeriodIndex]) + def non_monotonic_idx(self, request): + if request.param is DatetimeIndex: + return DatetimeIndex(["2000-01-04", "2000-01-01", "2000-01-02"]) + elif request.param is PeriodIndex: + dti = DatetimeIndex(["2000-01-04", "2000-01-01", "2000-01-02"]) + return dti.to_period("D") + else: + return TimedeltaIndex( + ["1 day 00:00:05", "1 day 00:00:01", "1 day 00:00:02"] + ) + + def test_argmin_argmax(self, non_monotonic_idx): + assert non_monotonic_idx.argmin() == 1 + assert non_monotonic_idx.argmax() == 0 + + def test_sort_values(self, non_monotonic_idx): + idx = non_monotonic_idx + ordered = idx.sort_values() + assert ordered.is_monotonic_increasing + ordered = idx.sort_values(ascending=False) + assert ordered[::-1].is_monotonic_increasing + + ordered, dexer = idx.sort_values(return_indexer=True) + assert ordered.is_monotonic_increasing + tm.assert_numpy_array_equal(dexer, np.array([1, 2, 0], dtype=np.intp)) + + ordered, dexer = idx.sort_values(return_indexer=True, ascending=False) + assert ordered[::-1].is_monotonic_increasing + tm.assert_numpy_array_equal(dexer, np.array([0, 2, 1], dtype=np.intp)) + + def check_sort_values_with_freq(self, idx): + ordered = idx.sort_values() + tm.assert_index_equal(ordered, idx) + check_freq_ascending(ordered, idx, True) + + ordered = idx.sort_values(ascending=False) + expected = idx[::-1] + tm.assert_index_equal(ordered, expected) + check_freq_ascending(ordered, idx, False) + + ordered, indexer = idx.sort_values(return_indexer=True) + tm.assert_index_equal(ordered, idx) + tm.assert_numpy_array_equal(indexer, np.array([0, 1, 2], dtype=np.intp)) + check_freq_ascending(ordered, idx, True) + + ordered, indexer = idx.sort_values(return_indexer=True, ascending=False) + expected = idx[::-1] + tm.assert_index_equal(ordered, expected) + tm.assert_numpy_array_equal(indexer, np.array([2, 1, 0], dtype=np.intp)) + check_freq_ascending(ordered, idx, False) + + @pytest.mark.parametrize("freq", ["D", "h"]) + def test_sort_values_with_freq_timedeltaindex(self, freq): + # GH#10295 + idx = timedelta_range(start=f"1{freq}", periods=3, freq=freq).rename("idx") + + self.check_sort_values_with_freq(idx) + + @pytest.mark.parametrize( + "idx", + [ + DatetimeIndex( + ["2011-01-01", "2011-01-02", "2011-01-03"], freq="D", name="idx" + ), + DatetimeIndex( + ["2011-01-01 09:00", "2011-01-01 10:00", "2011-01-01 11:00"], + freq="h", + name="tzidx", + tz="Asia/Tokyo", + ), + ], + ) + def test_sort_values_with_freq_datetimeindex(self, idx): + self.check_sort_values_with_freq(idx) + + @pytest.mark.parametrize("freq", ["D", "2D", "4D"]) + def test_sort_values_with_freq_periodindex(self, freq): + # here with_freq refers to being period_range-like + idx = PeriodIndex( + ["2011-01-01", "2011-01-02", "2011-01-03"], freq=freq, name="idx" + ) + self.check_sort_values_with_freq(idx) + + @pytest.mark.parametrize( + "idx", + [ + PeriodIndex(["2011", "2012", "2013"], name="pidx", freq="Y"), + Index([2011, 2012, 2013], name="idx"), # for compatibility check + ], + ) + def test_sort_values_with_freq_periodindex2(self, idx): + # here with_freq indicates this is period_range-like + self.check_sort_values_with_freq(idx) + + def check_sort_values_without_freq(self, idx, expected): + ordered = idx.sort_values(na_position="first") + tm.assert_index_equal(ordered, expected) + check_freq_nonmonotonic(ordered, idx) + + if not idx.isna().any(): + ordered = idx.sort_values() + tm.assert_index_equal(ordered, expected) + check_freq_nonmonotonic(ordered, idx) + + ordered = idx.sort_values(ascending=False) + tm.assert_index_equal(ordered, expected[::-1]) + check_freq_nonmonotonic(ordered, idx) + + ordered, indexer = idx.sort_values(return_indexer=True, na_position="first") + tm.assert_index_equal(ordered, expected) + + exp = np.array([0, 4, 3, 1, 2], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, exp) + check_freq_nonmonotonic(ordered, idx) + + if not idx.isna().any(): + ordered, indexer = idx.sort_values(return_indexer=True) + tm.assert_index_equal(ordered, expected) + + exp = np.array([0, 4, 3, 1, 2], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, exp) + check_freq_nonmonotonic(ordered, idx) + + ordered, indexer = idx.sort_values(return_indexer=True, ascending=False) + tm.assert_index_equal(ordered, expected[::-1]) + + exp = np.array([2, 1, 3, 0, 4], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, exp) + check_freq_nonmonotonic(ordered, idx) + + def test_sort_values_without_freq_timedeltaindex(self): + # GH#10295 + + idx = TimedeltaIndex( + ["1 hour", "3 hour", "5 hour", "2 hour ", "1 hour"], name="idx1" + ) + expected = TimedeltaIndex( + ["1 hour", "1 hour", "2 hour", "3 hour", "5 hour"], name="idx1" + ) + self.check_sort_values_without_freq(idx, expected) + + @pytest.mark.parametrize( + "index_dates,expected_dates", + [ + ( + ["2011-01-01", "2011-01-03", "2011-01-05", "2011-01-02", "2011-01-01"], + ["2011-01-01", "2011-01-01", "2011-01-02", "2011-01-03", "2011-01-05"], + ), + ( + ["2011-01-01", "2011-01-03", "2011-01-05", "2011-01-02", "2011-01-01"], + ["2011-01-01", "2011-01-01", "2011-01-02", "2011-01-03", "2011-01-05"], + ), + ( + [NaT, "2011-01-03", "2011-01-05", "2011-01-02", NaT], + [NaT, NaT, "2011-01-02", "2011-01-03", "2011-01-05"], + ), + ], + ) + def test_sort_values_without_freq_datetimeindex( + self, index_dates, expected_dates, tz_naive_fixture + ): + tz = tz_naive_fixture + + # without freq + idx = DatetimeIndex(index_dates, tz=tz, name="idx") + expected = DatetimeIndex(expected_dates, tz=tz, name="idx") + + self.check_sort_values_without_freq(idx, expected) + + @pytest.mark.parametrize( + "idx,expected", + [ + ( + PeriodIndex( + [ + "2011-01-01", + "2011-01-03", + "2011-01-05", + "2011-01-02", + "2011-01-01", + ], + freq="D", + name="idx1", + ), + PeriodIndex( + [ + "2011-01-01", + "2011-01-01", + "2011-01-02", + "2011-01-03", + "2011-01-05", + ], + freq="D", + name="idx1", + ), + ), + ( + PeriodIndex( + [ + "2011-01-01", + "2011-01-03", + "2011-01-05", + "2011-01-02", + "2011-01-01", + ], + freq="D", + name="idx2", + ), + PeriodIndex( + [ + "2011-01-01", + "2011-01-01", + "2011-01-02", + "2011-01-03", + "2011-01-05", + ], + freq="D", + name="idx2", + ), + ), + ( + PeriodIndex( + [NaT, "2011-01-03", "2011-01-05", "2011-01-02", NaT], + freq="D", + name="idx3", + ), + PeriodIndex( + [NaT, NaT, "2011-01-02", "2011-01-03", "2011-01-05"], + freq="D", + name="idx3", + ), + ), + ( + PeriodIndex( + ["2011", "2013", "2015", "2012", "2011"], name="pidx", freq="Y" + ), + PeriodIndex( + ["2011", "2011", "2012", "2013", "2015"], name="pidx", freq="Y" + ), + ), + ( + # For compatibility check + Index([2011, 2013, 2015, 2012, 2011], name="idx"), + Index([2011, 2011, 2012, 2013, 2015], name="idx"), + ), + ], + ) + def test_sort_values_without_freq_periodindex(self, idx, expected): + # here without_freq means not generateable by period_range + self.check_sort_values_without_freq(idx, expected) + + def test_sort_values_without_freq_periodindex_nat(self): + # doesn't quite fit into check_sort_values_without_freq + idx = PeriodIndex(["2011", "2013", "NaT", "2011"], name="pidx", freq="D") + expected = PeriodIndex(["NaT", "2011", "2011", "2013"], name="pidx", freq="D") + + ordered = idx.sort_values(na_position="first") + tm.assert_index_equal(ordered, expected) + check_freq_nonmonotonic(ordered, idx) + + ordered = idx.sort_values(ascending=False) + tm.assert_index_equal(ordered, expected[::-1]) + check_freq_nonmonotonic(ordered, idx) + + +def test_order_stability_compat(): + # GH#35922. sort_values is stable both for normal and datetime-like Index + pidx = PeriodIndex(["2011", "2013", "2015", "2012", "2011"], name="pidx", freq="Y") + iidx = Index([2011, 2013, 2015, 2012, 2011], name="idx") + ordered1, indexer1 = pidx.sort_values(return_indexer=True, ascending=False) + ordered2, indexer2 = iidx.sort_values(return_indexer=True, ascending=False) + tm.assert_numpy_array_equal(indexer1, indexer2) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_value_counts.py b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_value_counts.py new file mode 100644 index 0000000000000000000000000000000000000000..069e354a364c9343c595da9d18ee7c04eec04f43 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/datetimelike_/test_value_counts.py @@ -0,0 +1,103 @@ +import numpy as np + +from pandas import ( + DatetimeIndex, + NaT, + PeriodIndex, + Series, + TimedeltaIndex, + date_range, + period_range, + timedelta_range, +) +import pandas._testing as tm + + +class TestValueCounts: + # GH#7735 + + def test_value_counts_unique_datetimeindex(self, tz_naive_fixture): + tz = tz_naive_fixture + orig = date_range("2011-01-01 09:00", freq="h", periods=10, tz=tz) + self._check_value_counts_with_repeats(orig) + + def test_value_counts_unique_timedeltaindex(self): + orig = timedelta_range("1 days 09:00:00", freq="h", periods=10) + self._check_value_counts_with_repeats(orig) + + def test_value_counts_unique_periodindex(self): + orig = period_range("2011-01-01 09:00", freq="h", periods=10) + self._check_value_counts_with_repeats(orig) + + def _check_value_counts_with_repeats(self, orig): + # create repeated values, 'n'th element is repeated by n+1 times + idx = type(orig)( + np.repeat(orig._values, range(1, len(orig) + 1)), dtype=orig.dtype + ) + + exp_idx = orig[::-1] + if not isinstance(exp_idx, PeriodIndex): + exp_idx = exp_idx._with_freq(None) + expected = Series(range(10, 0, -1), index=exp_idx, dtype="int64", name="count") + + for obj in [idx, Series(idx)]: + tm.assert_series_equal(obj.value_counts(), expected) + + tm.assert_index_equal(idx.unique(), orig) + + def test_value_counts_unique_datetimeindex2(self, tz_naive_fixture): + tz = tz_naive_fixture + idx = DatetimeIndex( + [ + "2013-01-01 09:00", + "2013-01-01 09:00", + "2013-01-01 09:00", + "2013-01-01 08:00", + "2013-01-01 08:00", + NaT, + ], + tz=tz, + ) + self._check_value_counts_dropna(idx) + + def test_value_counts_unique_timedeltaindex2(self): + idx = TimedeltaIndex( + [ + "1 days 09:00:00", + "1 days 09:00:00", + "1 days 09:00:00", + "1 days 08:00:00", + "1 days 08:00:00", + NaT, + ] + ) + self._check_value_counts_dropna(idx) + + def test_value_counts_unique_periodindex2(self): + idx = PeriodIndex( + [ + "2013-01-01 09:00", + "2013-01-01 09:00", + "2013-01-01 09:00", + "2013-01-01 08:00", + "2013-01-01 08:00", + NaT, + ], + freq="h", + ) + self._check_value_counts_dropna(idx) + + def _check_value_counts_dropna(self, idx): + exp_idx = idx[[2, 3]] + expected = Series([3, 2], index=exp_idx, name="count") + + for obj in [idx, Series(idx)]: + tm.assert_series_equal(obj.value_counts(), expected) + + exp_idx = idx[[2, 3, -1]] + expected = Series([3, 2, 1], index=exp_idx, name="count") + + for obj in [idx, Series(idx)]: + tm.assert_series_equal(obj.value_counts(dropna=False), expected) + + tm.assert_index_equal(idx.unique(), exp_idx) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..81b200c54bffad99108f8b8e57e76b4d32ab92f0 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_astype.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_astype.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d99c3222cad725d8609f248258d64bde74a80567 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_astype.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..96a5e476a679e70086e8b7858cf803f241649df2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_equals.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_equals.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ec4d6d8244d025159bcd638467470fa289aab513 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_equals.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_formats.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_formats.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..246ae18f5b147d345abb0f71008acdb44092b05c Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_formats.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..22e487310c71d0aefc3d31a7d0d28833384229cb Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a787aa3ebe2ebc63fc788b3bc76e8c582b5f962b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_range.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_range.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2d9addac3c286da1bc5dfd2f9cbc414efe5ef75a Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_range.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_tree.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_tree.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..81432d01d3a33c49835a422ed002479e40ff80dc Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_interval_tree.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1953a4660583ef70ac9078c86f91d869134ace54 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_pickle.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_pickle.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..49536eba707178f46be96affd0dc9e9995407bdf Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_pickle.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..68a97f7aa2cc00144098d03b82ab4cc43fec0af2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/interval/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/interval/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/interval/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..e47a014f18045ae20fe27805a31b819b4ad229b9 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/interval/test_constructors.py @@ -0,0 +1,535 @@ +from functools import partial + +import numpy as np +import pytest + +import pandas.util._test_decorators as td + +from pandas.core.dtypes.common import is_unsigned_integer_dtype +from pandas.core.dtypes.dtypes import IntervalDtype + +from pandas import ( + Categorical, + CategoricalDtype, + CategoricalIndex, + Index, + Interval, + IntervalIndex, + date_range, + notna, + period_range, + timedelta_range, +) +import pandas._testing as tm +from pandas.core.arrays import IntervalArray +import pandas.core.common as com + + +@pytest.fixture(params=[None, "foo"]) +def name(request): + return request.param + + +class ConstructorTests: + """ + Common tests for all variations of IntervalIndex construction. Input data + to be supplied in breaks format, then converted by the subclass method + get_kwargs_from_breaks to the expected format. + """ + + @pytest.fixture( + params=[ + ([3, 14, 15, 92, 653], np.int64), + (np.arange(10, dtype="int64"), np.int64), + (Index(np.arange(-10, 11, dtype=np.int64)), np.int64), + (Index(np.arange(10, 31, dtype=np.uint64)), np.uint64), + (Index(np.arange(20, 30, 0.5), dtype=np.float64), np.float64), + (date_range("20180101", periods=10), " common dtype is f8 + other = empty_index(dtype="float64", closed=closed) + result = index.union(other, sort=sort) + expected = other + tm.assert_index_equal(result, expected) + + other = index.union(index, sort=sort) + tm.assert_index_equal(result, expected) + + other = empty_index(dtype="uint64", closed=closed) + result = index.union(other, sort=sort) + tm.assert_index_equal(result, expected) + + result = other.union(index, sort=sort) + tm.assert_index_equal(result, expected) + + def test_intersection(self, closed, sort): + index = monotonic_index(0, 11, closed=closed) + other = monotonic_index(5, 13, closed=closed) + + expected = monotonic_index(5, 11, closed=closed) + result = index[::-1].intersection(other, sort=sort) + if sort in (None, True): + tm.assert_index_equal(result, expected) + else: + tm.assert_index_equal(result.sort_values(), expected) + + result = other[::-1].intersection(index, sort=sort) + if sort in (None, True): + tm.assert_index_equal(result, expected) + else: + tm.assert_index_equal(result.sort_values(), expected) + + tm.assert_index_equal(index.intersection(index, sort=sort), index) + + # GH 26225: nested intervals + index = IntervalIndex.from_tuples([(1, 2), (1, 3), (1, 4), (0, 2)]) + other = IntervalIndex.from_tuples([(1, 2), (1, 3)]) + expected = IntervalIndex.from_tuples([(1, 2), (1, 3)]) + result = index.intersection(other) + tm.assert_index_equal(result, expected) + + # GH 26225 + index = IntervalIndex.from_tuples([(0, 3), (0, 2)]) + other = IntervalIndex.from_tuples([(0, 2), (1, 3)]) + expected = IntervalIndex.from_tuples([(0, 2)]) + result = index.intersection(other) + tm.assert_index_equal(result, expected) + + # GH 26225: duplicate nan element + index = IntervalIndex([np.nan, np.nan]) + other = IntervalIndex([np.nan]) + expected = IntervalIndex([np.nan]) + result = index.intersection(other) + tm.assert_index_equal(result, expected) + + def test_intersection_empty_result(self, closed, sort): + index = monotonic_index(0, 11, closed=closed) + + # GH 19101: empty result, same dtype + other = monotonic_index(300, 314, closed=closed) + expected = empty_index(dtype="int64", closed=closed) + result = index.intersection(other, sort=sort) + tm.assert_index_equal(result, expected) + + # GH 19101: empty result, different numeric dtypes -> common dtype is float64 + other = monotonic_index(300, 314, dtype="float64", closed=closed) + result = index.intersection(other, sort=sort) + expected = other[:0] + tm.assert_index_equal(result, expected) + + other = monotonic_index(300, 314, dtype="uint64", closed=closed) + result = index.intersection(other, sort=sort) + tm.assert_index_equal(result, expected) + + def test_intersection_duplicates(self): + # GH#38743 + index = IntervalIndex.from_tuples([(1, 2), (1, 2), (2, 3), (3, 4)]) + other = IntervalIndex.from_tuples([(1, 2), (2, 3)]) + expected = IntervalIndex.from_tuples([(1, 2), (2, 3)]) + result = index.intersection(other) + tm.assert_index_equal(result, expected) + + def test_difference(self, closed, sort): + index = IntervalIndex.from_arrays([1, 0, 3, 2], [1, 2, 3, 4], closed=closed) + result = index.difference(index[:1], sort=sort) + expected = index[1:] + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + + # GH 19101: empty result, same dtype + result = index.difference(index, sort=sort) + expected = empty_index(dtype="int64", closed=closed) + tm.assert_index_equal(result, expected) + + # GH 19101: empty result, different dtypes + other = IntervalIndex.from_arrays( + index.left.astype("float64"), index.right, closed=closed + ) + result = index.difference(other, sort=sort) + tm.assert_index_equal(result, expected) + + def test_symmetric_difference(self, closed, sort): + index = monotonic_index(0, 11, closed=closed) + result = index[1:].symmetric_difference(index[:-1], sort=sort) + expected = IntervalIndex([index[0], index[-1]]) + if sort in (None, True): + tm.assert_index_equal(result, expected) + else: + tm.assert_index_equal(result.sort_values(), expected) + + # GH 19101: empty result, same dtype + result = index.symmetric_difference(index, sort=sort) + expected = empty_index(dtype="int64", closed=closed) + if sort in (None, True): + tm.assert_index_equal(result, expected) + else: + tm.assert_index_equal(result.sort_values(), expected) + + # GH 19101: empty result, different dtypes + other = IntervalIndex.from_arrays( + index.left.astype("float64"), index.right, closed=closed + ) + result = index.symmetric_difference(other, sort=sort) + expected = empty_index(dtype="float64", closed=closed) + tm.assert_index_equal(result, expected) + + @pytest.mark.filterwarnings("ignore:'<' not supported between:RuntimeWarning") + @pytest.mark.parametrize( + "op_name", ["union", "intersection", "difference", "symmetric_difference"] + ) + def test_set_incompatible_types(self, closed, op_name, sort): + index = monotonic_index(0, 11, closed=closed) + set_op = getattr(index, op_name) + + # TODO: standardize return type of non-union setops type(self vs other) + # non-IntervalIndex + if op_name == "difference": + expected = index + else: + expected = getattr(index.astype("O"), op_name)(Index([1, 2, 3])) + result = set_op(Index([1, 2, 3]), sort=sort) + tm.assert_index_equal(result, expected) + + # mixed closed -> cast to object + for other_closed in {"right", "left", "both", "neither"} - {closed}: + other = monotonic_index(0, 11, closed=other_closed) + expected = getattr(index.astype(object), op_name)(other, sort=sort) + if op_name == "difference": + expected = index + result = set_op(other, sort=sort) + tm.assert_index_equal(result, expected) + + # GH 19016: incompatible dtypes -> cast to object + other = interval_range(Timestamp("20180101"), periods=9, closed=closed) + expected = getattr(index.astype(object), op_name)(other, sort=sort) + if op_name == "difference": + expected = index + result = set_op(other, sort=sort) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2d9d0325ff14671192825db80ee4a57f9346d291 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/conftest.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/conftest.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..da66770dd053c41e623bd653bdfe3a660d32b0e9 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/conftest.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_analytics.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_analytics.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..458d6a90928a586074f919c195fc9c156723df3a Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_analytics.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_astype.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_astype.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6d1224b070cc73f229ecfbc14f7133ecdded984b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_astype.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_compat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_compat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4e65ef1144b6600f3f9096116ca530633eb6f7f5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_compat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5914df673643a65989b3c66a4168997daa46283e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_conversion.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_conversion.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0d8e38f760dcc1edab7616e07830340b5f1a17d2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_conversion.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_copy.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_copy.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..eea2fa574a8c68ccaeea605839020346e7f76bbe Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_copy.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_drop.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_drop.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f37dc29bd0f336605a659755ab21c0527d5a3b03 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_drop.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_duplicates.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_duplicates.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5616dded9f08bd999248709f304994ce6ae04322 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_duplicates.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_equivalence.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_equivalence.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..43477f4d2615d625fa1f8a689d7365ca33d48e05 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_equivalence.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_formats.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_formats.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d8f2474d32f4340de1e648e2d3cc55e98f3eac16 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_formats.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_level_values.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_level_values.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..14b75a608713540f9d463f9a0473d7548a92a954 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_level_values.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_set.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_set.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6a068d8e5164c1159ff62ca6c879f0e9d57e465f Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_get_set.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2d054817d9e810c46b03e284272d50fc164d6ed2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_integrity.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_integrity.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0218bc85ab02d35d843eef25c4111ee3dbbabc48 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_integrity.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_isin.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_isin.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b4fcec08f8600646079919cb3870a85289e38f64 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_isin.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..380add96f29e168b28616cf326050c29b316288b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_lexsort.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_lexsort.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..865b8820f7e818fc4828d5b63a78befa5d13d909 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_lexsort.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_missing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_missing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7ec159d831362536647e03203e9a1440044b14e2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_missing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_monotonic.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_monotonic.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d64df5d90fa27a66ee7391f87c795c3d3ccf4996 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_monotonic.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_names.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_names.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1b87819d030fb24da9386077db00fdbaadaa960e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_names.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_partial_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_partial_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..02db2c8637cce4437ad3598df9ac69a586a03af3 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_partial_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_pickle.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_pickle.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..aeb6ce81b37b5b9165ab943df811852dfae33c7c Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_pickle.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reindex.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reindex.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5c359c3534190905763d7e6b73ea6f555b4c8fd1 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reindex.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reshape.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reshape.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b6ba625d4346f96617d736a06f8a67ec5c2c6ad9 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_reshape.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b92761596894234ca5deed396a9c8d10765fe44a Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_sorting.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_sorting.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f6e9d9309ccd202a500e09cca716335111605f02 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_sorting.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_take.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_take.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..528ca661576650649e703e4712c145a6952de33b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/multi/__pycache__/test_take.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/conftest.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/conftest.py new file mode 100644 index 0000000000000000000000000000000000000000..15062aee56e3a1b91d1f6eb76a4f86e381e0ad44 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/conftest.py @@ -0,0 +1,27 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + MultiIndex, +) + + +# Note: identical the "multi" entry in the top-level "index" fixture +@pytest.fixture +def idx(): + # a MultiIndex used to test the general functionality of the + # general functionality of this object + major_axis = Index(["foo", "bar", "baz", "qux"]) + minor_axis = Index(["one", "two"]) + + major_codes = np.array([0, 0, 1, 2, 3, 3]) + minor_codes = np.array([0, 1, 0, 1, 0, 1]) + index_names = ["first", "second"] + mi = MultiIndex( + levels=[major_axis, minor_axis], + codes=[major_codes, minor_codes], + names=index_names, + verify_integrity=False, + ) + return mi diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_analytics.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_analytics.py new file mode 100644 index 0000000000000000000000000000000000000000..87f1439db5fc87c3be08e3675df1dae0fdb5554d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_analytics.py @@ -0,0 +1,263 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + MultiIndex, + date_range, + period_range, +) +import pandas._testing as tm + + +def test_infer_objects(idx): + with pytest.raises(NotImplementedError, match="to_frame"): + idx.infer_objects() + + +def test_shift(idx): + # GH8083 test the base class for shift + msg = ( + "This method is only implemented for DatetimeIndex, PeriodIndex and " + "TimedeltaIndex; Got type MultiIndex" + ) + with pytest.raises(NotImplementedError, match=msg): + idx.shift(1) + with pytest.raises(NotImplementedError, match=msg): + idx.shift(1, 2) + + +def test_groupby(idx): + groups = idx.groupby(np.array([1, 1, 1, 2, 2, 2])) + labels = idx.tolist() + exp = {1: labels[:3], 2: labels[3:]} + tm.assert_dict_equal(groups, exp) + + # GH5620 + groups = idx.groupby(idx) + exp = {key: [key] for key in idx} + tm.assert_dict_equal(groups, exp) + + +def test_truncate_multiindex(): + # GH 34564 for MultiIndex level names check + major_axis = Index(list(range(4))) + minor_axis = Index(list(range(2))) + + major_codes = np.array([0, 0, 1, 2, 3, 3]) + minor_codes = np.array([0, 1, 0, 1, 0, 1]) + + index = MultiIndex( + levels=[major_axis, minor_axis], + codes=[major_codes, minor_codes], + names=["L1", "L2"], + ) + + result = index.truncate(before=1) + assert "foo" not in result.levels[0] + assert 1 in result.levels[0] + assert index.names == result.names + + result = index.truncate(after=1) + assert 2 not in result.levels[0] + assert 1 in result.levels[0] + assert index.names == result.names + + result = index.truncate(before=1, after=2) + assert len(result.levels[0]) == 2 + assert index.names == result.names + + msg = "after < before" + with pytest.raises(ValueError, match=msg): + index.truncate(3, 1) + + +# TODO: reshape + + +def test_reorder_levels(idx): + # this blows up + with pytest.raises(IndexError, match="^Too many levels"): + idx.reorder_levels([2, 1, 0]) + + +def test_numpy_repeat(): + reps = 2 + numbers = [1, 2, 3] + names = np.array(["foo", "bar"]) + + m = MultiIndex.from_product([numbers, names], names=names) + expected = MultiIndex.from_product([numbers, names.repeat(reps)], names=names) + tm.assert_index_equal(np.repeat(m, reps), expected) + + msg = "the 'axis' parameter is not supported" + with pytest.raises(ValueError, match=msg): + np.repeat(m, reps, axis=1) + + +def test_append_mixed_dtypes(): + # GH 13660 + dti = date_range("2011-01-01", freq="ME", periods=3) + dti_tz = date_range("2011-01-01", freq="ME", periods=3, tz="US/Eastern") + pi = period_range("2011-01", freq="M", periods=3) + + mi = MultiIndex.from_arrays( + [[1, 2, 3], [1.1, np.nan, 3.3], ["a", "b", "c"], dti, dti_tz, pi] + ) + assert mi.nlevels == 6 + + res = mi.append(mi) + exp = MultiIndex.from_arrays( + [ + [1, 2, 3, 1, 2, 3], + [1.1, np.nan, 3.3, 1.1, np.nan, 3.3], + ["a", "b", "c", "a", "b", "c"], + dti.append(dti), + dti_tz.append(dti_tz), + pi.append(pi), + ] + ) + tm.assert_index_equal(res, exp) + + other = MultiIndex.from_arrays( + [ + ["x", "y", "z"], + ["x", "y", "z"], + ["x", "y", "z"], + ["x", "y", "z"], + ["x", "y", "z"], + ["x", "y", "z"], + ] + ) + + res = mi.append(other) + exp = MultiIndex.from_arrays( + [ + [1, 2, 3, "x", "y", "z"], + [1.1, np.nan, 3.3, "x", "y", "z"], + ["a", "b", "c", "x", "y", "z"], + dti.append(Index(["x", "y", "z"])), + dti_tz.append(Index(["x", "y", "z"])), + pi.append(Index(["x", "y", "z"])), + ] + ) + tm.assert_index_equal(res, exp) + + +def test_iter(idx): + result = list(idx) + expected = [ + ("foo", "one"), + ("foo", "two"), + ("bar", "one"), + ("baz", "two"), + ("qux", "one"), + ("qux", "two"), + ] + assert result == expected + + +def test_sub(idx): + first = idx + + # - now raises (previously was set op difference) + msg = "cannot perform __sub__ with this index type: MultiIndex" + with pytest.raises(TypeError, match=msg): + first - idx[-3:] + with pytest.raises(TypeError, match=msg): + idx[-3:] - first + with pytest.raises(TypeError, match=msg): + idx[-3:] - first.tolist() + msg = "cannot perform __rsub__ with this index type: MultiIndex" + with pytest.raises(TypeError, match=msg): + first.tolist() - idx[-3:] + + +def test_map(idx): + # callable + index = idx + + result = index.map(lambda x: x) + tm.assert_index_equal(result, index) + + +@pytest.mark.parametrize( + "mapper", + [ + lambda values, idx: {i: e for e, i in zip(values, idx)}, + lambda values, idx: pd.Series(values, idx), + ], +) +def test_map_dictlike(idx, mapper): + identity = mapper(idx.values, idx) + + # we don't infer to uint64 dtype for a dict + if idx.dtype == np.uint64 and isinstance(identity, dict): + expected = idx.astype("int64") + else: + expected = idx + + result = idx.map(identity) + tm.assert_index_equal(result, expected) + + # empty mappable + expected = Index([np.nan] * len(idx)) + result = idx.map(mapper(expected, idx)) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + "func", + [ + np.exp, + np.exp2, + np.expm1, + np.log, + np.log2, + np.log10, + np.log1p, + np.sqrt, + np.sin, + np.cos, + np.tan, + np.arcsin, + np.arccos, + np.arctan, + np.sinh, + np.cosh, + np.tanh, + np.arcsinh, + np.arccosh, + np.arctanh, + np.deg2rad, + np.rad2deg, + ], + ids=lambda func: func.__name__, +) +def test_numpy_ufuncs(idx, func): + # test ufuncs of numpy. see: + # https://numpy.org/doc/stable/reference/ufuncs.html + + expected_exception = TypeError + msg = ( + "loop of ufunc does not support argument 0 of type tuple which " + f"has no callable {func.__name__} method" + ) + with pytest.raises(expected_exception, match=msg): + func(idx) + + +@pytest.mark.parametrize( + "func", + [np.isfinite, np.isinf, np.isnan, np.signbit], + ids=lambda func: func.__name__, +) +def test_numpy_type_funcs(idx, func): + msg = ( + f"ufunc '{func.__name__}' not supported for the input types, and the inputs " + "could not be safely coerced to any supported types according to " + "the casting rule ''safe''" + ) + with pytest.raises(TypeError, match=msg): + func(idx) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_astype.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_astype.py new file mode 100644 index 0000000000000000000000000000000000000000..29908537fbe590328ac586e05f90f3cc24cab9ab --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_astype.py @@ -0,0 +1,30 @@ +import numpy as np +import pytest + +from pandas.core.dtypes.dtypes import CategoricalDtype + +import pandas._testing as tm + + +def test_astype(idx): + expected = idx.copy() + actual = idx.astype("O") + tm.assert_copy(actual.levels, expected.levels) + tm.assert_copy(actual.codes, expected.codes) + assert actual.names == list(expected.names) + + with pytest.raises(TypeError, match="^Setting.*dtype.*object"): + idx.astype(np.dtype(int)) + + +@pytest.mark.parametrize("ordered", [True, False]) +def test_astype_category(idx, ordered): + # GH 18630 + msg = "> 1 ndim Categorical are not supported at this time" + with pytest.raises(NotImplementedError, match=msg): + idx.astype(CategoricalDtype(ordered=ordered)) + + if ordered is False: + # dtype='category' defaults to ordered=False, so only test once + with pytest.raises(NotImplementedError, match=msg): + idx.astype("category") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_compat.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_compat.py new file mode 100644 index 0000000000000000000000000000000000000000..27a8c6e9b715880a57e711e8eab457ae553a4867 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_compat.py @@ -0,0 +1,122 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import MultiIndex +import pandas._testing as tm + + +def test_numeric_compat(idx): + with pytest.raises(TypeError, match="cannot perform __mul__"): + idx * 1 + + with pytest.raises(TypeError, match="cannot perform __rmul__"): + 1 * idx + + div_err = "cannot perform __truediv__" + with pytest.raises(TypeError, match=div_err): + idx / 1 + + div_err = div_err.replace(" __", " __r") + with pytest.raises(TypeError, match=div_err): + 1 / idx + + with pytest.raises(TypeError, match="cannot perform __floordiv__"): + idx // 1 + + with pytest.raises(TypeError, match="cannot perform __rfloordiv__"): + 1 // idx + + +@pytest.mark.parametrize("method", ["all", "any", "__invert__"]) +def test_logical_compat(idx, method): + msg = f"cannot perform {method}" + + with pytest.raises(TypeError, match=msg): + getattr(idx, method)() + + +def test_inplace_mutation_resets_values(): + levels = [["a", "b", "c"], [4]] + levels2 = [[1, 2, 3], ["a"]] + codes = [[0, 1, 0, 2, 2, 0], [0, 0, 0, 0, 0, 0]] + + mi1 = MultiIndex(levels=levels, codes=codes) + mi2 = MultiIndex(levels=levels2, codes=codes) + + # instantiating MultiIndex should not access/cache _.values + assert "_values" not in mi1._cache + assert "_values" not in mi2._cache + + vals = mi1.values.copy() + vals2 = mi2.values.copy() + + # accessing .values should cache ._values + assert mi1._values is mi1._cache["_values"] + assert mi1.values is mi1._cache["_values"] + assert isinstance(mi1._cache["_values"], np.ndarray) + + # Make sure level setting works + new_vals = mi1.set_levels(levels2).values + tm.assert_almost_equal(vals2, new_vals) + + # Doesn't drop _values from _cache [implementation detail] + tm.assert_almost_equal(mi1._cache["_values"], vals) + + # ...and values is still same too + tm.assert_almost_equal(mi1.values, vals) + + # Make sure label setting works too + codes2 = [[0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0]] + exp_values = np.empty((6,), dtype=object) + exp_values[:] = [(1, "a")] * 6 + + # Must be 1d array of tuples + assert exp_values.shape == (6,) + + new_mi = mi2.set_codes(codes2) + assert "_values" not in new_mi._cache + new_values = new_mi.values + assert "_values" in new_mi._cache + + # Shouldn't change cache + tm.assert_almost_equal(mi2._cache["_values"], vals2) + + # Should have correct values + tm.assert_almost_equal(exp_values, new_values) + + +def test_boxable_categorical_values(): + cat = pd.Categorical(pd.date_range("2012-01-01", periods=3, freq="h")) + result = MultiIndex.from_product([["a", "b", "c"], cat]).values + expected = pd.Series( + [ + ("a", pd.Timestamp("2012-01-01 00:00:00")), + ("a", pd.Timestamp("2012-01-01 01:00:00")), + ("a", pd.Timestamp("2012-01-01 02:00:00")), + ("b", pd.Timestamp("2012-01-01 00:00:00")), + ("b", pd.Timestamp("2012-01-01 01:00:00")), + ("b", pd.Timestamp("2012-01-01 02:00:00")), + ("c", pd.Timestamp("2012-01-01 00:00:00")), + ("c", pd.Timestamp("2012-01-01 01:00:00")), + ("c", pd.Timestamp("2012-01-01 02:00:00")), + ] + ).values + tm.assert_numpy_array_equal(result, expected) + result = pd.DataFrame({"a": ["a", "b", "c"], "b": cat, "c": np.array(cat)}).values + expected = pd.DataFrame( + { + "a": ["a", "b", "c"], + "b": [ + pd.Timestamp("2012-01-01 00:00:00"), + pd.Timestamp("2012-01-01 01:00:00"), + pd.Timestamp("2012-01-01 02:00:00"), + ], + "c": [ + pd.Timestamp("2012-01-01 00:00:00"), + pd.Timestamp("2012-01-01 01:00:00"), + pd.Timestamp("2012-01-01 02:00:00"), + ], + } + ).values + tm.assert_numpy_array_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..8456e6a7acba5a160556f6f3192fa795ce678786 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_constructors.py @@ -0,0 +1,860 @@ +from datetime import ( + date, + datetime, +) +import itertools + +import numpy as np +import pytest + +from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike + +import pandas as pd +from pandas import ( + Index, + MultiIndex, + Series, + Timestamp, + date_range, +) +import pandas._testing as tm + + +def test_constructor_single_level(): + result = MultiIndex( + levels=[["foo", "bar", "baz", "qux"]], codes=[[0, 1, 2, 3]], names=["first"] + ) + assert isinstance(result, MultiIndex) + expected = Index(["foo", "bar", "baz", "qux"], name="first") + tm.assert_index_equal(result.levels[0], expected) + assert result.names == ["first"] + + +def test_constructor_no_levels(): + msg = "non-zero number of levels/codes" + with pytest.raises(ValueError, match=msg): + MultiIndex(levels=[], codes=[]) + + msg = "Must pass both levels and codes" + with pytest.raises(TypeError, match=msg): + MultiIndex(levels=[]) + with pytest.raises(TypeError, match=msg): + MultiIndex(codes=[]) + + +def test_constructor_nonhashable_names(): + # GH 20527 + levels = [[1, 2], ["one", "two"]] + codes = [[0, 0, 1, 1], [0, 1, 0, 1]] + names = (["foo"], ["bar"]) + msg = r"MultiIndex\.name must be a hashable type" + with pytest.raises(TypeError, match=msg): + MultiIndex(levels=levels, codes=codes, names=names) + + # With .rename() + mi = MultiIndex( + levels=[[1, 2], ["one", "two"]], + codes=[[0, 0, 1, 1], [0, 1, 0, 1]], + names=("foo", "bar"), + ) + renamed = [["fooo"], ["barr"]] + with pytest.raises(TypeError, match=msg): + mi.rename(names=renamed) + + # With .set_names() + with pytest.raises(TypeError, match=msg): + mi.set_names(names=renamed) + + +def test_constructor_mismatched_codes_levels(idx): + codes = [np.array([1]), np.array([2]), np.array([3])] + levels = ["a"] + + msg = "Length of levels and codes must be the same" + with pytest.raises(ValueError, match=msg): + MultiIndex(levels=levels, codes=codes) + + length_error = ( + r"On level 0, code max \(3\) >= length of level \(1\)\. " + "NOTE: this index is in an inconsistent state" + ) + label_error = r"Unequal code lengths: \[4, 2\]" + code_value_error = r"On level 0, code value \(-2\) < -1" + + # important to check that it's looking at the right thing. + with pytest.raises(ValueError, match=length_error): + MultiIndex(levels=[["a"], ["b"]], codes=[[0, 1, 2, 3], [0, 3, 4, 1]]) + + with pytest.raises(ValueError, match=label_error): + MultiIndex(levels=[["a"], ["b"]], codes=[[0, 0, 0, 0], [0, 0]]) + + # external API + with pytest.raises(ValueError, match=length_error): + idx.copy().set_levels([["a"], ["b"]]) + + with pytest.raises(ValueError, match=label_error): + idx.copy().set_codes([[0, 0, 0, 0], [0, 0]]) + + # test set_codes with verify_integrity=False + # the setting should not raise any value error + idx.copy().set_codes(codes=[[0, 0, 0, 0], [0, 0]], verify_integrity=False) + + # code value smaller than -1 + with pytest.raises(ValueError, match=code_value_error): + MultiIndex(levels=[["a"], ["b"]], codes=[[0, -2], [0, 0]]) + + +def test_na_levels(): + # GH26408 + # test if codes are re-assigned value -1 for levels + # with missing values (NaN, NaT, None) + result = MultiIndex( + levels=[[np.nan, None, pd.NaT, 128, 2]], codes=[[0, -1, 1, 2, 3, 4]] + ) + expected = MultiIndex( + levels=[[np.nan, None, pd.NaT, 128, 2]], codes=[[-1, -1, -1, -1, 3, 4]] + ) + tm.assert_index_equal(result, expected) + + result = MultiIndex( + levels=[[np.nan, "s", pd.NaT, 128, None]], codes=[[0, -1, 1, 2, 3, 4]] + ) + expected = MultiIndex( + levels=[[np.nan, "s", pd.NaT, 128, None]], codes=[[-1, -1, 1, -1, 3, -1]] + ) + tm.assert_index_equal(result, expected) + + # verify set_levels and set_codes + result = MultiIndex( + levels=[[1, 2, 3, 4, 5]], codes=[[0, -1, 1, 2, 3, 4]] + ).set_levels([[np.nan, "s", pd.NaT, 128, None]]) + tm.assert_index_equal(result, expected) + + result = MultiIndex( + levels=[[np.nan, "s", pd.NaT, 128, None]], codes=[[1, 2, 2, 2, 2, 2]] + ).set_codes([[0, -1, 1, 2, 3, 4]]) + tm.assert_index_equal(result, expected) + + +def test_copy_in_constructor(): + levels = np.array(["a", "b", "c"]) + codes = np.array([1, 1, 2, 0, 0, 1, 1]) + val = codes[0] + mi = MultiIndex(levels=[levels, levels], codes=[codes, codes], copy=True) + assert mi.codes[0][0] == val + codes[0] = 15 + assert mi.codes[0][0] == val + val = levels[0] + levels[0] = "PANDA" + assert mi.levels[0][0] == val + + +# ---------------------------------------------------------------------------- +# from_arrays +# ---------------------------------------------------------------------------- +def test_from_arrays(idx): + arrays = [ + np.asarray(lev).take(level_codes) + for lev, level_codes in zip(idx.levels, idx.codes) + ] + + # list of arrays as input + result = MultiIndex.from_arrays(arrays, names=idx.names) + tm.assert_index_equal(result, idx) + + # infer correctly + result = MultiIndex.from_arrays([[pd.NaT, Timestamp("20130101")], ["a", "b"]]) + assert result.levels[0].equals(Index([Timestamp("20130101")])) + assert result.levels[1].equals(Index(["a", "b"])) + + +def test_from_arrays_iterator(idx): + # GH 18434 + arrays = [ + np.asarray(lev).take(level_codes) + for lev, level_codes in zip(idx.levels, idx.codes) + ] + + # iterator as input + result = MultiIndex.from_arrays(iter(arrays), names=idx.names) + tm.assert_index_equal(result, idx) + + # invalid iterator input + msg = "Input must be a list / sequence of array-likes." + with pytest.raises(TypeError, match=msg): + MultiIndex.from_arrays(0) + + +def test_from_arrays_tuples(idx): + arrays = tuple( + tuple(np.asarray(lev).take(level_codes)) + for lev, level_codes in zip(idx.levels, idx.codes) + ) + + # tuple of tuples as input + result = MultiIndex.from_arrays(arrays, names=idx.names) + tm.assert_index_equal(result, idx) + + +@pytest.mark.parametrize( + ("idx1", "idx2"), + [ + ( + pd.period_range("2011-01-01", freq="D", periods=3), + pd.period_range("2015-01-01", freq="h", periods=3), + ), + ( + date_range("2015-01-01 10:00", freq="D", periods=3, tz="US/Eastern"), + date_range("2015-01-01 10:00", freq="h", periods=3, tz="Asia/Tokyo"), + ), + ( + pd.timedelta_range("1 days", freq="D", periods=3), + pd.timedelta_range("2 hours", freq="h", periods=3), + ), + ], +) +def test_from_arrays_index_series_period_datetimetz_and_timedelta(idx1, idx2): + result = MultiIndex.from_arrays([idx1, idx2]) + tm.assert_index_equal(result.get_level_values(0), idx1) + tm.assert_index_equal(result.get_level_values(1), idx2) + + result2 = MultiIndex.from_arrays([Series(idx1), Series(idx2)]) + tm.assert_index_equal(result2.get_level_values(0), idx1) + tm.assert_index_equal(result2.get_level_values(1), idx2) + + tm.assert_index_equal(result, result2) + + +def test_from_arrays_index_datetimelike_mixed(): + idx1 = date_range("2015-01-01 10:00", freq="D", periods=3, tz="US/Eastern") + idx2 = date_range("2015-01-01 10:00", freq="h", periods=3) + idx3 = pd.timedelta_range("1 days", freq="D", periods=3) + idx4 = pd.period_range("2011-01-01", freq="D", periods=3) + + result = MultiIndex.from_arrays([idx1, idx2, idx3, idx4]) + tm.assert_index_equal(result.get_level_values(0), idx1) + tm.assert_index_equal(result.get_level_values(1), idx2) + tm.assert_index_equal(result.get_level_values(2), idx3) + tm.assert_index_equal(result.get_level_values(3), idx4) + + result2 = MultiIndex.from_arrays( + [Series(idx1), Series(idx2), Series(idx3), Series(idx4)] + ) + tm.assert_index_equal(result2.get_level_values(0), idx1) + tm.assert_index_equal(result2.get_level_values(1), idx2) + tm.assert_index_equal(result2.get_level_values(2), idx3) + tm.assert_index_equal(result2.get_level_values(3), idx4) + + tm.assert_index_equal(result, result2) + + +def test_from_arrays_index_series_categorical(): + # GH13743 + idx1 = pd.CategoricalIndex(list("abcaab"), categories=list("bac"), ordered=False) + idx2 = pd.CategoricalIndex(list("abcaab"), categories=list("bac"), ordered=True) + + result = MultiIndex.from_arrays([idx1, idx2]) + tm.assert_index_equal(result.get_level_values(0), idx1) + tm.assert_index_equal(result.get_level_values(1), idx2) + + result2 = MultiIndex.from_arrays([Series(idx1), Series(idx2)]) + tm.assert_index_equal(result2.get_level_values(0), idx1) + tm.assert_index_equal(result2.get_level_values(1), idx2) + + result3 = MultiIndex.from_arrays([idx1.values, idx2.values]) + tm.assert_index_equal(result3.get_level_values(0), idx1) + tm.assert_index_equal(result3.get_level_values(1), idx2) + + +def test_from_arrays_empty(): + # 0 levels + msg = "Must pass non-zero number of levels/codes" + with pytest.raises(ValueError, match=msg): + MultiIndex.from_arrays(arrays=[]) + + # 1 level + result = MultiIndex.from_arrays(arrays=[[]], names=["A"]) + assert isinstance(result, MultiIndex) + expected = Index([], name="A") + tm.assert_index_equal(result.levels[0], expected) + assert result.names == ["A"] + + # N levels + for N in [2, 3]: + arrays = [[]] * N + names = list("ABC")[:N] + result = MultiIndex.from_arrays(arrays=arrays, names=names) + expected = MultiIndex(levels=[[]] * N, codes=[[]] * N, names=names) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + "invalid_sequence_of_arrays", + [ + 1, + [1], + [1, 2], + [[1], 2], + [1, [2]], + "a", + ["a"], + ["a", "b"], + [["a"], "b"], + (1,), + (1, 2), + ([1], 2), + (1, [2]), + "a", + ("a",), + ("a", "b"), + (["a"], "b"), + [(1,), 2], + [1, (2,)], + [("a",), "b"], + ((1,), 2), + (1, (2,)), + (("a",), "b"), + ], +) +def test_from_arrays_invalid_input(invalid_sequence_of_arrays): + msg = "Input must be a list / sequence of array-likes" + with pytest.raises(TypeError, match=msg): + MultiIndex.from_arrays(arrays=invalid_sequence_of_arrays) + + +@pytest.mark.parametrize( + "idx1, idx2", [([1, 2, 3], ["a", "b"]), ([], ["a", "b"]), ([1, 2, 3], [])] +) +def test_from_arrays_different_lengths(idx1, idx2): + # see gh-13599 + msg = "^all arrays must be same length$" + with pytest.raises(ValueError, match=msg): + MultiIndex.from_arrays([idx1, idx2]) + + +def test_from_arrays_respects_none_names(): + # GH27292 + a = Series([1, 2, 3], name="foo") + b = Series(["a", "b", "c"], name="bar") + + result = MultiIndex.from_arrays([a, b], names=None) + expected = MultiIndex( + levels=[[1, 2, 3], ["a", "b", "c"]], codes=[[0, 1, 2], [0, 1, 2]], names=None + ) + + tm.assert_index_equal(result, expected) + + +# ---------------------------------------------------------------------------- +# from_tuples +# ---------------------------------------------------------------------------- +def test_from_tuples(): + msg = "Cannot infer number of levels from empty list" + with pytest.raises(TypeError, match=msg): + MultiIndex.from_tuples([]) + + expected = MultiIndex( + levels=[[1, 3], [2, 4]], codes=[[0, 1], [0, 1]], names=["a", "b"] + ) + + # input tuples + result = MultiIndex.from_tuples(((1, 2), (3, 4)), names=["a", "b"]) + tm.assert_index_equal(result, expected) + + +def test_from_tuples_iterator(): + # GH 18434 + # input iterator for tuples + expected = MultiIndex( + levels=[[1, 3], [2, 4]], codes=[[0, 1], [0, 1]], names=["a", "b"] + ) + + result = MultiIndex.from_tuples(zip([1, 3], [2, 4]), names=["a", "b"]) + tm.assert_index_equal(result, expected) + + # input non-iterables + msg = "Input must be a list / sequence of tuple-likes." + with pytest.raises(TypeError, match=msg): + MultiIndex.from_tuples(0) + + +def test_from_tuples_empty(): + # GH 16777 + result = MultiIndex.from_tuples([], names=["a", "b"]) + expected = MultiIndex.from_arrays(arrays=[[], []], names=["a", "b"]) + tm.assert_index_equal(result, expected) + + +def test_from_tuples_index_values(idx): + result = MultiIndex.from_tuples(idx) + assert (result.values == idx.values).all() + + +def test_tuples_with_name_string(): + # GH 15110 and GH 14848 + + li = [(0, 0, 1), (0, 1, 0), (1, 0, 0)] + msg = "Names should be list-like for a MultiIndex" + with pytest.raises(ValueError, match=msg): + Index(li, name="abc") + with pytest.raises(ValueError, match=msg): + Index(li, name="a") + + +def test_from_tuples_with_tuple_label(): + # GH 15457 + expected = pd.DataFrame( + [[2, 1, 2], [4, (1, 2), 3]], columns=["a", "b", "c"] + ).set_index(["a", "b"]) + idx = MultiIndex.from_tuples([(2, 1), (4, (1, 2))], names=("a", "b")) + result = pd.DataFrame([2, 3], columns=["c"], index=idx) + tm.assert_frame_equal(expected, result) + + +# ---------------------------------------------------------------------------- +# from_product +# ---------------------------------------------------------------------------- +def test_from_product_empty_zero_levels(): + # 0 levels + msg = "Must pass non-zero number of levels/codes" + with pytest.raises(ValueError, match=msg): + MultiIndex.from_product([]) + + +def test_from_product_empty_one_level(): + result = MultiIndex.from_product([[]], names=["A"]) + expected = Index([], name="A") + tm.assert_index_equal(result.levels[0], expected) + assert result.names == ["A"] + + +@pytest.mark.parametrize( + "first, second", [([], []), (["foo", "bar", "baz"], []), ([], ["a", "b", "c"])] +) +def test_from_product_empty_two_levels(first, second): + names = ["A", "B"] + result = MultiIndex.from_product([first, second], names=names) + expected = MultiIndex(levels=[first, second], codes=[[], []], names=names) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("N", list(range(4))) +def test_from_product_empty_three_levels(N): + # GH12258 + names = ["A", "B", "C"] + lvl2 = list(range(N)) + result = MultiIndex.from_product([[], lvl2, []], names=names) + expected = MultiIndex(levels=[[], lvl2, []], codes=[[], [], []], names=names) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + "invalid_input", [1, [1], [1, 2], [[1], 2], "a", ["a"], ["a", "b"], [["a"], "b"]] +) +def test_from_product_invalid_input(invalid_input): + msg = r"Input must be a list / sequence of iterables|Input must be list-like" + with pytest.raises(TypeError, match=msg): + MultiIndex.from_product(iterables=invalid_input) + + +def test_from_product_datetimeindex(): + dt_index = date_range("2000-01-01", periods=2) + mi = MultiIndex.from_product([[1, 2], dt_index]) + etalon = construct_1d_object_array_from_listlike( + [ + (1, Timestamp("2000-01-01")), + (1, Timestamp("2000-01-02")), + (2, Timestamp("2000-01-01")), + (2, Timestamp("2000-01-02")), + ] + ) + tm.assert_numpy_array_equal(mi.values, etalon) + + +def test_from_product_rangeindex(): + # RangeIndex is preserved by factorize, so preserved in levels + rng = Index(range(5)) + other = ["a", "b"] + mi = MultiIndex.from_product([rng, other]) + tm.assert_index_equal(mi._levels[0], rng, exact=True) + + +@pytest.mark.parametrize("ordered", [False, True]) +@pytest.mark.parametrize("f", [lambda x: x, lambda x: Series(x), lambda x: x.values]) +def test_from_product_index_series_categorical(ordered, f): + # GH13743 + first = ["foo", "bar"] + + idx = pd.CategoricalIndex(list("abcaab"), categories=list("bac"), ordered=ordered) + expected = pd.CategoricalIndex( + list("abcaab") + list("abcaab"), categories=list("bac"), ordered=ordered + ) + + result = MultiIndex.from_product([first, f(idx)]) + tm.assert_index_equal(result.get_level_values(1), expected) + + +def test_from_product(): + first = ["foo", "bar", "buz"] + second = ["a", "b", "c"] + names = ["first", "second"] + result = MultiIndex.from_product([first, second], names=names) + + tuples = [ + ("foo", "a"), + ("foo", "b"), + ("foo", "c"), + ("bar", "a"), + ("bar", "b"), + ("bar", "c"), + ("buz", "a"), + ("buz", "b"), + ("buz", "c"), + ] + expected = MultiIndex.from_tuples(tuples, names=names) + + tm.assert_index_equal(result, expected) + + +def test_from_product_iterator(): + # GH 18434 + first = ["foo", "bar", "buz"] + second = ["a", "b", "c"] + names = ["first", "second"] + tuples = [ + ("foo", "a"), + ("foo", "b"), + ("foo", "c"), + ("bar", "a"), + ("bar", "b"), + ("bar", "c"), + ("buz", "a"), + ("buz", "b"), + ("buz", "c"), + ] + expected = MultiIndex.from_tuples(tuples, names=names) + + # iterator as input + result = MultiIndex.from_product(iter([first, second]), names=names) + tm.assert_index_equal(result, expected) + + # Invalid non-iterable input + msg = "Input must be a list / sequence of iterables." + with pytest.raises(TypeError, match=msg): + MultiIndex.from_product(0) + + +@pytest.mark.parametrize( + "a, b, expected_names", + [ + ( + Series([1, 2, 3], name="foo"), + Series(["a", "b"], name="bar"), + ["foo", "bar"], + ), + (Series([1, 2, 3], name="foo"), ["a", "b"], ["foo", None]), + ([1, 2, 3], ["a", "b"], None), + ], +) +def test_from_product_infer_names(a, b, expected_names): + # GH27292 + result = MultiIndex.from_product([a, b]) + expected = MultiIndex( + levels=[[1, 2, 3], ["a", "b"]], + codes=[[0, 0, 1, 1, 2, 2], [0, 1, 0, 1, 0, 1]], + names=expected_names, + ) + tm.assert_index_equal(result, expected) + + +def test_from_product_respects_none_names(): + # GH27292 + a = Series([1, 2, 3], name="foo") + b = Series(["a", "b"], name="bar") + + result = MultiIndex.from_product([a, b], names=None) + expected = MultiIndex( + levels=[[1, 2, 3], ["a", "b"]], + codes=[[0, 0, 1, 1, 2, 2], [0, 1, 0, 1, 0, 1]], + names=None, + ) + tm.assert_index_equal(result, expected) + + +def test_from_product_readonly(): + # GH#15286 passing read-only array to from_product + a = np.array(range(3)) + b = ["a", "b"] + expected = MultiIndex.from_product([a, b]) + + a.setflags(write=False) + result = MultiIndex.from_product([a, b]) + tm.assert_index_equal(result, expected) + + +def test_create_index_existing_name(idx): + # GH11193, when an existing index is passed, and a new name is not + # specified, the new index should inherit the previous object name + index = idx + index.names = ["foo", "bar"] + result = Index(index) + expected = Index( + Index( + [ + ("foo", "one"), + ("foo", "two"), + ("bar", "one"), + ("baz", "two"), + ("qux", "one"), + ("qux", "two"), + ], + dtype="object", + ) + ) + tm.assert_index_equal(result, expected) + + result = Index(index, name="A") + expected = Index( + Index( + [ + ("foo", "one"), + ("foo", "two"), + ("bar", "one"), + ("baz", "two"), + ("qux", "one"), + ("qux", "two"), + ], + dtype="object", + ), + name="A", + ) + tm.assert_index_equal(result, expected) + + +# ---------------------------------------------------------------------------- +# from_frame +# ---------------------------------------------------------------------------- +def test_from_frame(): + # GH 22420 + df = pd.DataFrame( + [["a", "a"], ["a", "b"], ["b", "a"], ["b", "b"]], columns=["L1", "L2"] + ) + expected = MultiIndex.from_tuples( + [("a", "a"), ("a", "b"), ("b", "a"), ("b", "b")], names=["L1", "L2"] + ) + result = MultiIndex.from_frame(df) + tm.assert_index_equal(expected, result) + + +def test_from_frame_missing_values_multiIndex(): + # GH 39984 + pa = pytest.importorskip("pyarrow") + + df = pd.DataFrame( + { + "a": Series([1, 2, None], dtype="Int64"), + "b": pd.Float64Dtype().__from_arrow__(pa.array([0.2, np.nan, None])), + } + ) + multi_indexed = MultiIndex.from_frame(df) + expected = MultiIndex.from_arrays( + [ + Series([1, 2, None]).astype("Int64"), + pd.Float64Dtype().__from_arrow__(pa.array([0.2, np.nan, None])), + ], + names=["a", "b"], + ) + tm.assert_index_equal(multi_indexed, expected) + + +@pytest.mark.parametrize( + "non_frame", + [ + Series([1, 2, 3, 4]), + [1, 2, 3, 4], + [[1, 2], [3, 4], [5, 6]], + Index([1, 2, 3, 4]), + np.array([[1, 2], [3, 4], [5, 6]]), + 27, + ], +) +def test_from_frame_error(non_frame): + # GH 22420 + with pytest.raises(TypeError, match="Input must be a DataFrame"): + MultiIndex.from_frame(non_frame) + + +def test_from_frame_dtype_fidelity(): + # GH 22420 + df = pd.DataFrame( + { + "dates": date_range("19910905", periods=6, tz="US/Eastern"), + "a": [1, 1, 1, 2, 2, 2], + "b": pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True), + "c": ["x", "x", "y", "z", "x", "y"], + } + ) + original_dtypes = df.dtypes.to_dict() + + expected_mi = MultiIndex.from_arrays( + [ + date_range("19910905", periods=6, tz="US/Eastern"), + [1, 1, 1, 2, 2, 2], + pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True), + ["x", "x", "y", "z", "x", "y"], + ], + names=["dates", "a", "b", "c"], + ) + mi = MultiIndex.from_frame(df) + mi_dtypes = {name: mi.levels[i].dtype for i, name in enumerate(mi.names)} + + tm.assert_index_equal(expected_mi, mi) + assert original_dtypes == mi_dtypes + + +@pytest.mark.parametrize( + "names_in,names_out", [(None, [("L1", "x"), ("L2", "y")]), (["x", "y"], ["x", "y"])] +) +def test_from_frame_valid_names(names_in, names_out): + # GH 22420 + df = pd.DataFrame( + [["a", "a"], ["a", "b"], ["b", "a"], ["b", "b"]], + columns=MultiIndex.from_tuples([("L1", "x"), ("L2", "y")]), + ) + mi = MultiIndex.from_frame(df, names=names_in) + assert mi.names == names_out + + +@pytest.mark.parametrize( + "names,expected_error_msg", + [ + ("bad_input", "Names should be list-like for a MultiIndex"), + (["a", "b", "c"], "Length of names must match number of levels in MultiIndex"), + ], +) +def test_from_frame_invalid_names(names, expected_error_msg): + # GH 22420 + df = pd.DataFrame( + [["a", "a"], ["a", "b"], ["b", "a"], ["b", "b"]], + columns=MultiIndex.from_tuples([("L1", "x"), ("L2", "y")]), + ) + with pytest.raises(ValueError, match=expected_error_msg): + MultiIndex.from_frame(df, names=names) + + +def test_index_equal_empty_iterable(): + # #16844 + a = MultiIndex(levels=[[], []], codes=[[], []], names=["a", "b"]) + b = MultiIndex.from_arrays(arrays=[[], []], names=["a", "b"]) + tm.assert_index_equal(a, b) + + +def test_raise_invalid_sortorder(): + # Test that the MultiIndex constructor raise when a incorrect sortorder is given + # GH#28518 + + levels = [[0, 1], [0, 1, 2]] + + # Correct sortorder + MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]], sortorder=2 + ) + + with pytest.raises(ValueError, match=r".* sortorder 2 with lexsort_depth 1.*"): + MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 2, 1]], sortorder=2 + ) + + with pytest.raises(ValueError, match=r".* sortorder 1 with lexsort_depth 0.*"): + MultiIndex( + levels=levels, codes=[[0, 0, 1, 0, 1, 1], [0, 1, 0, 2, 2, 1]], sortorder=1 + ) + + +def test_datetimeindex(): + idx1 = pd.DatetimeIndex( + ["2013-04-01 9:00", "2013-04-02 9:00", "2013-04-03 9:00"] * 2, tz="Asia/Tokyo" + ) + idx2 = date_range("2010/01/01", periods=6, freq="ME", tz="US/Eastern") + idx = MultiIndex.from_arrays([idx1, idx2]) + + expected1 = pd.DatetimeIndex( + ["2013-04-01 9:00", "2013-04-02 9:00", "2013-04-03 9:00"], tz="Asia/Tokyo" + ) + + tm.assert_index_equal(idx.levels[0], expected1) + tm.assert_index_equal(idx.levels[1], idx2) + + # from datetime combos + # GH 7888 + date1 = np.datetime64("today") + date2 = datetime.today() + date3 = Timestamp.today() + + for d1, d2 in itertools.product([date1, date2, date3], [date1, date2, date3]): + index = MultiIndex.from_product([[d1], [d2]]) + assert isinstance(index.levels[0], pd.DatetimeIndex) + assert isinstance(index.levels[1], pd.DatetimeIndex) + + # but NOT date objects, matching Index behavior + date4 = date.today() + index = MultiIndex.from_product([[date4], [date2]]) + assert not isinstance(index.levels[0], pd.DatetimeIndex) + assert isinstance(index.levels[1], pd.DatetimeIndex) + + +def test_constructor_with_tz(): + index = pd.DatetimeIndex( + ["2013/01/01 09:00", "2013/01/02 09:00"], name="dt1", tz="US/Pacific" + ) + columns = pd.DatetimeIndex( + ["2014/01/01 09:00", "2014/01/02 09:00"], name="dt2", tz="Asia/Tokyo" + ) + + result = MultiIndex.from_arrays([index, columns]) + + assert result.names == ["dt1", "dt2"] + tm.assert_index_equal(result.levels[0], index) + tm.assert_index_equal(result.levels[1], columns) + + result = MultiIndex.from_arrays([Series(index), Series(columns)]) + + assert result.names == ["dt1", "dt2"] + tm.assert_index_equal(result.levels[0], index) + tm.assert_index_equal(result.levels[1], columns) + + +def test_multiindex_inference_consistency(): + # check that inference behavior matches the base class + + v = date.today() + + arr = [v, v] + + idx = Index(arr) + assert idx.dtype == object + + mi = MultiIndex.from_arrays([arr]) + lev = mi.levels[0] + assert lev.dtype == object + + mi = MultiIndex.from_product([arr]) + lev = mi.levels[0] + assert lev.dtype == object + + mi = MultiIndex.from_tuples([(x,) for x in arr]) + lev = mi.levels[0] + assert lev.dtype == object + + +def test_dtype_representation(using_infer_string): + # GH#46900 + pmidx = MultiIndex.from_arrays([[1], ["a"]], names=[("a", "b"), ("c", "d")]) + result = pmidx.dtypes + exp = "object" if not using_infer_string else "string" + expected = Series( + ["int64", exp], + index=MultiIndex.from_tuples([("a", "b"), ("c", "d")]), + dtype=object, + ) + tm.assert_series_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_conversion.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_conversion.py new file mode 100644 index 0000000000000000000000000000000000000000..3c2ca045d6f990837fae4d2b3d7bcbbf40e175e9 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_conversion.py @@ -0,0 +1,164 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + DataFrame, + MultiIndex, +) +import pandas._testing as tm + + +def test_to_numpy(idx): + result = idx.to_numpy() + exp = idx.values + tm.assert_numpy_array_equal(result, exp) + + +def test_to_frame(): + tuples = [(1, "one"), (1, "two"), (2, "one"), (2, "two")] + + index = MultiIndex.from_tuples(tuples) + result = index.to_frame(index=False) + expected = DataFrame(tuples) + tm.assert_frame_equal(result, expected) + + result = index.to_frame() + expected.index = index + tm.assert_frame_equal(result, expected) + + tuples = [(1, "one"), (1, "two"), (2, "one"), (2, "two")] + index = MultiIndex.from_tuples(tuples, names=["first", "second"]) + result = index.to_frame(index=False) + expected = DataFrame(tuples) + expected.columns = ["first", "second"] + tm.assert_frame_equal(result, expected) + + result = index.to_frame() + expected.index = index + tm.assert_frame_equal(result, expected) + + # See GH-22580 + index = MultiIndex.from_tuples(tuples) + result = index.to_frame(index=False, name=["first", "second"]) + expected = DataFrame(tuples) + expected.columns = ["first", "second"] + tm.assert_frame_equal(result, expected) + + result = index.to_frame(name=["first", "second"]) + expected.index = index + expected.columns = ["first", "second"] + tm.assert_frame_equal(result, expected) + + msg = "'name' must be a list / sequence of column names." + with pytest.raises(TypeError, match=msg): + index.to_frame(name="first") + + msg = "'name' should have same length as number of levels on index." + with pytest.raises(ValueError, match=msg): + index.to_frame(name=["first"]) + + # Tests for datetime index + index = MultiIndex.from_product([range(5), pd.date_range("20130101", periods=3)]) + result = index.to_frame(index=False) + expected = DataFrame( + { + 0: np.repeat(np.arange(5, dtype="int64"), 3), + 1: np.tile(pd.date_range("20130101", periods=3), 5), + } + ) + tm.assert_frame_equal(result, expected) + + result = index.to_frame() + expected.index = index + tm.assert_frame_equal(result, expected) + + # See GH-22580 + result = index.to_frame(index=False, name=["first", "second"]) + expected = DataFrame( + { + "first": np.repeat(np.arange(5, dtype="int64"), 3), + "second": np.tile(pd.date_range("20130101", periods=3), 5), + } + ) + tm.assert_frame_equal(result, expected) + + result = index.to_frame(name=["first", "second"]) + expected.index = index + tm.assert_frame_equal(result, expected) + + +def test_to_frame_dtype_fidelity(): + # GH 22420 + mi = MultiIndex.from_arrays( + [ + pd.date_range("19910905", periods=6, tz="US/Eastern"), + [1, 1, 1, 2, 2, 2], + pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True), + ["x", "x", "y", "z", "x", "y"], + ], + names=["dates", "a", "b", "c"], + ) + original_dtypes = {name: mi.levels[i].dtype for i, name in enumerate(mi.names)} + + expected_df = DataFrame( + { + "dates": pd.date_range("19910905", periods=6, tz="US/Eastern"), + "a": [1, 1, 1, 2, 2, 2], + "b": pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True), + "c": ["x", "x", "y", "z", "x", "y"], + } + ) + df = mi.to_frame(index=False) + df_dtypes = df.dtypes.to_dict() + + tm.assert_frame_equal(df, expected_df) + assert original_dtypes == df_dtypes + + +def test_to_frame_resulting_column_order(): + # GH 22420 + expected = ["z", 0, "a"] + mi = MultiIndex.from_arrays( + [["a", "b", "c"], ["x", "y", "z"], ["q", "w", "e"]], names=expected + ) + result = mi.to_frame().columns.tolist() + assert result == expected + + +def test_to_frame_duplicate_labels(): + # GH 45245 + data = [(1, 2), (3, 4)] + names = ["a", "a"] + index = MultiIndex.from_tuples(data, names=names) + with pytest.raises(ValueError, match="Cannot create duplicate column labels"): + index.to_frame() + + result = index.to_frame(allow_duplicates=True) + expected = DataFrame(data, index=index, columns=names) + tm.assert_frame_equal(result, expected) + + names = [None, 0] + index = MultiIndex.from_tuples(data, names=names) + with pytest.raises(ValueError, match="Cannot create duplicate column labels"): + index.to_frame() + + result = index.to_frame(allow_duplicates=True) + expected = DataFrame(data, index=index, columns=[0, 0]) + tm.assert_frame_equal(result, expected) + + +def test_to_flat_index(idx): + expected = pd.Index( + ( + ("foo", "one"), + ("foo", "two"), + ("bar", "one"), + ("baz", "two"), + ("qux", "one"), + ("qux", "two"), + ), + tupleize_cols=False, + ) + result = idx.to_flat_index() + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_copy.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_copy.py new file mode 100644 index 0000000000000000000000000000000000000000..2e09a580f9528bc8197d55c6a7533098e0129fa2 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_copy.py @@ -0,0 +1,96 @@ +from copy import ( + copy, + deepcopy, +) + +import pytest + +from pandas import MultiIndex +import pandas._testing as tm + + +def assert_multiindex_copied(copy, original): + # Levels should be (at least, shallow copied) + tm.assert_copy(copy.levels, original.levels) + tm.assert_almost_equal(copy.codes, original.codes) + + # Labels doesn't matter which way copied + tm.assert_almost_equal(copy.codes, original.codes) + assert copy.codes is not original.codes + + # Names doesn't matter which way copied + assert copy.names == original.names + assert copy.names is not original.names + + # Sort order should be copied + assert copy.sortorder == original.sortorder + + +def test_copy(idx): + i_copy = idx.copy() + + assert_multiindex_copied(i_copy, idx) + + +def test_shallow_copy(idx): + i_copy = idx._view() + + assert_multiindex_copied(i_copy, idx) + + +def test_view(idx): + i_view = idx.view() + assert_multiindex_copied(i_view, idx) + + +@pytest.mark.parametrize("func", [copy, deepcopy]) +def test_copy_and_deepcopy(func): + idx = MultiIndex( + levels=[["foo", "bar"], ["fizz", "buzz"]], + codes=[[0, 0, 0, 1], [0, 0, 1, 1]], + names=["first", "second"], + ) + idx_copy = func(idx) + assert idx_copy is not idx + assert idx_copy.equals(idx) + + +@pytest.mark.parametrize("deep", [True, False]) +def test_copy_method(deep): + idx = MultiIndex( + levels=[["foo", "bar"], ["fizz", "buzz"]], + codes=[[0, 0, 0, 1], [0, 0, 1, 1]], + names=["first", "second"], + ) + idx_copy = idx.copy(deep=deep) + assert idx_copy.equals(idx) + + +@pytest.mark.parametrize("deep", [True, False]) +@pytest.mark.parametrize( + "kwarg, value", + [ + ("names", ["third", "fourth"]), + ], +) +def test_copy_method_kwargs(deep, kwarg, value): + # gh-12309: Check that the "name" argument as well other kwargs are honored + idx = MultiIndex( + levels=[["foo", "bar"], ["fizz", "buzz"]], + codes=[[0, 0, 0, 1], [0, 0, 1, 1]], + names=["first", "second"], + ) + idx_copy = idx.copy(**{kwarg: value, "deep": deep}) + assert getattr(idx_copy, kwarg) == value + + +def test_copy_deep_false_retains_id(): + # GH#47878 + idx = MultiIndex( + levels=[["foo", "bar"], ["fizz", "buzz"]], + codes=[[0, 0, 0, 1], [0, 0, 1, 1]], + names=["first", "second"], + ) + + res = idx.copy(deep=False) + assert res._id is idx._id diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_drop.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_drop.py new file mode 100644 index 0000000000000000000000000000000000000000..99c8ebb1e57b22059d5a545a79de7b8348d73b14 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_drop.py @@ -0,0 +1,190 @@ +import numpy as np +import pytest + +from pandas.errors import PerformanceWarning + +import pandas as pd +from pandas import ( + Index, + MultiIndex, +) +import pandas._testing as tm + + +def test_drop(idx): + dropped = idx.drop([("foo", "two"), ("qux", "one")]) + + index = MultiIndex.from_tuples([("foo", "two"), ("qux", "one")]) + dropped2 = idx.drop(index) + + expected = idx[[0, 2, 3, 5]] + tm.assert_index_equal(dropped, expected) + tm.assert_index_equal(dropped2, expected) + + dropped = idx.drop(["bar"]) + expected = idx[[0, 1, 3, 4, 5]] + tm.assert_index_equal(dropped, expected) + + dropped = idx.drop("foo") + expected = idx[[2, 3, 4, 5]] + tm.assert_index_equal(dropped, expected) + + index = MultiIndex.from_tuples([("bar", "two")]) + with pytest.raises(KeyError, match=r"^\('bar', 'two'\)$"): + idx.drop([("bar", "two")]) + with pytest.raises(KeyError, match=r"^\('bar', 'two'\)$"): + idx.drop(index) + with pytest.raises(KeyError, match=r"^'two'$"): + idx.drop(["foo", "two"]) + + # partially correct argument + mixed_index = MultiIndex.from_tuples([("qux", "one"), ("bar", "two")]) + with pytest.raises(KeyError, match=r"^\('bar', 'two'\)$"): + idx.drop(mixed_index) + + # error='ignore' + dropped = idx.drop(index, errors="ignore") + expected = idx[[0, 1, 2, 3, 4, 5]] + tm.assert_index_equal(dropped, expected) + + dropped = idx.drop(mixed_index, errors="ignore") + expected = idx[[0, 1, 2, 3, 5]] + tm.assert_index_equal(dropped, expected) + + dropped = idx.drop(["foo", "two"], errors="ignore") + expected = idx[[2, 3, 4, 5]] + tm.assert_index_equal(dropped, expected) + + # mixed partial / full drop + dropped = idx.drop(["foo", ("qux", "one")]) + expected = idx[[2, 3, 5]] + tm.assert_index_equal(dropped, expected) + + # mixed partial / full drop / error='ignore' + mixed_index = ["foo", ("qux", "one"), "two"] + with pytest.raises(KeyError, match=r"^'two'$"): + idx.drop(mixed_index) + dropped = idx.drop(mixed_index, errors="ignore") + expected = idx[[2, 3, 5]] + tm.assert_index_equal(dropped, expected) + + +def test_droplevel_with_names(idx): + index = idx[idx.get_loc("foo")] + dropped = index.droplevel(0) + assert dropped.name == "second" + + index = MultiIndex( + levels=[Index(range(4)), Index(range(4)), Index(range(4))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + names=["one", "two", "three"], + ) + dropped = index.droplevel(0) + assert dropped.names == ("two", "three") + + dropped = index.droplevel("two") + expected = index.droplevel(1) + assert dropped.equals(expected) + + +def test_droplevel_list(): + index = MultiIndex( + levels=[Index(range(4)), Index(range(4)), Index(range(4))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + names=["one", "two", "three"], + ) + + dropped = index[:2].droplevel(["three", "one"]) + expected = index[:2].droplevel(2).droplevel(0) + assert dropped.equals(expected) + + dropped = index[:2].droplevel([]) + expected = index[:2] + assert dropped.equals(expected) + + msg = ( + "Cannot remove 3 levels from an index with 3 levels: " + "at least one level must be left" + ) + with pytest.raises(ValueError, match=msg): + index[:2].droplevel(["one", "two", "three"]) + + with pytest.raises(KeyError, match="'Level four not found'"): + index[:2].droplevel(["one", "four"]) + + +def test_drop_not_lexsorted(): + # GH 12078 + + # define the lexsorted version of the multi-index + tuples = [("a", ""), ("b1", "c1"), ("b2", "c2")] + lexsorted_mi = MultiIndex.from_tuples(tuples, names=["b", "c"]) + assert lexsorted_mi._is_lexsorted() + + # and the not-lexsorted version + df = pd.DataFrame( + columns=["a", "b", "c", "d"], data=[[1, "b1", "c1", 3], [1, "b2", "c2", 4]] + ) + df = df.pivot_table(index="a", columns=["b", "c"], values="d") + df = df.reset_index() + not_lexsorted_mi = df.columns + assert not not_lexsorted_mi._is_lexsorted() + + # compare the results + tm.assert_index_equal(lexsorted_mi, not_lexsorted_mi) + with tm.assert_produces_warning(PerformanceWarning): + tm.assert_index_equal(lexsorted_mi.drop("a"), not_lexsorted_mi.drop("a")) + + +def test_drop_with_nan_in_index(nulls_fixture): + # GH#18853 + mi = MultiIndex.from_tuples([("blah", nulls_fixture)], names=["name", "date"]) + msg = r"labels \[Timestamp\('2001-01-01 00:00:00'\)\] not found in level" + with pytest.raises(KeyError, match=msg): + mi.drop(pd.Timestamp("2001"), level="date") + + +@pytest.mark.filterwarnings("ignore::pandas.errors.PerformanceWarning") +def test_drop_with_non_monotonic_duplicates(): + # GH#33494 + mi = MultiIndex.from_tuples([(1, 2), (2, 3), (1, 2)]) + result = mi.drop((1, 2)) + expected = MultiIndex.from_tuples([(2, 3)]) + tm.assert_index_equal(result, expected) + + +def test_single_level_drop_partially_missing_elements(): + # GH 37820 + + mi = MultiIndex.from_tuples([(1, 2), (2, 2), (3, 2)]) + msg = r"labels \[4\] not found in level" + with pytest.raises(KeyError, match=msg): + mi.drop(4, level=0) + with pytest.raises(KeyError, match=msg): + mi.drop([1, 4], level=0) + msg = r"labels \[nan\] not found in level" + with pytest.raises(KeyError, match=msg): + mi.drop([np.nan], level=0) + with pytest.raises(KeyError, match=msg): + mi.drop([np.nan, 1, 2, 3], level=0) + + mi = MultiIndex.from_tuples([(np.nan, 1), (1, 2)]) + msg = r"labels \['a'\] not found in level" + with pytest.raises(KeyError, match=msg): + mi.drop([np.nan, 1, "a"], level=0) + + +def test_droplevel_multiindex_one_level(): + # GH#37208 + index = MultiIndex.from_tuples([(2,)], names=("b",)) + result = index.droplevel([]) + expected = Index([2], name="b") + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_duplicates.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_duplicates.py new file mode 100644 index 0000000000000000000000000000000000000000..6c6d9022b1af31e905b5ec739753af77a52f438b --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_duplicates.py @@ -0,0 +1,363 @@ +from itertools import product + +import numpy as np +import pytest + +from pandas._libs import ( + hashtable, + index as libindex, +) + +from pandas import ( + NA, + DatetimeIndex, + Index, + MultiIndex, + Series, +) +import pandas._testing as tm + + +@pytest.fixture +def idx_dup(): + # compare tests/indexes/multi/conftest.py + major_axis = Index(["foo", "bar", "baz", "qux"]) + minor_axis = Index(["one", "two"]) + + major_codes = np.array([0, 0, 1, 0, 1, 1]) + minor_codes = np.array([0, 1, 0, 1, 0, 1]) + index_names = ["first", "second"] + mi = MultiIndex( + levels=[major_axis, minor_axis], + codes=[major_codes, minor_codes], + names=index_names, + verify_integrity=False, + ) + return mi + + +@pytest.mark.parametrize("names", [None, ["first", "second"]]) +def test_unique(names): + mi = MultiIndex.from_arrays([[1, 2, 1, 2], [1, 1, 1, 2]], names=names) + + res = mi.unique() + exp = MultiIndex.from_arrays([[1, 2, 2], [1, 1, 2]], names=mi.names) + tm.assert_index_equal(res, exp) + + mi = MultiIndex.from_arrays([list("aaaa"), list("abab")], names=names) + res = mi.unique() + exp = MultiIndex.from_arrays([list("aa"), list("ab")], names=mi.names) + tm.assert_index_equal(res, exp) + + mi = MultiIndex.from_arrays([list("aaaa"), list("aaaa")], names=names) + res = mi.unique() + exp = MultiIndex.from_arrays([["a"], ["a"]], names=mi.names) + tm.assert_index_equal(res, exp) + + # GH #20568 - empty MI + mi = MultiIndex.from_arrays([[], []], names=names) + res = mi.unique() + tm.assert_index_equal(mi, res) + + +def test_unique_datetimelike(): + idx1 = DatetimeIndex( + ["2015-01-01", "2015-01-01", "2015-01-01", "2015-01-01", "NaT", "NaT"] + ) + idx2 = DatetimeIndex( + ["2015-01-01", "2015-01-01", "2015-01-02", "2015-01-02", "NaT", "2015-01-01"], + tz="Asia/Tokyo", + ) + result = MultiIndex.from_arrays([idx1, idx2]).unique() + + eidx1 = DatetimeIndex(["2015-01-01", "2015-01-01", "NaT", "NaT"]) + eidx2 = DatetimeIndex( + ["2015-01-01", "2015-01-02", "NaT", "2015-01-01"], tz="Asia/Tokyo" + ) + exp = MultiIndex.from_arrays([eidx1, eidx2]) + tm.assert_index_equal(result, exp) + + +@pytest.mark.parametrize("level", [0, "first", 1, "second"]) +def test_unique_level(idx, level): + # GH #17896 - with level= argument + result = idx.unique(level=level) + expected = idx.get_level_values(level).unique() + tm.assert_index_equal(result, expected) + + # With already unique level + mi = MultiIndex.from_arrays([[1, 3, 2, 4], [1, 3, 2, 5]], names=["first", "second"]) + result = mi.unique(level=level) + expected = mi.get_level_values(level) + tm.assert_index_equal(result, expected) + + # With empty MI + mi = MultiIndex.from_arrays([[], []], names=["first", "second"]) + result = mi.unique(level=level) + expected = mi.get_level_values(level) + tm.assert_index_equal(result, expected) + + +def test_duplicate_multiindex_codes(): + # GH 17464 + # Make sure that a MultiIndex with duplicate levels throws a ValueError + msg = r"Level values must be unique: \[[A', ]+\] on level 0" + with pytest.raises(ValueError, match=msg): + mi = MultiIndex([["A"] * 10, range(10)], [[0] * 10, range(10)]) + + # And that using set_levels with duplicate levels fails + mi = MultiIndex.from_arrays([["A", "A", "B", "B", "B"], [1, 2, 1, 2, 3]]) + msg = r"Level values must be unique: \[[AB', ]+\] on level 0" + with pytest.raises(ValueError, match=msg): + mi.set_levels([["A", "B", "A", "A", "B"], [2, 1, 3, -2, 5]]) + + +@pytest.mark.parametrize("names", [["a", "b", "a"], [1, 1, 2], [1, "a", 1]]) +def test_duplicate_level_names(names): + # GH18872, GH19029 + mi = MultiIndex.from_product([[0, 1]] * 3, names=names) + assert mi.names == names + + # With .rename() + mi = MultiIndex.from_product([[0, 1]] * 3) + mi = mi.rename(names) + assert mi.names == names + + # With .rename(., level=) + mi.rename(names[1], level=1, inplace=True) + mi = mi.rename([names[0], names[2]], level=[0, 2]) + assert mi.names == names + + +def test_duplicate_meta_data(): + # GH 10115 + mi = MultiIndex( + levels=[[0, 1], [0, 1, 2]], codes=[[0, 0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 0, 1, 2]] + ) + + for idx in [ + mi, + mi.set_names([None, None]), + mi.set_names([None, "Num"]), + mi.set_names(["Upper", "Num"]), + ]: + assert idx.has_duplicates + assert idx.drop_duplicates().names == idx.names + + +def test_has_duplicates(idx, idx_dup): + # see fixtures + assert idx.is_unique is True + assert idx.has_duplicates is False + assert idx_dup.is_unique is False + assert idx_dup.has_duplicates is True + + mi = MultiIndex( + levels=[[0, 1], [0, 1, 2]], codes=[[0, 0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 0, 1, 2]] + ) + assert mi.is_unique is False + assert mi.has_duplicates is True + + # single instance of NaN + mi_nan = MultiIndex( + levels=[["a", "b"], [0, 1]], codes=[[-1, 0, 0, 1, 1], [-1, 0, 1, 0, 1]] + ) + assert mi_nan.is_unique is True + assert mi_nan.has_duplicates is False + + # multiple instances of NaN + mi_nan_dup = MultiIndex( + levels=[["a", "b"], [0, 1]], codes=[[-1, -1, 0, 0, 1, 1], [-1, -1, 0, 1, 0, 1]] + ) + assert mi_nan_dup.is_unique is False + assert mi_nan_dup.has_duplicates is True + + +def test_has_duplicates_from_tuples(): + # GH 9075 + t = [ + ("x", "out", "z", 5, "y", "in", "z", 169), + ("x", "out", "z", 7, "y", "in", "z", 119), + ("x", "out", "z", 9, "y", "in", "z", 135), + ("x", "out", "z", 13, "y", "in", "z", 145), + ("x", "out", "z", 14, "y", "in", "z", 158), + ("x", "out", "z", 16, "y", "in", "z", 122), + ("x", "out", "z", 17, "y", "in", "z", 160), + ("x", "out", "z", 18, "y", "in", "z", 180), + ("x", "out", "z", 20, "y", "in", "z", 143), + ("x", "out", "z", 21, "y", "in", "z", 128), + ("x", "out", "z", 22, "y", "in", "z", 129), + ("x", "out", "z", 25, "y", "in", "z", 111), + ("x", "out", "z", 28, "y", "in", "z", 114), + ("x", "out", "z", 29, "y", "in", "z", 121), + ("x", "out", "z", 31, "y", "in", "z", 126), + ("x", "out", "z", 32, "y", "in", "z", 155), + ("x", "out", "z", 33, "y", "in", "z", 123), + ("x", "out", "z", 12, "y", "in", "z", 144), + ] + + mi = MultiIndex.from_tuples(t) + assert not mi.has_duplicates + + +@pytest.mark.parametrize("nlevels", [4, 8]) +@pytest.mark.parametrize("with_nulls", [True, False]) +def test_has_duplicates_overflow(nlevels, with_nulls): + # handle int64 overflow if possible + # no overflow with 4 + # overflow possible with 8 + codes = np.tile(np.arange(500), 2) + level = np.arange(500) + + if with_nulls: # inject some null values + codes[500] = -1 # common nan value + codes = [codes.copy() for i in range(nlevels)] + for i in range(nlevels): + codes[i][500 + i - nlevels // 2] = -1 + + codes += [np.array([-1, 1]).repeat(500)] + else: + codes = [codes] * nlevels + [np.arange(2).repeat(500)] + + levels = [level] * nlevels + [[0, 1]] + + # no dups + mi = MultiIndex(levels=levels, codes=codes) + assert not mi.has_duplicates + + # with a dup + if with_nulls: + + def f(a): + return np.insert(a, 1000, a[0]) + + codes = list(map(f, codes)) + mi = MultiIndex(levels=levels, codes=codes) + else: + values = mi.values.tolist() + mi = MultiIndex.from_tuples(values + [values[0]]) + + assert mi.has_duplicates + + +@pytest.mark.parametrize( + "keep, expected", + [ + ("first", np.array([False, False, False, True, True, False])), + ("last", np.array([False, True, True, False, False, False])), + (False, np.array([False, True, True, True, True, False])), + ], +) +def test_duplicated(idx_dup, keep, expected): + result = idx_dup.duplicated(keep=keep) + tm.assert_numpy_array_equal(result, expected) + + +@pytest.mark.arm_slow +def test_duplicated_hashtable_impl(keep, monkeypatch): + # GH 9125 + n, k = 6, 10 + levels = [np.arange(n), [str(i) for i in range(n)], 1000 + np.arange(n)] + codes = [np.random.default_rng(2).choice(n, k * n) for _ in levels] + with monkeypatch.context() as m: + m.setattr(libindex, "_SIZE_CUTOFF", 50) + mi = MultiIndex(levels=levels, codes=codes) + + result = mi.duplicated(keep=keep) + expected = hashtable.duplicated(mi.values, keep=keep) + tm.assert_numpy_array_equal(result, expected) + + +@pytest.mark.parametrize("val", [101, 102]) +def test_duplicated_with_nan(val): + # GH5873 + mi = MultiIndex.from_arrays([[101, val], [3.5, np.nan]]) + assert not mi.has_duplicates + + tm.assert_numpy_array_equal(mi.duplicated(), np.zeros(2, dtype="bool")) + + +@pytest.mark.parametrize("n", range(1, 6)) +@pytest.mark.parametrize("m", range(1, 5)) +def test_duplicated_with_nan_multi_shape(n, m): + # GH5873 + # all possible unique combinations, including nan + codes = product(range(-1, n), range(-1, m)) + mi = MultiIndex( + levels=[list("abcde")[:n], list("WXYZ")[:m]], + codes=np.random.default_rng(2).permutation(list(codes)).T, + ) + assert len(mi) == (n + 1) * (m + 1) + assert not mi.has_duplicates + + tm.assert_numpy_array_equal(mi.duplicated(), np.zeros(len(mi), dtype="bool")) + + +def test_duplicated_drop_duplicates(): + # GH#4060 + idx = MultiIndex.from_arrays(([1, 2, 3, 1, 2, 3], [1, 1, 1, 1, 2, 2])) + + expected = np.array([False, False, False, True, False, False], dtype=bool) + duplicated = idx.duplicated() + tm.assert_numpy_array_equal(duplicated, expected) + assert duplicated.dtype == bool + expected = MultiIndex.from_arrays(([1, 2, 3, 2, 3], [1, 1, 1, 2, 2])) + tm.assert_index_equal(idx.drop_duplicates(), expected) + + expected = np.array([True, False, False, False, False, False]) + duplicated = idx.duplicated(keep="last") + tm.assert_numpy_array_equal(duplicated, expected) + assert duplicated.dtype == bool + expected = MultiIndex.from_arrays(([2, 3, 1, 2, 3], [1, 1, 1, 2, 2])) + tm.assert_index_equal(idx.drop_duplicates(keep="last"), expected) + + expected = np.array([True, False, False, True, False, False]) + duplicated = idx.duplicated(keep=False) + tm.assert_numpy_array_equal(duplicated, expected) + assert duplicated.dtype == bool + expected = MultiIndex.from_arrays(([2, 3, 2, 3], [1, 1, 2, 2])) + tm.assert_index_equal(idx.drop_duplicates(keep=False), expected) + + +@pytest.mark.parametrize( + "dtype", + [ + np.complex64, + np.complex128, + ], +) +def test_duplicated_series_complex_numbers(dtype): + # GH 17927 + expected = Series( + [False, False, False, True, False, False, False, True, False, True], + dtype=bool, + ) + result = Series( + [ + np.nan + np.nan * 1j, + 0, + 1j, + 1j, + 1, + 1 + 1j, + 1 + 2j, + 1 + 1j, + np.nan, + np.nan + np.nan * 1j, + ], + dtype=dtype, + ).duplicated() + tm.assert_series_equal(result, expected) + + +def test_midx_unique_ea_dtype(): + # GH#48335 + vals_a = Series([1, 2, NA, NA], dtype="Int64") + vals_b = np.array([1, 2, 3, 3]) + midx = MultiIndex.from_arrays([vals_a, vals_b], names=["a", "b"]) + result = midx.unique() + + exp_vals_a = Series([1, 2, NA], dtype="Int64") + exp_vals_b = np.array([1, 2, 3]) + expected = MultiIndex.from_arrays([exp_vals_a, exp_vals_b], names=["a", "b"]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_equivalence.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_equivalence.py new file mode 100644 index 0000000000000000000000000000000000000000..9babbd5b8d56d64d704978758efb81f8d730274f --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_equivalence.py @@ -0,0 +1,284 @@ +import numpy as np +import pytest + +from pandas.core.dtypes.common import is_any_real_numeric_dtype + +import pandas as pd +from pandas import ( + Index, + MultiIndex, + Series, +) +import pandas._testing as tm + + +def test_equals(idx): + assert idx.equals(idx) + assert idx.equals(idx.copy()) + assert idx.equals(idx.astype(object)) + assert idx.equals(idx.to_flat_index()) + assert idx.equals(idx.to_flat_index().astype("category")) + + assert not idx.equals(list(idx)) + assert not idx.equals(np.array(idx)) + + same_values = Index(idx, dtype=object) + assert idx.equals(same_values) + assert same_values.equals(idx) + + if idx.nlevels == 1: + # do not test MultiIndex + assert not idx.equals(Series(idx)) + + +def test_equals_op(idx): + # GH9947, GH10637 + index_a = idx + + n = len(index_a) + index_b = index_a[0:-1] + index_c = index_a[0:-1].append(index_a[-2:-1]) + index_d = index_a[0:1] + with pytest.raises(ValueError, match="Lengths must match"): + index_a == index_b + expected1 = np.array([True] * n) + expected2 = np.array([True] * (n - 1) + [False]) + tm.assert_numpy_array_equal(index_a == index_a, expected1) + tm.assert_numpy_array_equal(index_a == index_c, expected2) + + # test comparisons with numpy arrays + array_a = np.array(index_a) + array_b = np.array(index_a[0:-1]) + array_c = np.array(index_a[0:-1].append(index_a[-2:-1])) + array_d = np.array(index_a[0:1]) + with pytest.raises(ValueError, match="Lengths must match"): + index_a == array_b + tm.assert_numpy_array_equal(index_a == array_a, expected1) + tm.assert_numpy_array_equal(index_a == array_c, expected2) + + # test comparisons with Series + series_a = Series(array_a) + series_b = Series(array_b) + series_c = Series(array_c) + series_d = Series(array_d) + with pytest.raises(ValueError, match="Lengths must match"): + index_a == series_b + + tm.assert_numpy_array_equal(index_a == series_a, expected1) + tm.assert_numpy_array_equal(index_a == series_c, expected2) + + # cases where length is 1 for one of them + with pytest.raises(ValueError, match="Lengths must match"): + index_a == index_d + with pytest.raises(ValueError, match="Lengths must match"): + index_a == series_d + with pytest.raises(ValueError, match="Lengths must match"): + index_a == array_d + msg = "Can only compare identically-labeled Series objects" + with pytest.raises(ValueError, match=msg): + series_a == series_d + with pytest.raises(ValueError, match="Lengths must match"): + series_a == array_d + + # comparing with a scalar should broadcast; note that we are excluding + # MultiIndex because in this case each item in the index is a tuple of + # length 2, and therefore is considered an array of length 2 in the + # comparison instead of a scalar + if not isinstance(index_a, MultiIndex): + expected3 = np.array([False] * (len(index_a) - 2) + [True, False]) + # assuming the 2nd to last item is unique in the data + item = index_a[-2] + tm.assert_numpy_array_equal(index_a == item, expected3) + tm.assert_series_equal(series_a == item, Series(expected3)) + + +def test_compare_tuple(): + # GH#21517 + mi = MultiIndex.from_product([[1, 2]] * 2) + + all_false = np.array([False, False, False, False]) + + result = mi == mi[0] + expected = np.array([True, False, False, False]) + tm.assert_numpy_array_equal(result, expected) + + result = mi != mi[0] + tm.assert_numpy_array_equal(result, ~expected) + + result = mi < mi[0] + tm.assert_numpy_array_equal(result, all_false) + + result = mi <= mi[0] + tm.assert_numpy_array_equal(result, expected) + + result = mi > mi[0] + tm.assert_numpy_array_equal(result, ~expected) + + result = mi >= mi[0] + tm.assert_numpy_array_equal(result, ~all_false) + + +def test_compare_tuple_strs(): + # GH#34180 + + mi = MultiIndex.from_tuples([("a", "b"), ("b", "c"), ("c", "a")]) + + result = mi == ("c", "a") + expected = np.array([False, False, True]) + tm.assert_numpy_array_equal(result, expected) + + result = mi == ("c",) + expected = np.array([False, False, False]) + tm.assert_numpy_array_equal(result, expected) + + +def test_equals_multi(idx): + assert idx.equals(idx) + assert not idx.equals(idx.values) + assert idx.equals(Index(idx.values)) + + assert idx.equal_levels(idx) + assert not idx.equals(idx[:-1]) + assert not idx.equals(idx[-1]) + + # different number of levels + index = MultiIndex( + levels=[Index(list(range(4))), Index(list(range(4))), Index(list(range(4)))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + ) + + index2 = MultiIndex(levels=index.levels[:-1], codes=index.codes[:-1]) + assert not index.equals(index2) + assert not index.equal_levels(index2) + + # levels are different + major_axis = Index(list(range(4))) + minor_axis = Index(list(range(2))) + + major_codes = np.array([0, 0, 1, 2, 2, 3]) + minor_codes = np.array([0, 1, 0, 0, 1, 0]) + + index = MultiIndex( + levels=[major_axis, minor_axis], codes=[major_codes, minor_codes] + ) + assert not idx.equals(index) + assert not idx.equal_levels(index) + + # some of the labels are different + major_axis = Index(["foo", "bar", "baz", "qux"]) + minor_axis = Index(["one", "two"]) + + major_codes = np.array([0, 0, 2, 2, 3, 3]) + minor_codes = np.array([0, 1, 0, 1, 0, 1]) + + index = MultiIndex( + levels=[major_axis, minor_axis], codes=[major_codes, minor_codes] + ) + assert not idx.equals(index) + + +def test_identical(idx): + mi = idx.copy() + mi2 = idx.copy() + assert mi.identical(mi2) + + mi = mi.set_names(["new1", "new2"]) + assert mi.equals(mi2) + assert not mi.identical(mi2) + + mi2 = mi2.set_names(["new1", "new2"]) + assert mi.identical(mi2) + + mi4 = Index(mi.tolist(), tupleize_cols=False) + assert not mi.identical(mi4) + assert mi.equals(mi4) + + +def test_equals_operator(idx): + # GH9785 + assert (idx == idx).all() + + +def test_equals_missing_values(): + # make sure take is not using -1 + i = MultiIndex.from_tuples([(0, pd.NaT), (0, pd.Timestamp("20130101"))]) + result = i[0:1].equals(i[0]) + assert not result + result = i[1:2].equals(i[1]) + assert not result + + +def test_equals_missing_values_differently_sorted(): + # GH#38439 + mi1 = MultiIndex.from_tuples([(81.0, np.nan), (np.nan, np.nan)]) + mi2 = MultiIndex.from_tuples([(np.nan, np.nan), (81.0, np.nan)]) + assert not mi1.equals(mi2) + + mi2 = MultiIndex.from_tuples([(81.0, np.nan), (np.nan, np.nan)]) + assert mi1.equals(mi2) + + +def test_is_(): + mi = MultiIndex.from_tuples(zip(range(10), range(10))) + assert mi.is_(mi) + assert mi.is_(mi.view()) + assert mi.is_(mi.view().view().view().view()) + mi2 = mi.view() + # names are metadata, they don't change id + mi2.names = ["A", "B"] + assert mi2.is_(mi) + assert mi.is_(mi2) + + assert not mi.is_(mi.set_names(["C", "D"])) + # levels are inherent properties, they change identity + mi3 = mi2.set_levels([list(range(10)), list(range(10))]) + assert not mi3.is_(mi2) + # shouldn't change + assert mi2.is_(mi) + mi4 = mi3.view() + + # GH 17464 - Remove duplicate MultiIndex levels + mi4 = mi4.set_levels([list(range(10)), list(range(10))]) + assert not mi4.is_(mi3) + mi5 = mi.view() + mi5 = mi5.set_levels(mi5.levels) + assert not mi5.is_(mi) + + +def test_is_all_dates(idx): + assert not idx._is_all_dates + + +def test_is_numeric(idx): + # MultiIndex is never numeric + assert not is_any_real_numeric_dtype(idx) + + +def test_multiindex_compare(): + # GH 21149 + # Ensure comparison operations for MultiIndex with nlevels == 1 + # behave consistently with those for MultiIndex with nlevels > 1 + + midx = MultiIndex.from_product([[0, 1]]) + + # Equality self-test: MultiIndex object vs self + expected = Series([True, True]) + result = Series(midx == midx) + tm.assert_series_equal(result, expected) + + # Greater than comparison: MultiIndex object vs self + expected = Series([False, False]) + result = Series(midx > midx) + tm.assert_series_equal(result, expected) + + +def test_equals_ea_int_regular_int(): + # GH#46026 + mi1 = MultiIndex.from_arrays([Index([1, 2], dtype="Int64"), [3, 4]]) + mi2 = MultiIndex.from_arrays([[1, 2], [3, 4]]) + assert not mi1.equals(mi2) + assert not mi2.equals(mi1) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_formats.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_formats.py new file mode 100644 index 0000000000000000000000000000000000000000..52ff3109128f24f43d9a12527d08770b463459a5 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_formats.py @@ -0,0 +1,249 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + MultiIndex, +) +import pandas._testing as tm + + +def test_format(idx): + msg = "MultiIndex.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + idx.format() + idx[:0].format() + + +def test_format_integer_names(): + index = MultiIndex( + levels=[[0, 1], [0, 1]], codes=[[0, 0, 1, 1], [0, 1, 0, 1]], names=[0, 1] + ) + msg = "MultiIndex.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + index.format(names=True) + + +def test_format_sparse_config(idx): + # GH1538 + msg = "MultiIndex.format is deprecated" + with pd.option_context("display.multi_sparse", False): + with tm.assert_produces_warning(FutureWarning, match=msg): + result = idx.format() + assert result[1] == "foo two" + + +def test_format_sparse_display(): + index = MultiIndex( + levels=[[0, 1], [0, 1], [0, 1], [0]], + codes=[ + [0, 0, 0, 1, 1, 1], + [0, 0, 1, 0, 0, 1], + [0, 1, 0, 0, 1, 0], + [0, 0, 0, 0, 0, 0], + ], + ) + msg = "MultiIndex.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = index.format() + assert result[3] == "1 0 0 0" + + +def test_repr_with_unicode_data(): + with pd.option_context("display.encoding", "UTF-8"): + d = {"a": ["\u05d0", 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]} + index = pd.DataFrame(d).set_index(["a", "b"]).index + assert "\\" not in repr(index) # we don't want unicode-escaped + + +def test_repr_roundtrip_raises(): + mi = MultiIndex.from_product([list("ab"), range(3)], names=["first", "second"]) + msg = "Must pass both levels and codes" + with pytest.raises(TypeError, match=msg): + eval(repr(mi)) + + +def test_unicode_string_with_unicode(): + d = {"a": ["\u05d0", 2, 3], "b": [4, 5, 6], "c": [7, 8, 9]} + idx = pd.DataFrame(d).set_index(["a", "b"]).index + str(idx) + + +def test_repr_max_seq_item_setting(idx): + # GH10182 + idx = idx.repeat(50) + with pd.option_context("display.max_seq_items", None): + repr(idx) + assert "..." not in str(idx) + + +class TestRepr: + def test_unicode_repr_issues(self): + levels = [Index(["a/\u03c3", "b/\u03c3", "c/\u03c3"]), Index([0, 1])] + codes = [np.arange(3).repeat(2), np.tile(np.arange(2), 3)] + index = MultiIndex(levels=levels, codes=codes) + + repr(index.levels) + repr(index.get_level_values(1)) + + def test_repr_max_seq_items_equal_to_n(self, idx): + # display.max_seq_items == n + with pd.option_context("display.max_seq_items", 6): + result = idx.__repr__() + expected = """\ +MultiIndex([('foo', 'one'), + ('foo', 'two'), + ('bar', 'one'), + ('baz', 'two'), + ('qux', 'one'), + ('qux', 'two')], + names=['first', 'second'])""" + assert result == expected + + def test_repr(self, idx): + result = idx[:1].__repr__() + expected = """\ +MultiIndex([('foo', 'one')], + names=['first', 'second'])""" + assert result == expected + + result = idx.__repr__() + expected = """\ +MultiIndex([('foo', 'one'), + ('foo', 'two'), + ('bar', 'one'), + ('baz', 'two'), + ('qux', 'one'), + ('qux', 'two')], + names=['first', 'second'])""" + assert result == expected + + with pd.option_context("display.max_seq_items", 5): + result = idx.__repr__() + expected = """\ +MultiIndex([('foo', 'one'), + ('foo', 'two'), + ... + ('qux', 'one'), + ('qux', 'two')], + names=['first', 'second'], length=6)""" + assert result == expected + + # display.max_seq_items == 1 + with pd.option_context("display.max_seq_items", 1): + result = idx.__repr__() + expected = """\ +MultiIndex([... + ('qux', 'two')], + names=['first', ...], length=6)""" + assert result == expected + + def test_rjust(self): + n = 1000 + ci = pd.CategoricalIndex(list("a" * n) + (["abc"] * n)) + dti = pd.date_range("2000-01-01", freq="s", periods=n * 2) + mi = MultiIndex.from_arrays([ci, ci.codes + 9, dti], names=["a", "b", "dti"]) + result = mi[:1].__repr__() + expected = """\ +MultiIndex([('a', 9, '2000-01-01 00:00:00')], + names=['a', 'b', 'dti'])""" + assert result == expected + + result = mi[::500].__repr__() + expected = """\ +MultiIndex([( 'a', 9, '2000-01-01 00:00:00'), + ( 'a', 9, '2000-01-01 00:08:20'), + ('abc', 10, '2000-01-01 00:16:40'), + ('abc', 10, '2000-01-01 00:25:00')], + names=['a', 'b', 'dti'])""" + assert result == expected + + result = mi.__repr__() + expected = """\ +MultiIndex([( 'a', 9, '2000-01-01 00:00:00'), + ( 'a', 9, '2000-01-01 00:00:01'), + ( 'a', 9, '2000-01-01 00:00:02'), + ( 'a', 9, '2000-01-01 00:00:03'), + ( 'a', 9, '2000-01-01 00:00:04'), + ( 'a', 9, '2000-01-01 00:00:05'), + ( 'a', 9, '2000-01-01 00:00:06'), + ( 'a', 9, '2000-01-01 00:00:07'), + ( 'a', 9, '2000-01-01 00:00:08'), + ( 'a', 9, '2000-01-01 00:00:09'), + ... + ('abc', 10, '2000-01-01 00:33:10'), + ('abc', 10, '2000-01-01 00:33:11'), + ('abc', 10, '2000-01-01 00:33:12'), + ('abc', 10, '2000-01-01 00:33:13'), + ('abc', 10, '2000-01-01 00:33:14'), + ('abc', 10, '2000-01-01 00:33:15'), + ('abc', 10, '2000-01-01 00:33:16'), + ('abc', 10, '2000-01-01 00:33:17'), + ('abc', 10, '2000-01-01 00:33:18'), + ('abc', 10, '2000-01-01 00:33:19')], + names=['a', 'b', 'dti'], length=2000)""" + assert result == expected + + def test_tuple_width(self): + n = 1000 + ci = pd.CategoricalIndex(list("a" * n) + (["abc"] * n)) + dti = pd.date_range("2000-01-01", freq="s", periods=n * 2) + levels = [ci, ci.codes + 9, dti, dti, dti] + names = ["a", "b", "dti_1", "dti_2", "dti_3"] + mi = MultiIndex.from_arrays(levels, names=names) + result = mi[:1].__repr__() + expected = """MultiIndex([('a', 9, '2000-01-01 00:00:00', '2000-01-01 00:00:00', ...)], + names=['a', 'b', 'dti_1', 'dti_2', 'dti_3'])""" # noqa: E501 + assert result == expected + + result = mi[:10].__repr__() + expected = """\ +MultiIndex([('a', 9, '2000-01-01 00:00:00', '2000-01-01 00:00:00', ...), + ('a', 9, '2000-01-01 00:00:01', '2000-01-01 00:00:01', ...), + ('a', 9, '2000-01-01 00:00:02', '2000-01-01 00:00:02', ...), + ('a', 9, '2000-01-01 00:00:03', '2000-01-01 00:00:03', ...), + ('a', 9, '2000-01-01 00:00:04', '2000-01-01 00:00:04', ...), + ('a', 9, '2000-01-01 00:00:05', '2000-01-01 00:00:05', ...), + ('a', 9, '2000-01-01 00:00:06', '2000-01-01 00:00:06', ...), + ('a', 9, '2000-01-01 00:00:07', '2000-01-01 00:00:07', ...), + ('a', 9, '2000-01-01 00:00:08', '2000-01-01 00:00:08', ...), + ('a', 9, '2000-01-01 00:00:09', '2000-01-01 00:00:09', ...)], + names=['a', 'b', 'dti_1', 'dti_2', 'dti_3'])""" + assert result == expected + + result = mi.__repr__() + expected = """\ +MultiIndex([( 'a', 9, '2000-01-01 00:00:00', '2000-01-01 00:00:00', ...), + ( 'a', 9, '2000-01-01 00:00:01', '2000-01-01 00:00:01', ...), + ( 'a', 9, '2000-01-01 00:00:02', '2000-01-01 00:00:02', ...), + ( 'a', 9, '2000-01-01 00:00:03', '2000-01-01 00:00:03', ...), + ( 'a', 9, '2000-01-01 00:00:04', '2000-01-01 00:00:04', ...), + ( 'a', 9, '2000-01-01 00:00:05', '2000-01-01 00:00:05', ...), + ( 'a', 9, '2000-01-01 00:00:06', '2000-01-01 00:00:06', ...), + ( 'a', 9, '2000-01-01 00:00:07', '2000-01-01 00:00:07', ...), + ( 'a', 9, '2000-01-01 00:00:08', '2000-01-01 00:00:08', ...), + ( 'a', 9, '2000-01-01 00:00:09', '2000-01-01 00:00:09', ...), + ... + ('abc', 10, '2000-01-01 00:33:10', '2000-01-01 00:33:10', ...), + ('abc', 10, '2000-01-01 00:33:11', '2000-01-01 00:33:11', ...), + ('abc', 10, '2000-01-01 00:33:12', '2000-01-01 00:33:12', ...), + ('abc', 10, '2000-01-01 00:33:13', '2000-01-01 00:33:13', ...), + ('abc', 10, '2000-01-01 00:33:14', '2000-01-01 00:33:14', ...), + ('abc', 10, '2000-01-01 00:33:15', '2000-01-01 00:33:15', ...), + ('abc', 10, '2000-01-01 00:33:16', '2000-01-01 00:33:16', ...), + ('abc', 10, '2000-01-01 00:33:17', '2000-01-01 00:33:17', ...), + ('abc', 10, '2000-01-01 00:33:18', '2000-01-01 00:33:18', ...), + ('abc', 10, '2000-01-01 00:33:19', '2000-01-01 00:33:19', ...)], + names=['a', 'b', 'dti_1', 'dti_2', 'dti_3'], length=2000)""" + assert result == expected + + def test_multiindex_long_element(self): + # Non-regression test towards GH#52960 + data = MultiIndex.from_tuples([("c" * 62,)]) + + expected = ( + "MultiIndex([('cccccccccccccccccccccccccccccccccccccccc" + "cccccccccccccccccccccc',)],\n )" + ) + assert str(data) == expected diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_level_values.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_level_values.py new file mode 100644 index 0000000000000000000000000000000000000000..28c77e78924cbc35feed4ae838b81f6be38478b5 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_level_values.py @@ -0,0 +1,124 @@ +import numpy as np + +import pandas as pd +from pandas import ( + CategoricalIndex, + Index, + MultiIndex, + Timestamp, + date_range, +) +import pandas._testing as tm + + +class TestGetLevelValues: + def test_get_level_values_box_datetime64(self): + dates = date_range("1/1/2000", periods=4) + levels = [dates, [0, 1]] + codes = [[0, 0, 1, 1, 2, 2, 3, 3], [0, 1, 0, 1, 0, 1, 0, 1]] + + index = MultiIndex(levels=levels, codes=codes) + + assert isinstance(index.get_level_values(0)[0], Timestamp) + + +def test_get_level_values(idx): + result = idx.get_level_values(0) + expected = Index(["foo", "foo", "bar", "baz", "qux", "qux"], name="first") + tm.assert_index_equal(result, expected) + assert result.name == "first" + + result = idx.get_level_values("first") + expected = idx.get_level_values(0) + tm.assert_index_equal(result, expected) + + # GH 10460 + index = MultiIndex( + levels=[CategoricalIndex(["A", "B"]), CategoricalIndex([1, 2, 3])], + codes=[np.array([0, 0, 0, 1, 1, 1]), np.array([0, 1, 2, 0, 1, 2])], + ) + + exp = CategoricalIndex(["A", "A", "A", "B", "B", "B"]) + tm.assert_index_equal(index.get_level_values(0), exp) + exp = CategoricalIndex([1, 2, 3, 1, 2, 3]) + tm.assert_index_equal(index.get_level_values(1), exp) + + +def test_get_level_values_all_na(): + # GH#17924 when level entirely consists of nan + arrays = [[np.nan, np.nan, np.nan], ["a", np.nan, 1]] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(0) + expected = Index([np.nan, np.nan, np.nan], dtype=np.float64) + tm.assert_index_equal(result, expected) + + result = index.get_level_values(1) + expected = Index(["a", np.nan, 1], dtype=object) + tm.assert_index_equal(result, expected) + + +def test_get_level_values_int_with_na(): + # GH#17924 + arrays = [["a", "b", "b"], [1, np.nan, 2]] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(1) + expected = Index([1, np.nan, 2]) + tm.assert_index_equal(result, expected) + + arrays = [["a", "b", "b"], [np.nan, np.nan, 2]] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(1) + expected = Index([np.nan, np.nan, 2]) + tm.assert_index_equal(result, expected) + + +def test_get_level_values_na(): + arrays = [[np.nan, np.nan, np.nan], ["a", np.nan, 1]] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(0) + expected = Index([np.nan, np.nan, np.nan]) + tm.assert_index_equal(result, expected) + + result = index.get_level_values(1) + expected = Index(["a", np.nan, 1]) + tm.assert_index_equal(result, expected) + + arrays = [["a", "b", "b"], pd.DatetimeIndex([0, 1, pd.NaT])] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(1) + expected = pd.DatetimeIndex([0, 1, pd.NaT]) + tm.assert_index_equal(result, expected) + + arrays = [[], []] + index = MultiIndex.from_arrays(arrays) + result = index.get_level_values(0) + expected = Index([], dtype=object) + tm.assert_index_equal(result, expected) + + +def test_get_level_values_when_periods(): + # GH33131. See also discussion in GH32669. + # This test can probably be removed when PeriodIndex._engine is removed. + from pandas import ( + Period, + PeriodIndex, + ) + + idx = MultiIndex.from_arrays( + [PeriodIndex([Period("2019Q1"), Period("2019Q2")], name="b")] + ) + idx2 = MultiIndex.from_arrays( + [idx._get_level_values(level) for level in range(idx.nlevels)] + ) + assert all(x.is_monotonic_increasing for x in idx2.levels) + + +def test_values_loses_freq_of_underlying_index(): + # GH#49054 + idx = pd.DatetimeIndex(date_range("20200101", periods=3, freq="BME")) + expected = idx.copy(deep=True) + idx2 = Index([1, 2, 3]) + midx = MultiIndex(levels=[idx, idx2], codes=[[0, 1, 2], [0, 1, 2]]) + midx.values + assert idx.freq is not None + tm.assert_index_equal(idx, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_set.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_set.py new file mode 100644 index 0000000000000000000000000000000000000000..6eeaeb6711d03c981fb190964de2ec5501380378 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_get_set.py @@ -0,0 +1,384 @@ +import numpy as np +import pytest + +from pandas.compat import PY311 + +from pandas.core.dtypes.dtypes import DatetimeTZDtype + +import pandas as pd +from pandas import ( + CategoricalIndex, + MultiIndex, +) +import pandas._testing as tm + + +def assert_matching(actual, expected, check_dtype=False): + # avoid specifying internal representation + # as much as possible + assert len(actual) == len(expected) + for act, exp in zip(actual, expected): + act = np.asarray(act) + exp = np.asarray(exp) + tm.assert_numpy_array_equal(act, exp, check_dtype=check_dtype) + + +def test_get_level_number_integer(idx): + idx.names = [1, 0] + assert idx._get_level_number(1) == 0 + assert idx._get_level_number(0) == 1 + msg = "Too many levels: Index has only 2 levels, not 3" + with pytest.raises(IndexError, match=msg): + idx._get_level_number(2) + with pytest.raises(KeyError, match="Level fourth not found"): + idx._get_level_number("fourth") + + +def test_get_dtypes(using_infer_string): + # Test MultiIndex.dtypes (# Gh37062) + idx_multitype = MultiIndex.from_product( + [[1, 2, 3], ["a", "b", "c"], pd.date_range("20200101", periods=2, tz="UTC")], + names=["int", "string", "dt"], + ) + + exp = "object" if not using_infer_string else "string" + expected = pd.Series( + { + "int": np.dtype("int64"), + "string": exp, + "dt": DatetimeTZDtype(tz="utc"), + } + ) + tm.assert_series_equal(expected, idx_multitype.dtypes) + + +def test_get_dtypes_no_level_name(using_infer_string): + # Test MultiIndex.dtypes (# GH38580 ) + idx_multitype = MultiIndex.from_product( + [ + [1, 2, 3], + ["a", "b", "c"], + pd.date_range("20200101", periods=2, tz="UTC"), + ], + ) + exp = "object" if not using_infer_string else "string" + expected = pd.Series( + { + "level_0": np.dtype("int64"), + "level_1": exp, + "level_2": DatetimeTZDtype(tz="utc"), + } + ) + tm.assert_series_equal(expected, idx_multitype.dtypes) + + +def test_get_dtypes_duplicate_level_names(using_infer_string): + # Test MultiIndex.dtypes with non-unique level names (# GH45174) + result = MultiIndex.from_product( + [ + [1, 2, 3], + ["a", "b", "c"], + pd.date_range("20200101", periods=2, tz="UTC"), + ], + names=["A", "A", "A"], + ).dtypes + exp = "object" if not using_infer_string else "string" + expected = pd.Series( + [np.dtype("int64"), exp, DatetimeTZDtype(tz="utc")], + index=["A", "A", "A"], + ) + tm.assert_series_equal(result, expected) + + +def test_get_level_number_out_of_bounds(multiindex_dataframe_random_data): + frame = multiindex_dataframe_random_data + + with pytest.raises(IndexError, match="Too many levels"): + frame.index._get_level_number(2) + with pytest.raises(IndexError, match="not a valid level number"): + frame.index._get_level_number(-3) + + +def test_set_name_methods(idx): + # so long as these are synonyms, we don't need to test set_names + index_names = ["first", "second"] + assert idx.rename == idx.set_names + new_names = [name + "SUFFIX" for name in index_names] + ind = idx.set_names(new_names) + assert idx.names == index_names + assert ind.names == new_names + msg = "Length of names must match number of levels in MultiIndex" + with pytest.raises(ValueError, match=msg): + ind.set_names(new_names + new_names) + new_names2 = [name + "SUFFIX2" for name in new_names] + res = ind.set_names(new_names2, inplace=True) + assert res is None + assert ind.names == new_names2 + + # set names for specific level (# GH7792) + ind = idx.set_names(new_names[0], level=0) + assert idx.names == index_names + assert ind.names == [new_names[0], index_names[1]] + + res = ind.set_names(new_names2[0], level=0, inplace=True) + assert res is None + assert ind.names == [new_names2[0], index_names[1]] + + # set names for multiple levels + ind = idx.set_names(new_names, level=[0, 1]) + assert idx.names == index_names + assert ind.names == new_names + + res = ind.set_names(new_names2, level=[0, 1], inplace=True) + assert res is None + assert ind.names == new_names2 + + +def test_set_levels_codes_directly(idx): + # setting levels/codes directly raises AttributeError + + levels = idx.levels + new_levels = [[lev + "a" for lev in level] for level in levels] + + codes = idx.codes + major_codes, minor_codes = codes + major_codes = [(x + 1) % 3 for x in major_codes] + minor_codes = [(x + 1) % 1 for x in minor_codes] + new_codes = [major_codes, minor_codes] + + msg = "Can't set attribute" + with pytest.raises(AttributeError, match=msg): + idx.levels = new_levels + + msg = ( + "property 'codes' of 'MultiIndex' object has no setter" + if PY311 + else "can't set attribute" + ) + with pytest.raises(AttributeError, match=msg): + idx.codes = new_codes + + +def test_set_levels(idx): + # side note - you probably wouldn't want to use levels and codes + # directly like this - but it is possible. + levels = idx.levels + new_levels = [[lev + "a" for lev in level] for level in levels] + + # level changing [w/o mutation] + ind2 = idx.set_levels(new_levels) + assert_matching(ind2.levels, new_levels) + assert_matching(idx.levels, levels) + + # level changing specific level [w/o mutation] + ind2 = idx.set_levels(new_levels[0], level=0) + assert_matching(ind2.levels, [new_levels[0], levels[1]]) + assert_matching(idx.levels, levels) + + ind2 = idx.set_levels(new_levels[1], level=1) + assert_matching(ind2.levels, [levels[0], new_levels[1]]) + assert_matching(idx.levels, levels) + + # level changing multiple levels [w/o mutation] + ind2 = idx.set_levels(new_levels, level=[0, 1]) + assert_matching(ind2.levels, new_levels) + assert_matching(idx.levels, levels) + + # illegal level changing should not change levels + # GH 13754 + original_index = idx.copy() + with pytest.raises(ValueError, match="^On"): + idx.set_levels(["c"], level=0) + assert_matching(idx.levels, original_index.levels, check_dtype=True) + + with pytest.raises(ValueError, match="^On"): + idx.set_codes([0, 1, 2, 3, 4, 5], level=0) + assert_matching(idx.codes, original_index.codes, check_dtype=True) + + with pytest.raises(TypeError, match="^Levels"): + idx.set_levels("c", level=0) + assert_matching(idx.levels, original_index.levels, check_dtype=True) + + with pytest.raises(TypeError, match="^Codes"): + idx.set_codes(1, level=0) + assert_matching(idx.codes, original_index.codes, check_dtype=True) + + +def test_set_codes(idx): + # side note - you probably wouldn't want to use levels and codes + # directly like this - but it is possible. + codes = idx.codes + major_codes, minor_codes = codes + major_codes = [(x + 1) % 3 for x in major_codes] + minor_codes = [(x + 1) % 1 for x in minor_codes] + new_codes = [major_codes, minor_codes] + + # changing codes w/o mutation + ind2 = idx.set_codes(new_codes) + assert_matching(ind2.codes, new_codes) + assert_matching(idx.codes, codes) + + # codes changing specific level w/o mutation + ind2 = idx.set_codes(new_codes[0], level=0) + assert_matching(ind2.codes, [new_codes[0], codes[1]]) + assert_matching(idx.codes, codes) + + ind2 = idx.set_codes(new_codes[1], level=1) + assert_matching(ind2.codes, [codes[0], new_codes[1]]) + assert_matching(idx.codes, codes) + + # codes changing multiple levels w/o mutation + ind2 = idx.set_codes(new_codes, level=[0, 1]) + assert_matching(ind2.codes, new_codes) + assert_matching(idx.codes, codes) + + # label changing for levels of different magnitude of categories + ind = MultiIndex.from_tuples([(0, i) for i in range(130)]) + new_codes = range(129, -1, -1) + expected = MultiIndex.from_tuples([(0, i) for i in new_codes]) + + # [w/o mutation] + result = ind.set_codes(codes=new_codes, level=1) + assert result.equals(expected) + + +def test_set_levels_codes_names_bad_input(idx): + levels, codes = idx.levels, idx.codes + names = idx.names + + with pytest.raises(ValueError, match="Length of levels"): + idx.set_levels([levels[0]]) + + with pytest.raises(ValueError, match="Length of codes"): + idx.set_codes([codes[0]]) + + with pytest.raises(ValueError, match="Length of names"): + idx.set_names([names[0]]) + + # shouldn't scalar data error, instead should demand list-like + with pytest.raises(TypeError, match="list of lists-like"): + idx.set_levels(levels[0]) + + # shouldn't scalar data error, instead should demand list-like + with pytest.raises(TypeError, match="list of lists-like"): + idx.set_codes(codes[0]) + + # shouldn't scalar data error, instead should demand list-like + with pytest.raises(TypeError, match="list-like"): + idx.set_names(names[0]) + + # should have equal lengths + with pytest.raises(TypeError, match="list of lists-like"): + idx.set_levels(levels[0], level=[0, 1]) + + with pytest.raises(TypeError, match="list-like"): + idx.set_levels(levels, level=0) + + # should have equal lengths + with pytest.raises(TypeError, match="list of lists-like"): + idx.set_codes(codes[0], level=[0, 1]) + + with pytest.raises(TypeError, match="list-like"): + idx.set_codes(codes, level=0) + + # should have equal lengths + with pytest.raises(ValueError, match="Length of names"): + idx.set_names(names[0], level=[0, 1]) + + with pytest.raises(TypeError, match="Names must be a"): + idx.set_names(names, level=0) + + +@pytest.mark.parametrize("inplace", [True, False]) +def test_set_names_with_nlevel_1(inplace): + # GH 21149 + # Ensure that .set_names for MultiIndex with + # nlevels == 1 does not raise any errors + expected = MultiIndex(levels=[[0, 1]], codes=[[0, 1]], names=["first"]) + m = MultiIndex.from_product([[0, 1]]) + result = m.set_names("first", level=0, inplace=inplace) + + if inplace: + result = m + + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("ordered", [True, False]) +def test_set_levels_categorical(ordered): + # GH13854 + index = MultiIndex.from_arrays([list("xyzx"), [0, 1, 2, 3]]) + + cidx = CategoricalIndex(list("bac"), ordered=ordered) + result = index.set_levels(cidx, level=0) + expected = MultiIndex(levels=[cidx, [0, 1, 2, 3]], codes=index.codes) + tm.assert_index_equal(result, expected) + + result_lvl = result.get_level_values(0) + expected_lvl = CategoricalIndex( + list("bacb"), categories=cidx.categories, ordered=cidx.ordered + ) + tm.assert_index_equal(result_lvl, expected_lvl) + + +def test_set_value_keeps_names(): + # motivating example from #3742 + lev1 = ["hans", "hans", "hans", "grethe", "grethe", "grethe"] + lev2 = ["1", "2", "3"] * 2 + idx = MultiIndex.from_arrays([lev1, lev2], names=["Name", "Number"]) + df = pd.DataFrame( + np.random.default_rng(2).standard_normal((6, 4)), + columns=["one", "two", "three", "four"], + index=idx, + ) + df = df.sort_index() + assert df._is_copy is None + assert df.index.names == ("Name", "Number") + df.at[("grethe", "4"), "one"] = 99.34 + assert df._is_copy is None + assert df.index.names == ("Name", "Number") + + +def test_set_levels_with_iterable(): + # GH23273 + sizes = [1, 2, 3] + colors = ["black"] * 3 + index = MultiIndex.from_arrays([sizes, colors], names=["size", "color"]) + + result = index.set_levels(map(int, ["3", "2", "1"]), level="size") + + expected_sizes = [3, 2, 1] + expected = MultiIndex.from_arrays([expected_sizes, colors], names=["size", "color"]) + tm.assert_index_equal(result, expected) + + +def test_set_empty_level(): + # GH#48636 + midx = MultiIndex.from_arrays([[]], names=["A"]) + result = midx.set_levels(pd.DatetimeIndex([]), level=0) + expected = MultiIndex.from_arrays([pd.DatetimeIndex([])], names=["A"]) + tm.assert_index_equal(result, expected) + + +def test_set_levels_pos_args_removal(): + # https://github.com/pandas-dev/pandas/issues/41485 + idx = MultiIndex.from_tuples( + [ + (1, "one"), + (3, "one"), + ], + names=["foo", "bar"], + ) + with pytest.raises(TypeError, match="positional arguments"): + idx.set_levels(["a", "b", "c"], 0) + + with pytest.raises(TypeError, match="positional arguments"): + idx.set_codes([[0, 1], [1, 0]], 0) + + +def test_set_levels_categorical_keep_dtype(): + # GH#52125 + midx = MultiIndex.from_arrays([[5, 6]]) + result = midx.set_levels(levels=pd.Categorical([1, 2]), level=0) + expected = MultiIndex.from_arrays([pd.Categorical([1, 2])]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..5e2d3c23da6452a4155af2674b7ce4a6dd7d2680 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_indexing.py @@ -0,0 +1,1001 @@ +from datetime import timedelta +import re + +import numpy as np +import pytest + +from pandas._libs import index as libindex +from pandas.errors import ( + InvalidIndexError, + PerformanceWarning, +) + +import pandas as pd +from pandas import ( + Categorical, + DataFrame, + Index, + MultiIndex, + date_range, +) +import pandas._testing as tm + + +class TestSliceLocs: + def test_slice_locs_partial(self, idx): + sorted_idx, _ = idx.sortlevel(0) + + result = sorted_idx.slice_locs(("foo", "two"), ("qux", "one")) + assert result == (1, 5) + + result = sorted_idx.slice_locs(None, ("qux", "one")) + assert result == (0, 5) + + result = sorted_idx.slice_locs(("foo", "two"), None) + assert result == (1, len(sorted_idx)) + + result = sorted_idx.slice_locs("bar", "baz") + assert result == (2, 4) + + def test_slice_locs(self): + df = DataFrame( + np.random.default_rng(2).standard_normal((50, 4)), + columns=Index(list("ABCD"), dtype=object), + index=date_range("2000-01-01", periods=50, freq="B"), + ) + stacked = df.stack(future_stack=True) + idx = stacked.index + + slob = slice(*idx.slice_locs(df.index[5], df.index[15])) + sliced = stacked[slob] + expected = df[5:16].stack(future_stack=True) + tm.assert_almost_equal(sliced.values, expected.values) + + slob = slice( + *idx.slice_locs( + df.index[5] + timedelta(seconds=30), + df.index[15] - timedelta(seconds=30), + ) + ) + sliced = stacked[slob] + expected = df[6:15].stack(future_stack=True) + tm.assert_almost_equal(sliced.values, expected.values) + + def test_slice_locs_with_type_mismatch(self): + df = DataFrame( + np.random.default_rng(2).standard_normal((10, 4)), + columns=Index(list("ABCD"), dtype=object), + index=date_range("2000-01-01", periods=10, freq="B"), + ) + stacked = df.stack(future_stack=True) + idx = stacked.index + with pytest.raises(TypeError, match="^Level type mismatch"): + idx.slice_locs((1, 3)) + with pytest.raises(TypeError, match="^Level type mismatch"): + idx.slice_locs(df.index[5] + timedelta(seconds=30), (5, 2)) + df = DataFrame( + np.ones((5, 5)), + index=Index([f"i-{i}" for i in range(5)], name="a"), + columns=Index([f"i-{i}" for i in range(5)], name="a"), + ) + stacked = df.stack(future_stack=True) + idx = stacked.index + with pytest.raises(TypeError, match="^Level type mismatch"): + idx.slice_locs(timedelta(seconds=30)) + # TODO: Try creating a UnicodeDecodeError in exception message + with pytest.raises(TypeError, match="^Level type mismatch"): + idx.slice_locs(df.index[1], (16, "a")) + + def test_slice_locs_not_sorted(self): + index = MultiIndex( + levels=[Index(np.arange(4)), Index(np.arange(4)), Index(np.arange(4))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + ) + msg = "[Kk]ey length.*greater than MultiIndex lexsort depth" + with pytest.raises(KeyError, match=msg): + index.slice_locs((1, 0, 1), (2, 1, 0)) + + # works + sorted_index, _ = index.sortlevel(0) + # should there be a test case here??? + sorted_index.slice_locs((1, 0, 1), (2, 1, 0)) + + def test_slice_locs_not_contained(self): + # some searchsorted action + + index = MultiIndex( + levels=[[0, 2, 4, 6], [0, 2, 4]], + codes=[[0, 0, 0, 1, 1, 2, 3, 3, 3], [0, 1, 2, 1, 2, 2, 0, 1, 2]], + ) + + result = index.slice_locs((1, 0), (5, 2)) + assert result == (3, 6) + + result = index.slice_locs(1, 5) + assert result == (3, 6) + + result = index.slice_locs((2, 2), (5, 2)) + assert result == (3, 6) + + result = index.slice_locs(2, 5) + assert result == (3, 6) + + result = index.slice_locs((1, 0), (6, 3)) + assert result == (3, 8) + + result = index.slice_locs(-1, 10) + assert result == (0, len(index)) + + @pytest.mark.parametrize( + "index_arr,expected,start_idx,end_idx", + [ + ([[np.nan, "a", "b"], ["c", "d", "e"]], (0, 3), np.nan, None), + ([[np.nan, "a", "b"], ["c", "d", "e"]], (0, 3), np.nan, "b"), + ([[np.nan, "a", "b"], ["c", "d", "e"]], (0, 3), np.nan, ("b", "e")), + ([["a", "b", "c"], ["d", np.nan, "e"]], (1, 3), ("b", np.nan), None), + ([["a", "b", "c"], ["d", np.nan, "e"]], (1, 3), ("b", np.nan), "c"), + ([["a", "b", "c"], ["d", np.nan, "e"]], (1, 3), ("b", np.nan), ("c", "e")), + ], + ) + def test_slice_locs_with_missing_value( + self, index_arr, expected, start_idx, end_idx + ): + # issue 19132 + idx = MultiIndex.from_arrays(index_arr) + result = idx.slice_locs(start=start_idx, end=end_idx) + assert result == expected + + +class TestPutmask: + def test_putmask_with_wrong_mask(self, idx): + # GH18368 + + msg = "putmask: mask and data must be the same size" + with pytest.raises(ValueError, match=msg): + idx.putmask(np.ones(len(idx) + 1, np.bool_), 1) + + with pytest.raises(ValueError, match=msg): + idx.putmask(np.ones(len(idx) - 1, np.bool_), 1) + + with pytest.raises(ValueError, match=msg): + idx.putmask("foo", 1) + + def test_putmask_multiindex_other(self): + # GH#43212 `value` is also a MultiIndex + + left = MultiIndex.from_tuples([(np.nan, 6), (np.nan, 6), ("a", 4)]) + right = MultiIndex.from_tuples([("a", 1), ("a", 1), ("d", 1)]) + mask = np.array([True, True, False]) + + result = left.putmask(mask, right) + + expected = MultiIndex.from_tuples([right[0], right[1], left[2]]) + tm.assert_index_equal(result, expected) + + def test_putmask_keep_dtype(self, any_numeric_ea_dtype): + # GH#49830 + midx = MultiIndex.from_arrays( + [pd.Series([1, 2, 3], dtype=any_numeric_ea_dtype), [10, 11, 12]] + ) + midx2 = MultiIndex.from_arrays( + [pd.Series([5, 6, 7], dtype=any_numeric_ea_dtype), [-1, -2, -3]] + ) + result = midx.putmask([True, False, False], midx2) + expected = MultiIndex.from_arrays( + [pd.Series([5, 2, 3], dtype=any_numeric_ea_dtype), [-1, 11, 12]] + ) + tm.assert_index_equal(result, expected) + + def test_putmask_keep_dtype_shorter_value(self, any_numeric_ea_dtype): + # GH#49830 + midx = MultiIndex.from_arrays( + [pd.Series([1, 2, 3], dtype=any_numeric_ea_dtype), [10, 11, 12]] + ) + midx2 = MultiIndex.from_arrays( + [pd.Series([5], dtype=any_numeric_ea_dtype), [-1]] + ) + result = midx.putmask([True, False, False], midx2) + expected = MultiIndex.from_arrays( + [pd.Series([5, 2, 3], dtype=any_numeric_ea_dtype), [-1, 11, 12]] + ) + tm.assert_index_equal(result, expected) + + +class TestGetIndexer: + def test_get_indexer(self): + major_axis = Index(np.arange(4)) + minor_axis = Index(np.arange(2)) + + major_codes = np.array([0, 0, 1, 2, 2, 3, 3], dtype=np.intp) + minor_codes = np.array([0, 1, 0, 0, 1, 0, 1], dtype=np.intp) + + index = MultiIndex( + levels=[major_axis, minor_axis], codes=[major_codes, minor_codes] + ) + idx1 = index[:5] + idx2 = index[[1, 3, 5]] + + r1 = idx1.get_indexer(idx2) + tm.assert_almost_equal(r1, np.array([1, 3, -1], dtype=np.intp)) + + r1 = idx2.get_indexer(idx1, method="pad") + e1 = np.array([-1, 0, 0, 1, 1], dtype=np.intp) + tm.assert_almost_equal(r1, e1) + + r2 = idx2.get_indexer(idx1[::-1], method="pad") + tm.assert_almost_equal(r2, e1[::-1]) + + rffill1 = idx2.get_indexer(idx1, method="ffill") + tm.assert_almost_equal(r1, rffill1) + + r1 = idx2.get_indexer(idx1, method="backfill") + e1 = np.array([0, 0, 1, 1, 2], dtype=np.intp) + tm.assert_almost_equal(r1, e1) + + r2 = idx2.get_indexer(idx1[::-1], method="backfill") + tm.assert_almost_equal(r2, e1[::-1]) + + rbfill1 = idx2.get_indexer(idx1, method="bfill") + tm.assert_almost_equal(r1, rbfill1) + + # pass non-MultiIndex + r1 = idx1.get_indexer(idx2.values) + rexp1 = idx1.get_indexer(idx2) + tm.assert_almost_equal(r1, rexp1) + + r1 = idx1.get_indexer([1, 2, 3]) + assert (r1 == [-1, -1, -1]).all() + + # create index with duplicates + idx1 = Index(list(range(10)) + list(range(10))) + idx2 = Index(list(range(20))) + + msg = "Reindexing only valid with uniquely valued Index objects" + with pytest.raises(InvalidIndexError, match=msg): + idx1.get_indexer(idx2) + + def test_get_indexer_nearest(self): + midx = MultiIndex.from_tuples([("a", 1), ("b", 2)]) + msg = ( + "method='nearest' not implemented yet for MultiIndex; " + "see GitHub issue 9365" + ) + with pytest.raises(NotImplementedError, match=msg): + midx.get_indexer(["a"], method="nearest") + msg = "tolerance not implemented yet for MultiIndex" + with pytest.raises(NotImplementedError, match=msg): + midx.get_indexer(["a"], method="pad", tolerance=2) + + def test_get_indexer_categorical_time(self): + # https://github.com/pandas-dev/pandas/issues/21390 + midx = MultiIndex.from_product( + [ + Categorical(["a", "b", "c"]), + Categorical(date_range("2012-01-01", periods=3, freq="h")), + ] + ) + result = midx.get_indexer(midx) + tm.assert_numpy_array_equal(result, np.arange(9, dtype=np.intp)) + + @pytest.mark.parametrize( + "index_arr,labels,expected", + [ + ( + [[1, np.nan, 2], [3, 4, 5]], + [1, np.nan, 2], + np.array([-1, -1, -1], dtype=np.intp), + ), + ([[1, np.nan, 2], [3, 4, 5]], [(np.nan, 4)], np.array([1], dtype=np.intp)), + ([[1, 2, 3], [np.nan, 4, 5]], [(1, np.nan)], np.array([0], dtype=np.intp)), + ( + [[1, 2, 3], [np.nan, 4, 5]], + [np.nan, 4, 5], + np.array([-1, -1, -1], dtype=np.intp), + ), + ], + ) + def test_get_indexer_with_missing_value(self, index_arr, labels, expected): + # issue 19132 + idx = MultiIndex.from_arrays(index_arr) + result = idx.get_indexer(labels) + tm.assert_numpy_array_equal(result, expected) + + def test_get_indexer_methods(self): + # https://github.com/pandas-dev/pandas/issues/29896 + # test getting an indexer for another index with different methods + # confirms that getting an indexer without a filling method, getting an + # indexer and backfilling, and getting an indexer and padding all behave + # correctly in the case where all of the target values fall in between + # several levels in the MultiIndex into which they are getting an indexer + # + # visually, the MultiIndexes used in this test are: + # mult_idx_1: + # 0: -1 0 + # 1: 2 + # 2: 3 + # 3: 4 + # 4: 0 0 + # 5: 2 + # 6: 3 + # 7: 4 + # 8: 1 0 + # 9: 2 + # 10: 3 + # 11: 4 + # + # mult_idx_2: + # 0: 0 1 + # 1: 3 + # 2: 4 + mult_idx_1 = MultiIndex.from_product([[-1, 0, 1], [0, 2, 3, 4]]) + mult_idx_2 = MultiIndex.from_product([[0], [1, 3, 4]]) + + indexer = mult_idx_1.get_indexer(mult_idx_2) + expected = np.array([-1, 6, 7], dtype=indexer.dtype) + tm.assert_almost_equal(expected, indexer) + + backfill_indexer = mult_idx_1.get_indexer(mult_idx_2, method="backfill") + expected = np.array([5, 6, 7], dtype=backfill_indexer.dtype) + tm.assert_almost_equal(expected, backfill_indexer) + + # ensure the legacy "bfill" option functions identically to "backfill" + backfill_indexer = mult_idx_1.get_indexer(mult_idx_2, method="bfill") + expected = np.array([5, 6, 7], dtype=backfill_indexer.dtype) + tm.assert_almost_equal(expected, backfill_indexer) + + pad_indexer = mult_idx_1.get_indexer(mult_idx_2, method="pad") + expected = np.array([4, 6, 7], dtype=pad_indexer.dtype) + tm.assert_almost_equal(expected, pad_indexer) + + # ensure the legacy "ffill" option functions identically to "pad" + pad_indexer = mult_idx_1.get_indexer(mult_idx_2, method="ffill") + expected = np.array([4, 6, 7], dtype=pad_indexer.dtype) + tm.assert_almost_equal(expected, pad_indexer) + + @pytest.mark.parametrize("method", ["pad", "ffill", "backfill", "bfill", "nearest"]) + def test_get_indexer_methods_raise_for_non_monotonic(self, method): + # 53452 + mi = MultiIndex.from_arrays([[0, 4, 2], [0, 4, 2]]) + if method == "nearest": + err = NotImplementedError + msg = "not implemented yet for MultiIndex" + else: + err = ValueError + msg = "index must be monotonic increasing or decreasing" + with pytest.raises(err, match=msg): + mi.get_indexer([(1, 1)], method=method) + + def test_get_indexer_three_or_more_levels(self): + # https://github.com/pandas-dev/pandas/issues/29896 + # tests get_indexer() on MultiIndexes with 3+ levels + # visually, these are + # mult_idx_1: + # 0: 1 2 5 + # 1: 7 + # 2: 4 5 + # 3: 7 + # 4: 6 5 + # 5: 7 + # 6: 3 2 5 + # 7: 7 + # 8: 4 5 + # 9: 7 + # 10: 6 5 + # 11: 7 + # + # mult_idx_2: + # 0: 1 1 8 + # 1: 1 5 9 + # 2: 1 6 7 + # 3: 2 1 6 + # 4: 2 7 6 + # 5: 2 7 8 + # 6: 3 6 8 + mult_idx_1 = MultiIndex.from_product([[1, 3], [2, 4, 6], [5, 7]]) + mult_idx_2 = MultiIndex.from_tuples( + [ + (1, 1, 8), + (1, 5, 9), + (1, 6, 7), + (2, 1, 6), + (2, 7, 7), + (2, 7, 8), + (3, 6, 8), + ] + ) + # sanity check + assert mult_idx_1.is_monotonic_increasing + assert mult_idx_1.is_unique + assert mult_idx_2.is_monotonic_increasing + assert mult_idx_2.is_unique + + # show the relationships between the two + assert mult_idx_2[0] < mult_idx_1[0] + assert mult_idx_1[3] < mult_idx_2[1] < mult_idx_1[4] + assert mult_idx_1[5] == mult_idx_2[2] + assert mult_idx_1[5] < mult_idx_2[3] < mult_idx_1[6] + assert mult_idx_1[5] < mult_idx_2[4] < mult_idx_1[6] + assert mult_idx_1[5] < mult_idx_2[5] < mult_idx_1[6] + assert mult_idx_1[-1] < mult_idx_2[6] + + indexer_no_fill = mult_idx_1.get_indexer(mult_idx_2) + expected = np.array([-1, -1, 5, -1, -1, -1, -1], dtype=indexer_no_fill.dtype) + tm.assert_almost_equal(expected, indexer_no_fill) + + # test with backfilling + indexer_backfilled = mult_idx_1.get_indexer(mult_idx_2, method="backfill") + expected = np.array([0, 4, 5, 6, 6, 6, -1], dtype=indexer_backfilled.dtype) + tm.assert_almost_equal(expected, indexer_backfilled) + + # now, the same thing, but forward-filled (aka "padded") + indexer_padded = mult_idx_1.get_indexer(mult_idx_2, method="pad") + expected = np.array([-1, 3, 5, 5, 5, 5, 11], dtype=indexer_padded.dtype) + tm.assert_almost_equal(expected, indexer_padded) + + # now, do the indexing in the other direction + assert mult_idx_2[0] < mult_idx_1[0] < mult_idx_2[1] + assert mult_idx_2[0] < mult_idx_1[1] < mult_idx_2[1] + assert mult_idx_2[0] < mult_idx_1[2] < mult_idx_2[1] + assert mult_idx_2[0] < mult_idx_1[3] < mult_idx_2[1] + assert mult_idx_2[1] < mult_idx_1[4] < mult_idx_2[2] + assert mult_idx_2[2] == mult_idx_1[5] + assert mult_idx_2[5] < mult_idx_1[6] < mult_idx_2[6] + assert mult_idx_2[5] < mult_idx_1[7] < mult_idx_2[6] + assert mult_idx_2[5] < mult_idx_1[8] < mult_idx_2[6] + assert mult_idx_2[5] < mult_idx_1[9] < mult_idx_2[6] + assert mult_idx_2[5] < mult_idx_1[10] < mult_idx_2[6] + assert mult_idx_2[5] < mult_idx_1[11] < mult_idx_2[6] + + indexer = mult_idx_2.get_indexer(mult_idx_1) + expected = np.array( + [-1, -1, -1, -1, -1, 2, -1, -1, -1, -1, -1, -1], dtype=indexer.dtype + ) + tm.assert_almost_equal(expected, indexer) + + backfill_indexer = mult_idx_2.get_indexer(mult_idx_1, method="bfill") + expected = np.array( + [1, 1, 1, 1, 2, 2, 6, 6, 6, 6, 6, 6], dtype=backfill_indexer.dtype + ) + tm.assert_almost_equal(expected, backfill_indexer) + + pad_indexer = mult_idx_2.get_indexer(mult_idx_1, method="pad") + expected = np.array( + [0, 0, 0, 0, 1, 2, 5, 5, 5, 5, 5, 5], dtype=pad_indexer.dtype + ) + tm.assert_almost_equal(expected, pad_indexer) + + def test_get_indexer_crossing_levels(self): + # https://github.com/pandas-dev/pandas/issues/29896 + # tests a corner case with get_indexer() with MultiIndexes where, when we + # need to "carry" across levels, proper tuple ordering is respected + # + # the MultiIndexes used in this test, visually, are: + # mult_idx_1: + # 0: 1 1 1 1 + # 1: 2 + # 2: 2 1 + # 3: 2 + # 4: 1 2 1 1 + # 5: 2 + # 6: 2 1 + # 7: 2 + # 8: 2 1 1 1 + # 9: 2 + # 10: 2 1 + # 11: 2 + # 12: 2 2 1 1 + # 13: 2 + # 14: 2 1 + # 15: 2 + # + # mult_idx_2: + # 0: 1 3 2 2 + # 1: 2 3 2 2 + mult_idx_1 = MultiIndex.from_product([[1, 2]] * 4) + mult_idx_2 = MultiIndex.from_tuples([(1, 3, 2, 2), (2, 3, 2, 2)]) + + # show the tuple orderings, which get_indexer() should respect + assert mult_idx_1[7] < mult_idx_2[0] < mult_idx_1[8] + assert mult_idx_1[-1] < mult_idx_2[1] + + indexer = mult_idx_1.get_indexer(mult_idx_2) + expected = np.array([-1, -1], dtype=indexer.dtype) + tm.assert_almost_equal(expected, indexer) + + backfill_indexer = mult_idx_1.get_indexer(mult_idx_2, method="bfill") + expected = np.array([8, -1], dtype=backfill_indexer.dtype) + tm.assert_almost_equal(expected, backfill_indexer) + + pad_indexer = mult_idx_1.get_indexer(mult_idx_2, method="ffill") + expected = np.array([7, 15], dtype=pad_indexer.dtype) + tm.assert_almost_equal(expected, pad_indexer) + + def test_get_indexer_kwarg_validation(self): + # GH#41918 + mi = MultiIndex.from_product([range(3), ["A", "B"]]) + + msg = "limit argument only valid if doing pad, backfill or nearest" + with pytest.raises(ValueError, match=msg): + mi.get_indexer(mi[:-1], limit=4) + + msg = "tolerance argument only valid if doing pad, backfill or nearest" + with pytest.raises(ValueError, match=msg): + mi.get_indexer(mi[:-1], tolerance="piano") + + def test_get_indexer_nan(self): + # GH#37222 + idx1 = MultiIndex.from_product([["A"], [1.0, 2.0]], names=["id1", "id2"]) + idx2 = MultiIndex.from_product([["A"], [np.nan, 2.0]], names=["id1", "id2"]) + expected = np.array([-1, 1]) + result = idx2.get_indexer(idx1) + tm.assert_numpy_array_equal(result, expected, check_dtype=False) + result = idx1.get_indexer(idx2) + tm.assert_numpy_array_equal(result, expected, check_dtype=False) + + +def test_getitem(idx): + # scalar + assert idx[2] == ("bar", "one") + + # slice + result = idx[2:5] + expected = idx[[2, 3, 4]] + assert result.equals(expected) + + # boolean + result = idx[[True, False, True, False, True, True]] + result2 = idx[np.array([True, False, True, False, True, True])] + expected = idx[[0, 2, 4, 5]] + assert result.equals(expected) + assert result2.equals(expected) + + +def test_getitem_group_select(idx): + sorted_idx, _ = idx.sortlevel(0) + assert sorted_idx.get_loc("baz") == slice(3, 4) + assert sorted_idx.get_loc("foo") == slice(0, 2) + + +@pytest.mark.parametrize("ind1", [[True] * 5, Index([True] * 5)]) +@pytest.mark.parametrize( + "ind2", + [[True, False, True, False, False], Index([True, False, True, False, False])], +) +def test_getitem_bool_index_all(ind1, ind2): + # GH#22533 + idx = MultiIndex.from_tuples([(10, 1), (20, 2), (30, 3), (40, 4), (50, 5)]) + tm.assert_index_equal(idx[ind1], idx) + + expected = MultiIndex.from_tuples([(10, 1), (30, 3)]) + tm.assert_index_equal(idx[ind2], expected) + + +@pytest.mark.parametrize("ind1", [[True], Index([True])]) +@pytest.mark.parametrize("ind2", [[False], Index([False])]) +def test_getitem_bool_index_single(ind1, ind2): + # GH#22533 + idx = MultiIndex.from_tuples([(10, 1)]) + tm.assert_index_equal(idx[ind1], idx) + + expected = MultiIndex( + levels=[np.array([], dtype=np.int64), np.array([], dtype=np.int64)], + codes=[[], []], + ) + tm.assert_index_equal(idx[ind2], expected) + + +class TestGetLoc: + def test_get_loc(self, idx): + assert idx.get_loc(("foo", "two")) == 1 + assert idx.get_loc(("baz", "two")) == 3 + with pytest.raises(KeyError, match=r"^\('bar', 'two'\)$"): + idx.get_loc(("bar", "two")) + with pytest.raises(KeyError, match=r"^'quux'$"): + idx.get_loc("quux") + + # 3 levels + index = MultiIndex( + levels=[Index(np.arange(4)), Index(np.arange(4)), Index(np.arange(4))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + ) + with pytest.raises(KeyError, match=r"^\(1, 1\)$"): + index.get_loc((1, 1)) + assert index.get_loc((2, 0)) == slice(3, 5) + + def test_get_loc_duplicates(self): + index = Index([2, 2, 2, 2]) + result = index.get_loc(2) + expected = slice(0, 4) + assert result == expected + + index = Index(["c", "a", "a", "b", "b"]) + rs = index.get_loc("c") + xp = 0 + assert rs == xp + + with pytest.raises(KeyError, match="2"): + index.get_loc(2) + + def test_get_loc_level(self): + index = MultiIndex( + levels=[Index(np.arange(4)), Index(np.arange(4)), Index(np.arange(4))], + codes=[ + np.array([0, 0, 1, 2, 2, 2, 3, 3]), + np.array([0, 1, 0, 0, 0, 1, 0, 1]), + np.array([1, 0, 1, 1, 0, 0, 1, 0]), + ], + ) + loc, new_index = index.get_loc_level((0, 1)) + expected = slice(1, 2) + exp_index = index[expected].droplevel(0).droplevel(0) + assert loc == expected + assert new_index.equals(exp_index) + + loc, new_index = index.get_loc_level((0, 1, 0)) + expected = 1 + assert loc == expected + assert new_index is None + + with pytest.raises(KeyError, match=r"^\(2, 2\)$"): + index.get_loc_level((2, 2)) + # GH 22221: unused label + with pytest.raises(KeyError, match=r"^2$"): + index.drop(2).get_loc_level(2) + # Unused label on unsorted level: + with pytest.raises(KeyError, match=r"^2$"): + index.drop(1, level=2).get_loc_level(2, level=2) + + index = MultiIndex( + levels=[[2000], list(range(4))], + codes=[np.array([0, 0, 0, 0]), np.array([0, 1, 2, 3])], + ) + result, new_index = index.get_loc_level((2000, slice(None, None))) + expected = slice(None, None) + assert result == expected + assert new_index.equals(index.droplevel(0)) + + @pytest.mark.parametrize("dtype1", [int, float, bool, str]) + @pytest.mark.parametrize("dtype2", [int, float, bool, str]) + def test_get_loc_multiple_dtypes(self, dtype1, dtype2): + # GH 18520 + levels = [np.array([0, 1]).astype(dtype1), np.array([0, 1]).astype(dtype2)] + idx = MultiIndex.from_product(levels) + assert idx.get_loc(idx[2]) == 2 + + @pytest.mark.parametrize("level", [0, 1]) + @pytest.mark.parametrize("dtypes", [[int, float], [float, int]]) + def test_get_loc_implicit_cast(self, level, dtypes): + # GH 18818, GH 15994 : as flat index, cast int to float and vice-versa + levels = [["a", "b"], ["c", "d"]] + key = ["b", "d"] + lev_dtype, key_dtype = dtypes + levels[level] = np.array([0, 1], dtype=lev_dtype) + key[level] = key_dtype(1) + idx = MultiIndex.from_product(levels) + assert idx.get_loc(tuple(key)) == 3 + + @pytest.mark.parametrize("dtype", [bool, object]) + def test_get_loc_cast_bool(self, dtype): + # GH 19086 : int is casted to bool, but not vice-versa (for object dtype) + # With bool dtype, we don't cast in either direction. + levels = [Index([False, True], dtype=dtype), np.arange(2, dtype="int64")] + idx = MultiIndex.from_product(levels) + + if dtype is bool: + with pytest.raises(KeyError, match=r"^\(0, 1\)$"): + assert idx.get_loc((0, 1)) == 1 + with pytest.raises(KeyError, match=r"^\(1, 0\)$"): + assert idx.get_loc((1, 0)) == 2 + else: + # We use python object comparisons, which treat 0 == False and 1 == True + assert idx.get_loc((0, 1)) == 1 + assert idx.get_loc((1, 0)) == 2 + + with pytest.raises(KeyError, match=r"^\(False, True\)$"): + idx.get_loc((False, True)) + with pytest.raises(KeyError, match=r"^\(True, False\)$"): + idx.get_loc((True, False)) + + @pytest.mark.parametrize("level", [0, 1]) + def test_get_loc_nan(self, level, nulls_fixture): + # GH 18485 : NaN in MultiIndex + levels = [["a", "b"], ["c", "d"]] + key = ["b", "d"] + levels[level] = np.array([0, nulls_fixture], dtype=type(nulls_fixture)) + key[level] = nulls_fixture + idx = MultiIndex.from_product(levels) + assert idx.get_loc(tuple(key)) == 3 + + def test_get_loc_missing_nan(self): + # GH 8569 + idx = MultiIndex.from_arrays([[1.0, 2.0], [3.0, 4.0]]) + assert isinstance(idx.get_loc(1), slice) + with pytest.raises(KeyError, match=r"^3$"): + idx.get_loc(3) + with pytest.raises(KeyError, match=r"^nan$"): + idx.get_loc(np.nan) + with pytest.raises(InvalidIndexError, match=r"\[nan\]"): + # listlike/non-hashable raises TypeError + idx.get_loc([np.nan]) + + def test_get_loc_with_values_including_missing_values(self): + # issue 19132 + idx = MultiIndex.from_product([[np.nan, 1]] * 2) + expected = slice(0, 2, None) + assert idx.get_loc(np.nan) == expected + + idx = MultiIndex.from_arrays([[np.nan, 1, 2, np.nan]]) + expected = np.array([True, False, False, True]) + tm.assert_numpy_array_equal(idx.get_loc(np.nan), expected) + + idx = MultiIndex.from_product([[np.nan, 1]] * 3) + expected = slice(2, 4, None) + assert idx.get_loc((np.nan, 1)) == expected + + def test_get_loc_duplicates2(self): + # TODO: de-duplicate with test_get_loc_duplicates above? + index = MultiIndex( + levels=[["D", "B", "C"], [0, 26, 27, 37, 57, 67, 75, 82]], + codes=[[0, 0, 0, 1, 2, 2, 2, 2, 2, 2], [1, 3, 4, 6, 0, 2, 2, 3, 5, 7]], + names=["tag", "day"], + ) + + assert index.get_loc("D") == slice(0, 3) + + def test_get_loc_past_lexsort_depth(self): + # GH#30053 + idx = MultiIndex( + levels=[["a"], [0, 7], [1]], + codes=[[0, 0], [1, 0], [0, 0]], + names=["x", "y", "z"], + sortorder=0, + ) + key = ("a", 7) + + with tm.assert_produces_warning(PerformanceWarning): + # PerformanceWarning: indexing past lexsort depth may impact performance + result = idx.get_loc(key) + + assert result == slice(0, 1, None) + + def test_multiindex_get_loc_list_raises(self): + # GH#35878 + idx = MultiIndex.from_tuples([("a", 1), ("b", 2)]) + msg = r"\[\]" + with pytest.raises(InvalidIndexError, match=msg): + idx.get_loc([]) + + def test_get_loc_nested_tuple_raises_keyerror(self): + # raise KeyError, not TypeError + mi = MultiIndex.from_product([range(3), range(4), range(5), range(6)]) + key = ((2, 3, 4), "foo") + + with pytest.raises(KeyError, match=re.escape(str(key))): + mi.get_loc(key) + + +class TestWhere: + def test_where(self): + i = MultiIndex.from_tuples([("A", 1), ("A", 2)]) + + msg = r"\.where is not supported for MultiIndex operations" + with pytest.raises(NotImplementedError, match=msg): + i.where(True) + + def test_where_array_like(self, listlike_box): + mi = MultiIndex.from_tuples([("A", 1), ("A", 2)]) + cond = [False, True] + msg = r"\.where is not supported for MultiIndex operations" + with pytest.raises(NotImplementedError, match=msg): + mi.where(listlike_box(cond)) + + +class TestContains: + def test_contains_top_level(self): + midx = MultiIndex.from_product([["A", "B"], [1, 2]]) + assert "A" in midx + assert "A" not in midx._engine + + def test_contains_with_nat(self): + # MI with a NaT + mi = MultiIndex( + levels=[["C"], date_range("2012-01-01", periods=5)], + codes=[[0, 0, 0, 0, 0, 0], [-1, 0, 1, 2, 3, 4]], + names=[None, "B"], + ) + assert ("C", pd.Timestamp("2012-01-01")) in mi + for val in mi.values: + assert val in mi + + def test_contains(self, idx): + assert ("foo", "two") in idx + assert ("bar", "two") not in idx + assert None not in idx + + def test_contains_with_missing_value(self): + # GH#19132 + idx = MultiIndex.from_arrays([[1, np.nan, 2]]) + assert np.nan in idx + + idx = MultiIndex.from_arrays([[1, 2], [np.nan, 3]]) + assert np.nan not in idx + assert (1, np.nan) in idx + + def test_multiindex_contains_dropped(self): + # GH#19027 + # test that dropped MultiIndex levels are not in the MultiIndex + # despite continuing to be in the MultiIndex's levels + idx = MultiIndex.from_product([[1, 2], [3, 4]]) + assert 2 in idx + idx = idx.drop(2) + + # drop implementation keeps 2 in the levels + assert 2 in idx.levels[0] + # but it should no longer be in the index itself + assert 2 not in idx + + # also applies to strings + idx = MultiIndex.from_product([["a", "b"], ["c", "d"]]) + assert "a" in idx + idx = idx.drop("a") + assert "a" in idx.levels[0] + assert "a" not in idx + + def test_contains_td64_level(self): + # GH#24570 + tx = pd.timedelta_range("09:30:00", "16:00:00", freq="30 min") + idx = MultiIndex.from_arrays([tx, np.arange(len(tx))]) + assert tx[0] in idx + assert "element_not_exit" not in idx + assert "0 day 09:30:00" in idx + + def test_large_mi_contains(self, monkeypatch): + # GH#10645 + with monkeypatch.context(): + monkeypatch.setattr(libindex, "_SIZE_CUTOFF", 10) + result = MultiIndex.from_arrays([range(10), range(10)]) + assert (10, 0) not in result + + +def test_timestamp_multiindex_indexer(): + # https://github.com/pandas-dev/pandas/issues/26944 + idx = MultiIndex.from_product( + [ + date_range("2019-01-01T00:15:33", periods=100, freq="h", name="date"), + ["x"], + [3], + ] + ) + df = DataFrame({"foo": np.arange(len(idx))}, idx) + result = df.loc[pd.IndexSlice["2019-1-2":, "x", :], "foo"] + qidx = MultiIndex.from_product( + [ + date_range( + start="2019-01-02T00:15:33", + end="2019-01-05T03:15:33", + freq="h", + name="date", + ), + ["x"], + [3], + ] + ) + should_be = pd.Series(data=np.arange(24, len(qidx) + 24), index=qidx, name="foo") + tm.assert_series_equal(result, should_be) + + +@pytest.mark.parametrize( + "index_arr,expected,target,algo", + [ + ([[np.nan, "a", "b"], ["c", "d", "e"]], 0, np.nan, "left"), + ([[np.nan, "a", "b"], ["c", "d", "e"]], 1, (np.nan, "c"), "right"), + ([["a", "b", "c"], ["d", np.nan, "d"]], 1, ("b", np.nan), "left"), + ], +) +def test_get_slice_bound_with_missing_value(index_arr, expected, target, algo): + # issue 19132 + idx = MultiIndex.from_arrays(index_arr) + result = idx.get_slice_bound(target, side=algo) + assert result == expected + + +@pytest.mark.parametrize( + "index_arr,expected,start_idx,end_idx", + [ + ([[np.nan, 1, 2], [3, 4, 5]], slice(0, 2, None), np.nan, 1), + ([[np.nan, 1, 2], [3, 4, 5]], slice(0, 3, None), np.nan, (2, 5)), + ([[1, 2, 3], [4, np.nan, 5]], slice(1, 3, None), (2, np.nan), 3), + ([[1, 2, 3], [4, np.nan, 5]], slice(1, 3, None), (2, np.nan), (3, 5)), + ], +) +def test_slice_indexer_with_missing_value(index_arr, expected, start_idx, end_idx): + # issue 19132 + idx = MultiIndex.from_arrays(index_arr) + result = idx.slice_indexer(start=start_idx, end=end_idx) + assert result == expected + + +def test_pyint_engine(): + # GH#18519 : when combinations of codes cannot be represented in 64 + # bits, the index underlying the MultiIndex engine works with Python + # integers, rather than uint64. + N = 5 + keys = [ + tuple(arr) + for arr in [ + [0] * 10 * N, + [1] * 10 * N, + [2] * 10 * N, + [np.nan] * N + [2] * 9 * N, + [0] * N + [2] * 9 * N, + [np.nan] * N + [2] * 8 * N + [0] * N, + ] + ] + # Each level contains 4 elements (including NaN), so it is represented + # in 2 bits, for a total of 2*N*10 = 100 > 64 bits. If we were using a + # 64 bit engine and truncating the first levels, the fourth and fifth + # keys would collide; if truncating the last levels, the fifth and + # sixth; if rotating bits rather than shifting, the third and fifth. + + for idx, key_value in enumerate(keys): + index = MultiIndex.from_tuples(keys) + assert index.get_loc(key_value) == idx + + expected = np.arange(idx + 1, dtype=np.intp) + result = index.get_indexer([keys[i] for i in expected]) + tm.assert_numpy_array_equal(result, expected) + + # With missing key: + idces = range(len(keys)) + expected = np.array([-1] + list(idces), dtype=np.intp) + missing = tuple([0, 1] * 5 * N) + result = index.get_indexer([missing] + [keys[i] for i in idces]) + tm.assert_numpy_array_equal(result, expected) + + +@pytest.mark.parametrize( + "keys,expected", + [ + ((slice(None), [5, 4]), [1, 0]), + ((slice(None), [4, 5]), [0, 1]), + (([True, False, True], [4, 6]), [0, 2]), + (([True, False, True], [6, 4]), [0, 2]), + ((2, [4, 5]), [0, 1]), + ((2, [5, 4]), [1, 0]), + (([2], [4, 5]), [0, 1]), + (([2], [5, 4]), [1, 0]), + ], +) +def test_get_locs_reordering(keys, expected): + # GH48384 + idx = MultiIndex.from_arrays( + [ + [2, 2, 1], + [4, 5, 6], + ] + ) + result = idx.get_locs(keys) + expected = np.array(expected, dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + + +def test_get_indexer_for_multiindex_with_nans(nulls_fixture): + # GH37222 + idx1 = MultiIndex.from_product([["A"], [1.0, 2.0]], names=["id1", "id2"]) + idx2 = MultiIndex.from_product([["A"], [nulls_fixture, 2.0]], names=["id1", "id2"]) + + result = idx2.get_indexer(idx1) + expected = np.array([-1, 1], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + + result = idx1.get_indexer(idx2) + expected = np.array([-1, 1], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_integrity.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_integrity.py new file mode 100644 index 0000000000000000000000000000000000000000..d956747cbc859f40b69e52ea78c85ebce31f3427 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_integrity.py @@ -0,0 +1,289 @@ +import re + +import numpy as np +import pytest + +from pandas._libs import index as libindex + +from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike + +import pandas as pd +from pandas import ( + Index, + IntervalIndex, + MultiIndex, + RangeIndex, +) +import pandas._testing as tm + + +def test_labels_dtypes(): + # GH 8456 + i = MultiIndex.from_tuples([("A", 1), ("A", 2)]) + assert i.codes[0].dtype == "int8" + assert i.codes[1].dtype == "int8" + + i = MultiIndex.from_product([["a"], range(40)]) + assert i.codes[1].dtype == "int8" + i = MultiIndex.from_product([["a"], range(400)]) + assert i.codes[1].dtype == "int16" + i = MultiIndex.from_product([["a"], range(40000)]) + assert i.codes[1].dtype == "int32" + + i = MultiIndex.from_product([["a"], range(1000)]) + assert (i.codes[0] >= 0).all() + assert (i.codes[1] >= 0).all() + + +def test_values_boxed(): + tuples = [ + (1, pd.Timestamp("2000-01-01")), + (2, pd.NaT), + (3, pd.Timestamp("2000-01-03")), + (1, pd.Timestamp("2000-01-04")), + (2, pd.Timestamp("2000-01-02")), + (3, pd.Timestamp("2000-01-03")), + ] + result = MultiIndex.from_tuples(tuples) + expected = construct_1d_object_array_from_listlike(tuples) + tm.assert_numpy_array_equal(result.values, expected) + # Check that code branches for boxed values produce identical results + tm.assert_numpy_array_equal(result.values[:4], result[:4].values) + + +def test_values_multiindex_datetimeindex(): + # Test to ensure we hit the boxing / nobox part of MI.values + ints = np.arange(10**18, 10**18 + 5) + naive = pd.DatetimeIndex(ints) + + aware = pd.DatetimeIndex(ints, tz="US/Central") + + idx = MultiIndex.from_arrays([naive, aware]) + result = idx.values + + outer = pd.DatetimeIndex([x[0] for x in result]) + tm.assert_index_equal(outer, naive) + + inner = pd.DatetimeIndex([x[1] for x in result]) + tm.assert_index_equal(inner, aware) + + # n_lev > n_lab + result = idx[:2].values + + outer = pd.DatetimeIndex([x[0] for x in result]) + tm.assert_index_equal(outer, naive[:2]) + + inner = pd.DatetimeIndex([x[1] for x in result]) + tm.assert_index_equal(inner, aware[:2]) + + +def test_values_multiindex_periodindex(): + # Test to ensure we hit the boxing / nobox part of MI.values + ints = np.arange(2007, 2012) + pidx = pd.PeriodIndex(ints, freq="D") + + idx = MultiIndex.from_arrays([ints, pidx]) + result = idx.values + + outer = Index([x[0] for x in result]) + tm.assert_index_equal(outer, Index(ints, dtype=np.int64)) + + inner = pd.PeriodIndex([x[1] for x in result]) + tm.assert_index_equal(inner, pidx) + + # n_lev > n_lab + result = idx[:2].values + + outer = Index([x[0] for x in result]) + tm.assert_index_equal(outer, Index(ints[:2], dtype=np.int64)) + + inner = pd.PeriodIndex([x[1] for x in result]) + tm.assert_index_equal(inner, pidx[:2]) + + +def test_consistency(): + # need to construct an overflow + major_axis = list(range(70000)) + minor_axis = list(range(10)) + + major_codes = np.arange(70000) + minor_codes = np.repeat(range(10), 7000) + + # the fact that is works means it's consistent + index = MultiIndex( + levels=[major_axis, minor_axis], codes=[major_codes, minor_codes] + ) + + # inconsistent + major_codes = np.array([0, 0, 1, 1, 1, 2, 2, 3, 3]) + minor_codes = np.array([0, 1, 0, 1, 1, 0, 1, 0, 1]) + index = MultiIndex( + levels=[major_axis, minor_axis], codes=[major_codes, minor_codes] + ) + + assert index.is_unique is False + + +@pytest.mark.slow +def test_hash_collisions(monkeypatch): + # non-smoke test that we don't get hash collisions + size_cutoff = 50 + with monkeypatch.context() as m: + m.setattr(libindex, "_SIZE_CUTOFF", size_cutoff) + index = MultiIndex.from_product( + [np.arange(8), np.arange(8)], names=["one", "two"] + ) + result = index.get_indexer(index.values) + tm.assert_numpy_array_equal(result, np.arange(len(index), dtype="intp")) + + for i in [0, 1, len(index) - 2, len(index) - 1]: + result = index.get_loc(index[i]) + assert result == i + + +def test_dims(): + pass + + +def test_take_invalid_kwargs(): + vals = [["A", "B"], [pd.Timestamp("2011-01-01"), pd.Timestamp("2011-01-02")]] + idx = MultiIndex.from_product(vals, names=["str", "dt"]) + indices = [1, 2] + + msg = r"take\(\) got an unexpected keyword argument 'foo'" + with pytest.raises(TypeError, match=msg): + idx.take(indices, foo=2) + + msg = "the 'out' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, out=indices) + + msg = "the 'mode' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, mode="clip") + + +def test_isna_behavior(idx): + # should not segfault GH5123 + # NOTE: if MI representation changes, may make sense to allow + # isna(MI) + msg = "isna is not defined for MultiIndex" + with pytest.raises(NotImplementedError, match=msg): + pd.isna(idx) + + +def test_large_multiindex_error(monkeypatch): + # GH12527 + size_cutoff = 50 + with monkeypatch.context() as m: + m.setattr(libindex, "_SIZE_CUTOFF", size_cutoff) + df_below_cutoff = pd.DataFrame( + 1, + index=MultiIndex.from_product([[1, 2], range(size_cutoff - 1)]), + columns=["dest"], + ) + with pytest.raises(KeyError, match=r"^\(-1, 0\)$"): + df_below_cutoff.loc[(-1, 0), "dest"] + with pytest.raises(KeyError, match=r"^\(3, 0\)$"): + df_below_cutoff.loc[(3, 0), "dest"] + df_above_cutoff = pd.DataFrame( + 1, + index=MultiIndex.from_product([[1, 2], range(size_cutoff + 1)]), + columns=["dest"], + ) + with pytest.raises(KeyError, match=r"^\(-1, 0\)$"): + df_above_cutoff.loc[(-1, 0), "dest"] + with pytest.raises(KeyError, match=r"^\(3, 0\)$"): + df_above_cutoff.loc[(3, 0), "dest"] + + +def test_mi_hashtable_populated_attribute_error(monkeypatch): + # GH 18165 + monkeypatch.setattr(libindex, "_SIZE_CUTOFF", 50) + r = range(50) + df = pd.DataFrame({"a": r, "b": r}, index=MultiIndex.from_arrays([r, r])) + + msg = "'Series' object has no attribute 'foo'" + with pytest.raises(AttributeError, match=msg): + df["a"].foo() + + +def test_can_hold_identifiers(idx): + key = idx[0] + assert idx._can_hold_identifiers_and_holds_name(key) is True + + +def test_metadata_immutable(idx): + levels, codes = idx.levels, idx.codes + # shouldn't be able to set at either the top level or base level + mutable_regex = re.compile("does not support mutable operations") + with pytest.raises(TypeError, match=mutable_regex): + levels[0] = levels[0] + with pytest.raises(TypeError, match=mutable_regex): + levels[0][0] = levels[0][0] + # ditto for labels + with pytest.raises(TypeError, match=mutable_regex): + codes[0] = codes[0] + with pytest.raises(ValueError, match="assignment destination is read-only"): + codes[0][0] = codes[0][0] + # and for names + names = idx.names + with pytest.raises(TypeError, match=mutable_regex): + names[0] = names[0] + + +def test_level_setting_resets_attributes(): + ind = MultiIndex.from_arrays([["A", "A", "B", "B", "B"], [1, 2, 1, 2, 3]]) + assert ind.is_monotonic_increasing + ind = ind.set_levels([["A", "B"], [1, 3, 2]]) + # if this fails, probably didn't reset the cache correctly. + assert not ind.is_monotonic_increasing + + +def test_rangeindex_fallback_coercion_bug(): + # GH 12893 + df1 = pd.DataFrame(np.arange(100).reshape((10, 10))) + df2 = pd.DataFrame(np.arange(100).reshape((10, 10))) + df = pd.concat( + {"df1": df1.stack(future_stack=True), "df2": df2.stack(future_stack=True)}, + axis=1, + ) + df.index.names = ["fizz", "buzz"] + + expected = pd.DataFrame( + {"df2": np.arange(100), "df1": np.arange(100)}, + index=MultiIndex.from_product([range(10), range(10)], names=["fizz", "buzz"]), + ) + tm.assert_frame_equal(df, expected, check_like=True) + + result = df.index.get_level_values("fizz") + expected = Index(np.arange(10, dtype=np.int64), name="fizz").repeat(10) + tm.assert_index_equal(result, expected) + + result = df.index.get_level_values("buzz") + expected = Index(np.tile(np.arange(10, dtype=np.int64), 10), name="buzz") + tm.assert_index_equal(result, expected) + + +def test_memory_usage(idx): + result = idx.memory_usage() + if len(idx): + idx.get_loc(idx[0]) + result2 = idx.memory_usage() + result3 = idx.memory_usage(deep=True) + + # RangeIndex, IntervalIndex + # don't have engines + if not isinstance(idx, (RangeIndex, IntervalIndex)): + assert result2 > result + + if idx.inferred_type == "object": + assert result3 > result2 + + else: + # we report 0 for no-length + assert result == 0 + + +def test_nlevels(idx): + assert idx.nlevels == 2 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_isin.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_isin.py new file mode 100644 index 0000000000000000000000000000000000000000..68fdf25359f1bbada24f6a2403d5a04331bee84c --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_isin.py @@ -0,0 +1,103 @@ +import numpy as np +import pytest + +from pandas import MultiIndex +import pandas._testing as tm + + +def test_isin_nan(): + idx = MultiIndex.from_arrays([["foo", "bar"], [1.0, np.nan]]) + tm.assert_numpy_array_equal(idx.isin([("bar", np.nan)]), np.array([False, True])) + tm.assert_numpy_array_equal( + idx.isin([("bar", float("nan"))]), np.array([False, True]) + ) + + +def test_isin_missing(nulls_fixture): + # GH48905 + mi1 = MultiIndex.from_tuples([(1, nulls_fixture)]) + mi2 = MultiIndex.from_tuples([(1, 1), (1, 2)]) + result = mi2.isin(mi1) + expected = np.array([False, False]) + tm.assert_numpy_array_equal(result, expected) + + +def test_isin(): + values = [("foo", 2), ("bar", 3), ("quux", 4)] + + idx = MultiIndex.from_arrays([["qux", "baz", "foo", "bar"], np.arange(4)]) + result = idx.isin(values) + expected = np.array([False, False, True, True]) + tm.assert_numpy_array_equal(result, expected) + + # empty, return dtype bool + idx = MultiIndex.from_arrays([[], []]) + result = idx.isin(values) + assert len(result) == 0 + assert result.dtype == np.bool_ + + +def test_isin_level_kwarg(): + idx = MultiIndex.from_arrays([["qux", "baz", "foo", "bar"], np.arange(4)]) + + vals_0 = ["foo", "bar", "quux"] + vals_1 = [2, 3, 10] + + expected = np.array([False, False, True, True]) + tm.assert_numpy_array_equal(expected, idx.isin(vals_0, level=0)) + tm.assert_numpy_array_equal(expected, idx.isin(vals_0, level=-2)) + + tm.assert_numpy_array_equal(expected, idx.isin(vals_1, level=1)) + tm.assert_numpy_array_equal(expected, idx.isin(vals_1, level=-1)) + + msg = "Too many levels: Index has only 2 levels, not 6" + with pytest.raises(IndexError, match=msg): + idx.isin(vals_0, level=5) + msg = "Too many levels: Index has only 2 levels, -5 is not a valid level number" + with pytest.raises(IndexError, match=msg): + idx.isin(vals_0, level=-5) + + with pytest.raises(KeyError, match=r"'Level 1\.0 not found'"): + idx.isin(vals_0, level=1.0) + with pytest.raises(KeyError, match=r"'Level -1\.0 not found'"): + idx.isin(vals_1, level=-1.0) + with pytest.raises(KeyError, match="'Level A not found'"): + idx.isin(vals_1, level="A") + + idx.names = ["A", "B"] + tm.assert_numpy_array_equal(expected, idx.isin(vals_0, level="A")) + tm.assert_numpy_array_equal(expected, idx.isin(vals_1, level="B")) + + with pytest.raises(KeyError, match="'Level C not found'"): + idx.isin(vals_1, level="C") + + +@pytest.mark.parametrize( + "labels,expected,level", + [ + ([("b", np.nan)], np.array([False, False, True]), None), + ([np.nan, "a"], np.array([True, True, False]), 0), + (["d", np.nan], np.array([False, True, True]), 1), + ], +) +def test_isin_multi_index_with_missing_value(labels, expected, level): + # GH 19132 + midx = MultiIndex.from_arrays([[np.nan, "a", "b"], ["c", "d", np.nan]]) + result = midx.isin(labels, level=level) + tm.assert_numpy_array_equal(result, expected) + + +def test_isin_empty(): + # GH#51599 + midx = MultiIndex.from_arrays([[1, 2], [3, 4]]) + result = midx.isin([]) + expected = np.array([False, False]) + tm.assert_numpy_array_equal(result, expected) + + +def test_isin_generator(): + # GH#52568 + midx = MultiIndex.from_tuples([(1, 2)]) + result = midx.isin(x for x in [(1, 2)]) + expected = np.array([True]) + tm.assert_numpy_array_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_join.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_join.py new file mode 100644 index 0000000000000000000000000000000000000000..edd0feaaa1159ff8340af772d27f2a7af09ceb87 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_join.py @@ -0,0 +1,268 @@ +import numpy as np +import pytest + +from pandas import ( + DataFrame, + Index, + Interval, + MultiIndex, + Series, + StringDtype, +) +import pandas._testing as tm + + +@pytest.mark.parametrize( + "other", [Index(["three", "one", "two"]), Index(["one"]), Index(["one", "three"])] +) +def test_join_level(idx, other, join_type): + join_index, lidx, ridx = other.join( + idx, how=join_type, level="second", return_indexers=True + ) + + exp_level = other.join(idx.levels[1], how=join_type) + assert join_index.levels[0].equals(idx.levels[0]) + assert join_index.levels[1].equals(exp_level) + + # pare down levels + mask = np.array([x[1] in exp_level for x in idx], dtype=bool) + exp_values = idx.values[mask] + tm.assert_numpy_array_equal(join_index.values, exp_values) + + if join_type in ("outer", "inner"): + join_index2, ridx2, lidx2 = idx.join( + other, how=join_type, level="second", return_indexers=True + ) + + assert join_index.equals(join_index2) + tm.assert_numpy_array_equal(lidx, lidx2) + tm.assert_numpy_array_equal(ridx, ridx2) + tm.assert_numpy_array_equal(join_index2.values, exp_values) + + +def test_join_level_corner_case(idx): + # some corner cases + index = Index(["three", "one", "two"]) + result = index.join(idx, level="second") + assert isinstance(result, MultiIndex) + + with pytest.raises(TypeError, match="Join.*MultiIndex.*ambiguous"): + idx.join(idx, level=1) + + +def test_join_self(idx, join_type): + result = idx.join(idx, how=join_type) + expected = idx + if join_type == "outer": + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + + +def test_join_multi(): + # GH 10665 + midx = MultiIndex.from_product([np.arange(4), np.arange(4)], names=["a", "b"]) + idx = Index([1, 2, 5], name="b") + + # inner + jidx, lidx, ridx = midx.join(idx, how="inner", return_indexers=True) + exp_idx = MultiIndex.from_product([np.arange(4), [1, 2]], names=["a", "b"]) + exp_lidx = np.array([1, 2, 5, 6, 9, 10, 13, 14], dtype=np.intp) + exp_ridx = np.array([0, 1, 0, 1, 0, 1, 0, 1], dtype=np.intp) + tm.assert_index_equal(jidx, exp_idx) + tm.assert_numpy_array_equal(lidx, exp_lidx) + tm.assert_numpy_array_equal(ridx, exp_ridx) + # flip + jidx, ridx, lidx = idx.join(midx, how="inner", return_indexers=True) + tm.assert_index_equal(jidx, exp_idx) + tm.assert_numpy_array_equal(lidx, exp_lidx) + tm.assert_numpy_array_equal(ridx, exp_ridx) + + # keep MultiIndex + jidx, lidx, ridx = midx.join(idx, how="left", return_indexers=True) + exp_ridx = np.array( + [-1, 0, 1, -1, -1, 0, 1, -1, -1, 0, 1, -1, -1, 0, 1, -1], dtype=np.intp + ) + tm.assert_index_equal(jidx, midx) + assert lidx is None + tm.assert_numpy_array_equal(ridx, exp_ridx) + # flip + jidx, ridx, lidx = idx.join(midx, how="right", return_indexers=True) + tm.assert_index_equal(jidx, midx) + assert lidx is None + tm.assert_numpy_array_equal(ridx, exp_ridx) + + +def test_join_multi_wrong_order(): + # GH 25760 + # GH 28956 + + midx1 = MultiIndex.from_product([[1, 2], [3, 4]], names=["a", "b"]) + midx2 = MultiIndex.from_product([[1, 2], [3, 4]], names=["b", "a"]) + + join_idx, lidx, ridx = midx1.join(midx2, return_indexers=True) + + exp_ridx = np.array([-1, -1, -1, -1], dtype=np.intp) + + tm.assert_index_equal(midx1, join_idx) + assert lidx is None + tm.assert_numpy_array_equal(ridx, exp_ridx) + + +def test_join_multi_return_indexers(): + # GH 34074 + + midx1 = MultiIndex.from_product([[1, 2], [3, 4], [5, 6]], names=["a", "b", "c"]) + midx2 = MultiIndex.from_product([[1, 2], [3, 4]], names=["a", "b"]) + + result = midx1.join(midx2, return_indexers=False) + tm.assert_index_equal(result, midx1) + + +def test_join_overlapping_interval_level(): + # GH 44096 + idx_1 = MultiIndex.from_tuples( + [ + (1, Interval(0.0, 1.0)), + (1, Interval(1.0, 2.0)), + (1, Interval(2.0, 5.0)), + (2, Interval(0.0, 1.0)), + (2, Interval(1.0, 3.0)), # interval limit is here at 3.0, not at 2.0 + (2, Interval(3.0, 5.0)), + ], + names=["num", "interval"], + ) + + idx_2 = MultiIndex.from_tuples( + [ + (1, Interval(2.0, 5.0)), + (1, Interval(0.0, 1.0)), + (1, Interval(1.0, 2.0)), + (2, Interval(3.0, 5.0)), + (2, Interval(0.0, 1.0)), + (2, Interval(1.0, 3.0)), + ], + names=["num", "interval"], + ) + + expected = MultiIndex.from_tuples( + [ + (1, Interval(0.0, 1.0)), + (1, Interval(1.0, 2.0)), + (1, Interval(2.0, 5.0)), + (2, Interval(0.0, 1.0)), + (2, Interval(1.0, 3.0)), + (2, Interval(3.0, 5.0)), + ], + names=["num", "interval"], + ) + result = idx_1.join(idx_2, how="outer") + + tm.assert_index_equal(result, expected) + + +def test_join_midx_ea(): + # GH#49277 + midx = MultiIndex.from_arrays( + [Series([1, 1, 3], dtype="Int64"), Series([1, 2, 3], dtype="Int64")], + names=["a", "b"], + ) + midx2 = MultiIndex.from_arrays( + [Series([1], dtype="Int64"), Series([3], dtype="Int64")], names=["a", "c"] + ) + result = midx.join(midx2, how="inner") + expected = MultiIndex.from_arrays( + [ + Series([1, 1], dtype="Int64"), + Series([1, 2], dtype="Int64"), + Series([3, 3], dtype="Int64"), + ], + names=["a", "b", "c"], + ) + tm.assert_index_equal(result, expected) + + +def test_join_midx_string(): + # GH#49277 + midx = MultiIndex.from_arrays( + [ + Series(["a", "a", "c"], dtype=StringDtype()), + Series(["a", "b", "c"], dtype=StringDtype()), + ], + names=["a", "b"], + ) + midx2 = MultiIndex.from_arrays( + [Series(["a"], dtype=StringDtype()), Series(["c"], dtype=StringDtype())], + names=["a", "c"], + ) + result = midx.join(midx2, how="inner") + expected = MultiIndex.from_arrays( + [ + Series(["a", "a"], dtype=StringDtype()), + Series(["a", "b"], dtype=StringDtype()), + Series(["c", "c"], dtype=StringDtype()), + ], + names=["a", "b", "c"], + ) + tm.assert_index_equal(result, expected) + + +def test_join_multi_with_nan(): + # GH29252 + df1 = DataFrame( + data={"col1": [1.1, 1.2]}, + index=MultiIndex.from_product([["A"], [1.0, 2.0]], names=["id1", "id2"]), + ) + df2 = DataFrame( + data={"col2": [2.1, 2.2]}, + index=MultiIndex.from_product([["A"], [np.nan, 2.0]], names=["id1", "id2"]), + ) + result = df1.join(df2) + expected = DataFrame( + data={"col1": [1.1, 1.2], "col2": [np.nan, 2.2]}, + index=MultiIndex.from_product([["A"], [1.0, 2.0]], names=["id1", "id2"]), + ) + tm.assert_frame_equal(result, expected) + + +@pytest.mark.parametrize("val", [0, 5]) +def test_join_dtypes(any_numeric_ea_dtype, val): + # GH#49830 + midx = MultiIndex.from_arrays([Series([1, 2], dtype=any_numeric_ea_dtype), [3, 4]]) + midx2 = MultiIndex.from_arrays( + [Series([1, val, val], dtype=any_numeric_ea_dtype), [3, 4, 4]] + ) + result = midx.join(midx2, how="outer") + expected = MultiIndex.from_arrays( + [Series([val, val, 1, 2], dtype=any_numeric_ea_dtype), [4, 4, 3, 4]] + ).sort_values() + tm.assert_index_equal(result, expected) + + +def test_join_dtypes_all_nan(any_numeric_ea_dtype): + # GH#49830 + midx = MultiIndex.from_arrays( + [Series([1, 2], dtype=any_numeric_ea_dtype), [np.nan, np.nan]] + ) + midx2 = MultiIndex.from_arrays( + [Series([1, 0, 0], dtype=any_numeric_ea_dtype), [np.nan, np.nan, np.nan]] + ) + result = midx.join(midx2, how="outer") + expected = MultiIndex.from_arrays( + [ + Series([0, 0, 1, 2], dtype=any_numeric_ea_dtype), + [np.nan, np.nan, np.nan, np.nan], + ] + ) + tm.assert_index_equal(result, expected) + + +def test_join_index_levels(): + # GH#53093 + midx = midx = MultiIndex.from_tuples([("a", "2019-02-01"), ("a", "2019-02-01")]) + midx2 = MultiIndex.from_tuples([("a", "2019-01-31")]) + result = midx.join(midx2, how="outer") + expected = MultiIndex.from_tuples( + [("a", "2019-01-31"), ("a", "2019-02-01"), ("a", "2019-02-01")] + ) + tm.assert_index_equal(result.levels[1], expected.levels[1]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_lexsort.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_lexsort.py new file mode 100644 index 0000000000000000000000000000000000000000..fc16a4197a3a4daf65de6f58d85d13883d535d41 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_lexsort.py @@ -0,0 +1,46 @@ +from pandas import MultiIndex + + +class TestIsLexsorted: + def test_is_lexsorted(self): + levels = [[0, 1], [0, 1, 2]] + + index = MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]] + ) + assert index._is_lexsorted() + + index = MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 2, 1]] + ) + assert not index._is_lexsorted() + + index = MultiIndex( + levels=levels, codes=[[0, 0, 1, 0, 1, 1], [0, 1, 0, 2, 2, 1]] + ) + assert not index._is_lexsorted() + assert index._lexsort_depth == 0 + + +class TestLexsortDepth: + def test_lexsort_depth(self): + # Test that lexsort_depth return the correct sortorder + # when it was given to the MultiIndex const. + # GH#28518 + + levels = [[0, 1], [0, 1, 2]] + + index = MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]], sortorder=2 + ) + assert index._lexsort_depth == 2 + + index = MultiIndex( + levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 2, 1]], sortorder=1 + ) + assert index._lexsort_depth == 1 + + index = MultiIndex( + levels=levels, codes=[[0, 0, 1, 0, 1, 1], [0, 1, 0, 2, 2, 1]], sortorder=0 + ) + assert index._lexsort_depth == 0 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_missing.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_missing.py new file mode 100644 index 0000000000000000000000000000000000000000..14ffc42fb4b59074c3c830a83ff6bdc36bdf099e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_missing.py @@ -0,0 +1,111 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import MultiIndex +import pandas._testing as tm + + +def test_fillna(idx): + # GH 11343 + msg = "isna is not defined for MultiIndex" + with pytest.raises(NotImplementedError, match=msg): + idx.fillna(idx[0]) + + +def test_dropna(): + # GH 6194 + idx = MultiIndex.from_arrays( + [ + [1, np.nan, 3, np.nan, 5], + [1, 2, np.nan, np.nan, 5], + ["a", "b", "c", np.nan, "e"], + ] + ) + + exp = MultiIndex.from_arrays([[1, 5], [1, 5], ["a", "e"]]) + tm.assert_index_equal(idx.dropna(), exp) + tm.assert_index_equal(idx.dropna(how="any"), exp) + + exp = MultiIndex.from_arrays( + [[1, np.nan, 3, 5], [1, 2, np.nan, 5], ["a", "b", "c", "e"]] + ) + tm.assert_index_equal(idx.dropna(how="all"), exp) + + msg = "invalid how option: xxx" + with pytest.raises(ValueError, match=msg): + idx.dropna(how="xxx") + + # GH26408 + # test if missing values are dropped for multiindex constructed + # from codes and values + idx = MultiIndex( + levels=[[np.nan, None, pd.NaT, "128", 2], [np.nan, None, pd.NaT, "128", 2]], + codes=[[0, -1, 1, 2, 3, 4], [0, -1, 3, 3, 3, 4]], + ) + expected = MultiIndex.from_arrays([["128", 2], ["128", 2]]) + tm.assert_index_equal(idx.dropna(), expected) + tm.assert_index_equal(idx.dropna(how="any"), expected) + + expected = MultiIndex.from_arrays( + [[np.nan, np.nan, "128", 2], ["128", "128", "128", 2]] + ) + tm.assert_index_equal(idx.dropna(how="all"), expected) + + +def test_nulls(idx): + # this is really a smoke test for the methods + # as these are adequately tested for function elsewhere + + msg = "isna is not defined for MultiIndex" + with pytest.raises(NotImplementedError, match=msg): + idx.isna() + + +@pytest.mark.xfail(reason="isna is not defined for MultiIndex") +def test_hasnans_isnans(idx): + # GH 11343, added tests for hasnans / isnans + index = idx.copy() + + # cases in indices doesn't include NaN + expected = np.array([False] * len(index), dtype=bool) + tm.assert_numpy_array_equal(index._isnan, expected) + assert index.hasnans is False + + index = idx.copy() + values = index.values + values[1] = np.nan + + index = type(idx)(values) + + expected = np.array([False] * len(index), dtype=bool) + expected[1] = True + tm.assert_numpy_array_equal(index._isnan, expected) + assert index.hasnans is True + + +def test_nan_stays_float(): + # GH 7031 + idx0 = MultiIndex(levels=[["A", "B"], []], codes=[[1, 0], [-1, -1]], names=[0, 1]) + idx1 = MultiIndex(levels=[["C"], ["D"]], codes=[[0], [0]], names=[0, 1]) + idxm = idx0.join(idx1, how="outer") + assert pd.isna(idx0.get_level_values(1)).all() + # the following failed in 0.14.1 + assert pd.isna(idxm.get_level_values(1)[:-1]).all() + + df0 = pd.DataFrame([[1, 2]], index=idx0) + df1 = pd.DataFrame([[3, 4]], index=idx1) + dfm = df0 - df1 + assert pd.isna(df0.index.get_level_values(1)).all() + # the following failed in 0.14.1 + assert pd.isna(dfm.index.get_level_values(1)[:-1]).all() + + +def test_tuples_have_na(): + index = MultiIndex( + levels=[[1, 0], [0, 1, 2, 3]], + codes=[[1, 1, 1, 1, -1, 0, 0, 0], [0, 1, 2, 3, 0, 1, 2, 3]], + ) + + assert pd.isna(index[4][0]) + assert pd.isna(index.values[4][0]) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_monotonic.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_monotonic.py new file mode 100644 index 0000000000000000000000000000000000000000..2b0b3f7cb36d72abedc538eda9e6a85eb45067e2 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_monotonic.py @@ -0,0 +1,188 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + MultiIndex, +) + + +def test_is_monotonic_increasing_lexsorted(lexsorted_two_level_string_multiindex): + # string ordering + mi = lexsorted_two_level_string_multiindex + assert mi.is_monotonic_increasing is False + assert Index(mi.values).is_monotonic_increasing is False + assert mi._is_strictly_monotonic_increasing is False + assert Index(mi.values)._is_strictly_monotonic_increasing is False + + +def test_is_monotonic_increasing(): + i = MultiIndex.from_product([np.arange(10), np.arange(10)], names=["one", "two"]) + assert i.is_monotonic_increasing is True + assert i._is_strictly_monotonic_increasing is True + assert Index(i.values).is_monotonic_increasing is True + assert i._is_strictly_monotonic_increasing is True + + i = MultiIndex.from_product( + [np.arange(10, 0, -1), np.arange(10)], names=["one", "two"] + ) + assert i.is_monotonic_increasing is False + assert i._is_strictly_monotonic_increasing is False + assert Index(i.values).is_monotonic_increasing is False + assert Index(i.values)._is_strictly_monotonic_increasing is False + + i = MultiIndex.from_product( + [np.arange(10), np.arange(10, 0, -1)], names=["one", "two"] + ) + assert i.is_monotonic_increasing is False + assert i._is_strictly_monotonic_increasing is False + assert Index(i.values).is_monotonic_increasing is False + assert Index(i.values)._is_strictly_monotonic_increasing is False + + i = MultiIndex.from_product([[1.0, np.nan, 2.0], ["a", "b", "c"]]) + assert i.is_monotonic_increasing is False + assert i._is_strictly_monotonic_increasing is False + assert Index(i.values).is_monotonic_increasing is False + assert Index(i.values)._is_strictly_monotonic_increasing is False + + i = MultiIndex( + levels=[["bar", "baz", "foo", "qux"], ["mom", "next", "zenith"]], + codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]], + names=["first", "second"], + ) + assert i.is_monotonic_increasing is True + assert Index(i.values).is_monotonic_increasing is True + assert i._is_strictly_monotonic_increasing is True + assert Index(i.values)._is_strictly_monotonic_increasing is True + + # mixed levels, hits the TypeError + i = MultiIndex( + levels=[ + [1, 2, 3, 4], + [ + "gb00b03mlx29", + "lu0197800237", + "nl0000289783", + "nl0000289965", + "nl0000301109", + ], + ], + codes=[[0, 1, 1, 2, 2, 2, 3], [4, 2, 0, 0, 1, 3, -1]], + names=["household_id", "asset_id"], + ) + + assert i.is_monotonic_increasing is False + assert i._is_strictly_monotonic_increasing is False + + # empty + i = MultiIndex.from_arrays([[], []]) + assert i.is_monotonic_increasing is True + assert Index(i.values).is_monotonic_increasing is True + assert i._is_strictly_monotonic_increasing is True + assert Index(i.values)._is_strictly_monotonic_increasing is True + + +def test_is_monotonic_decreasing(): + i = MultiIndex.from_product( + [np.arange(9, -1, -1), np.arange(9, -1, -1)], names=["one", "two"] + ) + assert i.is_monotonic_decreasing is True + assert i._is_strictly_monotonic_decreasing is True + assert Index(i.values).is_monotonic_decreasing is True + assert i._is_strictly_monotonic_decreasing is True + + i = MultiIndex.from_product( + [np.arange(10), np.arange(10, 0, -1)], names=["one", "two"] + ) + assert i.is_monotonic_decreasing is False + assert i._is_strictly_monotonic_decreasing is False + assert Index(i.values).is_monotonic_decreasing is False + assert Index(i.values)._is_strictly_monotonic_decreasing is False + + i = MultiIndex.from_product( + [np.arange(10, 0, -1), np.arange(10)], names=["one", "two"] + ) + assert i.is_monotonic_decreasing is False + assert i._is_strictly_monotonic_decreasing is False + assert Index(i.values).is_monotonic_decreasing is False + assert Index(i.values)._is_strictly_monotonic_decreasing is False + + i = MultiIndex.from_product([[2.0, np.nan, 1.0], ["c", "b", "a"]]) + assert i.is_monotonic_decreasing is False + assert i._is_strictly_monotonic_decreasing is False + assert Index(i.values).is_monotonic_decreasing is False + assert Index(i.values)._is_strictly_monotonic_decreasing is False + + # string ordering + i = MultiIndex( + levels=[["qux", "foo", "baz", "bar"], ["three", "two", "one"]], + codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]], + names=["first", "second"], + ) + assert i.is_monotonic_decreasing is False + assert Index(i.values).is_monotonic_decreasing is False + assert i._is_strictly_monotonic_decreasing is False + assert Index(i.values)._is_strictly_monotonic_decreasing is False + + i = MultiIndex( + levels=[["qux", "foo", "baz", "bar"], ["zenith", "next", "mom"]], + codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]], + names=["first", "second"], + ) + assert i.is_monotonic_decreasing is True + assert Index(i.values).is_monotonic_decreasing is True + assert i._is_strictly_monotonic_decreasing is True + assert Index(i.values)._is_strictly_monotonic_decreasing is True + + # mixed levels, hits the TypeError + i = MultiIndex( + levels=[ + [4, 3, 2, 1], + [ + "nl0000301109", + "nl0000289965", + "nl0000289783", + "lu0197800237", + "gb00b03mlx29", + ], + ], + codes=[[0, 1, 1, 2, 2, 2, 3], [4, 2, 0, 0, 1, 3, -1]], + names=["household_id", "asset_id"], + ) + + assert i.is_monotonic_decreasing is False + assert i._is_strictly_monotonic_decreasing is False + + # empty + i = MultiIndex.from_arrays([[], []]) + assert i.is_monotonic_decreasing is True + assert Index(i.values).is_monotonic_decreasing is True + assert i._is_strictly_monotonic_decreasing is True + assert Index(i.values)._is_strictly_monotonic_decreasing is True + + +def test_is_strictly_monotonic_increasing(): + idx = MultiIndex( + levels=[["bar", "baz"], ["mom", "next"]], codes=[[0, 0, 1, 1], [0, 0, 0, 1]] + ) + assert idx.is_monotonic_increasing is True + assert idx._is_strictly_monotonic_increasing is False + + +def test_is_strictly_monotonic_decreasing(): + idx = MultiIndex( + levels=[["baz", "bar"], ["next", "mom"]], codes=[[0, 0, 1, 1], [0, 0, 0, 1]] + ) + assert idx.is_monotonic_decreasing is True + assert idx._is_strictly_monotonic_decreasing is False + + +@pytest.mark.parametrize("attr", ["is_monotonic_increasing", "is_monotonic_decreasing"]) +@pytest.mark.parametrize( + "values", + [[(np.nan,), (1,), (2,)], [(1,), (np.nan,), (2,)], [(1,), (2,), (np.nan,)]], +) +def test_is_monotonic_with_nans(values, attr): + # GH: 37220 + idx = MultiIndex.from_tuples(values, names=["test"]) + assert getattr(idx, attr) is False diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_names.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_names.py new file mode 100644 index 0000000000000000000000000000000000000000..45f19b4d70fb95cb2aee459a54d2ad53790b7df8 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_names.py @@ -0,0 +1,201 @@ +import pytest + +import pandas as pd +from pandas import MultiIndex +import pandas._testing as tm + + +def check_level_names(index, names): + assert [level.name for level in index.levels] == list(names) + + +def test_slice_keep_name(): + x = MultiIndex.from_tuples([("a", "b"), (1, 2), ("c", "d")], names=["x", "y"]) + assert x[1:].names == x.names + + +def test_index_name_retained(): + # GH9857 + result = pd.DataFrame({"x": [1, 2, 6], "y": [2, 2, 8], "z": [-5, 0, 5]}) + result = result.set_index("z") + result.loc[10] = [9, 10] + df_expected = pd.DataFrame( + {"x": [1, 2, 6, 9], "y": [2, 2, 8, 10], "z": [-5, 0, 5, 10]} + ) + df_expected = df_expected.set_index("z") + tm.assert_frame_equal(result, df_expected) + + +def test_changing_names(idx): + assert [level.name for level in idx.levels] == ["first", "second"] + + view = idx.view() + copy = idx.copy() + shallow_copy = idx._view() + + # changing names should not change level names on object + new_names = [name + "a" for name in idx.names] + idx.names = new_names + check_level_names(idx, ["firsta", "seconda"]) + + # and not on copies + check_level_names(view, ["first", "second"]) + check_level_names(copy, ["first", "second"]) + check_level_names(shallow_copy, ["first", "second"]) + + # and copies shouldn't change original + shallow_copy.names = [name + "c" for name in shallow_copy.names] + check_level_names(idx, ["firsta", "seconda"]) + + +def test_take_preserve_name(idx): + taken = idx.take([3, 0, 1]) + assert taken.names == idx.names + + +def test_copy_names(): + # Check that adding a "names" parameter to the copy is honored + # GH14302 + multi_idx = MultiIndex.from_tuples([(1, 2), (3, 4)], names=["MyName1", "MyName2"]) + multi_idx1 = multi_idx.copy() + + assert multi_idx.equals(multi_idx1) + assert multi_idx.names == ["MyName1", "MyName2"] + assert multi_idx1.names == ["MyName1", "MyName2"] + + multi_idx2 = multi_idx.copy(names=["NewName1", "NewName2"]) + + assert multi_idx.equals(multi_idx2) + assert multi_idx.names == ["MyName1", "MyName2"] + assert multi_idx2.names == ["NewName1", "NewName2"] + + multi_idx3 = multi_idx.copy(name=["NewName1", "NewName2"]) + + assert multi_idx.equals(multi_idx3) + assert multi_idx.names == ["MyName1", "MyName2"] + assert multi_idx3.names == ["NewName1", "NewName2"] + + # gh-35592 + with pytest.raises(ValueError, match="Length of new names must be 2, got 1"): + multi_idx.copy(names=["mario"]) + + with pytest.raises(TypeError, match="MultiIndex.name must be a hashable type"): + multi_idx.copy(names=[["mario"], ["luigi"]]) + + +def test_names(idx): + # names are assigned in setup + assert idx.names == ["first", "second"] + level_names = [level.name for level in idx.levels] + assert level_names == idx.names + + # setting bad names on existing + index = idx + with pytest.raises(ValueError, match="^Length of names"): + setattr(index, "names", list(index.names) + ["third"]) + with pytest.raises(ValueError, match="^Length of names"): + setattr(index, "names", []) + + # initializing with bad names (should always be equivalent) + major_axis, minor_axis = idx.levels + major_codes, minor_codes = idx.codes + with pytest.raises(ValueError, match="^Length of names"): + MultiIndex( + levels=[major_axis, minor_axis], + codes=[major_codes, minor_codes], + names=["first"], + ) + with pytest.raises(ValueError, match="^Length of names"): + MultiIndex( + levels=[major_axis, minor_axis], + codes=[major_codes, minor_codes], + names=["first", "second", "third"], + ) + + # names are assigned on index, but not transferred to the levels + index.names = ["a", "b"] + level_names = [level.name for level in index.levels] + assert level_names == ["a", "b"] + + +def test_duplicate_level_names_access_raises(idx): + # GH19029 + idx.names = ["foo", "foo"] + with pytest.raises(ValueError, match="name foo occurs multiple times"): + idx._get_level_number("foo") + + +def test_get_names_from_levels(): + idx = MultiIndex.from_product([["a"], [1, 2]], names=["a", "b"]) + + assert idx.levels[0].name == "a" + assert idx.levels[1].name == "b" + + +def test_setting_names_from_levels_raises(): + idx = MultiIndex.from_product([["a"], [1, 2]], names=["a", "b"]) + with pytest.raises(RuntimeError, match="set_names"): + idx.levels[0].name = "foo" + + with pytest.raises(RuntimeError, match="set_names"): + idx.levels[1].name = "foo" + + new = pd.Series(1, index=idx.levels[0]) + with pytest.raises(RuntimeError, match="set_names"): + new.index.name = "bar" + + assert pd.Index._no_setting_name is False + assert pd.RangeIndex._no_setting_name is False + + +@pytest.mark.parametrize("func", ["rename", "set_names"]) +@pytest.mark.parametrize( + "rename_dict, exp_names", + [ + ({"x": "z"}, ["z", "y", "z"]), + ({"x": "z", "y": "x"}, ["z", "x", "z"]), + ({"y": "z"}, ["x", "z", "x"]), + ({}, ["x", "y", "x"]), + ({"z": "a"}, ["x", "y", "x"]), + ({"y": "z", "a": "b"}, ["x", "z", "x"]), + ], +) +def test_name_mi_with_dict_like_duplicate_names(func, rename_dict, exp_names): + # GH#20421 + mi = MultiIndex.from_arrays([[1, 2], [3, 4], [5, 6]], names=["x", "y", "x"]) + result = getattr(mi, func)(rename_dict) + expected = MultiIndex.from_arrays([[1, 2], [3, 4], [5, 6]], names=exp_names) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("func", ["rename", "set_names"]) +@pytest.mark.parametrize( + "rename_dict, exp_names", + [ + ({"x": "z"}, ["z", "y"]), + ({"x": "z", "y": "x"}, ["z", "x"]), + ({"a": "z"}, ["x", "y"]), + ({}, ["x", "y"]), + ], +) +def test_name_mi_with_dict_like(func, rename_dict, exp_names): + # GH#20421 + mi = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["x", "y"]) + result = getattr(mi, func)(rename_dict) + expected = MultiIndex.from_arrays([[1, 2], [3, 4]], names=exp_names) + tm.assert_index_equal(result, expected) + + +def test_index_name_with_dict_like_raising(): + # GH#20421 + ix = pd.Index([1, 2]) + msg = "Can only pass dict-like as `names` for MultiIndex." + with pytest.raises(TypeError, match=msg): + ix.set_names({"x": "z"}) + + +def test_multiindex_name_and_level_raising(): + # GH#20421 + mi = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["x", "y"]) + with pytest.raises(TypeError, match="Can not pass level for dictlike `names`."): + mi.set_names(names={"x": "z"}, level={"x": "z"}) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_partial_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_partial_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..64cc1fa621b3195727cbfb3e62a8b6a6acf4dfaf --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_partial_indexing.py @@ -0,0 +1,148 @@ +import numpy as np +import pytest + +from pandas import ( + DataFrame, + IndexSlice, + MultiIndex, + date_range, +) +import pandas._testing as tm + + +@pytest.fixture +def df(): + # c1 + # 2016-01-01 00:00:00 a 0 + # b 1 + # c 2 + # 2016-01-01 12:00:00 a 3 + # b 4 + # c 5 + # 2016-01-02 00:00:00 a 6 + # b 7 + # c 8 + # 2016-01-02 12:00:00 a 9 + # b 10 + # c 11 + # 2016-01-03 00:00:00 a 12 + # b 13 + # c 14 + dr = date_range("2016-01-01", "2016-01-03", freq="12h") + abc = ["a", "b", "c"] + mi = MultiIndex.from_product([dr, abc]) + frame = DataFrame({"c1": range(15)}, index=mi) + return frame + + +def test_partial_string_matching_single_index(df): + # partial string matching on a single index + for df_swap in [df.swaplevel(), df.swaplevel(0), df.swaplevel(0, 1)]: + df_swap = df_swap.sort_index() + just_a = df_swap.loc["a"] + result = just_a.loc["2016-01-01"] + expected = df.loc[IndexSlice[:, "a"], :].iloc[0:2] + expected.index = expected.index.droplevel(1) + tm.assert_frame_equal(result, expected) + + +def test_get_loc_partial_timestamp_multiindex(df): + mi = df.index + key = ("2016-01-01", "a") + loc = mi.get_loc(key) + + expected = np.zeros(len(mi), dtype=bool) + expected[[0, 3]] = True + tm.assert_numpy_array_equal(loc, expected) + + key2 = ("2016-01-02", "a") + loc2 = mi.get_loc(key2) + expected2 = np.zeros(len(mi), dtype=bool) + expected2[[6, 9]] = True + tm.assert_numpy_array_equal(loc2, expected2) + + key3 = ("2016-01", "a") + loc3 = mi.get_loc(key3) + expected3 = np.zeros(len(mi), dtype=bool) + expected3[mi.get_level_values(1).get_loc("a")] = True + tm.assert_numpy_array_equal(loc3, expected3) + + key4 = ("2016", "a") + loc4 = mi.get_loc(key4) + expected4 = expected3 + tm.assert_numpy_array_equal(loc4, expected4) + + # non-monotonic + taker = np.arange(len(mi), dtype=np.intp) + taker[::2] = taker[::-2] + mi2 = mi.take(taker) + loc5 = mi2.get_loc(key) + expected5 = np.zeros(len(mi2), dtype=bool) + expected5[[3, 14]] = True + tm.assert_numpy_array_equal(loc5, expected5) + + +def test_partial_string_timestamp_multiindex(df): + # GH10331 + df_swap = df.swaplevel(0, 1).sort_index() + SLC = IndexSlice + + # indexing with IndexSlice + result = df.loc[SLC["2016-01-01":"2016-02-01", :], :] + expected = df + tm.assert_frame_equal(result, expected) + + # match on secondary index + result = df_swap.loc[SLC[:, "2016-01-01":"2016-01-01"], :] + expected = df_swap.iloc[[0, 1, 5, 6, 10, 11]] + tm.assert_frame_equal(result, expected) + + # partial string match on year only + result = df.loc["2016"] + expected = df + tm.assert_frame_equal(result, expected) + + # partial string match on date + result = df.loc["2016-01-01"] + expected = df.iloc[0:6] + tm.assert_frame_equal(result, expected) + + # partial string match on date and hour, from middle + result = df.loc["2016-01-02 12"] + # hourly resolution, same as index.levels[0], so we are _not_ slicing on + # that level, so that level gets dropped + expected = df.iloc[9:12].droplevel(0) + tm.assert_frame_equal(result, expected) + + # partial string match on secondary index + result = df_swap.loc[SLC[:, "2016-01-02"], :] + expected = df_swap.iloc[[2, 3, 7, 8, 12, 13]] + tm.assert_frame_equal(result, expected) + + # tuple selector with partial string match on date + # "2016-01-01" has daily resolution, so _is_ a slice on the first level. + result = df.loc[("2016-01-01", "a"), :] + expected = df.iloc[[0, 3]] + expected = df.iloc[[0, 3]].droplevel(1) + tm.assert_frame_equal(result, expected) + + # Slicing date on first level should break (of course) bc the DTI is the + # second level on df_swap + with pytest.raises(KeyError, match="'2016-01-01'"): + df_swap.loc["2016-01-01"] + + +def test_partial_string_timestamp_multiindex_str_key_raises(df): + # Even though this syntax works on a single index, this is somewhat + # ambiguous and we don't want to extend this behavior forward to work + # in multi-indexes. This would amount to selecting a scalar from a + # column. + with pytest.raises(KeyError, match="'2016-01-01'"): + df["2016-01-01"] + + +def test_partial_string_timestamp_multiindex_daily_resolution(df): + # GH12685 (partial string with daily resolution or below) + result = df.loc[IndexSlice["2013-03":"2013-03", :], :] + expected = df.iloc[118:180] + tm.assert_frame_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_pickle.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_pickle.py new file mode 100644 index 0000000000000000000000000000000000000000..1d8b72140442159fa0b8c608022d167bddd95db4 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_pickle.py @@ -0,0 +1,10 @@ +import pytest + +from pandas import MultiIndex + + +def test_pickle_compat_construction(): + # this is testing for pickle compat + # need an object to create with + with pytest.raises(TypeError, match="Must pass both levels and codes"): + MultiIndex() diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reindex.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reindex.py new file mode 100644 index 0000000000000000000000000000000000000000..d1b4fe8b98760a0b776c5d81d471a7745e8407de --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reindex.py @@ -0,0 +1,174 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + MultiIndex, +) +import pandas._testing as tm + + +def test_reindex(idx): + result, indexer = idx.reindex(list(idx[:4])) + assert isinstance(result, MultiIndex) + assert result.names == ["first", "second"] + assert [level.name for level in result.levels] == ["first", "second"] + + result, indexer = idx.reindex(list(idx)) + assert isinstance(result, MultiIndex) + assert indexer is None + assert result.names == ["first", "second"] + assert [level.name for level in result.levels] == ["first", "second"] + + +def test_reindex_level(idx): + index = Index(["one"]) + + target, indexer = idx.reindex(index, level="second") + target2, indexer2 = index.reindex(idx, level="second") + + exp_index = idx.join(index, level="second", how="right") + exp_index2 = idx.join(index, level="second", how="left") + + assert target.equals(exp_index) + exp_indexer = np.array([0, 2, 4]) + tm.assert_numpy_array_equal(indexer, exp_indexer, check_dtype=False) + + assert target2.equals(exp_index2) + exp_indexer2 = np.array([0, -1, 0, -1, 0, -1]) + tm.assert_numpy_array_equal(indexer2, exp_indexer2, check_dtype=False) + + with pytest.raises(TypeError, match="Fill method not supported"): + idx.reindex(idx, method="pad", level="second") + + +def test_reindex_preserves_names_when_target_is_list_or_ndarray(idx): + # GH6552 + idx = idx.copy() + target = idx.copy() + idx.names = target.names = [None, None] + + other_dtype = MultiIndex.from_product([[1, 2], [3, 4]]) + + # list & ndarray cases + assert idx.reindex([])[0].names == [None, None] + assert idx.reindex(np.array([]))[0].names == [None, None] + assert idx.reindex(target.tolist())[0].names == [None, None] + assert idx.reindex(target.values)[0].names == [None, None] + assert idx.reindex(other_dtype.tolist())[0].names == [None, None] + assert idx.reindex(other_dtype.values)[0].names == [None, None] + + idx.names = ["foo", "bar"] + assert idx.reindex([])[0].names == ["foo", "bar"] + assert idx.reindex(np.array([]))[0].names == ["foo", "bar"] + assert idx.reindex(target.tolist())[0].names == ["foo", "bar"] + assert idx.reindex(target.values)[0].names == ["foo", "bar"] + assert idx.reindex(other_dtype.tolist())[0].names == ["foo", "bar"] + assert idx.reindex(other_dtype.values)[0].names == ["foo", "bar"] + + +def test_reindex_lvl_preserves_names_when_target_is_list_or_array(): + # GH7774 + idx = MultiIndex.from_product([[0, 1], ["a", "b"]], names=["foo", "bar"]) + assert idx.reindex([], level=0)[0].names == ["foo", "bar"] + assert idx.reindex([], level=1)[0].names == ["foo", "bar"] + + +def test_reindex_lvl_preserves_type_if_target_is_empty_list_or_array( + using_infer_string, +): + # GH7774 + idx = MultiIndex.from_product([[0, 1], ["a", "b"]]) + assert idx.reindex([], level=0)[0].levels[0].dtype.type == np.int64 + exp = np.object_ if not using_infer_string else str + assert idx.reindex([], level=1)[0].levels[1].dtype.type == exp + + # case with EA levels + cat = pd.Categorical(["foo", "bar"]) + dti = pd.date_range("2016-01-01", periods=2, tz="US/Pacific") + mi = MultiIndex.from_product([cat, dti]) + assert mi.reindex([], level=0)[0].levels[0].dtype == cat.dtype + assert mi.reindex([], level=1)[0].levels[1].dtype == dti.dtype + + +def test_reindex_base(idx): + expected = np.arange(idx.size, dtype=np.intp) + + actual = idx.get_indexer(idx) + tm.assert_numpy_array_equal(expected, actual) + + with pytest.raises(ValueError, match="Invalid fill method"): + idx.get_indexer(idx, method="invalid") + + +def test_reindex_non_unique(): + idx = MultiIndex.from_tuples([(0, 0), (1, 1), (1, 1), (2, 2)]) + a = pd.Series(np.arange(4), index=idx) + new_idx = MultiIndex.from_tuples([(0, 0), (1, 1), (2, 2)]) + + msg = "cannot handle a non-unique multi-index!" + with pytest.raises(ValueError, match=msg): + a.reindex(new_idx) + + +@pytest.mark.parametrize("values", [[["a"], ["x"]], [[], []]]) +def test_reindex_empty_with_level(values): + # GH41170 + idx = MultiIndex.from_arrays(values) + result, result_indexer = idx.reindex(np.array(["b"]), level=0) + expected = MultiIndex(levels=[["b"], values[1]], codes=[[], []]) + expected_indexer = np.array([], dtype=result_indexer.dtype) + tm.assert_index_equal(result, expected) + tm.assert_numpy_array_equal(result_indexer, expected_indexer) + + +def test_reindex_not_all_tuples(): + keys = [("i", "i"), ("i", "j"), ("j", "i"), "j"] + mi = MultiIndex.from_tuples(keys[:-1]) + idx = Index(keys) + res, indexer = mi.reindex(idx) + + tm.assert_index_equal(res, idx) + expected = np.array([0, 1, 2, -1], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + +def test_reindex_limit_arg_with_multiindex(): + # GH21247 + + idx = MultiIndex.from_tuples([(3, "A"), (4, "A"), (4, "B")]) + + df = pd.Series([0.02, 0.01, 0.012], index=idx) + + new_idx = MultiIndex.from_tuples( + [ + (3, "A"), + (3, "B"), + (4, "A"), + (4, "B"), + (4, "C"), + (5, "B"), + (5, "C"), + (6, "B"), + (6, "C"), + ] + ) + + with pytest.raises( + ValueError, + match="limit argument only valid if doing pad, backfill or nearest reindexing", + ): + df.reindex(new_idx, fill_value=0, limit=1) + + +def test_reindex_with_none_in_nested_multiindex(): + # GH42883 + index = MultiIndex.from_tuples([(("a", None), 1), (("b", None), 2)]) + index2 = MultiIndex.from_tuples([(("b", None), 2), (("a", None), 1)]) + df1_dtype = pd.DataFrame([1, 2], index=index) + df2_dtype = pd.DataFrame([2, 1], index=index2) + + result = df1_dtype.reindex_like(df2_dtype) + expected = df2_dtype + tm.assert_frame_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reshape.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reshape.py new file mode 100644 index 0000000000000000000000000000000000000000..06dbb33aadf97a54e4bb283d3aed8fe1169164b3 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_reshape.py @@ -0,0 +1,224 @@ +from datetime import datetime + +import numpy as np +import pytest +import pytz + +import pandas as pd +from pandas import ( + Index, + MultiIndex, +) +import pandas._testing as tm + + +def test_insert(idx): + # key contained in all levels + new_index = idx.insert(0, ("bar", "two")) + assert new_index.equal_levels(idx) + assert new_index[0] == ("bar", "two") + + # key not contained in all levels + new_index = idx.insert(0, ("abc", "three")) + + exp0 = Index(list(idx.levels[0]) + ["abc"], name="first") + tm.assert_index_equal(new_index.levels[0], exp0) + assert new_index.names == ["first", "second"] + + exp1 = Index(list(idx.levels[1]) + ["three"], name="second") + tm.assert_index_equal(new_index.levels[1], exp1) + assert new_index[0] == ("abc", "three") + + # key wrong length + msg = "Item must have length equal to number of levels" + with pytest.raises(ValueError, match=msg): + idx.insert(0, ("foo2",)) + + left = pd.DataFrame([["a", "b", 0], ["b", "d", 1]], columns=["1st", "2nd", "3rd"]) + left.set_index(["1st", "2nd"], inplace=True) + ts = left["3rd"].copy(deep=True) + + left.loc[("b", "x"), "3rd"] = 2 + left.loc[("b", "a"), "3rd"] = -1 + left.loc[("b", "b"), "3rd"] = 3 + left.loc[("a", "x"), "3rd"] = 4 + left.loc[("a", "w"), "3rd"] = 5 + left.loc[("a", "a"), "3rd"] = 6 + + ts.loc[("b", "x")] = 2 + ts.loc["b", "a"] = -1 + ts.loc[("b", "b")] = 3 + ts.loc["a", "x"] = 4 + ts.loc[("a", "w")] = 5 + ts.loc["a", "a"] = 6 + + right = pd.DataFrame( + [ + ["a", "b", 0], + ["b", "d", 1], + ["b", "x", 2], + ["b", "a", -1], + ["b", "b", 3], + ["a", "x", 4], + ["a", "w", 5], + ["a", "a", 6], + ], + columns=["1st", "2nd", "3rd"], + ) + right.set_index(["1st", "2nd"], inplace=True) + # FIXME data types changes to float because + # of intermediate nan insertion; + tm.assert_frame_equal(left, right, check_dtype=False) + tm.assert_series_equal(ts, right["3rd"]) + + +def test_insert2(): + # GH9250 + idx = ( + [("test1", i) for i in range(5)] + + [("test2", i) for i in range(6)] + + [("test", 17), ("test", 18)] + ) + + left = pd.Series(np.linspace(0, 10, 11), MultiIndex.from_tuples(idx[:-2])) + + left.loc[("test", 17)] = 11 + left.loc[("test", 18)] = 12 + + right = pd.Series(np.linspace(0, 12, 13), MultiIndex.from_tuples(idx)) + + tm.assert_series_equal(left, right) + + +def test_append(idx): + result = idx[:3].append(idx[3:]) + assert result.equals(idx) + + foos = [idx[:1], idx[1:3], idx[3:]] + result = foos[0].append(foos[1:]) + assert result.equals(idx) + + # empty + result = idx.append([]) + assert result.equals(idx) + + +def test_append_index(): + idx1 = Index([1.1, 1.2, 1.3]) + idx2 = pd.date_range("2011-01-01", freq="D", periods=3, tz="Asia/Tokyo") + idx3 = Index(["A", "B", "C"]) + + midx_lv2 = MultiIndex.from_arrays([idx1, idx2]) + midx_lv3 = MultiIndex.from_arrays([idx1, idx2, idx3]) + + result = idx1.append(midx_lv2) + + # see gh-7112 + tz = pytz.timezone("Asia/Tokyo") + expected_tuples = [ + (1.1, tz.localize(datetime(2011, 1, 1))), + (1.2, tz.localize(datetime(2011, 1, 2))), + (1.3, tz.localize(datetime(2011, 1, 3))), + ] + expected = Index([1.1, 1.2, 1.3] + expected_tuples) + tm.assert_index_equal(result, expected) + + result = midx_lv2.append(idx1) + expected = Index(expected_tuples + [1.1, 1.2, 1.3]) + tm.assert_index_equal(result, expected) + + result = midx_lv2.append(midx_lv2) + expected = MultiIndex.from_arrays([idx1.append(idx1), idx2.append(idx2)]) + tm.assert_index_equal(result, expected) + + result = midx_lv2.append(midx_lv3) + tm.assert_index_equal(result, expected) + + result = midx_lv3.append(midx_lv2) + expected = Index._simple_new( + np.array( + [ + (1.1, tz.localize(datetime(2011, 1, 1)), "A"), + (1.2, tz.localize(datetime(2011, 1, 2)), "B"), + (1.3, tz.localize(datetime(2011, 1, 3)), "C"), + ] + + expected_tuples, + dtype=object, + ), + None, + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("name, exp", [("b", "b"), ("c", None)]) +def test_append_names_match(name, exp): + # GH#48288 + midx = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["a", "b"]) + midx2 = MultiIndex.from_arrays([[3], [5]], names=["a", name]) + result = midx.append(midx2) + expected = MultiIndex.from_arrays([[1, 2, 3], [3, 4, 5]], names=["a", exp]) + tm.assert_index_equal(result, expected) + + +def test_append_names_dont_match(): + # GH#48288 + midx = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["a", "b"]) + midx2 = MultiIndex.from_arrays([[3], [5]], names=["x", "y"]) + result = midx.append(midx2) + expected = MultiIndex.from_arrays([[1, 2, 3], [3, 4, 5]], names=None) + tm.assert_index_equal(result, expected) + + +def test_append_overlapping_interval_levels(): + # GH 54934 + ivl1 = pd.IntervalIndex.from_breaks([0.0, 1.0, 2.0]) + ivl2 = pd.IntervalIndex.from_breaks([0.5, 1.5, 2.5]) + mi1 = MultiIndex.from_product([ivl1, ivl1]) + mi2 = MultiIndex.from_product([ivl2, ivl2]) + result = mi1.append(mi2) + expected = MultiIndex.from_tuples( + [ + (pd.Interval(0.0, 1.0), pd.Interval(0.0, 1.0)), + (pd.Interval(0.0, 1.0), pd.Interval(1.0, 2.0)), + (pd.Interval(1.0, 2.0), pd.Interval(0.0, 1.0)), + (pd.Interval(1.0, 2.0), pd.Interval(1.0, 2.0)), + (pd.Interval(0.5, 1.5), pd.Interval(0.5, 1.5)), + (pd.Interval(0.5, 1.5), pd.Interval(1.5, 2.5)), + (pd.Interval(1.5, 2.5), pd.Interval(0.5, 1.5)), + (pd.Interval(1.5, 2.5), pd.Interval(1.5, 2.5)), + ] + ) + tm.assert_index_equal(result, expected) + + +def test_repeat(): + reps = 2 + numbers = [1, 2, 3] + names = np.array(["foo", "bar"]) + + m = MultiIndex.from_product([numbers, names], names=names) + expected = MultiIndex.from_product([numbers, names.repeat(reps)], names=names) + tm.assert_index_equal(m.repeat(reps), expected) + + +def test_insert_base(idx): + result = idx[1:4] + + # test 0th element + assert idx[0:4].equals(result.insert(0, idx[0])) + + +def test_delete_base(idx): + expected = idx[1:] + result = idx.delete(0) + assert result.equals(expected) + assert result.name == expected.name + + expected = idx[:-1] + result = idx.delete(-1) + assert result.equals(expected) + assert result.name == expected.name + + msg = "index 6 is out of bounds for axis 0 with size 6" + with pytest.raises(IndexError, match=msg): + idx.delete(len(idx)) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..0abb56ecf9de7182dd38e45d5a8938cb81248034 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_setops.py @@ -0,0 +1,772 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + CategoricalIndex, + DataFrame, + Index, + IntervalIndex, + MultiIndex, + Series, +) +import pandas._testing as tm +from pandas.api.types import ( + is_float_dtype, + is_unsigned_integer_dtype, +) + + +@pytest.mark.parametrize("case", [0.5, "xxx"]) +@pytest.mark.parametrize( + "method", ["intersection", "union", "difference", "symmetric_difference"] +) +def test_set_ops_error_cases(idx, case, sort, method): + # non-iterable input + msg = "Input must be Index or array-like" + with pytest.raises(TypeError, match=msg): + getattr(idx, method)(case, sort=sort) + + +@pytest.mark.parametrize("klass", [MultiIndex, np.array, Series, list]) +def test_intersection_base(idx, sort, klass): + first = idx[2::-1] # first 3 elements reversed + second = idx[:5] + + if klass is not MultiIndex: + second = klass(second.values) + + intersect = first.intersection(second, sort=sort) + if sort is None: + expected = first.sort_values() + else: + expected = first + tm.assert_index_equal(intersect, expected) + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + first.intersection([1, 2, 3], sort=sort) + + +@pytest.mark.arm_slow +@pytest.mark.parametrize("klass", [MultiIndex, np.array, Series, list]) +def test_union_base(idx, sort, klass): + first = idx[::-1] + second = idx[:5] + + if klass is not MultiIndex: + second = klass(second.values) + + union = first.union(second, sort=sort) + if sort is None: + expected = first.sort_values() + else: + expected = first + tm.assert_index_equal(union, expected) + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + first.union([1, 2, 3], sort=sort) + + +def test_difference_base(idx, sort): + second = idx[4:] + answer = idx[:4] + result = idx.difference(second, sort=sort) + + if sort is None: + answer = answer.sort_values() + + assert result.equals(answer) + tm.assert_index_equal(result, answer) + + # GH 10149 + cases = [klass(second.values) for klass in [np.array, Series, list]] + for case in cases: + result = idx.difference(case, sort=sort) + tm.assert_index_equal(result, answer) + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + idx.difference([1, 2, 3], sort=sort) + + +def test_symmetric_difference(idx, sort): + first = idx[1:] + second = idx[:-1] + answer = idx[[-1, 0]] + result = first.symmetric_difference(second, sort=sort) + + if sort is None: + answer = answer.sort_values() + + tm.assert_index_equal(result, answer) + + # GH 10149 + cases = [klass(second.values) for klass in [np.array, Series, list]] + for case in cases: + result = first.symmetric_difference(case, sort=sort) + tm.assert_index_equal(result, answer) + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + first.symmetric_difference([1, 2, 3], sort=sort) + + +def test_multiindex_symmetric_difference(): + # GH 13490 + idx = MultiIndex.from_product([["a", "b"], ["A", "B"]], names=["a", "b"]) + result = idx.symmetric_difference(idx) + assert result.names == idx.names + + idx2 = idx.copy().rename(["A", "B"]) + result = idx.symmetric_difference(idx2) + assert result.names == [None, None] + + +def test_empty(idx): + # GH 15270 + assert not idx.empty + assert idx[:0].empty + + +def test_difference(idx, sort): + first = idx + result = first.difference(idx[-3:], sort=sort) + vals = idx[:-3].values + + if sort is None: + vals = sorted(vals) + + expected = MultiIndex.from_tuples(vals, sortorder=0, names=idx.names) + + assert isinstance(result, MultiIndex) + assert result.equals(expected) + assert result.names == idx.names + tm.assert_index_equal(result, expected) + + # empty difference: reflexive + result = idx.difference(idx, sort=sort) + expected = idx[:0] + assert result.equals(expected) + assert result.names == idx.names + + # empty difference: superset + result = idx[-3:].difference(idx, sort=sort) + expected = idx[:0] + assert result.equals(expected) + assert result.names == idx.names + + # empty difference: degenerate + result = idx[:0].difference(idx, sort=sort) + expected = idx[:0] + assert result.equals(expected) + assert result.names == idx.names + + # names not the same + chunklet = idx[-3:] + chunklet.names = ["foo", "baz"] + result = first.difference(chunklet, sort=sort) + assert result.names == (None, None) + + # empty, but non-equal + result = idx.difference(idx.sortlevel(1)[0], sort=sort) + assert len(result) == 0 + + # raise Exception called with non-MultiIndex + result = first.difference(first.values, sort=sort) + assert result.equals(first[:0]) + + # name from empty array + result = first.difference([], sort=sort) + assert first.equals(result) + assert first.names == result.names + + # name from non-empty array + result = first.difference([("foo", "one")], sort=sort) + expected = MultiIndex.from_tuples( + [("bar", "one"), ("baz", "two"), ("foo", "two"), ("qux", "one"), ("qux", "two")] + ) + expected.names = first.names + assert first.names == result.names + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + first.difference([1, 2, 3, 4, 5], sort=sort) + + +def test_difference_sort_special(): + # GH-24959 + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + # sort=None, the default + result = idx.difference([]) + tm.assert_index_equal(result, idx) + + +def test_difference_sort_special_true(): + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + result = idx.difference([], sort=True) + expected = MultiIndex.from_product([[0, 1], ["a", "b"]]) + tm.assert_index_equal(result, expected) + + +def test_difference_sort_incomparable(): + # GH-24959 + idx = MultiIndex.from_product([[1, pd.Timestamp("2000"), 2], ["a", "b"]]) + + other = MultiIndex.from_product([[3, pd.Timestamp("2000"), 4], ["c", "d"]]) + # sort=None, the default + msg = "sort order is undefined for incomparable objects" + with tm.assert_produces_warning(RuntimeWarning, match=msg): + result = idx.difference(other) + tm.assert_index_equal(result, idx) + + # sort=False + result = idx.difference(other, sort=False) + tm.assert_index_equal(result, idx) + + +def test_difference_sort_incomparable_true(): + idx = MultiIndex.from_product([[1, pd.Timestamp("2000"), 2], ["a", "b"]]) + other = MultiIndex.from_product([[3, pd.Timestamp("2000"), 4], ["c", "d"]]) + + # TODO: this is raising in constructing a Categorical when calling + # algos.safe_sort. Should we catch and re-raise with a better message? + msg = "'values' is not ordered, please explicitly specify the categories order " + with pytest.raises(TypeError, match=msg): + idx.difference(other, sort=True) + + +def test_union(idx, sort): + piece1 = idx[:5][::-1] + piece2 = idx[3:] + + the_union = piece1.union(piece2, sort=sort) + + if sort in (None, False): + tm.assert_index_equal(the_union.sort_values(), idx.sort_values()) + else: + tm.assert_index_equal(the_union, idx) + + # corner case, pass self or empty thing: + the_union = idx.union(idx, sort=sort) + tm.assert_index_equal(the_union, idx) + + the_union = idx.union(idx[:0], sort=sort) + tm.assert_index_equal(the_union, idx) + + tuples = idx.values + result = idx[:4].union(tuples[4:], sort=sort) + if sort is None: + tm.assert_index_equal(result.sort_values(), idx.sort_values()) + else: + assert result.equals(idx) + + +def test_union_with_regular_index(idx, using_infer_string): + other = Index(["A", "B", "C"]) + + result = other.union(idx) + assert ("foo", "one") in result + assert "B" in result + + if using_infer_string: + with pytest.raises(NotImplementedError, match="Can only union"): + idx.union(other) + else: + msg = "The values in the array are unorderable" + with tm.assert_produces_warning(RuntimeWarning, match=msg): + result2 = idx.union(other) + # This is more consistent now, if sorting fails then we don't sort at all + # in the MultiIndex case. + assert not result.equals(result2) + + +def test_intersection(idx, sort): + piece1 = idx[:5][::-1] + piece2 = idx[3:] + + the_int = piece1.intersection(piece2, sort=sort) + + if sort in (None, True): + tm.assert_index_equal(the_int, idx[3:5]) + else: + tm.assert_index_equal(the_int.sort_values(), idx[3:5]) + + # corner case, pass self + the_int = idx.intersection(idx, sort=sort) + tm.assert_index_equal(the_int, idx) + + # empty intersection: disjoint + empty = idx[:2].intersection(idx[2:], sort=sort) + expected = idx[:0] + assert empty.equals(expected) + + tuples = idx.values + result = idx.intersection(tuples) + assert result.equals(idx) + + +@pytest.mark.parametrize( + "method", ["intersection", "union", "difference", "symmetric_difference"] +) +def test_setop_with_categorical(idx, sort, method): + other = idx.to_flat_index().astype("category") + res_names = [None] * idx.nlevels + + result = getattr(idx, method)(other, sort=sort) + expected = getattr(idx, method)(idx, sort=sort).rename(res_names) + tm.assert_index_equal(result, expected) + + result = getattr(idx, method)(other[:5], sort=sort) + expected = getattr(idx, method)(idx[:5], sort=sort).rename(res_names) + tm.assert_index_equal(result, expected) + + +def test_intersection_non_object(idx, sort): + other = Index(range(3), name="foo") + + result = idx.intersection(other, sort=sort) + expected = MultiIndex(levels=idx.levels, codes=[[]] * idx.nlevels, names=None) + tm.assert_index_equal(result, expected, exact=True) + + # if we pass a length-0 ndarray (i.e. no name, we retain our idx.name) + result = idx.intersection(np.asarray(other)[:0], sort=sort) + expected = MultiIndex(levels=idx.levels, codes=[[]] * idx.nlevels, names=idx.names) + tm.assert_index_equal(result, expected, exact=True) + + msg = "other must be a MultiIndex or a list of tuples" + with pytest.raises(TypeError, match=msg): + # With non-zero length non-index, we try and fail to convert to tuples + idx.intersection(np.asarray(other), sort=sort) + + +def test_intersect_equal_sort(): + # GH-24959 + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + tm.assert_index_equal(idx.intersection(idx, sort=False), idx) + tm.assert_index_equal(idx.intersection(idx, sort=None), idx) + + +def test_intersect_equal_sort_true(): + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + expected = MultiIndex.from_product([[0, 1], ["a", "b"]]) + result = idx.intersection(idx, sort=True) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("slice_", [slice(None), slice(0)]) +def test_union_sort_other_empty(slice_): + # https://github.com/pandas-dev/pandas/issues/24959 + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + + # default, sort=None + other = idx[slice_] + tm.assert_index_equal(idx.union(other), idx) + tm.assert_index_equal(other.union(idx), idx) + + # sort=False + tm.assert_index_equal(idx.union(other, sort=False), idx) + + +def test_union_sort_other_empty_sort(): + idx = MultiIndex.from_product([[1, 0], ["a", "b"]]) + other = idx[:0] + result = idx.union(other, sort=True) + expected = MultiIndex.from_product([[0, 1], ["a", "b"]]) + tm.assert_index_equal(result, expected) + + +def test_union_sort_other_incomparable(): + # https://github.com/pandas-dev/pandas/issues/24959 + idx = MultiIndex.from_product([[1, pd.Timestamp("2000")], ["a", "b"]]) + + # default, sort=None + with tm.assert_produces_warning(RuntimeWarning): + result = idx.union(idx[:1]) + tm.assert_index_equal(result, idx) + + # sort=False + result = idx.union(idx[:1], sort=False) + tm.assert_index_equal(result, idx) + + +def test_union_sort_other_incomparable_sort(): + idx = MultiIndex.from_product([[1, pd.Timestamp("2000")], ["a", "b"]]) + msg = "'<' not supported between instances of 'Timestamp' and 'int'" + with pytest.raises(TypeError, match=msg): + idx.union(idx[:1], sort=True) + + +def test_union_non_object_dtype_raises(): + # GH#32646 raise NotImplementedError instead of less-informative error + mi = MultiIndex.from_product([["a", "b"], [1, 2]]) + + idx = mi.levels[1] + + msg = "Can only union MultiIndex with MultiIndex or Index of tuples" + with pytest.raises(NotImplementedError, match=msg): + mi.union(idx) + + +def test_union_empty_self_different_names(): + # GH#38423 + mi = MultiIndex.from_arrays([[]]) + mi2 = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["a", "b"]) + result = mi.union(mi2) + expected = MultiIndex.from_arrays([[1, 2], [3, 4]]) + tm.assert_index_equal(result, expected) + + +def test_union_multiindex_empty_rangeindex(): + # GH#41234 + mi = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["a", "b"]) + ri = pd.RangeIndex(0) + + result_left = mi.union(ri) + tm.assert_index_equal(mi, result_left, check_names=False) + + result_right = ri.union(mi) + tm.assert_index_equal(mi, result_right, check_names=False) + + +@pytest.mark.parametrize( + "method", ["union", "intersection", "difference", "symmetric_difference"] +) +def test_setops_sort_validation(method): + idx1 = MultiIndex.from_product([["a", "b"], [1, 2]]) + idx2 = MultiIndex.from_product([["b", "c"], [1, 2]]) + + with pytest.raises(ValueError, match="The 'sort' keyword only takes"): + getattr(idx1, method)(idx2, sort=2) + + # sort=True is supported as of GH#? + getattr(idx1, method)(idx2, sort=True) + + +@pytest.mark.parametrize("val", [pd.NA, 100]) +def test_difference_keep_ea_dtypes(any_numeric_ea_dtype, val): + # GH#48606 + midx = MultiIndex.from_arrays( + [Series([1, 2], dtype=any_numeric_ea_dtype), [2, 1]], names=["a", None] + ) + midx2 = MultiIndex.from_arrays( + [Series([1, 2, val], dtype=any_numeric_ea_dtype), [1, 1, 3]] + ) + result = midx.difference(midx2) + expected = MultiIndex.from_arrays([Series([1], dtype=any_numeric_ea_dtype), [2]]) + tm.assert_index_equal(result, expected) + + result = midx.difference(midx.sort_values(ascending=False)) + expected = MultiIndex.from_arrays( + [Series([], dtype=any_numeric_ea_dtype), Series([], dtype=np.int64)], + names=["a", None], + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("val", [pd.NA, 5]) +def test_symmetric_difference_keeping_ea_dtype(any_numeric_ea_dtype, val): + # GH#48607 + midx = MultiIndex.from_arrays( + [Series([1, 2], dtype=any_numeric_ea_dtype), [2, 1]], names=["a", None] + ) + midx2 = MultiIndex.from_arrays( + [Series([1, 2, val], dtype=any_numeric_ea_dtype), [1, 1, 3]] + ) + result = midx.symmetric_difference(midx2) + expected = MultiIndex.from_arrays( + [Series([1, 1, val], dtype=any_numeric_ea_dtype), [1, 2, 3]] + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + ("tuples", "exp_tuples"), + [ + ([("val1", "test1")], [("val1", "test1")]), + ([("val1", "test1"), ("val1", "test1")], [("val1", "test1")]), + ( + [("val2", "test2"), ("val1", "test1")], + [("val2", "test2"), ("val1", "test1")], + ), + ], +) +def test_intersect_with_duplicates(tuples, exp_tuples): + # GH#36915 + left = MultiIndex.from_tuples(tuples, names=["first", "second"]) + right = MultiIndex.from_tuples( + [("val1", "test1"), ("val1", "test1"), ("val2", "test2")], + names=["first", "second"], + ) + result = left.intersection(right) + expected = MultiIndex.from_tuples(exp_tuples, names=["first", "second"]) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + "data, names, expected", + [ + ((1,), None, [None, None]), + ((1,), ["a"], [None, None]), + ((1,), ["b"], [None, None]), + ((1, 2), ["c", "d"], [None, None]), + ((1, 2), ["b", "a"], [None, None]), + ((1, 2, 3), ["a", "b", "c"], [None, None]), + ((1, 2), ["a", "c"], ["a", None]), + ((1, 2), ["c", "b"], [None, "b"]), + ((1, 2), ["a", "b"], ["a", "b"]), + ((1, 2), [None, "b"], [None, "b"]), + ], +) +def test_maybe_match_names(data, names, expected): + # GH#38323 + mi = MultiIndex.from_tuples([], names=["a", "b"]) + mi2 = MultiIndex.from_tuples([data], names=names) + result = mi._maybe_match_names(mi2) + assert result == expected + + +def test_intersection_equal_different_names(): + # GH#30302 + mi1 = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["c", "b"]) + mi2 = MultiIndex.from_arrays([[1, 2], [3, 4]], names=["a", "b"]) + + result = mi1.intersection(mi2) + expected = MultiIndex.from_arrays([[1, 2], [3, 4]], names=[None, "b"]) + tm.assert_index_equal(result, expected) + + +def test_intersection_different_names(): + # GH#38323 + mi = MultiIndex.from_arrays([[1], [3]], names=["c", "b"]) + mi2 = MultiIndex.from_arrays([[1], [3]]) + result = mi.intersection(mi2) + tm.assert_index_equal(result, mi2) + + +def test_intersection_with_missing_values_on_both_sides(nulls_fixture): + # GH#38623 + mi1 = MultiIndex.from_arrays([[3, nulls_fixture, 4, nulls_fixture], [1, 2, 4, 2]]) + mi2 = MultiIndex.from_arrays([[3, nulls_fixture, 3], [1, 2, 4]]) + result = mi1.intersection(mi2) + expected = MultiIndex.from_arrays([[3, nulls_fixture], [1, 2]]) + tm.assert_index_equal(result, expected) + + +def test_union_with_missing_values_on_both_sides(nulls_fixture): + # GH#38623 + mi1 = MultiIndex.from_arrays([[1, nulls_fixture]]) + mi2 = MultiIndex.from_arrays([[1, nulls_fixture, 3]]) + result = mi1.union(mi2) + expected = MultiIndex.from_arrays([[1, 3, nulls_fixture]]) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("dtype", ["float64", "Float64"]) +@pytest.mark.parametrize("sort", [None, False]) +def test_union_nan_got_duplicated(dtype, sort): + # GH#38977, GH#49010 + mi1 = MultiIndex.from_arrays([pd.array([1.0, np.nan], dtype=dtype), [2, 3]]) + mi2 = MultiIndex.from_arrays([pd.array([1.0, np.nan, 3.0], dtype=dtype), [2, 3, 4]]) + result = mi1.union(mi2, sort=sort) + if sort is None: + expected = MultiIndex.from_arrays( + [pd.array([1.0, 3.0, np.nan], dtype=dtype), [2, 4, 3]] + ) + else: + expected = mi2 + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("val", [4, 1]) +def test_union_keep_ea_dtype(any_numeric_ea_dtype, val): + # GH#48505 + + arr1 = Series([val, 2], dtype=any_numeric_ea_dtype) + arr2 = Series([2, 1], dtype=any_numeric_ea_dtype) + midx = MultiIndex.from_arrays([arr1, [1, 2]], names=["a", None]) + midx2 = MultiIndex.from_arrays([arr2, [2, 1]]) + result = midx.union(midx2) + if val == 4: + expected = MultiIndex.from_arrays( + [Series([1, 2, 4], dtype=any_numeric_ea_dtype), [1, 2, 1]] + ) + else: + expected = MultiIndex.from_arrays( + [Series([1, 2], dtype=any_numeric_ea_dtype), [1, 2]] + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("dupe_val", [3, pd.NA]) +def test_union_with_duplicates_keep_ea_dtype(dupe_val, any_numeric_ea_dtype): + # GH48900 + mi1 = MultiIndex.from_arrays( + [ + Series([1, dupe_val, 2], dtype=any_numeric_ea_dtype), + Series([1, dupe_val, 2], dtype=any_numeric_ea_dtype), + ] + ) + mi2 = MultiIndex.from_arrays( + [ + Series([2, dupe_val, dupe_val], dtype=any_numeric_ea_dtype), + Series([2, dupe_val, dupe_val], dtype=any_numeric_ea_dtype), + ] + ) + result = mi1.union(mi2) + expected = MultiIndex.from_arrays( + [ + Series([1, 2, dupe_val, dupe_val], dtype=any_numeric_ea_dtype), + Series([1, 2, dupe_val, dupe_val], dtype=any_numeric_ea_dtype), + ] + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") +def test_union_duplicates(index, request): + # GH#38977 + if index.empty or isinstance(index, (IntervalIndex, CategoricalIndex)): + pytest.skip(f"No duplicates in an empty {type(index).__name__}") + + values = index.unique().values.tolist() + mi1 = MultiIndex.from_arrays([values, [1] * len(values)]) + mi2 = MultiIndex.from_arrays([[values[0]] + values, [1] * (len(values) + 1)]) + result = mi2.union(mi1) + expected = mi2.sort_values() + tm.assert_index_equal(result, expected) + + if ( + is_unsigned_integer_dtype(mi2.levels[0]) + and (mi2.get_level_values(0) < 2**63).all() + ): + # GH#47294 - union uses lib.fast_zip, converting data to Python integers + # and loses type information. Result is then unsigned only when values are + # sufficiently large to require unsigned dtype. This happens only if other + # has dups or one of both have missing values + expected = expected.set_levels( + [expected.levels[0].astype(np.int64), expected.levels[1]] + ) + elif is_float_dtype(mi2.levels[0]): + # mi2 has duplicates witch is a different path than above, Fix that path + # to use correct float dtype? + expected = expected.set_levels( + [expected.levels[0].astype(float), expected.levels[1]] + ) + + result = mi1.union(mi2) + tm.assert_index_equal(result, expected) + + +def test_union_keep_dtype_precision(any_real_numeric_dtype): + # GH#48498 + arr1 = Series([4, 1, 1], dtype=any_real_numeric_dtype) + arr2 = Series([1, 4], dtype=any_real_numeric_dtype) + midx = MultiIndex.from_arrays([arr1, [2, 1, 1]], names=["a", None]) + midx2 = MultiIndex.from_arrays([arr2, [1, 2]], names=["a", None]) + + result = midx.union(midx2) + expected = MultiIndex.from_arrays( + ([Series([1, 1, 4], dtype=any_real_numeric_dtype), [1, 1, 2]]), + names=["a", None], + ) + tm.assert_index_equal(result, expected) + + +def test_union_keep_ea_dtype_with_na(any_numeric_ea_dtype): + # GH#48498 + arr1 = Series([4, pd.NA], dtype=any_numeric_ea_dtype) + arr2 = Series([1, pd.NA], dtype=any_numeric_ea_dtype) + midx = MultiIndex.from_arrays([arr1, [2, 1]], names=["a", None]) + midx2 = MultiIndex.from_arrays([arr2, [1, 2]]) + result = midx.union(midx2) + expected = MultiIndex.from_arrays( + [Series([1, 4, pd.NA, pd.NA], dtype=any_numeric_ea_dtype), [1, 2, 1, 2]] + ) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize( + "levels1, levels2, codes1, codes2, names", + [ + ( + [["a", "b", "c"], [0, ""]], + [["c", "d", "b"], [""]], + [[0, 1, 2], [1, 1, 1]], + [[0, 1, 2], [0, 0, 0]], + ["name1", "name2"], + ), + ], +) +def test_intersection_lexsort_depth(levels1, levels2, codes1, codes2, names): + # GH#25169 + mi1 = MultiIndex(levels=levels1, codes=codes1, names=names) + mi2 = MultiIndex(levels=levels2, codes=codes2, names=names) + mi_int = mi1.intersection(mi2) + assert mi_int._lexsort_depth == 2 + + +@pytest.mark.parametrize( + "a", + [pd.Categorical(["a", "b"], categories=["a", "b"]), ["a", "b"]], +) +@pytest.mark.parametrize( + "b", + [ + pd.Categorical(["a", "b"], categories=["b", "a"], ordered=True), + pd.Categorical(["a", "b"], categories=["b", "a"]), + ], +) +def test_intersection_with_non_lex_sorted_categories(a, b): + # GH#49974 + other = ["1", "2"] + + df1 = DataFrame({"x": a, "y": other}) + df2 = DataFrame({"x": b, "y": other}) + + expected = MultiIndex.from_arrays([a, other], names=["x", "y"]) + + res1 = MultiIndex.from_frame(df1).intersection( + MultiIndex.from_frame(df2.sort_values(["x", "y"])) + ) + res2 = MultiIndex.from_frame(df1).intersection(MultiIndex.from_frame(df2)) + res3 = MultiIndex.from_frame(df1.sort_values(["x", "y"])).intersection( + MultiIndex.from_frame(df2) + ) + res4 = MultiIndex.from_frame(df1.sort_values(["x", "y"])).intersection( + MultiIndex.from_frame(df2.sort_values(["x", "y"])) + ) + + tm.assert_index_equal(res1, expected) + tm.assert_index_equal(res2, expected) + tm.assert_index_equal(res3, expected) + tm.assert_index_equal(res4, expected) + + +@pytest.mark.parametrize("val", [pd.NA, 100]) +def test_intersection_keep_ea_dtypes(val, any_numeric_ea_dtype): + # GH#48604 + midx = MultiIndex.from_arrays( + [Series([1, 2], dtype=any_numeric_ea_dtype), [2, 1]], names=["a", None] + ) + midx2 = MultiIndex.from_arrays( + [Series([1, 2, val], dtype=any_numeric_ea_dtype), [1, 1, 3]] + ) + result = midx.intersection(midx2) + expected = MultiIndex.from_arrays([Series([2], dtype=any_numeric_ea_dtype), [1]]) + tm.assert_index_equal(result, expected) + + +def test_union_with_na_when_constructing_dataframe(): + # GH43222 + series1 = Series( + (1,), + index=MultiIndex.from_arrays( + [Series([None], dtype="string"), Series([None], dtype="string")] + ), + ) + series2 = Series((10, 20), index=MultiIndex.from_tuples(((None, None), ("a", "b")))) + result = DataFrame([series1, series2]) + expected = DataFrame({(np.nan, np.nan): [1.0, 10.0], ("a", "b"): [np.nan, 20.0]}) + tm.assert_frame_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_sorting.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_sorting.py new file mode 100644 index 0000000000000000000000000000000000000000..b4dcef71dcf50724c90599b03d1c1c5aa99b7916 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_sorting.py @@ -0,0 +1,349 @@ +import numpy as np +import pytest + +from pandas.errors import ( + PerformanceWarning, + UnsortedIndexError, +) + +from pandas import ( + CategoricalIndex, + DataFrame, + Index, + MultiIndex, + RangeIndex, + Series, + Timestamp, +) +import pandas._testing as tm +from pandas.core.indexes.frozen import FrozenList + + +def test_sortlevel(idx): + tuples = list(idx) + np.random.default_rng(2).shuffle(tuples) + + index = MultiIndex.from_tuples(tuples) + + sorted_idx, _ = index.sortlevel(0) + expected = MultiIndex.from_tuples(sorted(tuples)) + assert sorted_idx.equals(expected) + + sorted_idx, _ = index.sortlevel(0, ascending=False) + assert sorted_idx.equals(expected[::-1]) + + sorted_idx, _ = index.sortlevel(1) + by1 = sorted(tuples, key=lambda x: (x[1], x[0])) + expected = MultiIndex.from_tuples(by1) + assert sorted_idx.equals(expected) + + sorted_idx, _ = index.sortlevel(1, ascending=False) + assert sorted_idx.equals(expected[::-1]) + + +def test_sortlevel_not_sort_remaining(): + mi = MultiIndex.from_tuples([[1, 1, 3], [1, 1, 1]], names=list("ABC")) + sorted_idx, _ = mi.sortlevel("A", sort_remaining=False) + assert sorted_idx.equals(mi) + + +def test_sortlevel_deterministic(): + tuples = [ + ("bar", "one"), + ("foo", "two"), + ("qux", "two"), + ("foo", "one"), + ("baz", "two"), + ("qux", "one"), + ] + + index = MultiIndex.from_tuples(tuples) + + sorted_idx, _ = index.sortlevel(0) + expected = MultiIndex.from_tuples(sorted(tuples)) + assert sorted_idx.equals(expected) + + sorted_idx, _ = index.sortlevel(0, ascending=False) + assert sorted_idx.equals(expected[::-1]) + + sorted_idx, _ = index.sortlevel(1) + by1 = sorted(tuples, key=lambda x: (x[1], x[0])) + expected = MultiIndex.from_tuples(by1) + assert sorted_idx.equals(expected) + + sorted_idx, _ = index.sortlevel(1, ascending=False) + assert sorted_idx.equals(expected[::-1]) + + +def test_sortlevel_na_position(): + # GH#51612 + midx = MultiIndex.from_tuples([(1, np.nan), (1, 1)]) + result = midx.sortlevel(level=[0, 1], na_position="last")[0] + expected = MultiIndex.from_tuples([(1, 1), (1, np.nan)]) + tm.assert_index_equal(result, expected) + + +def test_numpy_argsort(idx): + result = np.argsort(idx) + expected = idx.argsort() + tm.assert_numpy_array_equal(result, expected) + + # these are the only two types that perform + # pandas compatibility input validation - the + # rest already perform separate (or no) such + # validation via their 'values' attribute as + # defined in pandas.core.indexes/base.py - they + # cannot be changed at the moment due to + # backwards compatibility concerns + if isinstance(type(idx), (CategoricalIndex, RangeIndex)): + msg = "the 'axis' parameter is not supported" + with pytest.raises(ValueError, match=msg): + np.argsort(idx, axis=1) + + msg = "the 'kind' parameter is not supported" + with pytest.raises(ValueError, match=msg): + np.argsort(idx, kind="mergesort") + + msg = "the 'order' parameter is not supported" + with pytest.raises(ValueError, match=msg): + np.argsort(idx, order=("a", "b")) + + +def test_unsortedindex(): + # GH 11897 + mi = MultiIndex.from_tuples( + [("z", "a"), ("x", "a"), ("y", "b"), ("x", "b"), ("y", "a"), ("z", "b")], + names=["one", "two"], + ) + df = DataFrame([[i, 10 * i] for i in range(6)], index=mi, columns=["one", "two"]) + + # GH 16734: not sorted, but no real slicing + result = df.loc(axis=0)["z", "a"] + expected = df.iloc[0] + tm.assert_series_equal(result, expected) + + msg = ( + "MultiIndex slicing requires the index to be lexsorted: " + r"slicing on levels \[1\], lexsort depth 0" + ) + with pytest.raises(UnsortedIndexError, match=msg): + df.loc(axis=0)["z", slice("a")] + df.sort_index(inplace=True) + assert len(df.loc(axis=0)["z", :]) == 2 + + with pytest.raises(KeyError, match="'q'"): + df.loc(axis=0)["q", :] + + +def test_unsortedindex_doc_examples(): + # https://pandas.pydata.org/pandas-docs/stable/advanced.html#sorting-a-multiindex + dfm = DataFrame( + { + "jim": [0, 0, 1, 1], + "joe": ["x", "x", "z", "y"], + "jolie": np.random.default_rng(2).random(4), + } + ) + + dfm = dfm.set_index(["jim", "joe"]) + with tm.assert_produces_warning(PerformanceWarning): + dfm.loc[(1, "z")] + + msg = r"Key length \(2\) was greater than MultiIndex lexsort depth \(1\)" + with pytest.raises(UnsortedIndexError, match=msg): + dfm.loc[(0, "y"):(1, "z")] + + assert not dfm.index._is_lexsorted() + assert dfm.index._lexsort_depth == 1 + + # sort it + dfm = dfm.sort_index() + dfm.loc[(1, "z")] + dfm.loc[(0, "y"):(1, "z")] + + assert dfm.index._is_lexsorted() + assert dfm.index._lexsort_depth == 2 + + +def test_reconstruct_sort(): + # starts off lexsorted & monotonic + mi = MultiIndex.from_arrays([["A", "A", "B", "B", "B"], [1, 2, 1, 2, 3]]) + assert mi.is_monotonic_increasing + recons = mi._sort_levels_monotonic() + assert recons.is_monotonic_increasing + assert mi is recons + + assert mi.equals(recons) + assert Index(mi.values).equals(Index(recons.values)) + + # cannot convert to lexsorted + mi = MultiIndex.from_tuples( + [("z", "a"), ("x", "a"), ("y", "b"), ("x", "b"), ("y", "a"), ("z", "b")], + names=["one", "two"], + ) + assert not mi.is_monotonic_increasing + recons = mi._sort_levels_monotonic() + assert not recons.is_monotonic_increasing + assert mi.equals(recons) + assert Index(mi.values).equals(Index(recons.values)) + + # cannot convert to lexsorted + mi = MultiIndex( + levels=[["b", "d", "a"], [1, 2, 3]], + codes=[[0, 1, 0, 2], [2, 0, 0, 1]], + names=["col1", "col2"], + ) + assert not mi.is_monotonic_increasing + recons = mi._sort_levels_monotonic() + assert not recons.is_monotonic_increasing + assert mi.equals(recons) + assert Index(mi.values).equals(Index(recons.values)) + + +def test_reconstruct_remove_unused(): + # xref to GH 2770 + df = DataFrame( + [["deleteMe", 1, 9], ["keepMe", 2, 9], ["keepMeToo", 3, 9]], + columns=["first", "second", "third"], + ) + df2 = df.set_index(["first", "second"], drop=False) + df2 = df2[df2["first"] != "deleteMe"] + + # removed levels are there + expected = MultiIndex( + levels=[["deleteMe", "keepMe", "keepMeToo"], [1, 2, 3]], + codes=[[1, 2], [1, 2]], + names=["first", "second"], + ) + result = df2.index + tm.assert_index_equal(result, expected) + + expected = MultiIndex( + levels=[["keepMe", "keepMeToo"], [2, 3]], + codes=[[0, 1], [0, 1]], + names=["first", "second"], + ) + result = df2.index.remove_unused_levels() + tm.assert_index_equal(result, expected) + + # idempotent + result2 = result.remove_unused_levels() + tm.assert_index_equal(result2, expected) + assert result2.is_(result) + + +@pytest.mark.parametrize( + "first_type,second_type", [("int64", "int64"), ("datetime64[D]", "str")] +) +def test_remove_unused_levels_large(first_type, second_type): + # GH16556 + + # because tests should be deterministic (and this test in particular + # checks that levels are removed, which is not the case for every + # random input): + rng = np.random.default_rng(10) # seed is arbitrary value that works + + size = 1 << 16 + df = DataFrame( + { + "first": rng.integers(0, 1 << 13, size).astype(first_type), + "second": rng.integers(0, 1 << 10, size).astype(second_type), + "third": rng.random(size), + } + ) + df = df.groupby(["first", "second"]).sum() + df = df[df.third < 0.1] + + result = df.index.remove_unused_levels() + assert len(result.levels[0]) < len(df.index.levels[0]) + assert len(result.levels[1]) < len(df.index.levels[1]) + assert result.equals(df.index) + + expected = df.reset_index().set_index(["first", "second"]).index + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("level0", [["a", "d", "b"], ["a", "d", "b", "unused"]]) +@pytest.mark.parametrize( + "level1", [["w", "x", "y", "z"], ["w", "x", "y", "z", "unused"]] +) +def test_remove_unused_nan(level0, level1): + # GH 18417 + mi = MultiIndex(levels=[level0, level1], codes=[[0, 2, -1, 1, -1], [0, 1, 2, 3, 2]]) + + result = mi.remove_unused_levels() + tm.assert_index_equal(result, mi) + for level in 0, 1: + assert "unused" not in result.levels[level] + + +def test_argsort(idx): + result = idx.argsort() + expected = idx.values.argsort() + tm.assert_numpy_array_equal(result, expected) + + +def test_remove_unused_levels_with_nan(): + # GH 37510 + idx = Index([(1, np.nan), (3, 4)]).rename(["id1", "id2"]) + idx = idx.set_levels(["a", np.nan], level="id1") + idx = idx.remove_unused_levels() + result = idx.levels + expected = FrozenList([["a", np.nan], [4]]) + assert str(result) == str(expected) + + +def test_sort_values_nan(): + # GH48495, GH48626 + midx = MultiIndex(levels=[["A", "B", "C"], ["D"]], codes=[[1, 0, 2], [-1, -1, 0]]) + result = midx.sort_values() + expected = MultiIndex( + levels=[["A", "B", "C"], ["D"]], codes=[[0, 1, 2], [-1, -1, 0]] + ) + tm.assert_index_equal(result, expected) + + +def test_sort_values_incomparable(): + # GH48495 + mi = MultiIndex.from_arrays( + [ + [1, Timestamp("2000-01-01")], + [3, 4], + ] + ) + match = "'<' not supported between instances of 'Timestamp' and 'int'" + with pytest.raises(TypeError, match=match): + mi.sort_values() + + +@pytest.mark.parametrize("na_position", ["first", "last"]) +@pytest.mark.parametrize("dtype", ["float64", "Int64", "Float64"]) +def test_sort_values_with_na_na_position(dtype, na_position): + # 51612 + arrays = [ + Series([1, 1, 2], dtype=dtype), + Series([1, None, 3], dtype=dtype), + ] + index = MultiIndex.from_arrays(arrays) + result = index.sort_values(na_position=na_position) + if na_position == "first": + arrays = [ + Series([1, 1, 2], dtype=dtype), + Series([None, 1, 3], dtype=dtype), + ] + else: + arrays = [ + Series([1, 1, 2], dtype=dtype), + Series([1, None, 3], dtype=dtype), + ] + expected = MultiIndex.from_arrays(arrays) + tm.assert_index_equal(result, expected) + + +def test_sort_unnecessary_warning(): + # GH#55386 + midx = MultiIndex.from_tuples([(1.5, 2), (3.5, 3), (0, 1)]) + midx = midx.set_levels([2.5, np.nan, 1], level=0) + result = midx.sort_values() + expected = MultiIndex.from_tuples([(1, 3), (2.5, 1), (np.nan, 2)]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_take.py b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_take.py new file mode 100644 index 0000000000000000000000000000000000000000..543cba25c373b71b8c79c7fe0ea5ae2fb7f40b18 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/multi/test_take.py @@ -0,0 +1,78 @@ +import numpy as np +import pytest + +import pandas as pd +import pandas._testing as tm + + +def test_take(idx): + indexer = [4, 3, 0, 2] + result = idx.take(indexer) + expected = idx[indexer] + assert result.equals(expected) + + # GH 10791 + msg = "'MultiIndex' object has no attribute 'freq'" + with pytest.raises(AttributeError, match=msg): + idx.freq + + +def test_take_invalid_kwargs(idx): + indices = [1, 2] + + msg = r"take\(\) got an unexpected keyword argument 'foo'" + with pytest.raises(TypeError, match=msg): + idx.take(indices, foo=2) + + msg = "the 'out' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, out=indices) + + msg = "the 'mode' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, mode="clip") + + +def test_take_fill_value(): + # GH 12631 + vals = [["A", "B"], [pd.Timestamp("2011-01-01"), pd.Timestamp("2011-01-02")]] + idx = pd.MultiIndex.from_product(vals, names=["str", "dt"]) + + result = idx.take(np.array([1, 0, -1])) + exp_vals = [ + ("A", pd.Timestamp("2011-01-02")), + ("A", pd.Timestamp("2011-01-01")), + ("B", pd.Timestamp("2011-01-02")), + ] + expected = pd.MultiIndex.from_tuples(exp_vals, names=["str", "dt"]) + tm.assert_index_equal(result, expected) + + # fill_value + result = idx.take(np.array([1, 0, -1]), fill_value=True) + exp_vals = [ + ("A", pd.Timestamp("2011-01-02")), + ("A", pd.Timestamp("2011-01-01")), + (np.nan, pd.NaT), + ] + expected = pd.MultiIndex.from_tuples(exp_vals, names=["str", "dt"]) + tm.assert_index_equal(result, expected) + + # allow_fill=False + result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True) + exp_vals = [ + ("A", pd.Timestamp("2011-01-02")), + ("A", pd.Timestamp("2011-01-01")), + ("B", pd.Timestamp("2011-01-02")), + ] + expected = pd.MultiIndex.from_tuples(exp_vals, names=["str", "dt"]) + tm.assert_index_equal(result, expected) + + msg = "When allow_fill=True and fill_value is not None, all indices must be >= -1" + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + msg = "index -5 is out of bounds for( axis 0 with)? size 4" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4f9e8e5dc32a406d53d0f796d067672551748000 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_astype.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_astype.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..767dcf30ba136f60123d761d601c0318e2b7d4e8 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_astype.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..114106b3949fa6135f3c8d02d04bd7776905a1d8 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..647f0d52d1a4a53936725bb461c12291da2c98be Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_numeric.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_numeric.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..04752edf9730f0e8b5953331c8ccbae616ef3597 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_numeric.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7585e8a16ed04fde6a9b9b57425ae109d7f4e5fe Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_astype.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_astype.py new file mode 100644 index 0000000000000000000000000000000000000000..1c2df6008de5d85789b026e947ac27a8036a9be7 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_astype.py @@ -0,0 +1,95 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + to_datetime, + to_timedelta, +) +import pandas._testing as tm + + +class TestAstype: + def test_astype_float64_to_uint64(self): + # GH#45309 used to incorrectly return Index with int64 dtype + idx = Index([0.0, 5.0, 10.0, 15.0, 20.0], dtype=np.float64) + result = idx.astype("u8") + expected = Index([0, 5, 10, 15, 20], dtype=np.uint64) + tm.assert_index_equal(result, expected, exact=True) + + idx_with_negatives = idx - 10 + with pytest.raises(ValueError, match="losslessly"): + idx_with_negatives.astype(np.uint64) + + def test_astype_float64_to_object(self): + float_index = Index([0.0, 2.5, 5.0, 7.5, 10.0], dtype=np.float64) + result = float_index.astype(object) + assert result.equals(float_index) + assert float_index.equals(result) + assert isinstance(result, Index) and result.dtype == object + + def test_astype_float64_mixed_to_object(self): + # mixed int-float + idx = Index([1.5, 2, 3, 4, 5], dtype=np.float64) + idx.name = "foo" + result = idx.astype(object) + assert result.equals(idx) + assert idx.equals(result) + assert isinstance(result, Index) and result.dtype == object + + @pytest.mark.parametrize("dtype", ["int16", "int32", "int64"]) + def test_astype_float64_to_int_dtype(self, dtype): + # GH#12881 + # a float astype int + idx = Index([0, 1, 2], dtype=np.float64) + result = idx.astype(dtype) + expected = Index([0, 1, 2], dtype=dtype) + tm.assert_index_equal(result, expected, exact=True) + + idx = Index([0, 1.1, 2], dtype=np.float64) + result = idx.astype(dtype) + expected = Index([0, 1, 2], dtype=dtype) + tm.assert_index_equal(result, expected, exact=True) + + @pytest.mark.parametrize("dtype", ["float32", "float64"]) + def test_astype_float64_to_float_dtype(self, dtype): + # GH#12881 + # a float astype int + idx = Index([0, 1, 2], dtype=np.float64) + result = idx.astype(dtype) + assert isinstance(result, Index) and result.dtype == dtype + + @pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"]) + def test_astype_float_to_datetimelike(self, dtype): + # GH#49660 pre-2.0 Index.astype from floating to M8/m8/Period raised, + # inconsistent with Series.astype + idx = Index([0, 1.1, 2], dtype=np.float64) + + result = idx.astype(dtype) + if dtype[0] == "M": + expected = to_datetime(idx.values) + else: + expected = to_timedelta(idx.values) + tm.assert_index_equal(result, expected) + + # check that we match Series behavior + result = idx.to_series().set_axis(range(3)).astype(dtype) + expected = expected.to_series().set_axis(range(3)) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize("dtype", [int, "int16", "int32", "int64"]) + @pytest.mark.parametrize("non_finite", [np.inf, np.nan]) + def test_cannot_cast_inf_to_int(self, non_finite, dtype): + # GH#13149 + idx = Index([1, 2, non_finite], dtype=np.float64) + + msg = r"Cannot convert non-finite values \(NA or inf\) to integer" + with pytest.raises(ValueError, match=msg): + idx.astype(dtype) + + def test_astype_from_object(self): + index = Index([1.0, np.nan, 0.2], dtype="object") + result = index.astype(float) + expected = Index([1.0, np.nan, 0.2], dtype=np.float64) + assert result.dtype == expected.dtype + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..cd28d519313ed36228040361dfbb2a8dccf77be5 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_indexing.py @@ -0,0 +1,611 @@ +import numpy as np +import pytest + +from pandas.errors import InvalidIndexError + +from pandas import ( + NA, + Index, + RangeIndex, + Series, + Timestamp, +) +import pandas._testing as tm +from pandas.core.arrays import ( + ArrowExtensionArray, + FloatingArray, +) + + +@pytest.fixture +def index_large(): + # large values used in Index[uint64] tests where no compat needed with Int64/Float64 + large = [2**63, 2**63 + 10, 2**63 + 15, 2**63 + 20, 2**63 + 25] + return Index(large, dtype=np.uint64) + + +class TestGetLoc: + def test_get_loc(self): + index = Index([0, 1, 2]) + assert index.get_loc(1) == 1 + + def test_get_loc_raises_bad_label(self): + index = Index([0, 1, 2]) + with pytest.raises(InvalidIndexError, match=r"\[1, 2\]"): + index.get_loc([1, 2]) + + def test_get_loc_float64(self): + idx = Index([0.0, 1.0, 2.0], dtype=np.float64) + + with pytest.raises(KeyError, match="^'foo'$"): + idx.get_loc("foo") + with pytest.raises(KeyError, match=r"^1\.5$"): + idx.get_loc(1.5) + with pytest.raises(KeyError, match="^True$"): + idx.get_loc(True) + with pytest.raises(KeyError, match="^False$"): + idx.get_loc(False) + + def test_get_loc_na(self): + idx = Index([np.nan, 1, 2], dtype=np.float64) + assert idx.get_loc(1) == 1 + assert idx.get_loc(np.nan) == 0 + + idx = Index([np.nan, 1, np.nan], dtype=np.float64) + assert idx.get_loc(1) == 1 + + # representable by slice [0:2:2] + msg = "'Cannot get left slice bound for non-unique label: nan'" + with pytest.raises(KeyError, match=msg): + idx.slice_locs(np.nan) + # not representable by slice + idx = Index([np.nan, 1, np.nan, np.nan], dtype=np.float64) + assert idx.get_loc(1) == 1 + msg = "'Cannot get left slice bound for non-unique label: nan" + with pytest.raises(KeyError, match=msg): + idx.slice_locs(np.nan) + + def test_get_loc_missing_nan(self): + # GH#8569 + idx = Index([1, 2], dtype=np.float64) + assert idx.get_loc(1) == 0 + with pytest.raises(KeyError, match=r"^3$"): + idx.get_loc(3) + with pytest.raises(KeyError, match="^nan$"): + idx.get_loc(np.nan) + with pytest.raises(InvalidIndexError, match=r"\[nan\]"): + # listlike/non-hashable raises TypeError + idx.get_loc([np.nan]) + + @pytest.mark.parametrize("vals", [[1], [1.0], [Timestamp("2019-12-31")], ["test"]]) + def test_get_loc_float_index_nan_with_method(self, vals): + # GH#39382 + idx = Index(vals) + with pytest.raises(KeyError, match="nan"): + idx.get_loc(np.nan) + + @pytest.mark.parametrize("dtype", ["f8", "i8", "u8"]) + def test_get_loc_numericindex_none_raises(self, dtype): + # case that goes through searchsorted and key is non-comparable to values + arr = np.arange(10**7, dtype=dtype) + idx = Index(arr) + with pytest.raises(KeyError, match="None"): + idx.get_loc(None) + + def test_get_loc_overflows(self): + # unique but non-monotonic goes through IndexEngine.mapping.get_item + idx = Index([0, 2, 1]) + + val = np.iinfo(np.int64).max + 1 + + with pytest.raises(KeyError, match=str(val)): + idx.get_loc(val) + with pytest.raises(KeyError, match=str(val)): + idx._engine.get_loc(val) + + +class TestGetIndexer: + def test_get_indexer(self): + index1 = Index([1, 2, 3, 4, 5]) + index2 = Index([2, 4, 6]) + + r1 = index1.get_indexer(index2) + e1 = np.array([1, 3, -1], dtype=np.intp) + tm.assert_almost_equal(r1, e1) + + @pytest.mark.parametrize("reverse", [True, False]) + @pytest.mark.parametrize( + "expected,method", + [ + (np.array([-1, 0, 0, 1, 1], dtype=np.intp), "pad"), + (np.array([-1, 0, 0, 1, 1], dtype=np.intp), "ffill"), + (np.array([0, 0, 1, 1, 2], dtype=np.intp), "backfill"), + (np.array([0, 0, 1, 1, 2], dtype=np.intp), "bfill"), + ], + ) + def test_get_indexer_methods(self, reverse, expected, method): + index1 = Index([1, 2, 3, 4, 5]) + index2 = Index([2, 4, 6]) + + if reverse: + index1 = index1[::-1] + expected = expected[::-1] + + result = index2.get_indexer(index1, method=method) + tm.assert_almost_equal(result, expected) + + def test_get_indexer_invalid(self): + # GH10411 + index = Index(np.arange(10)) + + with pytest.raises(ValueError, match="tolerance argument"): + index.get_indexer([1, 0], tolerance=1) + + with pytest.raises(ValueError, match="limit argument"): + index.get_indexer([1, 0], limit=1) + + @pytest.mark.parametrize( + "method, tolerance, indexer, expected", + [ + ("pad", None, [0, 5, 9], [0, 5, 9]), + ("backfill", None, [0, 5, 9], [0, 5, 9]), + ("nearest", None, [0, 5, 9], [0, 5, 9]), + ("pad", 0, [0, 5, 9], [0, 5, 9]), + ("backfill", 0, [0, 5, 9], [0, 5, 9]), + ("nearest", 0, [0, 5, 9], [0, 5, 9]), + ("pad", None, [0.2, 1.8, 8.5], [0, 1, 8]), + ("backfill", None, [0.2, 1.8, 8.5], [1, 2, 9]), + ("nearest", None, [0.2, 1.8, 8.5], [0, 2, 9]), + ("pad", 1, [0.2, 1.8, 8.5], [0, 1, 8]), + ("backfill", 1, [0.2, 1.8, 8.5], [1, 2, 9]), + ("nearest", 1, [0.2, 1.8, 8.5], [0, 2, 9]), + ("pad", 0.2, [0.2, 1.8, 8.5], [0, -1, -1]), + ("backfill", 0.2, [0.2, 1.8, 8.5], [-1, 2, -1]), + ("nearest", 0.2, [0.2, 1.8, 8.5], [0, 2, -1]), + ], + ) + def test_get_indexer_nearest(self, method, tolerance, indexer, expected): + index = Index(np.arange(10)) + + actual = index.get_indexer(indexer, method=method, tolerance=tolerance) + tm.assert_numpy_array_equal(actual, np.array(expected, dtype=np.intp)) + + @pytest.mark.parametrize("listtype", [list, tuple, Series, np.array]) + @pytest.mark.parametrize( + "tolerance, expected", + list( + zip( + [[0.3, 0.3, 0.1], [0.2, 0.1, 0.1], [0.1, 0.5, 0.5]], + [[0, 2, -1], [0, -1, -1], [-1, 2, 9]], + ) + ), + ) + def test_get_indexer_nearest_listlike_tolerance( + self, tolerance, expected, listtype + ): + index = Index(np.arange(10)) + + actual = index.get_indexer( + [0.2, 1.8, 8.5], method="nearest", tolerance=listtype(tolerance) + ) + tm.assert_numpy_array_equal(actual, np.array(expected, dtype=np.intp)) + + def test_get_indexer_nearest_error(self): + index = Index(np.arange(10)) + with pytest.raises(ValueError, match="limit argument"): + index.get_indexer([1, 0], method="nearest", limit=1) + + with pytest.raises(ValueError, match="tolerance size must match"): + index.get_indexer([1, 0], method="nearest", tolerance=[1, 2, 3]) + + @pytest.mark.parametrize( + "method,expected", + [("pad", [8, 7, 0]), ("backfill", [9, 8, 1]), ("nearest", [9, 7, 0])], + ) + def test_get_indexer_nearest_decreasing(self, method, expected): + index = Index(np.arange(10))[::-1] + + actual = index.get_indexer([0, 5, 9], method=method) + tm.assert_numpy_array_equal(actual, np.array([9, 4, 0], dtype=np.intp)) + + actual = index.get_indexer([0.2, 1.8, 8.5], method=method) + tm.assert_numpy_array_equal(actual, np.array(expected, dtype=np.intp)) + + @pytest.mark.parametrize("idx_dtype", ["int64", "float64", "uint64", "range"]) + @pytest.mark.parametrize("method", ["get_indexer", "get_indexer_non_unique"]) + def test_get_indexer_numeric_index_boolean_target(self, method, idx_dtype): + # GH 16877 + + if idx_dtype == "range": + numeric_index = RangeIndex(4) + else: + numeric_index = Index(np.arange(4, dtype=idx_dtype)) + + other = Index([True, False, True]) + + result = getattr(numeric_index, method)(other) + expected = np.array([-1, -1, -1], dtype=np.intp) + if method == "get_indexer": + tm.assert_numpy_array_equal(result, expected) + else: + missing = np.arange(3, dtype=np.intp) + tm.assert_numpy_array_equal(result[0], expected) + tm.assert_numpy_array_equal(result[1], missing) + + @pytest.mark.parametrize("method", ["pad", "backfill", "nearest"]) + def test_get_indexer_with_method_numeric_vs_bool(self, method): + left = Index([1, 2, 3]) + right = Index([True, False]) + + with pytest.raises(TypeError, match="Cannot compare"): + left.get_indexer(right, method=method) + + with pytest.raises(TypeError, match="Cannot compare"): + right.get_indexer(left, method=method) + + def test_get_indexer_numeric_vs_bool(self): + left = Index([1, 2, 3]) + right = Index([True, False]) + + res = left.get_indexer(right) + expected = -1 * np.ones(len(right), dtype=np.intp) + tm.assert_numpy_array_equal(res, expected) + + res = right.get_indexer(left) + expected = -1 * np.ones(len(left), dtype=np.intp) + tm.assert_numpy_array_equal(res, expected) + + res = left.get_indexer_non_unique(right)[0] + expected = -1 * np.ones(len(right), dtype=np.intp) + tm.assert_numpy_array_equal(res, expected) + + res = right.get_indexer_non_unique(left)[0] + expected = -1 * np.ones(len(left), dtype=np.intp) + tm.assert_numpy_array_equal(res, expected) + + def test_get_indexer_float64(self): + idx = Index([0.0, 1.0, 2.0], dtype=np.float64) + tm.assert_numpy_array_equal( + idx.get_indexer(idx), np.array([0, 1, 2], dtype=np.intp) + ) + + target = [-0.1, 0.5, 1.1] + tm.assert_numpy_array_equal( + idx.get_indexer(target, "pad"), np.array([-1, 0, 1], dtype=np.intp) + ) + tm.assert_numpy_array_equal( + idx.get_indexer(target, "backfill"), np.array([0, 1, 2], dtype=np.intp) + ) + tm.assert_numpy_array_equal( + idx.get_indexer(target, "nearest"), np.array([0, 1, 1], dtype=np.intp) + ) + + def test_get_indexer_nan(self): + # GH#7820 + result = Index([1, 2, np.nan], dtype=np.float64).get_indexer([np.nan]) + expected = np.array([2], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + + def test_get_indexer_int64(self): + index = Index(range(0, 20, 2), dtype=np.int64) + target = Index(np.arange(10), dtype=np.int64) + indexer = index.get_indexer(target) + expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + target = Index(np.arange(10), dtype=np.int64) + indexer = index.get_indexer(target, method="pad") + expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + target = Index(np.arange(10), dtype=np.int64) + indexer = index.get_indexer(target, method="backfill") + expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + def test_get_indexer_uint64(self, index_large): + target = Index(np.arange(10).astype("uint64") * 5 + 2**63) + indexer = index_large.get_indexer(target) + expected = np.array([0, -1, 1, 2, 3, 4, -1, -1, -1, -1], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + target = Index(np.arange(10).astype("uint64") * 5 + 2**63) + indexer = index_large.get_indexer(target, method="pad") + expected = np.array([0, 0, 1, 2, 3, 4, 4, 4, 4, 4], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + target = Index(np.arange(10).astype("uint64") * 5 + 2**63) + indexer = index_large.get_indexer(target, method="backfill") + expected = np.array([0, 1, 1, 2, 3, 4, -1, -1, -1, -1], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + @pytest.mark.parametrize("val, val2", [(4, 5), (4, 4), (4, NA), (NA, NA)]) + def test_get_loc_masked(self, val, val2, any_numeric_ea_and_arrow_dtype): + # GH#39133 + idx = Index([1, 2, 3, val, val2], dtype=any_numeric_ea_and_arrow_dtype) + result = idx.get_loc(2) + assert result == 1 + + with pytest.raises(KeyError, match="9"): + idx.get_loc(9) + + def test_get_loc_masked_na(self, any_numeric_ea_and_arrow_dtype): + # GH#39133 + idx = Index([1, 2, NA], dtype=any_numeric_ea_and_arrow_dtype) + result = idx.get_loc(NA) + assert result == 2 + + idx = Index([1, 2, NA, NA], dtype=any_numeric_ea_and_arrow_dtype) + result = idx.get_loc(NA) + tm.assert_numpy_array_equal(result, np.array([False, False, True, True])) + + idx = Index([1, 2, 3], dtype=any_numeric_ea_and_arrow_dtype) + with pytest.raises(KeyError, match="NA"): + idx.get_loc(NA) + + def test_get_loc_masked_na_and_nan(self): + # GH#39133 + idx = Index( + FloatingArray( + np.array([1, 2, 1, np.nan]), mask=np.array([False, False, True, False]) + ) + ) + result = idx.get_loc(NA) + assert result == 2 + result = idx.get_loc(np.nan) + assert result == 3 + + idx = Index( + FloatingArray(np.array([1, 2, 1.0]), mask=np.array([False, False, True])) + ) + result = idx.get_loc(NA) + assert result == 2 + with pytest.raises(KeyError, match="nan"): + idx.get_loc(np.nan) + + idx = Index( + FloatingArray( + np.array([1, 2, np.nan]), mask=np.array([False, False, False]) + ) + ) + result = idx.get_loc(np.nan) + assert result == 2 + with pytest.raises(KeyError, match="NA"): + idx.get_loc(NA) + + @pytest.mark.parametrize("val", [4, 2]) + def test_get_indexer_masked_na(self, any_numeric_ea_and_arrow_dtype, val): + # GH#39133 + idx = Index([1, 2, NA, 3, val], dtype=any_numeric_ea_and_arrow_dtype) + result = idx.get_indexer_for([1, NA, 5]) + expected = np.array([0, 2, -1]) + tm.assert_numpy_array_equal(result, expected, check_dtype=False) + + @pytest.mark.parametrize("dtype", ["boolean", "bool[pyarrow]"]) + def test_get_indexer_masked_na_boolean(self, dtype): + # GH#39133 + if dtype == "bool[pyarrow]": + pytest.importorskip("pyarrow") + idx = Index([True, False, NA], dtype=dtype) + result = idx.get_loc(False) + assert result == 1 + result = idx.get_loc(NA) + assert result == 2 + + def test_get_indexer_arrow_dictionary_target(self): + pa = pytest.importorskip("pyarrow") + target = Index( + ArrowExtensionArray( + pa.array([1, 2], type=pa.dictionary(pa.int8(), pa.int8())) + ) + ) + idx = Index([1]) + + result = idx.get_indexer(target) + expected = np.array([0, -1], dtype=np.int64) + tm.assert_numpy_array_equal(result, expected) + + result_1, result_2 = idx.get_indexer_non_unique(target) + expected_1, expected_2 = np.array([0, -1], dtype=np.int64), np.array( + [1], dtype=np.int64 + ) + tm.assert_numpy_array_equal(result_1, expected_1) + tm.assert_numpy_array_equal(result_2, expected_2) + + +class TestWhere: + @pytest.mark.parametrize( + "index", + [ + Index(np.arange(5, dtype="float64")), + Index(range(0, 20, 2), dtype=np.int64), + Index(np.arange(5, dtype="uint64")), + ], + ) + def test_where(self, listlike_box, index): + cond = [True] * len(index) + expected = index + result = index.where(listlike_box(cond)) + + cond = [False] + [True] * (len(index) - 1) + expected = Index([index._na_value] + index[1:].tolist(), dtype=np.float64) + result = index.where(listlike_box(cond)) + tm.assert_index_equal(result, expected) + + def test_where_uint64(self): + idx = Index([0, 6, 2], dtype=np.uint64) + mask = np.array([False, True, False]) + other = np.array([1], dtype=np.int64) + + expected = Index([1, 6, 1], dtype=np.uint64) + + result = idx.where(mask, other) + tm.assert_index_equal(result, expected) + + result = idx.putmask(~mask, other) + tm.assert_index_equal(result, expected) + + def test_where_infers_type_instead_of_trying_to_convert_string_to_float(self): + # GH 32413 + index = Index([1, np.nan]) + cond = index.notna() + other = Index(["a", "b"], dtype="string") + + expected = Index([1.0, "b"]) + result = index.where(cond, other) + + tm.assert_index_equal(result, expected) + + +class TestTake: + @pytest.mark.parametrize("idx_dtype", [np.float64, np.int64, np.uint64]) + def test_take_preserve_name(self, idx_dtype): + index = Index([1, 2, 3, 4], dtype=idx_dtype, name="foo") + taken = index.take([3, 0, 1]) + assert index.name == taken.name + + def test_take_fill_value_float64(self): + # GH 12631 + idx = Index([1.0, 2.0, 3.0], name="xxx", dtype=np.float64) + result = idx.take(np.array([1, 0, -1])) + expected = Index([2.0, 1.0, 3.0], dtype=np.float64, name="xxx") + tm.assert_index_equal(result, expected) + + # fill_value + result = idx.take(np.array([1, 0, -1]), fill_value=True) + expected = Index([2.0, 1.0, np.nan], dtype=np.float64, name="xxx") + tm.assert_index_equal(result, expected) + + # allow_fill=False + result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True) + expected = Index([2.0, 1.0, 3.0], dtype=np.float64, name="xxx") + tm.assert_index_equal(result, expected) + + msg = ( + "When allow_fill=True and fill_value is not None, " + "all indices must be >= -1" + ) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + msg = "index -5 is out of bounds for (axis 0 with )?size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) + + @pytest.mark.parametrize("dtype", [np.int64, np.uint64]) + def test_take_fill_value_ints(self, dtype): + # see gh-12631 + idx = Index([1, 2, 3], dtype=dtype, name="xxx") + result = idx.take(np.array([1, 0, -1])) + expected = Index([2, 1, 3], dtype=dtype, name="xxx") + tm.assert_index_equal(result, expected) + + name = type(idx).__name__ + msg = f"Unable to fill values because {name} cannot contain NA" + + # fill_value=True + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -1]), fill_value=True) + + # allow_fill=False + result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True) + expected = Index([2, 1, 3], dtype=dtype, name="xxx") + tm.assert_index_equal(result, expected) + + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + msg = "index -5 is out of bounds for (axis 0 with )?size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) + + +class TestContains: + @pytest.mark.parametrize("dtype", [np.float64, np.int64, np.uint64]) + def test_contains_none(self, dtype): + # GH#35788 should return False, not raise TypeError + index = Index([0, 1, 2, 3, 4], dtype=dtype) + assert None not in index + + def test_contains_float64_nans(self): + index = Index([1.0, 2.0, np.nan], dtype=np.float64) + assert np.nan in index + + def test_contains_float64_not_nans(self): + index = Index([1.0, 2.0, np.nan], dtype=np.float64) + assert 1.0 in index + + +class TestSliceLocs: + @pytest.mark.parametrize("dtype", [int, float]) + def test_slice_locs(self, dtype): + index = Index(np.array([0, 1, 2, 5, 6, 7, 9, 10], dtype=dtype)) + n = len(index) + + assert index.slice_locs(start=2) == (2, n) + assert index.slice_locs(start=3) == (3, n) + assert index.slice_locs(3, 8) == (3, 6) + assert index.slice_locs(5, 10) == (3, n) + assert index.slice_locs(end=8) == (0, 6) + assert index.slice_locs(end=9) == (0, 7) + + # reversed + index2 = index[::-1] + assert index2.slice_locs(8, 2) == (2, 6) + assert index2.slice_locs(7, 3) == (2, 5) + + @pytest.mark.parametrize("dtype", [int, float]) + def test_slice_locs_float_locs(self, dtype): + index = Index(np.array([0, 1, 2, 5, 6, 7, 9, 10], dtype=dtype)) + n = len(index) + assert index.slice_locs(5.0, 10.0) == (3, n) + assert index.slice_locs(4.5, 10.5) == (3, 8) + + index2 = index[::-1] + assert index2.slice_locs(8.5, 1.5) == (2, 6) + assert index2.slice_locs(10.5, -1) == (0, n) + + @pytest.mark.parametrize("dtype", [int, float]) + def test_slice_locs_dup_numeric(self, dtype): + index = Index(np.array([10, 12, 12, 14], dtype=dtype)) + assert index.slice_locs(12, 12) == (1, 3) + assert index.slice_locs(11, 13) == (1, 3) + + index2 = index[::-1] + assert index2.slice_locs(12, 12) == (1, 3) + assert index2.slice_locs(13, 11) == (1, 3) + + def test_slice_locs_na(self): + index = Index([np.nan, 1, 2]) + assert index.slice_locs(1) == (1, 3) + assert index.slice_locs(np.nan) == (0, 3) + + index = Index([0, np.nan, np.nan, 1, 2]) + assert index.slice_locs(np.nan) == (1, 5) + + def test_slice_locs_na_raises(self): + index = Index([np.nan, 1, 2]) + with pytest.raises(KeyError, match=""): + index.slice_locs(start=1.5) + + with pytest.raises(KeyError, match=""): + index.slice_locs(end=1.5) + + +class TestGetSliceBounds: + @pytest.mark.parametrize("side, expected", [("left", 4), ("right", 5)]) + def test_get_slice_bounds_within(self, side, expected): + index = Index(range(6)) + result = index.get_slice_bound(4, side=side) + assert result == expected + + @pytest.mark.parametrize("side", ["left", "right"]) + @pytest.mark.parametrize("bound, expected", [(-1, 0), (10, 6)]) + def test_get_slice_bounds_outside(self, side, expected, bound): + index = Index(range(6)) + result = index.get_slice_bound(bound, side=side) + assert result == expected diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_join.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_join.py new file mode 100644 index 0000000000000000000000000000000000000000..918d5052167356b1d51018434c03e6682f828872 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_join.py @@ -0,0 +1,380 @@ +import numpy as np +import pytest + +import pandas._testing as tm +from pandas.core.indexes.api import Index + + +class TestJoinInt64Index: + def test_join_non_unique(self): + left = Index([4, 4, 3, 3]) + + joined, lidx, ridx = left.join(left, return_indexers=True) + + exp_joined = Index([4, 4, 4, 4, 3, 3, 3, 3]) + tm.assert_index_equal(joined, exp_joined) + + exp_lidx = np.array([0, 0, 1, 1, 2, 2, 3, 3], dtype=np.intp) + tm.assert_numpy_array_equal(lidx, exp_lidx) + + exp_ridx = np.array([0, 1, 0, 1, 2, 3, 2, 3], dtype=np.intp) + tm.assert_numpy_array_equal(ridx, exp_ridx) + + def test_join_inner(self): + index = Index(range(0, 20, 2), dtype=np.int64) + other = Index([7, 12, 25, 1, 2, 5], dtype=np.int64) + other_mono = Index([1, 2, 5, 7, 12, 25], dtype=np.int64) + + # not monotonic + res, lidx, ridx = index.join(other, how="inner", return_indexers=True) + + # no guarantee of sortedness, so sort for comparison purposes + ind = res.argsort() + res = res.take(ind) + lidx = lidx.take(ind) + ridx = ridx.take(ind) + + eres = Index([2, 12], dtype=np.int64) + elidx = np.array([1, 6], dtype=np.intp) + eridx = np.array([4, 1], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index.join(other_mono, how="inner", return_indexers=True) + + res2 = index.intersection(other_mono) + tm.assert_index_equal(res, res2) + + elidx = np.array([1, 6], dtype=np.intp) + eridx = np.array([1, 4], dtype=np.intp) + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_left(self): + index = Index(range(0, 20, 2), dtype=np.int64) + other = Index([7, 12, 25, 1, 2, 5], dtype=np.int64) + other_mono = Index([1, 2, 5, 7, 12, 25], dtype=np.int64) + + # not monotonic + res, lidx, ridx = index.join(other, how="left", return_indexers=True) + eres = index + eridx = np.array([-1, 4, -1, -1, -1, -1, 1, -1, -1, -1], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index.join(other_mono, how="left", return_indexers=True) + eridx = np.array([-1, 1, -1, -1, -1, -1, 4, -1, -1, -1], dtype=np.intp) + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + # non-unique + idx = Index([1, 1, 2, 5]) + idx2 = Index([1, 2, 5, 7, 9]) + res, lidx, ridx = idx2.join(idx, how="left", return_indexers=True) + eres = Index([1, 1, 2, 5, 7, 9]) # 1 is in idx2, so it should be x2 + eridx = np.array([0, 1, 2, 3, -1, -1], dtype=np.intp) + elidx = np.array([0, 0, 1, 2, 3, 4], dtype=np.intp) + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_right(self): + index = Index(range(0, 20, 2), dtype=np.int64) + other = Index([7, 12, 25, 1, 2, 5], dtype=np.int64) + other_mono = Index([1, 2, 5, 7, 12, 25], dtype=np.int64) + + # not monotonic + res, lidx, ridx = index.join(other, how="right", return_indexers=True) + eres = other + elidx = np.array([-1, 6, -1, -1, 1, -1], dtype=np.intp) + + assert isinstance(other, Index) and other.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + assert ridx is None + + # monotonic + res, lidx, ridx = index.join(other_mono, how="right", return_indexers=True) + eres = other_mono + elidx = np.array([-1, 1, -1, -1, 6, -1], dtype=np.intp) + assert isinstance(other, Index) and other.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + assert ridx is None + + # non-unique + idx = Index([1, 1, 2, 5]) + idx2 = Index([1, 2, 5, 7, 9]) + res, lidx, ridx = idx.join(idx2, how="right", return_indexers=True) + eres = Index([1, 1, 2, 5, 7, 9]) # 1 is in idx2, so it should be x2 + elidx = np.array([0, 1, 2, 3, -1, -1], dtype=np.intp) + eridx = np.array([0, 0, 1, 2, 3, 4], dtype=np.intp) + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_non_int_index(self): + index = Index(range(0, 20, 2), dtype=np.int64) + other = Index([3, 6, 7, 8, 10], dtype=object) + + outer = index.join(other, how="outer") + outer2 = other.join(index, how="outer") + expected = Index([0, 2, 3, 4, 6, 7, 8, 10, 12, 14, 16, 18]) + tm.assert_index_equal(outer, outer2) + tm.assert_index_equal(outer, expected) + + inner = index.join(other, how="inner") + inner2 = other.join(index, how="inner") + expected = Index([6, 8, 10]) + tm.assert_index_equal(inner, inner2) + tm.assert_index_equal(inner, expected) + + left = index.join(other, how="left") + tm.assert_index_equal(left, index.astype(object)) + + left2 = other.join(index, how="left") + tm.assert_index_equal(left2, other) + + right = index.join(other, how="right") + tm.assert_index_equal(right, other) + + right2 = other.join(index, how="right") + tm.assert_index_equal(right2, index.astype(object)) + + def test_join_outer(self): + index = Index(range(0, 20, 2), dtype=np.int64) + other = Index([7, 12, 25, 1, 2, 5], dtype=np.int64) + other_mono = Index([1, 2, 5, 7, 12, 25], dtype=np.int64) + + # not monotonic + # guarantee of sortedness + res, lidx, ridx = index.join(other, how="outer", return_indexers=True) + noidx_res = index.join(other, how="outer") + tm.assert_index_equal(res, noidx_res) + + eres = Index([0, 1, 2, 4, 5, 6, 7, 8, 10, 12, 14, 16, 18, 25], dtype=np.int64) + elidx = np.array([0, -1, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, 9, -1], dtype=np.intp) + eridx = np.array( + [-1, 3, 4, -1, 5, -1, 0, -1, -1, 1, -1, -1, -1, 2], dtype=np.intp + ) + + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index.join(other_mono, how="outer", return_indexers=True) + noidx_res = index.join(other_mono, how="outer") + tm.assert_index_equal(res, noidx_res) + + elidx = np.array([0, -1, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, 9, -1], dtype=np.intp) + eridx = np.array( + [-1, 0, 1, -1, 2, -1, 3, -1, -1, 4, -1, -1, -1, 5], dtype=np.intp + ) + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + +class TestJoinUInt64Index: + @pytest.fixture + def index_large(self): + # large values used in TestUInt64Index where no compat needed with int64/float64 + large = [2**63, 2**63 + 10, 2**63 + 15, 2**63 + 20, 2**63 + 25] + return Index(large, dtype=np.uint64) + + def test_join_inner(self, index_large): + other = Index(2**63 + np.array([7, 12, 25, 1, 2, 10], dtype="uint64")) + other_mono = Index(2**63 + np.array([1, 2, 7, 10, 12, 25], dtype="uint64")) + + # not monotonic + res, lidx, ridx = index_large.join(other, how="inner", return_indexers=True) + + # no guarantee of sortedness, so sort for comparison purposes + ind = res.argsort() + res = res.take(ind) + lidx = lidx.take(ind) + ridx = ridx.take(ind) + + eres = Index(2**63 + np.array([10, 25], dtype="uint64")) + elidx = np.array([1, 4], dtype=np.intp) + eridx = np.array([5, 2], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index_large.join( + other_mono, how="inner", return_indexers=True + ) + + res2 = index_large.intersection(other_mono) + tm.assert_index_equal(res, res2) + + elidx = np.array([1, 4], dtype=np.intp) + eridx = np.array([3, 5], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_left(self, index_large): + other = Index(2**63 + np.array([7, 12, 25, 1, 2, 10], dtype="uint64")) + other_mono = Index(2**63 + np.array([1, 2, 7, 10, 12, 25], dtype="uint64")) + + # not monotonic + res, lidx, ridx = index_large.join(other, how="left", return_indexers=True) + eres = index_large + eridx = np.array([-1, 5, -1, -1, 2], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index_large.join(other_mono, how="left", return_indexers=True) + eridx = np.array([-1, 3, -1, -1, 5], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + # non-unique + idx = Index(2**63 + np.array([1, 1, 2, 5], dtype="uint64")) + idx2 = Index(2**63 + np.array([1, 2, 5, 7, 9], dtype="uint64")) + res, lidx, ridx = idx2.join(idx, how="left", return_indexers=True) + + # 1 is in idx2, so it should be x2 + eres = Index(2**63 + np.array([1, 1, 2, 5, 7, 9], dtype="uint64")) + eridx = np.array([0, 1, 2, 3, -1, -1], dtype=np.intp) + elidx = np.array([0, 0, 1, 2, 3, 4], dtype=np.intp) + + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_right(self, index_large): + other = Index(2**63 + np.array([7, 12, 25, 1, 2, 10], dtype="uint64")) + other_mono = Index(2**63 + np.array([1, 2, 7, 10, 12, 25], dtype="uint64")) + + # not monotonic + res, lidx, ridx = index_large.join(other, how="right", return_indexers=True) + eres = other + elidx = np.array([-1, -1, 4, -1, -1, 1], dtype=np.intp) + + tm.assert_numpy_array_equal(lidx, elidx) + assert isinstance(other, Index) and other.dtype == np.uint64 + tm.assert_index_equal(res, eres) + assert ridx is None + + # monotonic + res, lidx, ridx = index_large.join( + other_mono, how="right", return_indexers=True + ) + eres = other_mono + elidx = np.array([-1, -1, -1, 1, -1, 4], dtype=np.intp) + + assert isinstance(other, Index) and other.dtype == np.uint64 + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_index_equal(res, eres) + assert ridx is None + + # non-unique + idx = Index(2**63 + np.array([1, 1, 2, 5], dtype="uint64")) + idx2 = Index(2**63 + np.array([1, 2, 5, 7, 9], dtype="uint64")) + res, lidx, ridx = idx.join(idx2, how="right", return_indexers=True) + + # 1 is in idx2, so it should be x2 + eres = Index(2**63 + np.array([1, 1, 2, 5, 7, 9], dtype="uint64")) + elidx = np.array([0, 1, 2, 3, -1, -1], dtype=np.intp) + eridx = np.array([0, 0, 1, 2, 3, 4], dtype=np.intp) + + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_non_int_index(self, index_large): + other = Index( + 2**63 + np.array([1, 5, 7, 10, 20], dtype="uint64"), dtype=object + ) + + outer = index_large.join(other, how="outer") + outer2 = other.join(index_large, how="outer") + expected = Index( + 2**63 + np.array([0, 1, 5, 7, 10, 15, 20, 25], dtype="uint64") + ) + tm.assert_index_equal(outer, outer2) + tm.assert_index_equal(outer, expected) + + inner = index_large.join(other, how="inner") + inner2 = other.join(index_large, how="inner") + expected = Index(2**63 + np.array([10, 20], dtype="uint64")) + tm.assert_index_equal(inner, inner2) + tm.assert_index_equal(inner, expected) + + left = index_large.join(other, how="left") + tm.assert_index_equal(left, index_large.astype(object)) + + left2 = other.join(index_large, how="left") + tm.assert_index_equal(left2, other) + + right = index_large.join(other, how="right") + tm.assert_index_equal(right, other) + + right2 = other.join(index_large, how="right") + tm.assert_index_equal(right2, index_large.astype(object)) + + def test_join_outer(self, index_large): + other = Index(2**63 + np.array([7, 12, 25, 1, 2, 10], dtype="uint64")) + other_mono = Index(2**63 + np.array([1, 2, 7, 10, 12, 25], dtype="uint64")) + + # not monotonic + # guarantee of sortedness + res, lidx, ridx = index_large.join(other, how="outer", return_indexers=True) + noidx_res = index_large.join(other, how="outer") + tm.assert_index_equal(res, noidx_res) + + eres = Index( + 2**63 + np.array([0, 1, 2, 7, 10, 12, 15, 20, 25], dtype="uint64") + ) + elidx = np.array([0, -1, -1, -1, 1, -1, 2, 3, 4], dtype=np.intp) + eridx = np.array([-1, 3, 4, 0, 5, 1, -1, -1, 2], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # monotonic + res, lidx, ridx = index_large.join( + other_mono, how="outer", return_indexers=True + ) + noidx_res = index_large.join(other_mono, how="outer") + tm.assert_index_equal(res, noidx_res) + + elidx = np.array([0, -1, -1, -1, 1, -1, 2, 3, 4], dtype=np.intp) + eridx = np.array([-1, 0, 1, 2, 3, 4, -1, -1, 5], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.uint64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_numeric.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_numeric.py new file mode 100644 index 0000000000000000000000000000000000000000..4fd807e1827ddc4faf900f15dcefa18c08d4cd0b --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_numeric.py @@ -0,0 +1,553 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + Series, +) +import pandas._testing as tm + + +class TestFloatNumericIndex: + @pytest.fixture(params=[np.float64, np.float32]) + def dtype(self, request): + return request.param + + @pytest.fixture + def simple_index(self, dtype): + values = np.arange(5, dtype=dtype) + return Index(values) + + @pytest.fixture( + params=[ + [1.5, 2, 3, 4, 5], + [0.0, 2.5, 5.0, 7.5, 10.0], + [5, 4, 3, 2, 1.5], + [10.0, 7.5, 5.0, 2.5, 0.0], + ], + ids=["mixed", "float", "mixed_dec", "float_dec"], + ) + def index(self, request, dtype): + return Index(request.param, dtype=dtype) + + @pytest.fixture + def mixed_index(self, dtype): + return Index([1.5, 2, 3, 4, 5], dtype=dtype) + + @pytest.fixture + def float_index(self, dtype): + return Index([0.0, 2.5, 5.0, 7.5, 10.0], dtype=dtype) + + def test_repr_roundtrip(self, index): + tm.assert_index_equal(eval(repr(index)), index, exact=True) + + def check_coerce(self, a, b, is_float_index=True): + assert a.equals(b) + tm.assert_index_equal(a, b, exact=False) + if is_float_index: + assert isinstance(b, Index) + else: + assert type(b) is Index + + def test_constructor_from_list_no_dtype(self): + index = Index([1.5, 2.5, 3.5]) + assert index.dtype == np.float64 + + def test_constructor(self, dtype): + index_cls = Index + + # explicit construction + index = index_cls([1, 2, 3, 4, 5], dtype=dtype) + + assert isinstance(index, index_cls) + assert index.dtype == dtype + + expected = np.array([1, 2, 3, 4, 5], dtype=dtype) + tm.assert_numpy_array_equal(index.values, expected) + + index = index_cls(np.array([1, 2, 3, 4, 5]), dtype=dtype) + assert isinstance(index, index_cls) + assert index.dtype == dtype + + index = index_cls([1.0, 2, 3, 4, 5], dtype=dtype) + assert isinstance(index, index_cls) + assert index.dtype == dtype + + index = index_cls(np.array([1.0, 2, 3, 4, 5]), dtype=dtype) + assert isinstance(index, index_cls) + assert index.dtype == dtype + + index = index_cls([1.0, 2, 3, 4, 5], dtype=dtype) + assert isinstance(index, index_cls) + assert index.dtype == dtype + + index = index_cls(np.array([1.0, 2, 3, 4, 5]), dtype=dtype) + assert isinstance(index, index_cls) + assert index.dtype == dtype + + # nan handling + result = index_cls([np.nan, np.nan], dtype=dtype) + assert pd.isna(result.values).all() + + result = index_cls(np.array([np.nan]), dtype=dtype) + assert pd.isna(result.values).all() + + def test_constructor_invalid(self): + index_cls = Index + cls_name = index_cls.__name__ + # invalid + msg = ( + rf"{cls_name}\(\.\.\.\) must be called with a collection of " + r"some kind, 0\.0 was passed" + ) + with pytest.raises(TypeError, match=msg): + index_cls(0.0) + + def test_constructor_coerce(self, mixed_index, float_index): + self.check_coerce(mixed_index, Index([1.5, 2, 3, 4, 5])) + self.check_coerce(float_index, Index(np.arange(5) * 2.5)) + + result = Index(np.array(np.arange(5) * 2.5, dtype=object)) + assert result.dtype == object # as of 2.0 to match Series + self.check_coerce(float_index, result.astype("float64")) + + def test_constructor_explicit(self, mixed_index, float_index): + # these don't auto convert + self.check_coerce( + float_index, Index((np.arange(5) * 2.5), dtype=object), is_float_index=False + ) + self.check_coerce( + mixed_index, Index([1.5, 2, 3, 4, 5], dtype=object), is_float_index=False + ) + + def test_type_coercion_fail(self, any_int_numpy_dtype): + # see gh-15832 + msg = "Trying to coerce float values to integers" + with pytest.raises(ValueError, match=msg): + Index([1, 2, 3.5], dtype=any_int_numpy_dtype) + + def test_equals_numeric(self): + index_cls = Index + + idx = index_cls([1.0, 2.0]) + assert idx.equals(idx) + assert idx.identical(idx) + + idx2 = index_cls([1.0, 2.0]) + assert idx.equals(idx2) + + idx = index_cls([1.0, np.nan]) + assert idx.equals(idx) + assert idx.identical(idx) + + idx2 = index_cls([1.0, np.nan]) + assert idx.equals(idx2) + + @pytest.mark.parametrize( + "other", + ( + Index([1, 2], dtype=np.int64), + Index([1.0, 2.0], dtype=object), + Index([1, 2], dtype=object), + ), + ) + def test_equals_numeric_other_index_type(self, other): + idx = Index([1.0, 2.0]) + assert idx.equals(other) + assert other.equals(idx) + + @pytest.mark.parametrize( + "vals", + [ + pd.date_range("2016-01-01", periods=3), + pd.timedelta_range("1 Day", periods=3), + ], + ) + def test_lookups_datetimelike_values(self, vals, dtype): + # If we have datetime64 or timedelta64 values, make sure they are + # wrapped correctly GH#31163 + ser = Series(vals, index=range(3, 6)) + ser.index = ser.index.astype(dtype) + + expected = vals[1] + + result = ser[4.0] + assert isinstance(result, type(expected)) and result == expected + result = ser[4] + assert isinstance(result, type(expected)) and result == expected + + result = ser.loc[4.0] + assert isinstance(result, type(expected)) and result == expected + result = ser.loc[4] + assert isinstance(result, type(expected)) and result == expected + + result = ser.at[4.0] + assert isinstance(result, type(expected)) and result == expected + # GH#31329 .at[4] should cast to 4.0, matching .loc behavior + result = ser.at[4] + assert isinstance(result, type(expected)) and result == expected + + result = ser.iloc[1] + assert isinstance(result, type(expected)) and result == expected + + result = ser.iat[1] + assert isinstance(result, type(expected)) and result == expected + + def test_doesnt_contain_all_the_things(self): + idx = Index([np.nan]) + assert not idx.isin([0]).item() + assert not idx.isin([1]).item() + assert idx.isin([np.nan]).item() + + def test_nan_multiple_containment(self): + index_cls = Index + + idx = index_cls([1.0, np.nan]) + tm.assert_numpy_array_equal(idx.isin([1.0]), np.array([True, False])) + tm.assert_numpy_array_equal(idx.isin([2.0, np.pi]), np.array([False, False])) + tm.assert_numpy_array_equal(idx.isin([np.nan]), np.array([False, True])) + tm.assert_numpy_array_equal(idx.isin([1.0, np.nan]), np.array([True, True])) + idx = index_cls([1.0, 2.0]) + tm.assert_numpy_array_equal(idx.isin([np.nan]), np.array([False, False])) + + def test_fillna_float64(self): + index_cls = Index + # GH 11343 + idx = Index([1.0, np.nan, 3.0], dtype=float, name="x") + # can't downcast + exp = Index([1.0, 0.1, 3.0], name="x") + tm.assert_index_equal(idx.fillna(0.1), exp, exact=True) + + # downcast + exp = index_cls([1.0, 2.0, 3.0], name="x") + tm.assert_index_equal(idx.fillna(2), exp) + + # object + exp = Index([1.0, "obj", 3.0], name="x") + tm.assert_index_equal(idx.fillna("obj"), exp, exact=True) + + def test_logical_compat(self, simple_index): + idx = simple_index + assert idx.all() == idx.values.all() + assert idx.any() == idx.values.any() + + assert idx.all() == idx.to_series().all() + assert idx.any() == idx.to_series().any() + + +class TestNumericInt: + @pytest.fixture(params=[np.int64, np.int32, np.int16, np.int8, np.uint64]) + def dtype(self, request): + return request.param + + @pytest.fixture + def simple_index(self, dtype): + return Index(range(0, 20, 2), dtype=dtype) + + def test_is_monotonic(self): + index_cls = Index + + index = index_cls([1, 2, 3, 4]) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index._is_strictly_monotonic_increasing is True + assert index.is_monotonic_decreasing is False + assert index._is_strictly_monotonic_decreasing is False + + index = index_cls([4, 3, 2, 1]) + assert index.is_monotonic_increasing is False + assert index._is_strictly_monotonic_increasing is False + assert index._is_strictly_monotonic_decreasing is True + + index = index_cls([1]) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_increasing is True + assert index._is_strictly_monotonic_decreasing is True + + def test_is_strictly_monotonic(self): + index_cls = Index + + index = index_cls([1, 1, 2, 3]) + assert index.is_monotonic_increasing is True + assert index._is_strictly_monotonic_increasing is False + + index = index_cls([3, 2, 1, 1]) + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_decreasing is False + + index = index_cls([1, 1]) + assert index.is_monotonic_increasing + assert index.is_monotonic_decreasing + assert not index._is_strictly_monotonic_increasing + assert not index._is_strictly_monotonic_decreasing + + def test_logical_compat(self, simple_index): + idx = simple_index + assert idx.all() == idx.values.all() + assert idx.any() == idx.values.any() + + def test_identical(self, simple_index, dtype): + index = simple_index + + idx = Index(index.copy()) + assert idx.identical(index) + + same_values_different_type = Index(idx, dtype=object) + assert not idx.identical(same_values_different_type) + + idx = index.astype(dtype=object) + idx = idx.rename("foo") + same_values = Index(idx, dtype=object) + assert same_values.identical(idx) + + assert not idx.identical(index) + assert Index(same_values, name="foo", dtype=object).identical(idx) + + assert not index.astype(dtype=object).identical(index.astype(dtype=dtype)) + + def test_cant_or_shouldnt_cast(self, dtype): + msg = r"invalid literal for int\(\) with base 10: 'foo'" + + # can't + data = ["foo", "bar", "baz"] + with pytest.raises(ValueError, match=msg): + Index(data, dtype=dtype) + + def test_view_index(self, simple_index): + index = simple_index + msg = "Passing a type in .*Index.view is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + index.view(Index) + + def test_prevent_casting(self, simple_index): + index = simple_index + result = index.astype("O") + assert result.dtype == np.object_ + + +class TestIntNumericIndex: + @pytest.fixture(params=[np.int64, np.int32, np.int16, np.int8]) + def dtype(self, request): + return request.param + + def test_constructor_from_list_no_dtype(self): + index = Index([1, 2, 3]) + assert index.dtype == np.int64 + + def test_constructor(self, dtype): + index_cls = Index + + # scalar raise Exception + msg = ( + rf"{index_cls.__name__}\(\.\.\.\) must be called with a collection of some " + "kind, 5 was passed" + ) + with pytest.raises(TypeError, match=msg): + index_cls(5) + + # copy + # pass list, coerce fine + index = index_cls([-5, 0, 1, 2], dtype=dtype) + arr = index.values.copy() + new_index = index_cls(arr, copy=True) + tm.assert_index_equal(new_index, index, exact=True) + val = int(arr[0]) + 3000 + + # this should not change index + if dtype != np.int8: + # NEP 50 won't allow assignment that would overflow + arr[0] = val + assert new_index[0] != val + + if dtype == np.int64: + # pass list, coerce fine + index = index_cls([-5, 0, 1, 2], dtype=dtype) + expected = Index([-5, 0, 1, 2], dtype=dtype) + tm.assert_index_equal(index, expected) + + # from iterable + index = index_cls(iter([-5, 0, 1, 2]), dtype=dtype) + expected = index_cls([-5, 0, 1, 2], dtype=dtype) + tm.assert_index_equal(index, expected, exact=True) + + # interpret list-like + expected = index_cls([5, 0], dtype=dtype) + for cls in [Index, index_cls]: + for idx in [ + cls([5, 0], dtype=dtype), + cls(np.array([5, 0]), dtype=dtype), + cls(Series([5, 0]), dtype=dtype), + ]: + tm.assert_index_equal(idx, expected) + + def test_constructor_corner(self, dtype): + index_cls = Index + + arr = np.array([1, 2, 3, 4], dtype=object) + + index = index_cls(arr, dtype=dtype) + assert index.values.dtype == index.dtype + if dtype == np.int64: + without_dtype = Index(arr) + # as of 2.0 we do not infer a dtype when we get an object-dtype + # ndarray of numbers, matching Series behavior + assert without_dtype.dtype == object + + tm.assert_index_equal(index, without_dtype.astype(np.int64)) + + # preventing casting + arr = np.array([1, "2", 3, "4"], dtype=object) + msg = "Trying to coerce float values to integers" + with pytest.raises(ValueError, match=msg): + index_cls(arr, dtype=dtype) + + def test_constructor_coercion_signed_to_unsigned( + self, + any_unsigned_int_numpy_dtype, + ): + # see gh-15832 + msg = "|".join( + [ + "Trying to coerce negative values to unsigned integers", + "The elements provided in the data cannot all be casted", + ] + ) + with pytest.raises(OverflowError, match=msg): + Index([-1], dtype=any_unsigned_int_numpy_dtype) + + def test_constructor_np_signed(self, any_signed_int_numpy_dtype): + # GH#47475 + scalar = np.dtype(any_signed_int_numpy_dtype).type(1) + result = Index([scalar]) + expected = Index([1], dtype=any_signed_int_numpy_dtype) + tm.assert_index_equal(result, expected, exact=True) + + def test_constructor_np_unsigned(self, any_unsigned_int_numpy_dtype): + # GH#47475 + scalar = np.dtype(any_unsigned_int_numpy_dtype).type(1) + result = Index([scalar]) + expected = Index([1], dtype=any_unsigned_int_numpy_dtype) + tm.assert_index_equal(result, expected, exact=True) + + def test_coerce_list(self): + # coerce things + arr = Index([1, 2, 3, 4]) + assert isinstance(arr, Index) + + # but not if explicit dtype passed + arr = Index([1, 2, 3, 4], dtype=object) + assert type(arr) is Index + + +class TestFloat16Index: + # float 16 indexes not supported + # GH 49535 + def test_constructor(self): + index_cls = Index + dtype = np.float16 + + msg = "float16 indexes are not supported" + + # explicit construction + with pytest.raises(NotImplementedError, match=msg): + index_cls([1, 2, 3, 4, 5], dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls(np.array([1, 2, 3, 4, 5]), dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls([1.0, 2, 3, 4, 5], dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls(np.array([1.0, 2, 3, 4, 5]), dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls([1.0, 2, 3, 4, 5], dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls(np.array([1.0, 2, 3, 4, 5]), dtype=dtype) + + # nan handling + with pytest.raises(NotImplementedError, match=msg): + index_cls([np.nan, np.nan], dtype=dtype) + + with pytest.raises(NotImplementedError, match=msg): + index_cls(np.array([np.nan]), dtype=dtype) + + +@pytest.mark.parametrize( + "box", + [list, lambda x: np.array(x, dtype=object), lambda x: Index(x, dtype=object)], +) +def test_uint_index_does_not_convert_to_float64(box): + # https://github.com/pandas-dev/pandas/issues/28279 + # https://github.com/pandas-dev/pandas/issues/28023 + series = Series( + [0, 1, 2, 3, 4, 5], + index=[ + 7606741985629028552, + 17876870360202815256, + 17876870360202815256, + 13106359306506049338, + 8991270399732411471, + 8991270399732411472, + ], + ) + + result = series.loc[box([7606741985629028552, 17876870360202815256])] + + expected = Index( + [7606741985629028552, 17876870360202815256, 17876870360202815256], + dtype="uint64", + ) + tm.assert_index_equal(result.index, expected) + + tm.assert_equal(result, series.iloc[:3]) + + +def test_float64_index_equals(): + # https://github.com/pandas-dev/pandas/issues/35217 + float_index = Index([1.0, 2, 3]) + string_index = Index(["1", "2", "3"]) + + result = float_index.equals(string_index) + assert result is False + + result = string_index.equals(float_index) + assert result is False + + +def test_map_dtype_inference_unsigned_to_signed(): + # GH#44609 cases where we don't retain dtype + idx = Index([1, 2, 3], dtype=np.uint64) + result = idx.map(lambda x: -x) + expected = Index([-1, -2, -3], dtype=np.int64) + tm.assert_index_equal(result, expected) + + +def test_map_dtype_inference_overflows(): + # GH#44609 case where we have to upcast + idx = Index(np.array([1, 2, 3], dtype=np.int8)) + result = idx.map(lambda x: x * 1000) + # TODO: we could plausibly try to infer down to int16 here + expected = Index([1000, 2000, 3000], dtype=np.int64) + tm.assert_index_equal(result, expected) + + +def test_view_to_datetimelike(): + # GH#55710 + idx = Index([1, 2, 3]) + res = idx.view("m8[s]") + expected = pd.TimedeltaIndex(idx.values.view("m8[s]")) + tm.assert_index_equal(res, expected) + + res2 = idx.view("m8[D]") + expected2 = idx.values.view("m8[D]") + tm.assert_numpy_array_equal(res2, expected2) + + res3 = idx.view("M8[h]") + expected3 = idx.values.view("M8[h]") + tm.assert_numpy_array_equal(res3, expected3) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..376b51dd98bb1b1c7c6c8a67914bc72f6c6c588d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/numeric/test_setops.py @@ -0,0 +1,168 @@ +from datetime import ( + datetime, + timedelta, +) + +import numpy as np +import pytest + +import pandas._testing as tm +from pandas.core.indexes.api import ( + Index, + RangeIndex, +) + + +@pytest.fixture +def index_large(): + # large values used in TestUInt64Index where no compat needed with int64/float64 + large = [2**63, 2**63 + 10, 2**63 + 15, 2**63 + 20, 2**63 + 25] + return Index(large, dtype=np.uint64) + + +class TestSetOps: + @pytest.mark.parametrize("dtype", ["f8", "u8", "i8"]) + def test_union_non_numeric(self, dtype): + # corner case, non-numeric + index = Index(np.arange(5, dtype=dtype), dtype=dtype) + assert index.dtype == dtype + + other = Index([datetime.now() + timedelta(i) for i in range(4)], dtype=object) + result = index.union(other) + expected = Index(np.concatenate((index, other))) + tm.assert_index_equal(result, expected) + + result = other.union(index) + expected = Index(np.concatenate((other, index))) + tm.assert_index_equal(result, expected) + + def test_intersection(self): + index = Index(range(5), dtype=np.int64) + + other = Index([1, 2, 3, 4, 5]) + result = index.intersection(other) + expected = Index(np.sort(np.intersect1d(index.values, other.values))) + tm.assert_index_equal(result, expected) + + result = other.intersection(index) + expected = Index( + np.sort(np.asarray(np.intersect1d(index.values, other.values))) + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("dtype", ["int64", "uint64"]) + def test_int_float_union_dtype(self, dtype): + # https://github.com/pandas-dev/pandas/issues/26778 + # [u]int | float -> float + index = Index([0, 2, 3], dtype=dtype) + other = Index([0.5, 1.5], dtype=np.float64) + expected = Index([0.0, 0.5, 1.5, 2.0, 3.0], dtype=np.float64) + result = index.union(other) + tm.assert_index_equal(result, expected) + + result = other.union(index) + tm.assert_index_equal(result, expected) + + def test_range_float_union_dtype(self): + # https://github.com/pandas-dev/pandas/issues/26778 + index = RangeIndex(start=0, stop=3) + other = Index([0.5, 1.5], dtype=np.float64) + result = index.union(other) + expected = Index([0.0, 0.5, 1, 1.5, 2.0], dtype=np.float64) + tm.assert_index_equal(result, expected) + + result = other.union(index) + tm.assert_index_equal(result, expected) + + def test_range_uint64_union_dtype(self): + # https://github.com/pandas-dev/pandas/issues/26778 + index = RangeIndex(start=0, stop=3) + other = Index([0, 10], dtype=np.uint64) + result = index.union(other) + expected = Index([0, 1, 2, 10], dtype=object) + tm.assert_index_equal(result, expected) + + result = other.union(index) + tm.assert_index_equal(result, expected) + + def test_float64_index_difference(self): + # https://github.com/pandas-dev/pandas/issues/35217 + float_index = Index([1.0, 2, 3]) + string_index = Index(["1", "2", "3"]) + + result = float_index.difference(string_index) + tm.assert_index_equal(result, float_index) + + result = string_index.difference(float_index) + tm.assert_index_equal(result, string_index) + + def test_intersection_uint64_outside_int64_range(self, index_large): + other = Index([2**63, 2**63 + 5, 2**63 + 10, 2**63 + 15, 2**63 + 20]) + result = index_large.intersection(other) + expected = Index(np.sort(np.intersect1d(index_large.values, other.values))) + tm.assert_index_equal(result, expected) + + result = other.intersection(index_large) + expected = Index( + np.sort(np.asarray(np.intersect1d(index_large.values, other.values))) + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "index2,keeps_name", + [ + (Index([4, 7, 6, 5, 3], name="index"), True), + (Index([4, 7, 6, 5, 3], name="other"), False), + ], + ) + def test_intersection_monotonic(self, index2, keeps_name, sort): + index1 = Index([5, 3, 2, 4, 1], name="index") + expected = Index([5, 3, 4]) + + if keeps_name: + expected.name = "index" + + result = index1.intersection(index2, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + + def test_symmetric_difference(self, sort): + # smoke + index1 = Index([5, 2, 3, 4], name="index1") + index2 = Index([2, 3, 4, 1]) + result = index1.symmetric_difference(index2, sort=sort) + expected = Index([5, 1]) + if sort is not None: + tm.assert_index_equal(result, expected) + else: + tm.assert_index_equal(result, expected.sort_values()) + assert result.name is None + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + + +class TestSetOpsSort: + @pytest.mark.parametrize("slice_", [slice(None), slice(0)]) + def test_union_sort_other_special(self, slice_): + # https://github.com/pandas-dev/pandas/issues/24959 + + idx = Index([1, 0, 2]) + # default, sort=None + other = idx[slice_] + tm.assert_index_equal(idx.union(other), idx) + tm.assert_index_equal(other.union(idx), idx) + + # sort=False + tm.assert_index_equal(idx.union(other, sort=False), idx) + + @pytest.mark.parametrize("slice_", [slice(None), slice(0)]) + def test_union_sort_special_true(self, slice_): + idx = Index([1, 0, 2]) + # default, sort=None + other = idx[slice_] + + result = idx.union(other, sort=True) + expected = Index([0, 1, 2]) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0efc8f44011bbcf40bcab85b5cd0b8e1426d9cab Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9ee1dc901ed338b41d5b16c00544f677bcb6323a Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_formats.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_formats.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3742cd3e13365c27fdcab075972ee2f5dcd595ec Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_formats.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_freq_attr.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_freq_attr.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c7b1be413fd18ab4db65977a60a40f36ff75e32f Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_freq_attr.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fe325aa161bbf13e498cd772f7f4998ce4ac90d6 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9cef1895a6f79f6e8caddf8a28f6db24a2a8059d Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_monotonic.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_monotonic.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2eeddca918b1ef36f49207dbe4b1722c3c522e77 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_monotonic.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_partial_slicing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_partial_slicing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..825c7dad9e64eea17b5cda55cc89ea6f28e546f7 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_partial_slicing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a1ff8380b4a34f28b2b21925178a445e2dd420f1 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period_range.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period_range.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8081ffc2ab65ac5af53aa961c1c68a30e5365fae Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_period_range.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_pickle.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_pickle.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9decf473b09f1c834fe6a8c0c618cf6e75142474 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_pickle.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_resolution.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_resolution.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..43ab47e0514aae89e19f8a562a822dec0c42184e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_resolution.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_scalar_compat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_scalar_compat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0bdcdefb0f3744fbe9a76c7c43c77191d955397b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_scalar_compat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_searchsorted.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_searchsorted.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7b8a05c094b24553195d76593f5867176a603f3e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_searchsorted.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..103b476ada118ec1d41b6d36a930b061b42dcbad Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_tools.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_tools.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..40ddaad3cd2558d5dc3432b10c413548b2e00967 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/__pycache__/test_tools.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..647a9618898211d2ef36a9fe823d7869cc936f9d Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_asfreq.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_asfreq.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8abbc20d53976d500d27bbabc0d82e77580e036b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_asfreq.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_astype.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_astype.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e83aaa08966c4b9ee34245c19299d0bbd7760c60 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_astype.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_factorize.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_factorize.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4a8b9f3e9ad98f415f24e4af3bdf218bb34d6aac Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_factorize.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_fillna.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_fillna.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d39be1fb03648a2a22e9780ecd83d476b57753f1 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_fillna.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_insert.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_insert.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..75894176ce5ae35fcc534dc88a2d2e27c8ecabfd Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_insert.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_is_full.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_is_full.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7771ba1cca6043b31b20ad1585a7cc6f6e9697bc Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_is_full.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_repeat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_repeat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9b12e2d2057a116a3ba54d1d1df1410044c38210 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_repeat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_shift.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_shift.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b7447afcb9fd14d78d00d36bd0376af9c3bc62d5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_shift.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_to_timestamp.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_to_timestamp.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..feca31c86906794333c1d846be9cb87cc47ff0d6 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/__pycache__/test_to_timestamp.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_asfreq.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_asfreq.py new file mode 100644 index 0000000000000000000000000000000000000000..865bae69d91c7960e286646e22d0fa2646333303 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_asfreq.py @@ -0,0 +1,189 @@ +import re + +import pytest + +from pandas import ( + PeriodIndex, + Series, + period_range, +) +import pandas._testing as tm + +from pandas.tseries import offsets + + +class TestPeriodIndex: + def test_asfreq(self): + pi1 = period_range(freq="Y", start="1/1/2001", end="1/1/2001") + pi2 = period_range(freq="Q", start="1/1/2001", end="1/1/2001") + pi3 = period_range(freq="M", start="1/1/2001", end="1/1/2001") + pi4 = period_range(freq="D", start="1/1/2001", end="1/1/2001") + pi5 = period_range(freq="h", start="1/1/2001", end="1/1/2001 00:00") + pi6 = period_range(freq="Min", start="1/1/2001", end="1/1/2001 00:00") + pi7 = period_range(freq="s", start="1/1/2001", end="1/1/2001 00:00:00") + + assert pi1.asfreq("Q", "s") == pi2 + assert pi1.asfreq("Q", "s") == pi2 + assert pi1.asfreq("M", "start") == pi3 + assert pi1.asfreq("D", "StarT") == pi4 + assert pi1.asfreq("h", "beGIN") == pi5 + assert pi1.asfreq("Min", "s") == pi6 + assert pi1.asfreq("s", "s") == pi7 + + assert pi2.asfreq("Y", "s") == pi1 + assert pi2.asfreq("M", "s") == pi3 + assert pi2.asfreq("D", "s") == pi4 + assert pi2.asfreq("h", "s") == pi5 + assert pi2.asfreq("Min", "s") == pi6 + assert pi2.asfreq("s", "s") == pi7 + + assert pi3.asfreq("Y", "s") == pi1 + assert pi3.asfreq("Q", "s") == pi2 + assert pi3.asfreq("D", "s") == pi4 + assert pi3.asfreq("h", "s") == pi5 + assert pi3.asfreq("Min", "s") == pi6 + assert pi3.asfreq("s", "s") == pi7 + + assert pi4.asfreq("Y", "s") == pi1 + assert pi4.asfreq("Q", "s") == pi2 + assert pi4.asfreq("M", "s") == pi3 + assert pi4.asfreq("h", "s") == pi5 + assert pi4.asfreq("Min", "s") == pi6 + assert pi4.asfreq("s", "s") == pi7 + + assert pi5.asfreq("Y", "s") == pi1 + assert pi5.asfreq("Q", "s") == pi2 + assert pi5.asfreq("M", "s") == pi3 + assert pi5.asfreq("D", "s") == pi4 + assert pi5.asfreq("Min", "s") == pi6 + assert pi5.asfreq("s", "s") == pi7 + + assert pi6.asfreq("Y", "s") == pi1 + assert pi6.asfreq("Q", "s") == pi2 + assert pi6.asfreq("M", "s") == pi3 + assert pi6.asfreq("D", "s") == pi4 + assert pi6.asfreq("h", "s") == pi5 + assert pi6.asfreq("s", "s") == pi7 + + assert pi7.asfreq("Y", "s") == pi1 + assert pi7.asfreq("Q", "s") == pi2 + assert pi7.asfreq("M", "s") == pi3 + assert pi7.asfreq("D", "s") == pi4 + assert pi7.asfreq("h", "s") == pi5 + assert pi7.asfreq("Min", "s") == pi6 + + msg = "How must be one of S or E" + with pytest.raises(ValueError, match=msg): + pi7.asfreq("T", "foo") + result1 = pi1.asfreq("3M") + result2 = pi1.asfreq("M") + expected = period_range(freq="M", start="2001-12", end="2001-12") + tm.assert_numpy_array_equal(result1.asi8, expected.asi8) + assert result1.freqstr == "3M" + tm.assert_numpy_array_equal(result2.asi8, expected.asi8) + assert result2.freqstr == "M" + + def test_asfreq_nat(self): + idx = PeriodIndex(["2011-01", "2011-02", "NaT", "2011-04"], freq="M") + result = idx.asfreq(freq="Q") + expected = PeriodIndex(["2011Q1", "2011Q1", "NaT", "2011Q2"], freq="Q") + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("freq", ["D", "3D"]) + def test_asfreq_mult_pi(self, freq): + pi = PeriodIndex(["2001-01", "2001-02", "NaT", "2001-03"], freq="2M") + + result = pi.asfreq(freq) + exp = PeriodIndex(["2001-02-28", "2001-03-31", "NaT", "2001-04-30"], freq=freq) + tm.assert_index_equal(result, exp) + assert result.freq == exp.freq + + result = pi.asfreq(freq, how="S") + exp = PeriodIndex(["2001-01-01", "2001-02-01", "NaT", "2001-03-01"], freq=freq) + tm.assert_index_equal(result, exp) + assert result.freq == exp.freq + + def test_asfreq_combined_pi(self): + pi = PeriodIndex(["2001-01-01 00:00", "2001-01-02 02:00", "NaT"], freq="h") + exp = PeriodIndex(["2001-01-01 00:00", "2001-01-02 02:00", "NaT"], freq="25h") + for freq, how in zip(["1D1h", "1h1D"], ["S", "E"]): + result = pi.asfreq(freq, how=how) + tm.assert_index_equal(result, exp) + assert result.freq == exp.freq + + for freq in ["1D1h", "1h1D"]: + pi = PeriodIndex(["2001-01-01 00:00", "2001-01-02 02:00", "NaT"], freq=freq) + result = pi.asfreq("h") + exp = PeriodIndex(["2001-01-02 00:00", "2001-01-03 02:00", "NaT"], freq="h") + tm.assert_index_equal(result, exp) + assert result.freq == exp.freq + + pi = PeriodIndex(["2001-01-01 00:00", "2001-01-02 02:00", "NaT"], freq=freq) + result = pi.asfreq("h", how="S") + exp = PeriodIndex(["2001-01-01 00:00", "2001-01-02 02:00", "NaT"], freq="h") + tm.assert_index_equal(result, exp) + assert result.freq == exp.freq + + def test_astype_asfreq(self): + pi1 = PeriodIndex(["2011-01-01", "2011-02-01", "2011-03-01"], freq="D") + exp = PeriodIndex(["2011-01", "2011-02", "2011-03"], freq="M") + tm.assert_index_equal(pi1.asfreq("M"), exp) + tm.assert_index_equal(pi1.astype("period[M]"), exp) + + exp = PeriodIndex(["2011-01", "2011-02", "2011-03"], freq="3M") + tm.assert_index_equal(pi1.asfreq("3M"), exp) + tm.assert_index_equal(pi1.astype("period[3M]"), exp) + + def test_asfreq_with_different_n(self): + ser = Series([1, 2], index=PeriodIndex(["2020-01", "2020-03"], freq="2M")) + result = ser.asfreq("M") + + excepted = Series([1, 2], index=PeriodIndex(["2020-02", "2020-04"], freq="M")) + tm.assert_series_equal(result, excepted) + + @pytest.mark.parametrize( + "freq", + [ + "2BMS", + "2YS-MAR", + "2bh", + ], + ) + def test_pi_asfreq_not_supported_frequency(self, freq): + # GH#55785 + msg = f"{freq[1:]} is not supported as period frequency" + + pi = PeriodIndex(["2020-01-01", "2021-01-01"], freq="M") + with pytest.raises(ValueError, match=msg): + pi.asfreq(freq=freq) + + @pytest.mark.parametrize( + "freq", + [ + "2BME", + "2YE-MAR", + "2QE", + ], + ) + def test_pi_asfreq_invalid_frequency(self, freq): + # GH#55785 + msg = f"Invalid frequency: {freq}" + + pi = PeriodIndex(["2020-01-01", "2021-01-01"], freq="M") + with pytest.raises(ValueError, match=msg): + pi.asfreq(freq=freq) + + @pytest.mark.parametrize( + "freq", + [ + offsets.MonthBegin(2), + offsets.BusinessMonthEnd(2), + ], + ) + def test_pi_asfreq_invalid_baseoffset(self, freq): + # GH#56945 + msg = re.escape(f"{freq} is not supported as period frequency") + + pi = PeriodIndex(["2020-01-01", "2021-01-01"], freq="M") + with pytest.raises(ValueError, match=msg): + pi.asfreq(freq=freq) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_astype.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_astype.py new file mode 100644 index 0000000000000000000000000000000000000000..d545bfd2fae0f7034c8cb62a8955c8b3c0ba0d6d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_astype.py @@ -0,0 +1,151 @@ +import numpy as np +import pytest + +from pandas import ( + CategoricalIndex, + DatetimeIndex, + Index, + NaT, + Period, + PeriodIndex, + period_range, +) +import pandas._testing as tm + + +class TestPeriodIndexAsType: + @pytest.mark.parametrize("dtype", [float, "timedelta64", "timedelta64[ns]"]) + def test_astype_raises(self, dtype): + # GH#13149, GH#13209 + idx = PeriodIndex(["2016-05-16", "NaT", NaT, np.nan], freq="D") + msg = "Cannot cast PeriodIndex to dtype" + with pytest.raises(TypeError, match=msg): + idx.astype(dtype) + + def test_astype_conversion(self): + # GH#13149, GH#13209 + idx = PeriodIndex(["2016-05-16", "NaT", NaT, np.nan], freq="D", name="idx") + + result = idx.astype(object) + expected = Index( + [Period("2016-05-16", freq="D")] + [Period(NaT, freq="D")] * 3, + dtype="object", + name="idx", + ) + tm.assert_index_equal(result, expected) + + result = idx.astype(np.int64) + expected = Index( + [16937] + [-9223372036854775808] * 3, dtype=np.int64, name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.astype(str) + expected = Index([str(x) for x in idx], name="idx", dtype=object) + tm.assert_index_equal(result, expected) + + idx = period_range("1990", "2009", freq="Y", name="idx") + result = idx.astype("i8") + tm.assert_index_equal(result, Index(idx.asi8, name="idx")) + tm.assert_numpy_array_equal(result.values, idx.asi8) + + def test_astype_uint(self): + arr = period_range("2000", periods=2, name="idx") + + with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"): + arr.astype("uint64") + with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"): + arr.astype("uint32") + + def test_astype_object(self): + idx = PeriodIndex([], freq="M") + + exp = np.array([], dtype=object) + tm.assert_numpy_array_equal(idx.astype(object).values, exp) + tm.assert_numpy_array_equal(idx._mpl_repr(), exp) + + idx = PeriodIndex(["2011-01", NaT], freq="M") + + exp = np.array([Period("2011-01", freq="M"), NaT], dtype=object) + tm.assert_numpy_array_equal(idx.astype(object).values, exp) + tm.assert_numpy_array_equal(idx._mpl_repr(), exp) + + exp = np.array([Period("2011-01-01", freq="D"), NaT], dtype=object) + idx = PeriodIndex(["2011-01-01", NaT], freq="D") + tm.assert_numpy_array_equal(idx.astype(object).values, exp) + tm.assert_numpy_array_equal(idx._mpl_repr(), exp) + + # TODO: de-duplicate this version (from test_ops) with the one above + # (from test_period) + def test_astype_object2(self): + idx = period_range(start="2013-01-01", periods=4, freq="M", name="idx") + expected_list = [ + Period("2013-01-31", freq="M"), + Period("2013-02-28", freq="M"), + Period("2013-03-31", freq="M"), + Period("2013-04-30", freq="M"), + ] + expected = Index(expected_list, dtype=object, name="idx") + result = idx.astype(object) + assert isinstance(result, Index) + assert result.dtype == object + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert idx.tolist() == expected_list + + idx = PeriodIndex( + ["2013-01-01", "2013-01-02", "NaT", "2013-01-04"], freq="D", name="idx" + ) + expected_list = [ + Period("2013-01-01", freq="D"), + Period("2013-01-02", freq="D"), + Period("NaT", freq="D"), + Period("2013-01-04", freq="D"), + ] + expected = Index(expected_list, dtype=object, name="idx") + result = idx.astype(object) + assert isinstance(result, Index) + assert result.dtype == object + tm.assert_index_equal(result, expected) + for i in [0, 1, 3]: + assert result[i] == expected[i] + assert result[2] is NaT + assert result.name == expected.name + + result_list = idx.tolist() + for i in [0, 1, 3]: + assert result_list[i] == expected_list[i] + assert result_list[2] is NaT + + def test_astype_category(self): + obj = period_range("2000", periods=2, name="idx") + result = obj.astype("category") + expected = CategoricalIndex( + [Period("2000-01-01", freq="D"), Period("2000-01-02", freq="D")], name="idx" + ) + tm.assert_index_equal(result, expected) + + result = obj._data.astype("category") + expected = expected.values + tm.assert_categorical_equal(result, expected) + + def test_astype_array_fallback(self): + obj = period_range("2000", periods=2, name="idx") + result = obj.astype(bool) + expected = Index(np.array([True, True]), name="idx") + tm.assert_index_equal(result, expected) + + result = obj._data.astype(bool) + expected = np.array([True, True]) + tm.assert_numpy_array_equal(result, expected) + + def test_period_astype_to_timestamp(self, unit): + # GH#55958 + pi = PeriodIndex(["2011-01", "2011-02", "2011-03"], freq="M") + + exp = DatetimeIndex( + ["2011-01-01", "2011-02-01", "2011-03-01"], tz="US/Eastern" + ).as_unit(unit) + res = pi.astype(f"datetime64[{unit}, US/Eastern]") + tm.assert_index_equal(res, exp) + assert res.freq == exp.freq diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_factorize.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_factorize.py new file mode 100644 index 0000000000000000000000000000000000000000..1239eae6091b81dfcc1ac049996296f6af565df8 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_factorize.py @@ -0,0 +1,41 @@ +import numpy as np + +from pandas import PeriodIndex +import pandas._testing as tm + + +class TestFactorize: + def test_factorize_period(self): + idx1 = PeriodIndex( + ["2014-01", "2014-01", "2014-02", "2014-02", "2014-03", "2014-03"], + freq="M", + ) + + exp_arr = np.array([0, 0, 1, 1, 2, 2], dtype=np.intp) + exp_idx = PeriodIndex(["2014-01", "2014-02", "2014-03"], freq="M") + + arr, idx = idx1.factorize() + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) + + arr, idx = idx1.factorize(sort=True) + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) + + def test_factorize_period_nonmonotonic(self): + idx2 = PeriodIndex( + ["2014-03", "2014-03", "2014-02", "2014-01", "2014-03", "2014-01"], + freq="M", + ) + exp_idx = PeriodIndex(["2014-01", "2014-02", "2014-03"], freq="M") + + exp_arr = np.array([2, 2, 1, 0, 2, 0], dtype=np.intp) + arr, idx = idx2.factorize(sort=True) + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) + + exp_arr = np.array([0, 0, 1, 2, 0, 2], dtype=np.intp) + exp_idx = PeriodIndex(["2014-03", "2014-02", "2014-01"], freq="M") + arr, idx = idx2.factorize() + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_fillna.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_fillna.py new file mode 100644 index 0000000000000000000000000000000000000000..ed6b4686a06defdc3eac4e1f6427fb0569c2d48d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_fillna.py @@ -0,0 +1,41 @@ +from pandas import ( + Index, + NaT, + Period, + PeriodIndex, +) +import pandas._testing as tm + + +class TestFillNA: + def test_fillna_period(self): + # GH#11343 + idx = PeriodIndex(["2011-01-01 09:00", NaT, "2011-01-01 11:00"], freq="h") + + exp = PeriodIndex( + ["2011-01-01 09:00", "2011-01-01 10:00", "2011-01-01 11:00"], freq="h" + ) + result = idx.fillna(Period("2011-01-01 10:00", freq="h")) + tm.assert_index_equal(result, exp) + + exp = Index( + [ + Period("2011-01-01 09:00", freq="h"), + "x", + Period("2011-01-01 11:00", freq="h"), + ], + dtype=object, + ) + result = idx.fillna("x") + tm.assert_index_equal(result, exp) + + exp = Index( + [ + Period("2011-01-01 09:00", freq="h"), + Period("2011-01-01", freq="D"), + Period("2011-01-01 11:00", freq="h"), + ], + dtype=object, + ) + result = idx.fillna(Period("2011-01-01", freq="D")) + tm.assert_index_equal(result, exp) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_insert.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_insert.py new file mode 100644 index 0000000000000000000000000000000000000000..32bbe09d925679579c1ec015b435870d1282e6b3 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_insert.py @@ -0,0 +1,18 @@ +import numpy as np +import pytest + +from pandas import ( + NaT, + PeriodIndex, + period_range, +) +import pandas._testing as tm + + +class TestInsert: + @pytest.mark.parametrize("na", [np.nan, NaT, None]) + def test_insert(self, na): + # GH#18295 (test missing) + expected = PeriodIndex(["2017Q1", NaT, "2017Q2", "2017Q3", "2017Q4"], freq="Q") + result = period_range("2017Q1", periods=4, freq="Q").insert(1, na) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_is_full.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_is_full.py new file mode 100644 index 0000000000000000000000000000000000000000..b4105bedbe21d6dc85379f1a6eefb298db954056 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_is_full.py @@ -0,0 +1,23 @@ +import pytest + +from pandas import PeriodIndex + + +def test_is_full(): + index = PeriodIndex([2005, 2007, 2009], freq="Y") + assert not index.is_full + + index = PeriodIndex([2005, 2006, 2007], freq="Y") + assert index.is_full + + index = PeriodIndex([2005, 2005, 2007], freq="Y") + assert not index.is_full + + index = PeriodIndex([2005, 2005, 2006], freq="Y") + assert index.is_full + + index = PeriodIndex([2006, 2005, 2005], freq="Y") + with pytest.raises(ValueError, match="Index is not monotonic"): + index.is_full + + assert index[:0].is_full diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_repeat.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_repeat.py new file mode 100644 index 0000000000000000000000000000000000000000..fc344b06420d16a436c84a70f45a292cf6045856 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_repeat.py @@ -0,0 +1,26 @@ +import numpy as np +import pytest + +from pandas import ( + PeriodIndex, + period_range, +) +import pandas._testing as tm + + +class TestRepeat: + @pytest.mark.parametrize("use_numpy", [True, False]) + @pytest.mark.parametrize( + "index", + [ + period_range("2000-01-01", periods=3, freq="D"), + period_range("2001-01-01", periods=3, freq="2D"), + PeriodIndex(["2001-01", "NaT", "2003-01"], freq="M"), + ], + ) + def test_repeat_freqstr(self, index, use_numpy): + # GH#10183 + expected = PeriodIndex([per for per in index for _ in range(3)]) + result = np.repeat(index, 3) if use_numpy else index.repeat(3) + tm.assert_index_equal(result, expected) + assert result.freqstr == index.freqstr diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_shift.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_shift.py new file mode 100644 index 0000000000000000000000000000000000000000..fca3e3a559e1fe2e53571f5af919e9a0c49c4e68 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_shift.py @@ -0,0 +1,122 @@ +import numpy as np +import pytest + +from pandas import ( + PeriodIndex, + period_range, +) +import pandas._testing as tm + + +class TestPeriodIndexShift: + # --------------------------------------------------------------- + # PeriodIndex.shift is used by __add__ and __sub__ + + def test_pi_shift_ndarray(self): + idx = PeriodIndex( + ["2011-01", "2011-02", "NaT", "2011-04"], freq="M", name="idx" + ) + result = idx.shift(np.array([1, 2, 3, 4])) + expected = PeriodIndex( + ["2011-02", "2011-04", "NaT", "2011-08"], freq="M", name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.shift(np.array([1, -2, 3, -4])) + expected = PeriodIndex( + ["2011-02", "2010-12", "NaT", "2010-12"], freq="M", name="idx" + ) + tm.assert_index_equal(result, expected) + + def test_shift(self): + pi1 = period_range(freq="Y", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="Y", start="1/1/2002", end="12/1/2010") + + tm.assert_index_equal(pi1.shift(0), pi1) + + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(1), pi2) + + pi1 = period_range(freq="Y", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="Y", start="1/1/2000", end="12/1/2008") + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(-1), pi2) + + pi1 = period_range(freq="M", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="M", start="2/1/2001", end="1/1/2010") + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(1), pi2) + + pi1 = period_range(freq="M", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="M", start="12/1/2000", end="11/1/2009") + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(-1), pi2) + + pi1 = period_range(freq="D", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="D", start="1/2/2001", end="12/2/2009") + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(1), pi2) + + pi1 = period_range(freq="D", start="1/1/2001", end="12/1/2009") + pi2 = period_range(freq="D", start="12/31/2000", end="11/30/2009") + assert len(pi1) == len(pi2) + tm.assert_index_equal(pi1.shift(-1), pi2) + + def test_shift_corner_cases(self): + # GH#9903 + idx = PeriodIndex([], name="xxx", freq="h") + + msg = "`freq` argument is not supported for PeriodIndex.shift" + with pytest.raises(TypeError, match=msg): + # period shift doesn't accept freq + idx.shift(1, freq="h") + + tm.assert_index_equal(idx.shift(0), idx) + tm.assert_index_equal(idx.shift(3), idx) + + idx = PeriodIndex( + ["2011-01-01 10:00", "2011-01-01 11:00", "2011-01-01 12:00"], + name="xxx", + freq="h", + ) + tm.assert_index_equal(idx.shift(0), idx) + exp = PeriodIndex( + ["2011-01-01 13:00", "2011-01-01 14:00", "2011-01-01 15:00"], + name="xxx", + freq="h", + ) + tm.assert_index_equal(idx.shift(3), exp) + exp = PeriodIndex( + ["2011-01-01 07:00", "2011-01-01 08:00", "2011-01-01 09:00"], + name="xxx", + freq="h", + ) + tm.assert_index_equal(idx.shift(-3), exp) + + def test_shift_nat(self): + idx = PeriodIndex( + ["2011-01", "2011-02", "NaT", "2011-04"], freq="M", name="idx" + ) + result = idx.shift(1) + expected = PeriodIndex( + ["2011-02", "2011-03", "NaT", "2011-05"], freq="M", name="idx" + ) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + + def test_shift_gh8083(self): + # test shift for PeriodIndex + # GH#8083 + drange = period_range("20130101", periods=5, freq="D") + result = drange.shift(1) + expected = PeriodIndex( + ["2013-01-02", "2013-01-03", "2013-01-04", "2013-01-05", "2013-01-06"], + freq="D", + ) + tm.assert_index_equal(result, expected) + + def test_shift_periods(self): + # GH #22458 : argument 'n' was deprecated in favor of 'periods' + idx = period_range(freq="Y", start="1/1/2001", end="12/1/2009") + tm.assert_index_equal(idx.shift(periods=0), idx) + tm.assert_index_equal(idx.shift(0), idx) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_to_timestamp.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_to_timestamp.py new file mode 100644 index 0000000000000000000000000000000000000000..3867f9e3245dc10a90ab4fcb1458b861ee7e2f86 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/methods/test_to_timestamp.py @@ -0,0 +1,142 @@ +from datetime import datetime + +import numpy as np +import pytest + +from pandas import ( + DatetimeIndex, + NaT, + PeriodIndex, + Timedelta, + Timestamp, + date_range, + period_range, +) +import pandas._testing as tm + + +class TestToTimestamp: + def test_to_timestamp_non_contiguous(self): + # GH#44100 + dti = date_range("2021-10-18", periods=9, freq="D") + pi = dti.to_period() + + result = pi[::2].to_timestamp() + expected = dti[::2] + tm.assert_index_equal(result, expected) + + result = pi._data[::2].to_timestamp() + expected = dti._data[::2] + # TODO: can we get the freq to round-trip? + tm.assert_datetime_array_equal(result, expected, check_freq=False) + + result = pi[::-1].to_timestamp() + expected = dti[::-1] + tm.assert_index_equal(result, expected) + + result = pi._data[::-1].to_timestamp() + expected = dti._data[::-1] + tm.assert_datetime_array_equal(result, expected, check_freq=False) + + result = pi[::2][::-1].to_timestamp() + expected = dti[::2][::-1] + tm.assert_index_equal(result, expected) + + result = pi._data[::2][::-1].to_timestamp() + expected = dti._data[::2][::-1] + tm.assert_datetime_array_equal(result, expected, check_freq=False) + + def test_to_timestamp_freq(self): + idx = period_range("2017", periods=12, freq="Y-DEC") + result = idx.to_timestamp() + expected = date_range("2017", periods=12, freq="YS-JAN") + tm.assert_index_equal(result, expected) + + def test_to_timestamp_pi_nat(self): + # GH#7228 + index = PeriodIndex(["NaT", "2011-01", "2011-02"], freq="M", name="idx") + + result = index.to_timestamp("D") + expected = DatetimeIndex( + [NaT, datetime(2011, 1, 1), datetime(2011, 2, 1)], + dtype="M8[ns]", + name="idx", + ) + tm.assert_index_equal(result, expected) + assert result.name == "idx" + + result2 = result.to_period(freq="M") + tm.assert_index_equal(result2, index) + assert result2.name == "idx" + + result3 = result.to_period(freq="3M") + exp = PeriodIndex(["NaT", "2011-01", "2011-02"], freq="3M", name="idx") + tm.assert_index_equal(result3, exp) + assert result3.freqstr == "3M" + + msg = "Frequency must be positive, because it represents span: -2Y" + with pytest.raises(ValueError, match=msg): + result.to_period(freq="-2Y") + + def test_to_timestamp_preserve_name(self): + index = period_range(freq="Y", start="1/1/2001", end="12/1/2009", name="foo") + assert index.name == "foo" + + conv = index.to_timestamp("D") + assert conv.name == "foo" + + def test_to_timestamp_quarterly_bug(self): + years = np.arange(1960, 2000).repeat(4) + quarters = np.tile(list(range(1, 5)), 40) + + pindex = PeriodIndex.from_fields(year=years, quarter=quarters) + + stamps = pindex.to_timestamp("D", "end") + expected = DatetimeIndex([x.to_timestamp("D", "end") for x in pindex]) + tm.assert_index_equal(stamps, expected) + assert stamps.freq == expected.freq + + def test_to_timestamp_pi_mult(self): + idx = PeriodIndex(["2011-01", "NaT", "2011-02"], freq="2M", name="idx") + + result = idx.to_timestamp() + expected = DatetimeIndex( + ["2011-01-01", "NaT", "2011-02-01"], dtype="M8[ns]", name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.to_timestamp(how="E") + expected = DatetimeIndex( + ["2011-02-28", "NaT", "2011-03-31"], dtype="M8[ns]", name="idx" + ) + expected = expected + Timedelta(1, "D") - Timedelta(1, "ns") + tm.assert_index_equal(result, expected) + + def test_to_timestamp_pi_combined(self): + idx = period_range(start="2011", periods=2, freq="1D1h", name="idx") + + result = idx.to_timestamp() + expected = DatetimeIndex( + ["2011-01-01 00:00", "2011-01-02 01:00"], dtype="M8[ns]", name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.to_timestamp(how="E") + expected = DatetimeIndex( + ["2011-01-02 00:59:59", "2011-01-03 01:59:59"], name="idx", dtype="M8[ns]" + ) + expected = expected + Timedelta(1, "s") - Timedelta(1, "ns") + tm.assert_index_equal(result, expected) + + result = idx.to_timestamp(how="E", freq="h") + expected = DatetimeIndex( + ["2011-01-02 00:00", "2011-01-03 01:00"], dtype="M8[ns]", name="idx" + ) + expected = expected + Timedelta(1, "h") - Timedelta(1, "ns") + tm.assert_index_equal(result, expected) + + def test_to_timestamp_1703(self): + index = period_range("1/1/2012", periods=4, freq="D") + + result = index.to_timestamp() + assert result[0] == Timestamp("1/1/2012") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..892eb7b4a00d1ffbd9477194466bf9f2a2c522ff --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_constructors.py @@ -0,0 +1,691 @@ +import numpy as np +import pytest + +from pandas._libs.tslibs.period import IncompatibleFrequency + +from pandas.core.dtypes.dtypes import PeriodDtype + +from pandas import ( + Index, + NaT, + Period, + PeriodIndex, + Series, + date_range, + offsets, + period_range, +) +import pandas._testing as tm +from pandas.core.arrays import PeriodArray + + +class TestPeriodIndexDisallowedFreqs: + @pytest.mark.parametrize( + "freq,freq_depr", + [ + ("2M", "2ME"), + ("2Q-MAR", "2QE-MAR"), + ("2Y-FEB", "2YE-FEB"), + ("2M", "2me"), + ("2Q-MAR", "2qe-MAR"), + ("2Y-FEB", "2yE-feb"), + ], + ) + def test_period_index_offsets_frequency_error_message(self, freq, freq_depr): + # GH#52064 + msg = f"for Period, please use '{freq[1:]}' instead of '{freq_depr[1:]}'" + + with pytest.raises(ValueError, match=msg): + PeriodIndex(["2020-01-01", "2020-01-02"], freq=freq_depr) + + with pytest.raises(ValueError, match=msg): + period_range(start="2020-01-01", end="2020-01-02", freq=freq_depr) + + @pytest.mark.parametrize("freq_depr", ["2SME", "2sme", "2CBME", "2BYE", "2Bye"]) + def test_period_index_frequency_invalid_freq(self, freq_depr): + # GH#9586 + msg = f"Invalid frequency: {freq_depr[1:]}" + + with pytest.raises(ValueError, match=msg): + period_range("2020-01", "2020-05", freq=freq_depr) + with pytest.raises(ValueError, match=msg): + PeriodIndex(["2020-01", "2020-05"], freq=freq_depr) + + @pytest.mark.parametrize("freq", ["2BQE-SEP", "2BYE-MAR", "2BME"]) + def test_period_index_from_datetime_index_invalid_freq(self, freq): + # GH#56899 + msg = f"Invalid frequency: {freq[1:]}" + + rng = date_range("01-Jan-2012", periods=8, freq=freq) + with pytest.raises(ValueError, match=msg): + rng.to_period() + + +class TestPeriodIndex: + def test_from_ordinals(self): + Period(ordinal=-1000, freq="Y") + Period(ordinal=0, freq="Y") + + msg = "The 'ordinal' keyword in PeriodIndex is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + idx1 = PeriodIndex(ordinal=[-1, 0, 1], freq="Y") + with tm.assert_produces_warning(FutureWarning, match=msg): + idx2 = PeriodIndex(ordinal=np.array([-1, 0, 1]), freq="Y") + tm.assert_index_equal(idx1, idx2) + + alt1 = PeriodIndex.from_ordinals([-1, 0, 1], freq="Y") + tm.assert_index_equal(alt1, idx1) + + alt2 = PeriodIndex.from_ordinals(np.array([-1, 0, 1]), freq="Y") + tm.assert_index_equal(alt2, idx2) + + def test_keyword_mismatch(self): + # GH#55961 we should get exactly one of data/ordinals/**fields + per = Period("2016-01-01", "D") + depr_msg1 = "The 'ordinal' keyword in PeriodIndex is deprecated" + depr_msg2 = "Constructing PeriodIndex from fields is deprecated" + + err_msg1 = "Cannot pass both data and ordinal" + with pytest.raises(ValueError, match=err_msg1): + with tm.assert_produces_warning(FutureWarning, match=depr_msg1): + PeriodIndex(data=[per], ordinal=[per.ordinal], freq=per.freq) + + err_msg2 = "Cannot pass both data and fields" + with pytest.raises(ValueError, match=err_msg2): + with tm.assert_produces_warning(FutureWarning, match=depr_msg2): + PeriodIndex(data=[per], year=[per.year], freq=per.freq) + + err_msg3 = "Cannot pass both ordinal and fields" + with pytest.raises(ValueError, match=err_msg3): + with tm.assert_produces_warning(FutureWarning, match=depr_msg2): + PeriodIndex(ordinal=[per.ordinal], year=[per.year], freq=per.freq) + + def test_construction_base_constructor(self): + # GH 13664 + arr = [Period("2011-01", freq="M"), NaT, Period("2011-03", freq="M")] + tm.assert_index_equal(Index(arr), PeriodIndex(arr)) + tm.assert_index_equal(Index(np.array(arr)), PeriodIndex(np.array(arr))) + + arr = [np.nan, NaT, Period("2011-03", freq="M")] + tm.assert_index_equal(Index(arr), PeriodIndex(arr)) + tm.assert_index_equal(Index(np.array(arr)), PeriodIndex(np.array(arr))) + + arr = [Period("2011-01", freq="M"), NaT, Period("2011-03", freq="D")] + tm.assert_index_equal(Index(arr), Index(arr, dtype=object)) + + tm.assert_index_equal(Index(np.array(arr)), Index(np.array(arr), dtype=object)) + + def test_base_constructor_with_period_dtype(self): + dtype = PeriodDtype("D") + values = ["2011-01-01", "2012-03-04", "2014-05-01"] + result = Index(values, dtype=dtype) + + expected = PeriodIndex(values, dtype=dtype) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "values_constructor", [list, np.array, PeriodIndex, PeriodArray._from_sequence] + ) + def test_index_object_dtype(self, values_constructor): + # Index(periods, dtype=object) is an Index (not an PeriodIndex) + periods = [ + Period("2011-01", freq="M"), + NaT, + Period("2011-03", freq="M"), + ] + values = values_constructor(periods) + result = Index(values, dtype=object) + + assert type(result) is Index + tm.assert_numpy_array_equal(result.values, np.array(values)) + + def test_constructor_use_start_freq(self): + # GH #1118 + msg1 = "Period with BDay freq is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg1): + p = Period("4/2/2012", freq="B") + msg2 = r"PeriodDtype\[B\] is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg2): + expected = period_range(start="4/2/2012", periods=10, freq="B") + + with tm.assert_produces_warning(FutureWarning, match=msg2): + index = period_range(start=p, periods=10) + tm.assert_index_equal(index, expected) + + def test_constructor_field_arrays(self): + # GH #1264 + + years = np.arange(1990, 2010).repeat(4)[2:-2] + quarters = np.tile(np.arange(1, 5), 20)[2:-2] + + depr_msg = "Constructing PeriodIndex from fields is deprecated" + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + index = PeriodIndex(year=years, quarter=quarters, freq="Q-DEC") + expected = period_range("1990Q3", "2009Q2", freq="Q-DEC") + tm.assert_index_equal(index, expected) + + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + index2 = PeriodIndex(year=years, quarter=quarters, freq="2Q-DEC") + tm.assert_numpy_array_equal(index.asi8, index2.asi8) + + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + index = PeriodIndex(year=years, quarter=quarters) + tm.assert_index_equal(index, expected) + + years = [2007, 2007, 2007] + months = [1, 2] + + msg = "Mismatched Period array lengths" + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + PeriodIndex(year=years, month=months, freq="M") + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + PeriodIndex(year=years, month=months, freq="2M") + + years = [2007, 2007, 2007] + months = [1, 2, 3] + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + idx = PeriodIndex(year=years, month=months, freq="M") + exp = period_range("2007-01", periods=3, freq="M") + tm.assert_index_equal(idx, exp) + + def test_constructor_nano(self): + idx = period_range( + start=Period(ordinal=1, freq="ns"), + end=Period(ordinal=4, freq="ns"), + freq="ns", + ) + exp = PeriodIndex( + [ + Period(ordinal=1, freq="ns"), + Period(ordinal=2, freq="ns"), + Period(ordinal=3, freq="ns"), + Period(ordinal=4, freq="ns"), + ], + freq="ns", + ) + tm.assert_index_equal(idx, exp) + + def test_constructor_arrays_negative_year(self): + years = np.arange(1960, 2000, dtype=np.int64).repeat(4) + quarters = np.tile(np.array([1, 2, 3, 4], dtype=np.int64), 40) + + msg = "Constructing PeriodIndex from fields is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + pindex = PeriodIndex(year=years, quarter=quarters) + + tm.assert_index_equal(pindex.year, Index(years)) + tm.assert_index_equal(pindex.quarter, Index(quarters)) + + alt = PeriodIndex.from_fields(year=years, quarter=quarters) + tm.assert_index_equal(alt, pindex) + + def test_constructor_invalid_quarters(self): + depr_msg = "Constructing PeriodIndex from fields is deprecated" + msg = "Quarter must be 1 <= q <= 4" + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + PeriodIndex( + year=range(2000, 2004), quarter=list(range(4)), freq="Q-DEC" + ) + + def test_period_range_fractional_period(self): + msg = "Non-integer 'periods' in pd.date_range, pd.timedelta_range" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = period_range("2007-01", periods=10.5, freq="M") + exp = period_range("2007-01", periods=10, freq="M") + tm.assert_index_equal(result, exp) + + def test_constructor_with_without_freq(self): + # GH53687 + start = Period("2002-01-01 00:00", freq="30min") + exp = period_range(start=start, periods=5, freq=start.freq) + result = period_range(start=start, periods=5) + tm.assert_index_equal(exp, result) + + def test_constructor_fromarraylike(self): + idx = period_range("2007-01", periods=20, freq="M") + + # values is an array of Period, thus can retrieve freq + tm.assert_index_equal(PeriodIndex(idx.values), idx) + tm.assert_index_equal(PeriodIndex(list(idx.values)), idx) + + msg = "freq not specified and cannot be inferred" + with pytest.raises(ValueError, match=msg): + PeriodIndex(idx.asi8) + with pytest.raises(ValueError, match=msg): + PeriodIndex(list(idx.asi8)) + + msg = "'Period' object is not iterable" + with pytest.raises(TypeError, match=msg): + PeriodIndex(data=Period("2007", freq="Y")) + + result = PeriodIndex(iter(idx)) + tm.assert_index_equal(result, idx) + + result = PeriodIndex(idx) + tm.assert_index_equal(result, idx) + + result = PeriodIndex(idx, freq="M") + tm.assert_index_equal(result, idx) + + result = PeriodIndex(idx, freq=offsets.MonthEnd()) + tm.assert_index_equal(result, idx) + assert result.freq == "ME" + + result = PeriodIndex(idx, freq="2M") + tm.assert_index_equal(result, idx.asfreq("2M")) + assert result.freq == "2ME" + + result = PeriodIndex(idx, freq=offsets.MonthEnd(2)) + tm.assert_index_equal(result, idx.asfreq("2M")) + assert result.freq == "2ME" + + result = PeriodIndex(idx, freq="D") + exp = idx.asfreq("D", "e") + tm.assert_index_equal(result, exp) + + def test_constructor_datetime64arr(self): + vals = np.arange(100000, 100000 + 10000, 100, dtype=np.int64) + vals = vals.view(np.dtype("M8[us]")) + + pi = PeriodIndex(vals, freq="D") + + expected = PeriodIndex(vals.astype("M8[ns]"), freq="D") + tm.assert_index_equal(pi, expected) + + @pytest.mark.parametrize("box", [None, "series", "index"]) + def test_constructor_datetime64arr_ok(self, box): + # https://github.com/pandas-dev/pandas/issues/23438 + data = date_range("2017", periods=4, freq="ME") + if box is None: + data = data._values + elif box == "series": + data = Series(data) + + result = PeriodIndex(data, freq="D") + expected = PeriodIndex( + ["2017-01-31", "2017-02-28", "2017-03-31", "2017-04-30"], freq="D" + ) + tm.assert_index_equal(result, expected) + + def test_constructor_dtype(self): + # passing a dtype with a tz should localize + idx = PeriodIndex(["2013-01", "2013-03"], dtype="period[M]") + exp = PeriodIndex(["2013-01", "2013-03"], freq="M") + tm.assert_index_equal(idx, exp) + assert idx.dtype == "period[M]" + + idx = PeriodIndex(["2013-01-05", "2013-03-05"], dtype="period[3D]") + exp = PeriodIndex(["2013-01-05", "2013-03-05"], freq="3D") + tm.assert_index_equal(idx, exp) + assert idx.dtype == "period[3D]" + + # if we already have a freq and its not the same, then asfreq + # (not changed) + idx = PeriodIndex(["2013-01-01", "2013-01-02"], freq="D") + + res = PeriodIndex(idx, dtype="period[M]") + exp = PeriodIndex(["2013-01", "2013-01"], freq="M") + tm.assert_index_equal(res, exp) + assert res.dtype == "period[M]" + + res = PeriodIndex(idx, freq="M") + tm.assert_index_equal(res, exp) + assert res.dtype == "period[M]" + + msg = "specified freq and dtype are different" + with pytest.raises(IncompatibleFrequency, match=msg): + PeriodIndex(["2011-01"], freq="M", dtype="period[D]") + + def test_constructor_empty(self): + idx = PeriodIndex([], freq="M") + assert isinstance(idx, PeriodIndex) + assert len(idx) == 0 + assert idx.freq == "ME" + + with pytest.raises(ValueError, match="freq not specified"): + PeriodIndex([]) + + def test_constructor_pi_nat(self): + idx = PeriodIndex( + [Period("2011-01", freq="M"), NaT, Period("2011-01", freq="M")] + ) + exp = PeriodIndex(["2011-01", "NaT", "2011-01"], freq="M") + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex( + np.array([Period("2011-01", freq="M"), NaT, Period("2011-01", freq="M")]) + ) + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex( + [NaT, NaT, Period("2011-01", freq="M"), Period("2011-01", freq="M")] + ) + exp = PeriodIndex(["NaT", "NaT", "2011-01", "2011-01"], freq="M") + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex( + np.array( + [NaT, NaT, Period("2011-01", freq="M"), Period("2011-01", freq="M")] + ) + ) + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex([NaT, NaT, "2011-01", "2011-01"], freq="M") + tm.assert_index_equal(idx, exp) + + with pytest.raises(ValueError, match="freq not specified"): + PeriodIndex([NaT, NaT]) + + with pytest.raises(ValueError, match="freq not specified"): + PeriodIndex(np.array([NaT, NaT])) + + with pytest.raises(ValueError, match="freq not specified"): + PeriodIndex(["NaT", "NaT"]) + + with pytest.raises(ValueError, match="freq not specified"): + PeriodIndex(np.array(["NaT", "NaT"])) + + def test_constructor_incompat_freq(self): + msg = "Input has different freq=D from PeriodIndex\\(freq=M\\)" + + with pytest.raises(IncompatibleFrequency, match=msg): + PeriodIndex([Period("2011-01", freq="M"), NaT, Period("2011-01", freq="D")]) + + with pytest.raises(IncompatibleFrequency, match=msg): + PeriodIndex( + np.array( + [Period("2011-01", freq="M"), NaT, Period("2011-01", freq="D")] + ) + ) + + # first element is NaT + with pytest.raises(IncompatibleFrequency, match=msg): + PeriodIndex([NaT, Period("2011-01", freq="M"), Period("2011-01", freq="D")]) + + with pytest.raises(IncompatibleFrequency, match=msg): + PeriodIndex( + np.array( + [NaT, Period("2011-01", freq="M"), Period("2011-01", freq="D")] + ) + ) + + def test_constructor_mixed(self): + idx = PeriodIndex(["2011-01", NaT, Period("2011-01", freq="M")]) + exp = PeriodIndex(["2011-01", "NaT", "2011-01"], freq="M") + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex(["NaT", NaT, Period("2011-01", freq="M")]) + exp = PeriodIndex(["NaT", "NaT", "2011-01"], freq="M") + tm.assert_index_equal(idx, exp) + + idx = PeriodIndex([Period("2011-01-01", freq="D"), NaT, "2012-01-01"]) + exp = PeriodIndex(["2011-01-01", "NaT", "2012-01-01"], freq="D") + tm.assert_index_equal(idx, exp) + + @pytest.mark.parametrize("floats", [[1.1, 2.1], np.array([1.1, 2.1])]) + def test_constructor_floats(self, floats): + msg = "PeriodIndex does not allow floating point in construction" + with pytest.raises(TypeError, match=msg): + PeriodIndex(floats) + + def test_constructor_year_and_quarter(self): + year = Series([2001, 2002, 2003]) + quarter = year - 2000 + msg = "Constructing PeriodIndex from fields is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + idx = PeriodIndex(year=year, quarter=quarter) + strs = [f"{t[0]:d}Q{t[1]:d}" for t in zip(quarter, year)] + lops = list(map(Period, strs)) + p = PeriodIndex(lops) + tm.assert_index_equal(p, idx) + + def test_constructor_freq_mult(self): + # GH #7811 + pidx = period_range(start="2014-01", freq="2M", periods=4) + expected = PeriodIndex(["2014-01", "2014-03", "2014-05", "2014-07"], freq="2M") + tm.assert_index_equal(pidx, expected) + + pidx = period_range(start="2014-01-02", end="2014-01-15", freq="3D") + expected = PeriodIndex( + ["2014-01-02", "2014-01-05", "2014-01-08", "2014-01-11", "2014-01-14"], + freq="3D", + ) + tm.assert_index_equal(pidx, expected) + + pidx = period_range(end="2014-01-01 17:00", freq="4h", periods=3) + expected = PeriodIndex( + ["2014-01-01 09:00", "2014-01-01 13:00", "2014-01-01 17:00"], freq="4h" + ) + tm.assert_index_equal(pidx, expected) + + msg = "Frequency must be positive, because it represents span: -1M" + with pytest.raises(ValueError, match=msg): + PeriodIndex(["2011-01"], freq="-1M") + + msg = "Frequency must be positive, because it represents span: 0M" + with pytest.raises(ValueError, match=msg): + PeriodIndex(["2011-01"], freq="0M") + + msg = "Frequency must be positive, because it represents span: 0M" + with pytest.raises(ValueError, match=msg): + period_range("2011-01", periods=3, freq="0M") + + @pytest.mark.parametrize( + "freq_offset, freq_period", + [ + ("YE", "Y"), + ("ME", "M"), + ("D", "D"), + ("min", "min"), + ("s", "s"), + ], + ) + @pytest.mark.parametrize("mult", [1, 2, 3, 4, 5]) + def test_constructor_freq_mult_dti_compat(self, mult, freq_offset, freq_period): + freqstr_offset = str(mult) + freq_offset + freqstr_period = str(mult) + freq_period + pidx = period_range(start="2014-04-01", freq=freqstr_period, periods=10) + expected = date_range( + start="2014-04-01", freq=freqstr_offset, periods=10 + ).to_period(freqstr_period) + tm.assert_index_equal(pidx, expected) + + @pytest.mark.parametrize("mult", [1, 2, 3, 4, 5]) + def test_constructor_freq_mult_dti_compat_month(self, mult): + pidx = period_range(start="2014-04-01", freq=f"{mult}M", periods=10) + expected = date_range( + start="2014-04-01", freq=f"{mult}ME", periods=10 + ).to_period(f"{mult}M") + tm.assert_index_equal(pidx, expected) + + def test_constructor_freq_combined(self): + for freq in ["1D1h", "1h1D"]: + pidx = PeriodIndex(["2016-01-01", "2016-01-02"], freq=freq) + expected = PeriodIndex(["2016-01-01 00:00", "2016-01-02 00:00"], freq="25h") + for freq in ["1D1h", "1h1D"]: + pidx = period_range(start="2016-01-01", periods=2, freq=freq) + expected = PeriodIndex(["2016-01-01 00:00", "2016-01-02 01:00"], freq="25h") + tm.assert_index_equal(pidx, expected) + + def test_period_range_length(self): + pi = period_range(freq="Y", start="1/1/2001", end="12/1/2009") + assert len(pi) == 9 + + pi = period_range(freq="Q", start="1/1/2001", end="12/1/2009") + assert len(pi) == 4 * 9 + + pi = period_range(freq="M", start="1/1/2001", end="12/1/2009") + assert len(pi) == 12 * 9 + + pi = period_range(freq="D", start="1/1/2001", end="12/31/2009") + assert len(pi) == 365 * 9 + 2 + + msg = "Period with BDay freq is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + pi = period_range(freq="B", start="1/1/2001", end="12/31/2009") + assert len(pi) == 261 * 9 + + pi = period_range(freq="h", start="1/1/2001", end="12/31/2001 23:00") + assert len(pi) == 365 * 24 + + pi = period_range(freq="Min", start="1/1/2001", end="1/1/2001 23:59") + assert len(pi) == 24 * 60 + + pi = period_range(freq="s", start="1/1/2001", end="1/1/2001 23:59:59") + assert len(pi) == 24 * 60 * 60 + + with tm.assert_produces_warning(FutureWarning, match=msg): + start = Period("02-Apr-2005", "B") + i1 = period_range(start=start, periods=20) + assert len(i1) == 20 + assert i1.freq == start.freq + assert i1[0] == start + + end_intv = Period("2006-12-31", "W") + i1 = period_range(end=end_intv, periods=10) + assert len(i1) == 10 + assert i1.freq == end_intv.freq + assert i1[-1] == end_intv + + msg = "'w' is deprecated and will be removed in a future version." + with tm.assert_produces_warning(FutureWarning, match=msg): + end_intv = Period("2006-12-31", "1w") + i2 = period_range(end=end_intv, periods=10) + assert len(i1) == len(i2) + assert (i1 == i2).all() + assert i1.freq == i2.freq + + def test_infer_freq_from_first_element(self): + msg = "Period with BDay freq is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + start = Period("02-Apr-2005", "B") + end_intv = Period("2005-05-01", "B") + period_range(start=start, end=end_intv) + + # infer freq from first element + i2 = PeriodIndex([end_intv, Period("2005-05-05", "B")]) + assert len(i2) == 2 + assert i2[0] == end_intv + + with tm.assert_produces_warning(FutureWarning, match=msg): + i2 = PeriodIndex(np.array([end_intv, Period("2005-05-05", "B")])) + assert len(i2) == 2 + assert i2[0] == end_intv + + def test_mixed_freq_raises(self): + # Mixed freq should fail + msg = "Period with BDay freq is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + end_intv = Period("2005-05-01", "B") + + msg = "'w' is deprecated and will be removed in a future version." + with tm.assert_produces_warning(FutureWarning, match=msg): + vals = [end_intv, Period("2006-12-31", "w")] + msg = r"Input has different freq=W-SUN from PeriodIndex\(freq=B\)" + depr_msg = r"PeriodDtype\[B\] is deprecated" + with pytest.raises(IncompatibleFrequency, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + PeriodIndex(vals) + vals = np.array(vals) + with pytest.raises(IncompatibleFrequency, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + PeriodIndex(vals) + + @pytest.mark.parametrize( + "freq", ["M", "Q", "Y", "D", "B", "min", "s", "ms", "us", "ns", "h"] + ) + @pytest.mark.filterwarnings( + r"ignore:Period with BDay freq is deprecated:FutureWarning" + ) + @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") + def test_recreate_from_data(self, freq): + org = period_range(start="2001/04/01", freq=freq, periods=1) + idx = PeriodIndex(org.values, freq=freq) + tm.assert_index_equal(idx, org) + + def test_map_with_string_constructor(self): + raw = [2005, 2007, 2009] + index = PeriodIndex(raw, freq="Y") + + expected = Index([str(num) for num in raw]) + res = index.map(str) + + # should return an Index + assert isinstance(res, Index) + + # preserve element types + assert all(isinstance(resi, str) for resi in res) + + # lastly, values should compare equal + tm.assert_index_equal(res, expected) + + +class TestSimpleNew: + def test_constructor_simple_new(self): + idx = period_range("2007-01", name="p", periods=2, freq="M") + + with pytest.raises(AssertionError, match=""): + idx._simple_new(idx, name="p") + + result = idx._simple_new(idx._data, name="p") + tm.assert_index_equal(result, idx) + + msg = "Should be numpy array of type i8" + with pytest.raises(AssertionError, match=msg): + # Need ndarray, not int64 Index + type(idx._data)._simple_new(Index(idx.asi8), dtype=idx.dtype) + + arr = type(idx._data)._simple_new(idx.asi8, dtype=idx.dtype) + result = idx._simple_new(arr, name="p") + tm.assert_index_equal(result, idx) + + def test_constructor_simple_new_empty(self): + # GH13079 + idx = PeriodIndex([], freq="M", name="p") + with pytest.raises(AssertionError, match=""): + idx._simple_new(idx, name="p") + + result = idx._simple_new(idx._data, name="p") + tm.assert_index_equal(result, idx) + + @pytest.mark.parametrize("floats", [[1.1, 2.1], np.array([1.1, 2.1])]) + def test_period_index_simple_new_disallows_floats(self, floats): + with pytest.raises(AssertionError, match="= -1" + ) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + msg = "index -5 is out of bounds for( axis 0 with)? size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) + + +class TestGetValue: + @pytest.mark.parametrize("freq", ["h", "D"]) + def test_get_value_datetime_hourly(self, freq): + # get_loc and get_value should treat datetime objects symmetrically + # TODO: this test used to test get_value, which is removed in 2.0. + # should this test be moved somewhere, or is what's left redundant? + dti = date_range("2016-01-01", periods=3, freq="MS") + pi = dti.to_period(freq) + ser = Series(range(7, 10), index=pi) + + ts = dti[0] + + assert pi.get_loc(ts) == 0 + assert ser[ts] == 7 + assert ser.loc[ts] == 7 + + ts2 = ts + Timedelta(hours=3) + if freq == "h": + with pytest.raises(KeyError, match="2016-01-01 03:00"): + pi.get_loc(ts2) + with pytest.raises(KeyError, match="2016-01-01 03:00"): + ser[ts2] + with pytest.raises(KeyError, match="2016-01-01 03:00"): + ser.loc[ts2] + else: + assert pi.get_loc(ts2) == 0 + assert ser[ts2] == 7 + assert ser.loc[ts2] == 7 + + +class TestContains: + def test_contains(self): + # GH 17717 + p0 = Period("2017-09-01") + p1 = Period("2017-09-02") + p2 = Period("2017-09-03") + p3 = Period("2017-09-04") + + ps0 = [p0, p1, p2] + idx0 = PeriodIndex(ps0) + + for p in ps0: + assert p in idx0 + assert str(p) in idx0 + + # GH#31172 + # Higher-resolution period-like are _not_ considered as contained + key = "2017-09-01 00:00:01" + assert key not in idx0 + with pytest.raises(KeyError, match=key): + idx0.get_loc(key) + + assert "2017-09" in idx0 + + assert p3 not in idx0 + + def test_contains_freq_mismatch(self): + rng = period_range("2007-01", freq="M", periods=10) + + assert Period("2007-01", freq="M") in rng + assert Period("2007-01", freq="D") not in rng + assert Period("2007-01", freq="2M") not in rng + + def test_contains_nat(self): + # see gh-13582 + idx = period_range("2007-01", freq="M", periods=10) + assert NaT not in idx + assert None not in idx + assert float("nan") not in idx + assert np.nan not in idx + + idx = PeriodIndex(["2011-01", "NaT", "2011-02"], freq="M") + assert NaT in idx + assert None in idx + assert float("nan") in idx + assert np.nan in idx + + +class TestAsOfLocs: + def test_asof_locs_mismatched_type(self): + dti = date_range("2016-01-01", periods=3) + pi = dti.to_period("D") + pi2 = dti.to_period("h") + + mask = np.array([0, 1, 0], dtype=bool) + + msg = "must be DatetimeIndex or PeriodIndex" + with pytest.raises(TypeError, match=msg): + pi.asof_locs(pd.Index(pi.asi8, dtype=np.int64), mask) + + with pytest.raises(TypeError, match=msg): + pi.asof_locs(pd.Index(pi.asi8, dtype=np.float64), mask) + + with pytest.raises(TypeError, match=msg): + # TimedeltaIndex + pi.asof_locs(dti - dti, mask) + + msg = "Input has different freq=h" + with pytest.raises(libperiod.IncompatibleFrequency, match=msg): + pi.asof_locs(pi2, mask) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_join.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_join.py new file mode 100644 index 0000000000000000000000000000000000000000..3e659c1a632669c2b89d7ea0411de5c4c35108ad --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_join.py @@ -0,0 +1,58 @@ +import numpy as np +import pytest + +from pandas._libs.tslibs import IncompatibleFrequency + +from pandas import ( + DataFrame, + Index, + PeriodIndex, + date_range, + period_range, +) +import pandas._testing as tm + + +class TestJoin: + def test_join_outer_indexer(self): + pi = period_range("1/1/2000", "1/20/2000", freq="D") + + result = pi._outer_indexer(pi) + tm.assert_extension_array_equal(result[0], pi._values) + tm.assert_numpy_array_equal(result[1], np.arange(len(pi), dtype=np.intp)) + tm.assert_numpy_array_equal(result[2], np.arange(len(pi), dtype=np.intp)) + + def test_joins(self, join_type): + index = period_range("1/1/2000", "1/20/2000", freq="D") + + joined = index.join(index[:-5], how=join_type) + + assert isinstance(joined, PeriodIndex) + assert joined.freq == index.freq + + def test_join_self(self, join_type): + index = period_range("1/1/2000", "1/20/2000", freq="D") + + res = index.join(index, how=join_type) + assert index is res + + def test_join_does_not_recur(self): + df = DataFrame( + np.ones((3, 2)), + index=date_range("2020-01-01", periods=3), + columns=period_range("2020-01-01", periods=2), + ) + ser = df.iloc[:2, 0] + + res = ser.index.join(df.columns, how="outer") + expected = Index( + [ser.index[0], ser.index[1], df.columns[0], df.columns[1]], object + ) + tm.assert_index_equal(res, expected) + + def test_join_mismatched_freq_raises(self): + index = period_range("1/1/2000", "1/20/2000", freq="D") + index3 = period_range("1/1/2000", "1/20/2000", freq="2D") + msg = r".*Input has different freq=2D from Period\(freq=D\)" + with pytest.raises(IncompatibleFrequency, match=msg): + index.join(index3) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_monotonic.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_monotonic.py new file mode 100644 index 0000000000000000000000000000000000000000..15cb8f71cdcf3221800e6dca43390ae79114a9df --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_monotonic.py @@ -0,0 +1,42 @@ +from pandas import ( + Period, + PeriodIndex, +) + + +def test_is_monotonic_increasing(): + # GH#17717 + p0 = Period("2017-09-01") + p1 = Period("2017-09-02") + p2 = Period("2017-09-03") + + idx_inc0 = PeriodIndex([p0, p1, p2]) + idx_inc1 = PeriodIndex([p0, p1, p1]) + idx_dec0 = PeriodIndex([p2, p1, p0]) + idx_dec1 = PeriodIndex([p2, p1, p1]) + idx = PeriodIndex([p1, p2, p0]) + + assert idx_inc0.is_monotonic_increasing is True + assert idx_inc1.is_monotonic_increasing is True + assert idx_dec0.is_monotonic_increasing is False + assert idx_dec1.is_monotonic_increasing is False + assert idx.is_monotonic_increasing is False + + +def test_is_monotonic_decreasing(): + # GH#17717 + p0 = Period("2017-09-01") + p1 = Period("2017-09-02") + p2 = Period("2017-09-03") + + idx_inc0 = PeriodIndex([p0, p1, p2]) + idx_inc1 = PeriodIndex([p0, p1, p1]) + idx_dec0 = PeriodIndex([p2, p1, p0]) + idx_dec1 = PeriodIndex([p2, p1, p1]) + idx = PeriodIndex([p1, p2, p0]) + + assert idx_inc0.is_monotonic_decreasing is False + assert idx_inc1.is_monotonic_decreasing is False + assert idx_dec0.is_monotonic_decreasing is True + assert idx_dec1.is_monotonic_decreasing is True + assert idx.is_monotonic_decreasing is False diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_partial_slicing.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_partial_slicing.py new file mode 100644 index 0000000000000000000000000000000000000000..4fab12f195dc03d43e952d5ee424955330933c0a --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_partial_slicing.py @@ -0,0 +1,198 @@ +import numpy as np +import pytest + +from pandas import ( + DataFrame, + PeriodIndex, + Series, + date_range, + period_range, +) +import pandas._testing as tm + + +class TestPeriodIndex: + def test_getitem_periodindex_duplicates_string_slice( + self, using_copy_on_write, warn_copy_on_write + ): + # monotonic + idx = PeriodIndex([2000, 2007, 2007, 2009, 2009], freq="Y-JUN") + ts = Series(np.random.default_rng(2).standard_normal(len(idx)), index=idx) + original = ts.copy() + + result = ts["2007"] + expected = ts[1:3] + tm.assert_series_equal(result, expected) + with tm.assert_cow_warning(warn_copy_on_write): + result[:] = 1 + if using_copy_on_write: + tm.assert_series_equal(ts, original) + else: + assert (ts[1:3] == 1).all() + + # not monotonic + idx = PeriodIndex([2000, 2007, 2007, 2009, 2007], freq="Y-JUN") + ts = Series(np.random.default_rng(2).standard_normal(len(idx)), index=idx) + + result = ts["2007"] + expected = ts[idx == "2007"] + tm.assert_series_equal(result, expected) + + def test_getitem_periodindex_quarter_string(self): + pi = PeriodIndex(["2Q05", "3Q05", "4Q05", "1Q06", "2Q06"], freq="Q") + ser = Series(np.random.default_rng(2).random(len(pi)), index=pi).cumsum() + # Todo: fix these accessors! + assert ser["05Q4"] == ser.iloc[2] + + def test_pindex_slice_index(self): + pi = period_range(start="1/1/10", end="12/31/12", freq="M") + s = Series(np.random.default_rng(2).random(len(pi)), index=pi) + res = s["2010"] + exp = s[0:12] + tm.assert_series_equal(res, exp) + res = s["2011"] + exp = s[12:24] + tm.assert_series_equal(res, exp) + + @pytest.mark.parametrize("make_range", [date_range, period_range]) + def test_range_slice_day(self, make_range): + # GH#6716 + idx = make_range(start="2013/01/01", freq="D", periods=400) + + msg = "slice indices must be integers or None or have an __index__ method" + # slices against index should raise IndexError + values = [ + "2014", + "2013/02", + "2013/01/02", + "2013/02/01 9H", + "2013/02/01 09:00", + ] + for v in values: + with pytest.raises(TypeError, match=msg): + idx[v:] + + s = Series(np.random.default_rng(2).random(len(idx)), index=idx) + + tm.assert_series_equal(s["2013/01/02":], s[1:]) + tm.assert_series_equal(s["2013/01/02":"2013/01/05"], s[1:5]) + tm.assert_series_equal(s["2013/02":], s[31:]) + tm.assert_series_equal(s["2014":], s[365:]) + + invalid = ["2013/02/01 9H", "2013/02/01 09:00"] + for v in invalid: + with pytest.raises(TypeError, match=msg): + idx[v:] + + @pytest.mark.parametrize("make_range", [date_range, period_range]) + def test_range_slice_seconds(self, make_range): + # GH#6716 + idx = make_range(start="2013/01/01 09:00:00", freq="s", periods=4000) + msg = "slice indices must be integers or None or have an __index__ method" + + # slices against index should raise IndexError + values = [ + "2014", + "2013/02", + "2013/01/02", + "2013/02/01 9H", + "2013/02/01 09:00", + ] + for v in values: + with pytest.raises(TypeError, match=msg): + idx[v:] + + s = Series(np.random.default_rng(2).random(len(idx)), index=idx) + + tm.assert_series_equal(s["2013/01/01 09:05":"2013/01/01 09:10"], s[300:660]) + tm.assert_series_equal(s["2013/01/01 10:00":"2013/01/01 10:05"], s[3600:3960]) + tm.assert_series_equal(s["2013/01/01 10H":], s[3600:]) + tm.assert_series_equal(s[:"2013/01/01 09:30"], s[:1860]) + for d in ["2013/01/01", "2013/01", "2013"]: + tm.assert_series_equal(s[d:], s) + + @pytest.mark.parametrize("make_range", [date_range, period_range]) + def test_range_slice_outofbounds(self, make_range): + # GH#5407 + idx = make_range(start="2013/10/01", freq="D", periods=10) + + df = DataFrame({"units": [100 + i for i in range(10)]}, index=idx) + empty = DataFrame(index=idx[:0], columns=["units"]) + empty["units"] = empty["units"].astype("int64") + + tm.assert_frame_equal(df["2013/09/01":"2013/09/30"], empty) + tm.assert_frame_equal(df["2013/09/30":"2013/10/02"], df.iloc[:2]) + tm.assert_frame_equal(df["2013/10/01":"2013/10/02"], df.iloc[:2]) + tm.assert_frame_equal(df["2013/10/02":"2013/09/30"], empty) + tm.assert_frame_equal(df["2013/10/15":"2013/10/17"], empty) + tm.assert_frame_equal(df["2013-06":"2013-09"], empty) + tm.assert_frame_equal(df["2013-11":"2013-12"], empty) + + @pytest.mark.parametrize("make_range", [date_range, period_range]) + def test_maybe_cast_slice_bound(self, make_range, frame_or_series): + idx = make_range(start="2013/10/01", freq="D", periods=10) + + obj = DataFrame({"units": [100 + i for i in range(10)]}, index=idx) + obj = tm.get_obj(obj, frame_or_series) + + msg = ( + f"cannot do slice indexing on {type(idx).__name__} with " + r"these indexers \[foo\] of type str" + ) + + # Check the lower-level calls are raising where expected. + with pytest.raises(TypeError, match=msg): + idx._maybe_cast_slice_bound("foo", "left") + with pytest.raises(TypeError, match=msg): + idx.get_slice_bound("foo", "left") + + with pytest.raises(TypeError, match=msg): + obj["2013/09/30":"foo"] + with pytest.raises(TypeError, match=msg): + obj["foo":"2013/09/30"] + with pytest.raises(TypeError, match=msg): + obj.loc["2013/09/30":"foo"] + with pytest.raises(TypeError, match=msg): + obj.loc["foo":"2013/09/30"] + + def test_partial_slice_doesnt_require_monotonicity(self): + # See also: DatetimeIndex test ofm the same name + dti = date_range("2014-01-01", periods=30, freq="30D") + pi = dti.to_period("D") + + ser_montonic = Series(np.arange(30), index=pi) + + shuffler = list(range(0, 30, 2)) + list(range(1, 31, 2)) + ser = ser_montonic.iloc[shuffler] + nidx = ser.index + + # Manually identified locations of year==2014 + indexer_2014 = np.array( + [0, 1, 2, 3, 4, 5, 6, 15, 16, 17, 18, 19, 20], dtype=np.intp + ) + assert (nidx[indexer_2014].year == 2014).all() + assert not (nidx[~indexer_2014].year == 2014).any() + + result = nidx.get_loc("2014") + tm.assert_numpy_array_equal(result, indexer_2014) + + expected = ser.iloc[indexer_2014] + result = ser.loc["2014"] + tm.assert_series_equal(result, expected) + + result = ser["2014"] + tm.assert_series_equal(result, expected) + + # Manually identified locations where ser.index is within Mat 2015 + indexer_may2015 = np.array([23], dtype=np.intp) + assert nidx[23].year == 2015 and nidx[23].month == 5 + + result = nidx.get_loc("May 2015") + tm.assert_numpy_array_equal(result, indexer_may2015) + + expected = ser.iloc[indexer_may2015] + result = ser.loc["May 2015"] + tm.assert_series_equal(result, expected) + + result = ser["May 2015"] + tm.assert_series_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period.py new file mode 100644 index 0000000000000000000000000000000000000000..77b8e76894647f25ea94f8bf1dce460d0b2a165f --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period.py @@ -0,0 +1,231 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + NaT, + Period, + PeriodIndex, + Series, + date_range, + offsets, + period_range, +) +import pandas._testing as tm + + +class TestPeriodIndex: + def test_view_asi8(self): + idx = PeriodIndex([], freq="M") + + exp = np.array([], dtype=np.int64) + tm.assert_numpy_array_equal(idx.view("i8"), exp) + tm.assert_numpy_array_equal(idx.asi8, exp) + + idx = PeriodIndex(["2011-01", NaT], freq="M") + + exp = np.array([492, -9223372036854775808], dtype=np.int64) + tm.assert_numpy_array_equal(idx.view("i8"), exp) + tm.assert_numpy_array_equal(idx.asi8, exp) + + exp = np.array([14975, -9223372036854775808], dtype=np.int64) + idx = PeriodIndex(["2011-01-01", NaT], freq="D") + tm.assert_numpy_array_equal(idx.view("i8"), exp) + tm.assert_numpy_array_equal(idx.asi8, exp) + + def test_values(self): + idx = PeriodIndex([], freq="M") + + exp = np.array([], dtype=object) + tm.assert_numpy_array_equal(idx.values, exp) + tm.assert_numpy_array_equal(idx.to_numpy(), exp) + + exp = np.array([], dtype=np.int64) + tm.assert_numpy_array_equal(idx.asi8, exp) + + idx = PeriodIndex(["2011-01", NaT], freq="M") + + exp = np.array([Period("2011-01", freq="M"), NaT], dtype=object) + tm.assert_numpy_array_equal(idx.values, exp) + tm.assert_numpy_array_equal(idx.to_numpy(), exp) + exp = np.array([492, -9223372036854775808], dtype=np.int64) + tm.assert_numpy_array_equal(idx.asi8, exp) + + idx = PeriodIndex(["2011-01-01", NaT], freq="D") + + exp = np.array([Period("2011-01-01", freq="D"), NaT], dtype=object) + tm.assert_numpy_array_equal(idx.values, exp) + tm.assert_numpy_array_equal(idx.to_numpy(), exp) + exp = np.array([14975, -9223372036854775808], dtype=np.int64) + tm.assert_numpy_array_equal(idx.asi8, exp) + + @pytest.mark.parametrize( + "field", + [ + "year", + "month", + "day", + "hour", + "minute", + "second", + "weekofyear", + "week", + "dayofweek", + "day_of_week", + "dayofyear", + "day_of_year", + "quarter", + "qyear", + "days_in_month", + ], + ) + @pytest.mark.parametrize( + "periodindex", + [ + period_range(freq="Y", start="1/1/2001", end="12/1/2005"), + period_range(freq="Q", start="1/1/2001", end="12/1/2002"), + period_range(freq="M", start="1/1/2001", end="1/1/2002"), + period_range(freq="D", start="12/1/2001", end="6/1/2001"), + period_range(freq="h", start="12/31/2001", end="1/1/2002 23:00"), + period_range(freq="Min", start="12/31/2001", end="1/1/2002 00:20"), + period_range( + freq="s", start="12/31/2001 00:00:00", end="12/31/2001 00:05:00" + ), + period_range(end=Period("2006-12-31", "W"), periods=10), + ], + ) + def test_fields(self, periodindex, field): + periods = list(periodindex) + ser = Series(periodindex) + + field_idx = getattr(periodindex, field) + assert len(periodindex) == len(field_idx) + for x, val in zip(periods, field_idx): + assert getattr(x, field) == val + + if len(ser) == 0: + return + + field_s = getattr(ser.dt, field) + assert len(periodindex) == len(field_s) + for x, val in zip(periods, field_s): + assert getattr(x, field) == val + + def test_is_(self): + create_index = lambda: period_range(freq="Y", start="1/1/2001", end="12/1/2009") + index = create_index() + assert index.is_(index) + assert not index.is_(create_index()) + assert index.is_(index.view()) + assert index.is_(index.view().view().view().view().view()) + assert index.view().is_(index) + ind2 = index.view() + index.name = "Apple" + assert ind2.is_(index) + assert not index.is_(index[:]) + assert not index.is_(index.asfreq("M")) + assert not index.is_(index.asfreq("Y")) + + assert not index.is_(index - 2) + assert not index.is_(index - 0) + + def test_index_unique(self): + idx = PeriodIndex([2000, 2007, 2007, 2009, 2009], freq="Y-JUN") + expected = PeriodIndex([2000, 2007, 2009], freq="Y-JUN") + tm.assert_index_equal(idx.unique(), expected) + assert idx.nunique() == 3 + + def test_pindex_fieldaccessor_nat(self): + idx = PeriodIndex( + ["2011-01", "2011-02", "NaT", "2012-03", "2012-04"], freq="D", name="name" + ) + + exp = Index([2011, 2011, -1, 2012, 2012], dtype=np.int64, name="name") + tm.assert_index_equal(idx.year, exp) + exp = Index([1, 2, -1, 3, 4], dtype=np.int64, name="name") + tm.assert_index_equal(idx.month, exp) + + def test_pindex_multiples(self): + expected = PeriodIndex( + ["2011-01", "2011-03", "2011-05", "2011-07", "2011-09", "2011-11"], + freq="2M", + ) + + pi = period_range(start="1/1/11", end="12/31/11", freq="2M") + tm.assert_index_equal(pi, expected) + assert pi.freq == offsets.MonthEnd(2) + assert pi.freqstr == "2M" + + pi = period_range(start="1/1/11", periods=6, freq="2M") + tm.assert_index_equal(pi, expected) + assert pi.freq == offsets.MonthEnd(2) + assert pi.freqstr == "2M" + + @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") + @pytest.mark.filterwarnings("ignore:Period with BDay freq:FutureWarning") + def test_iteration(self): + index = period_range(start="1/1/10", periods=4, freq="B") + + result = list(index) + assert isinstance(result[0], Period) + assert result[0].freq == index.freq + + def test_with_multi_index(self): + # #1705 + index = date_range("1/1/2012", periods=4, freq="12h") + index_as_arrays = [index.to_period(freq="D"), index.hour] + + s = Series([0, 1, 2, 3], index_as_arrays) + + assert isinstance(s.index.levels[0], PeriodIndex) + + assert isinstance(s.index.values[0][0], Period) + + def test_map(self): + # test_map_dictlike generally tests + + index = PeriodIndex([2005, 2007, 2009], freq="Y") + result = index.map(lambda x: x.ordinal) + exp = Index([x.ordinal for x in index]) + tm.assert_index_equal(result, exp) + + +def test_maybe_convert_timedelta(): + pi = PeriodIndex(["2000", "2001"], freq="D") + offset = offsets.Day(2) + assert pi._maybe_convert_timedelta(offset) == 2 + assert pi._maybe_convert_timedelta(2) == 2 + + offset = offsets.BusinessDay() + msg = r"Input has different freq=B from PeriodIndex\(freq=D\)" + with pytest.raises(ValueError, match=msg): + pi._maybe_convert_timedelta(offset) + + +@pytest.mark.parametrize("array", [True, False]) +def test_dunder_array(array): + obj = PeriodIndex(["2000-01-01", "2001-01-01"], freq="D") + if array: + obj = obj._data + + expected = np.array([obj[0], obj[1]], dtype=object) + result = np.array(obj) + tm.assert_numpy_array_equal(result, expected) + + result = np.asarray(obj) + tm.assert_numpy_array_equal(result, expected) + + expected = obj.asi8 + for dtype in ["i8", "int64", np.int64]: + result = np.array(obj, dtype=dtype) + tm.assert_numpy_array_equal(result, expected) + + result = np.asarray(obj, dtype=dtype) + tm.assert_numpy_array_equal(result, expected) + + for dtype in ["float64", "int32", "uint64"]: + msg = "argument must be" + with pytest.raises(TypeError, match=msg): + np.array(obj, dtype=dtype) + with pytest.raises(TypeError, match=msg): + np.array(obj, dtype=getattr(np, dtype)) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period_range.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period_range.py new file mode 100644 index 0000000000000000000000000000000000000000..6f8e6d07da8bf3c730ef1f82224388ba4b99ccb1 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_period_range.py @@ -0,0 +1,241 @@ +import numpy as np +import pytest + +from pandas import ( + NaT, + Period, + PeriodIndex, + date_range, + period_range, +) +import pandas._testing as tm + + +class TestPeriodRangeKeywords: + def test_required_arguments(self): + msg = ( + "Of the three parameters: start, end, and periods, exactly two " + "must be specified" + ) + with pytest.raises(ValueError, match=msg): + period_range("2011-1-1", "2012-1-1", "B") + + def test_required_arguments2(self): + start = Period("02-Apr-2005", "D") + msg = ( + "Of the three parameters: start, end, and periods, exactly two " + "must be specified" + ) + with pytest.raises(ValueError, match=msg): + period_range(start=start) + + def test_required_arguments3(self): + # not enough params + msg = ( + "Of the three parameters: start, end, and periods, " + "exactly two must be specified" + ) + with pytest.raises(ValueError, match=msg): + period_range(start="2017Q1") + + with pytest.raises(ValueError, match=msg): + period_range(end="2017Q1") + + with pytest.raises(ValueError, match=msg): + period_range(periods=5) + + with pytest.raises(ValueError, match=msg): + period_range() + + def test_required_arguments_too_many(self): + msg = ( + "Of the three parameters: start, end, and periods, " + "exactly two must be specified" + ) + with pytest.raises(ValueError, match=msg): + period_range(start="2017Q1", end="2018Q1", periods=8, freq="Q") + + def test_start_end_non_nat(self): + # start/end NaT + msg = "start and end must not be NaT" + with pytest.raises(ValueError, match=msg): + period_range(start=NaT, end="2018Q1") + with pytest.raises(ValueError, match=msg): + period_range(start=NaT, end="2018Q1", freq="Q") + + with pytest.raises(ValueError, match=msg): + period_range(start="2017Q1", end=NaT) + with pytest.raises(ValueError, match=msg): + period_range(start="2017Q1", end=NaT, freq="Q") + + def test_periods_requires_integer(self): + # invalid periods param + msg = "periods must be a number, got foo" + with pytest.raises(TypeError, match=msg): + period_range(start="2017Q1", periods="foo") + + +class TestPeriodRange: + @pytest.mark.parametrize( + "freq_offset, freq_period", + [ + ("D", "D"), + ("W", "W"), + ("QE", "Q"), + ("YE", "Y"), + ], + ) + def test_construction_from_string(self, freq_offset, freq_period): + # non-empty + expected = date_range( + start="2017-01-01", periods=5, freq=freq_offset, name="foo" + ).to_period() + start, end = str(expected[0]), str(expected[-1]) + + result = period_range(start=start, end=end, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(start=start, periods=5, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(end=end, periods=5, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + # empty + expected = PeriodIndex([], freq=freq_period, name="foo") + + result = period_range(start=start, periods=0, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(end=end, periods=0, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(start=end, end=start, freq=freq_period, name="foo") + tm.assert_index_equal(result, expected) + + def test_construction_from_string_monthly(self): + # non-empty + expected = date_range( + start="2017-01-01", periods=5, freq="ME", name="foo" + ).to_period() + start, end = str(expected[0]), str(expected[-1]) + + result = period_range(start=start, end=end, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(start=start, periods=5, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(end=end, periods=5, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + # empty + expected = PeriodIndex([], freq="M", name="foo") + + result = period_range(start=start, periods=0, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(end=end, periods=0, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(start=end, end=start, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + def test_construction_from_period(self): + # upsampling + start, end = Period("2017Q1", freq="Q"), Period("2018Q1", freq="Q") + expected = date_range( + start="2017-03-31", end="2018-03-31", freq="ME", name="foo" + ).to_period() + result = period_range(start=start, end=end, freq="M", name="foo") + tm.assert_index_equal(result, expected) + + # downsampling + start = Period("2017-1", freq="M") + end = Period("2019-12", freq="M") + expected = date_range( + start="2017-01-31", end="2019-12-31", freq="QE", name="foo" + ).to_period() + result = period_range(start=start, end=end, freq="Q", name="foo") + tm.assert_index_equal(result, expected) + + # test for issue # 21793 + start = Period("2017Q1", freq="Q") + end = Period("2018Q1", freq="Q") + idx = period_range(start=start, end=end, freq="Q", name="foo") + result = idx == idx.values + expected = np.array([True, True, True, True, True]) + tm.assert_numpy_array_equal(result, expected) + + # empty + expected = PeriodIndex([], freq="W", name="foo") + + result = period_range(start=start, periods=0, freq="W", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(end=end, periods=0, freq="W", name="foo") + tm.assert_index_equal(result, expected) + + result = period_range(start=end, end=start, freq="W", name="foo") + tm.assert_index_equal(result, expected) + + def test_mismatched_start_end_freq_raises(self): + depr_msg = "Period with BDay freq is deprecated" + msg = "'w' is deprecated and will be removed in a future version." + with tm.assert_produces_warning(FutureWarning, match=msg): + end_w = Period("2006-12-31", "1w") + + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + start_b = Period("02-Apr-2005", "B") + end_b = Period("2005-05-01", "B") + + msg = "start and end must have same freq" + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + period_range(start=start_b, end=end_w) + + # without mismatch we are OK + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + period_range(start=start_b, end=end_b) + + +class TestPeriodRangeDisallowedFreqs: + def test_constructor_U(self): + # U was used as undefined period + with pytest.raises(ValueError, match="Invalid frequency: X"): + period_range("2007-1-1", periods=500, freq="X") + + @pytest.mark.parametrize( + "freq,freq_depr", + [ + ("2Y", "2A"), + ("2Y", "2a"), + ("2Y-AUG", "2A-AUG"), + ("2Y-AUG", "2A-aug"), + ], + ) + def test_a_deprecated_from_time_series(self, freq, freq_depr): + # GH#52536 + msg = f"'{freq_depr[1:]}' is deprecated and will be removed in a " + f"future version. Please use '{freq[1:]}' instead." + + with tm.assert_produces_warning(FutureWarning, match=msg): + period_range(freq=freq_depr, start="1/1/2001", end="12/1/2009") + + @pytest.mark.parametrize("freq_depr", ["2H", "2MIN", "2S", "2US", "2NS"]) + def test_uppercase_freq_deprecated_from_time_series(self, freq_depr): + # GH#52536, GH#54939 + msg = f"'{freq_depr[1:]}' is deprecated and will be removed in a " + f"future version. Please use '{freq_depr.lower()[1:]}' instead." + + with tm.assert_produces_warning(FutureWarning, match=msg): + period_range("2020-01-01 00:00:00 00:00", periods=2, freq=freq_depr) + + @pytest.mark.parametrize("freq_depr", ["2m", "2q-sep", "2y", "2w"]) + def test_lowercase_freq_deprecated_from_time_series(self, freq_depr): + # GH#52536, GH#54939 + msg = f"'{freq_depr[1:]}' is deprecated and will be removed in a " + f"future version. Please use '{freq_depr.upper()[1:]}' instead." + + with tm.assert_produces_warning(FutureWarning, match=msg): + period_range(freq=freq_depr, start="1/1/2001", end="12/1/2009") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_pickle.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_pickle.py new file mode 100644 index 0000000000000000000000000000000000000000..7d359fdabb6f1229e713e45452c6816d9f5743e9 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_pickle.py @@ -0,0 +1,26 @@ +import numpy as np +import pytest + +from pandas import ( + NaT, + PeriodIndex, + period_range, +) +import pandas._testing as tm + +from pandas.tseries import offsets + + +class TestPickle: + @pytest.mark.parametrize("freq", ["D", "M", "Y"]) + def test_pickle_round_trip(self, freq): + idx = PeriodIndex(["2016-05-16", "NaT", NaT, np.nan], freq=freq) + result = tm.round_trip_pickle(idx) + tm.assert_index_equal(result, idx) + + def test_pickle_freq(self): + # GH#2891 + prng = period_range("1/1/2011", "1/1/2012", freq="M") + new_prng = tm.round_trip_pickle(prng) + assert new_prng.freq == offsets.MonthEnd() + assert new_prng.freqstr == "M" diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_resolution.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_resolution.py new file mode 100644 index 0000000000000000000000000000000000000000..680bdaa2e2a44c9603c6465274e4f4cea35e8701 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_resolution.py @@ -0,0 +1,23 @@ +import pytest + +import pandas as pd + + +class TestResolution: + @pytest.mark.parametrize( + "freq,expected", + [ + ("Y", "year"), + ("Q", "quarter"), + ("M", "month"), + ("D", "day"), + ("h", "hour"), + ("min", "minute"), + ("s", "second"), + ("ms", "millisecond"), + ("us", "microsecond"), + ], + ) + def test_resolution(self, freq, expected): + idx = pd.period_range(start="2013-04-01", periods=30, freq=freq) + assert idx.resolution == expected diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_scalar_compat.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_scalar_compat.py new file mode 100644 index 0000000000000000000000000000000000000000..d8afd29ff31c558a7e99861852b08d86deaa9fac --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_scalar_compat.py @@ -0,0 +1,38 @@ +"""Tests for PeriodIndex behaving like a vectorized Period scalar""" + +import pytest + +from pandas import ( + Timedelta, + date_range, + period_range, +) +import pandas._testing as tm + + +class TestPeriodIndexOps: + def test_start_time(self): + # GH#17157 + index = period_range(freq="M", start="2016-01-01", end="2016-05-31") + expected_index = date_range("2016-01-01", end="2016-05-31", freq="MS") + tm.assert_index_equal(index.start_time, expected_index) + + def test_end_time(self): + # GH#17157 + index = period_range(freq="M", start="2016-01-01", end="2016-05-31") + expected_index = date_range("2016-01-01", end="2016-05-31", freq="ME") + expected_index += Timedelta(1, "D") - Timedelta(1, "ns") + tm.assert_index_equal(index.end_time, expected_index) + + @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") + @pytest.mark.filterwarnings( + "ignore:Period with BDay freq is deprecated:FutureWarning" + ) + def test_end_time_business_friday(self): + # GH#34449 + pi = period_range("1990-01-05", freq="B", periods=1) + result = pi.end_time + + dti = date_range("1990-01-05", freq="D", periods=1)._with_freq(None) + expected = dti + Timedelta(days=1, nanoseconds=-1) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_searchsorted.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_searchsorted.py new file mode 100644 index 0000000000000000000000000000000000000000..9b02a2f35fd0193bbc8133373299a0ac2cea38ea --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_searchsorted.py @@ -0,0 +1,80 @@ +import numpy as np +import pytest + +from pandas._libs.tslibs import IncompatibleFrequency + +from pandas import ( + NaT, + Period, + PeriodIndex, +) +import pandas._testing as tm + + +class TestSearchsorted: + @pytest.mark.parametrize("freq", ["D", "2D"]) + def test_searchsorted(self, freq): + pidx = PeriodIndex( + ["2014-01-01", "2014-01-02", "2014-01-03", "2014-01-04", "2014-01-05"], + freq=freq, + ) + + p1 = Period("2014-01-01", freq=freq) + assert pidx.searchsorted(p1) == 0 + + p2 = Period("2014-01-04", freq=freq) + assert pidx.searchsorted(p2) == 3 + + assert pidx.searchsorted(NaT) == 5 + + msg = "Input has different freq=h from PeriodArray" + with pytest.raises(IncompatibleFrequency, match=msg): + pidx.searchsorted(Period("2014-01-01", freq="h")) + + msg = "Input has different freq=5D from PeriodArray" + with pytest.raises(IncompatibleFrequency, match=msg): + pidx.searchsorted(Period("2014-01-01", freq="5D")) + + def test_searchsorted_different_argument_classes(self, listlike_box): + pidx = PeriodIndex( + ["2014-01-01", "2014-01-02", "2014-01-03", "2014-01-04", "2014-01-05"], + freq="D", + ) + result = pidx.searchsorted(listlike_box(pidx)) + expected = np.arange(len(pidx), dtype=result.dtype) + tm.assert_numpy_array_equal(result, expected) + + result = pidx._data.searchsorted(listlike_box(pidx)) + tm.assert_numpy_array_equal(result, expected) + + def test_searchsorted_invalid(self): + pidx = PeriodIndex( + ["2014-01-01", "2014-01-02", "2014-01-03", "2014-01-04", "2014-01-05"], + freq="D", + ) + + other = np.array([0, 1], dtype=np.int64) + + msg = "|".join( + [ + "searchsorted requires compatible dtype or scalar", + "value should be a 'Period', 'NaT', or array of those. Got", + ] + ) + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(other) + + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(other.astype("timedelta64[ns]")) + + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(np.timedelta64(4)) + + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(np.timedelta64("NaT", "ms")) + + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(np.datetime64(4, "ns")) + + with pytest.raises(TypeError, match=msg): + pidx.searchsorted(np.datetime64("NaT", "ns")) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..2fa7e8cd0d2df5982cc0c798fbfba4e0230df367 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_setops.py @@ -0,0 +1,363 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + PeriodIndex, + date_range, + period_range, +) +import pandas._testing as tm + + +def _permute(obj): + return obj.take(np.random.default_rng(2).permutation(len(obj))) + + +class TestPeriodIndex: + def test_union(self, sort): + # union + other1 = period_range("1/1/2000", freq="D", periods=5) + rng1 = period_range("1/6/2000", freq="D", periods=5) + expected1 = PeriodIndex( + [ + "2000-01-06", + "2000-01-07", + "2000-01-08", + "2000-01-09", + "2000-01-10", + "2000-01-01", + "2000-01-02", + "2000-01-03", + "2000-01-04", + "2000-01-05", + ], + freq="D", + ) + + rng2 = period_range("1/1/2000", freq="D", periods=5) + other2 = period_range("1/4/2000", freq="D", periods=5) + expected2 = period_range("1/1/2000", freq="D", periods=8) + + rng3 = period_range("1/1/2000", freq="D", periods=5) + other3 = PeriodIndex([], freq="D") + expected3 = period_range("1/1/2000", freq="D", periods=5) + + rng4 = period_range("2000-01-01 09:00", freq="h", periods=5) + other4 = period_range("2000-01-02 09:00", freq="h", periods=5) + expected4 = PeriodIndex( + [ + "2000-01-01 09:00", + "2000-01-01 10:00", + "2000-01-01 11:00", + "2000-01-01 12:00", + "2000-01-01 13:00", + "2000-01-02 09:00", + "2000-01-02 10:00", + "2000-01-02 11:00", + "2000-01-02 12:00", + "2000-01-02 13:00", + ], + freq="h", + ) + + rng5 = PeriodIndex( + ["2000-01-01 09:01", "2000-01-01 09:03", "2000-01-01 09:05"], freq="min" + ) + other5 = PeriodIndex( + ["2000-01-01 09:01", "2000-01-01 09:05", "2000-01-01 09:08"], freq="min" + ) + expected5 = PeriodIndex( + [ + "2000-01-01 09:01", + "2000-01-01 09:03", + "2000-01-01 09:05", + "2000-01-01 09:08", + ], + freq="min", + ) + + rng6 = period_range("2000-01-01", freq="M", periods=7) + other6 = period_range("2000-04-01", freq="M", periods=7) + expected6 = period_range("2000-01-01", freq="M", periods=10) + + rng7 = period_range("2003-01-01", freq="Y", periods=5) + other7 = period_range("1998-01-01", freq="Y", periods=8) + expected7 = PeriodIndex( + [ + "2003", + "2004", + "2005", + "2006", + "2007", + "1998", + "1999", + "2000", + "2001", + "2002", + ], + freq="Y", + ) + + rng8 = PeriodIndex( + ["1/3/2000", "1/2/2000", "1/1/2000", "1/5/2000", "1/4/2000"], freq="D" + ) + other8 = period_range("1/6/2000", freq="D", periods=5) + expected8 = PeriodIndex( + [ + "1/3/2000", + "1/2/2000", + "1/1/2000", + "1/5/2000", + "1/4/2000", + "1/6/2000", + "1/7/2000", + "1/8/2000", + "1/9/2000", + "1/10/2000", + ], + freq="D", + ) + + for rng, other, expected in [ + (rng1, other1, expected1), + (rng2, other2, expected2), + (rng3, other3, expected3), + (rng4, other4, expected4), + (rng5, other5, expected5), + (rng6, other6, expected6), + (rng7, other7, expected7), + (rng8, other8, expected8), + ]: + result_union = rng.union(other, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result_union, expected) + + def test_union_misc(self, sort): + index = period_range("1/1/2000", "1/20/2000", freq="D") + + result = index[:-5].union(index[10:], sort=sort) + tm.assert_index_equal(result, index) + + # not in order + result = _permute(index[:-5]).union(_permute(index[10:]), sort=sort) + if sort is False: + tm.assert_index_equal(result.sort_values(), index) + else: + tm.assert_index_equal(result, index) + + # cast if different frequencies + index = period_range("1/1/2000", "1/20/2000", freq="D") + index2 = period_range("1/1/2000", "1/20/2000", freq="W-WED") + result = index.union(index2, sort=sort) + expected = index.astype(object).union(index2.astype(object), sort=sort) + tm.assert_index_equal(result, expected) + + def test_intersection(self, sort): + index = period_range("1/1/2000", "1/20/2000", freq="D") + + result = index[:-5].intersection(index[10:], sort=sort) + tm.assert_index_equal(result, index[10:-5]) + + # not in order + left = _permute(index[:-5]) + right = _permute(index[10:]) + result = left.intersection(right, sort=sort) + if sort is False: + tm.assert_index_equal(result.sort_values(), index[10:-5]) + else: + tm.assert_index_equal(result, index[10:-5]) + + # cast if different frequencies + index = period_range("1/1/2000", "1/20/2000", freq="D") + index2 = period_range("1/1/2000", "1/20/2000", freq="W-WED") + + result = index.intersection(index2, sort=sort) + expected = pd.Index([], dtype=object) + tm.assert_index_equal(result, expected) + + index3 = period_range("1/1/2000", "1/20/2000", freq="2D") + result = index.intersection(index3, sort=sort) + tm.assert_index_equal(result, expected) + + def test_intersection_cases(self, sort): + base = period_range("6/1/2000", "6/30/2000", freq="D", name="idx") + + # if target has the same name, it is preserved + rng2 = period_range("5/15/2000", "6/20/2000", freq="D", name="idx") + expected2 = period_range("6/1/2000", "6/20/2000", freq="D", name="idx") + + # if target name is different, it will be reset + rng3 = period_range("5/15/2000", "6/20/2000", freq="D", name="other") + expected3 = period_range("6/1/2000", "6/20/2000", freq="D", name=None) + + rng4 = period_range("7/1/2000", "7/31/2000", freq="D", name="idx") + expected4 = PeriodIndex([], name="idx", freq="D") + + for rng, expected in [ + (rng2, expected2), + (rng3, expected3), + (rng4, expected4), + ]: + result = base.intersection(rng, sort=sort) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + # non-monotonic + base = PeriodIndex( + ["2011-01-05", "2011-01-04", "2011-01-02", "2011-01-03"], + freq="D", + name="idx", + ) + + rng2 = PeriodIndex( + ["2011-01-04", "2011-01-02", "2011-02-02", "2011-02-03"], + freq="D", + name="idx", + ) + expected2 = PeriodIndex(["2011-01-04", "2011-01-02"], freq="D", name="idx") + + rng3 = PeriodIndex( + ["2011-01-04", "2011-01-02", "2011-02-02", "2011-02-03"], + freq="D", + name="other", + ) + expected3 = PeriodIndex(["2011-01-04", "2011-01-02"], freq="D", name=None) + + rng4 = period_range("7/1/2000", "7/31/2000", freq="D", name="idx") + expected4 = PeriodIndex([], freq="D", name="idx") + + for rng, expected in [ + (rng2, expected2), + (rng3, expected3), + (rng4, expected4), + ]: + result = base.intersection(rng, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == "D" + + # empty same freq + rng = date_range("6/1/2000", "6/15/2000", freq="min") + result = rng[0:0].intersection(rng) + assert len(result) == 0 + + result = rng.intersection(rng[0:0]) + assert len(result) == 0 + + def test_difference(self, sort): + # diff + period_rng = ["1/3/2000", "1/2/2000", "1/1/2000", "1/5/2000", "1/4/2000"] + rng1 = PeriodIndex(period_rng, freq="D") + other1 = period_range("1/6/2000", freq="D", periods=5) + expected1 = rng1 + + rng2 = PeriodIndex(period_rng, freq="D") + other2 = period_range("1/4/2000", freq="D", periods=5) + expected2 = PeriodIndex(["1/3/2000", "1/2/2000", "1/1/2000"], freq="D") + + rng3 = PeriodIndex(period_rng, freq="D") + other3 = PeriodIndex([], freq="D") + expected3 = rng3 + + period_rng = [ + "2000-01-01 10:00", + "2000-01-01 09:00", + "2000-01-01 12:00", + "2000-01-01 11:00", + "2000-01-01 13:00", + ] + rng4 = PeriodIndex(period_rng, freq="h") + other4 = period_range("2000-01-02 09:00", freq="h", periods=5) + expected4 = rng4 + + rng5 = PeriodIndex( + ["2000-01-01 09:03", "2000-01-01 09:01", "2000-01-01 09:05"], freq="min" + ) + other5 = PeriodIndex(["2000-01-01 09:01", "2000-01-01 09:05"], freq="min") + expected5 = PeriodIndex(["2000-01-01 09:03"], freq="min") + + period_rng = [ + "2000-02-01", + "2000-01-01", + "2000-06-01", + "2000-07-01", + "2000-05-01", + "2000-03-01", + "2000-04-01", + ] + rng6 = PeriodIndex(period_rng, freq="M") + other6 = period_range("2000-04-01", freq="M", periods=7) + expected6 = PeriodIndex(["2000-02-01", "2000-01-01", "2000-03-01"], freq="M") + + period_rng = ["2003", "2007", "2006", "2005", "2004"] + rng7 = PeriodIndex(period_rng, freq="Y") + other7 = period_range("1998-01-01", freq="Y", periods=8) + expected7 = PeriodIndex(["2007", "2006"], freq="Y") + + for rng, other, expected in [ + (rng1, other1, expected1), + (rng2, other2, expected2), + (rng3, other3, expected3), + (rng4, other4, expected4), + (rng5, other5, expected5), + (rng6, other6, expected6), + (rng7, other7, expected7), + ]: + result_difference = rng.difference(other, sort=sort) + if sort is None and len(other): + # We dont sort (yet?) when empty GH#24959 + expected = expected.sort_values() + tm.assert_index_equal(result_difference, expected) + + def test_difference_freq(self, sort): + # GH14323: difference of Period MUST preserve frequency + # but the ability to union results must be preserved + + index = period_range("20160920", "20160925", freq="D") + + other = period_range("20160921", "20160924", freq="D") + expected = PeriodIndex(["20160920", "20160925"], freq="D") + idx_diff = index.difference(other, sort) + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) + + other = period_range("20160922", "20160925", freq="D") + idx_diff = index.difference(other, sort) + expected = PeriodIndex(["20160920", "20160921"], freq="D") + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) + + def test_intersection_equal_duplicates(self): + # GH#38302 + idx = period_range("2011-01-01", periods=2) + idx_dup = idx.append(idx) + result = idx_dup.intersection(idx_dup) + tm.assert_index_equal(result, idx) + + @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") + def test_union_duplicates(self): + # GH#36289 + idx = period_range("2011-01-01", periods=2) + idx_dup = idx.append(idx) + + idx2 = period_range("2011-01-02", periods=2) + idx2_dup = idx2.append(idx2) + result = idx_dup.union(idx2_dup) + + expected = PeriodIndex( + [ + "2011-01-01", + "2011-01-01", + "2011-01-02", + "2011-01-02", + "2011-01-03", + "2011-01-03", + ], + freq="D", + ) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/period/test_tools.py b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_tools.py new file mode 100644 index 0000000000000000000000000000000000000000..f507e64d88b06b5862de3e98c693ab9f85306116 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/period/test_tools.py @@ -0,0 +1,52 @@ +import numpy as np +import pytest + +from pandas import ( + Period, + PeriodIndex, + period_range, +) +import pandas._testing as tm + + +class TestPeriodRepresentation: + """ + Wish to match NumPy units + """ + + @pytest.mark.parametrize( + "freq, base_date", + [ + ("W-THU", "1970-01-01"), + ("D", "1970-01-01"), + ("B", "1970-01-01"), + ("h", "1970-01-01"), + ("min", "1970-01-01"), + ("s", "1970-01-01"), + ("ms", "1970-01-01"), + ("us", "1970-01-01"), + ("ns", "1970-01-01"), + ("M", "1970-01"), + ("Y", 1970), + ], + ) + @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning") + @pytest.mark.filterwarnings( + "ignore:Period with BDay freq is deprecated:FutureWarning" + ) + def test_freq(self, freq, base_date): + rng = period_range(start=base_date, periods=10, freq=freq) + exp = np.arange(10, dtype=np.int64) + + tm.assert_numpy_array_equal(rng.asi8, exp) + + +class TestPeriodIndexConversion: + def test_tolist(self): + index = period_range(freq="Y", start="1/1/2001", end="12/1/2009") + rs = index.tolist() + for x in rs: + assert isinstance(x, Period) + + recon = PeriodIndex(rs) + tm.assert_index_equal(index, recon) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..07024872dd3eb7ea9de253f5a57bb7ed20afd393 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a00e5eb8a88e8f3efa86dfe8132e0aed226caee4 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4d36e1f29d64d1b1338662694f3ddf897ef75167 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2df9400c9487c135062cbe9076c2eb6263abb62b Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_range.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_range.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..67f813c3b704d9b91a5a6c1614f8280a2e622a58 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_range.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..411f9297623dd174e7e6c12863a4a5501022f0b5 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..5e6f16075ae636a3aa14e7443097f426bd6f998a --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_constructors.py @@ -0,0 +1,164 @@ +from datetime import datetime + +import numpy as np +import pytest + +from pandas import ( + Index, + RangeIndex, + Series, +) +import pandas._testing as tm + + +class TestRangeIndexConstructors: + @pytest.mark.parametrize("name", [None, "foo"]) + @pytest.mark.parametrize( + "args, kwargs, start, stop, step", + [ + ((5,), {}, 0, 5, 1), + ((1, 5), {}, 1, 5, 1), + ((1, 5, 2), {}, 1, 5, 2), + ((0,), {}, 0, 0, 1), + ((0, 0), {}, 0, 0, 1), + ((), {"start": 0}, 0, 0, 1), + ((), {"stop": 0}, 0, 0, 1), + ], + ) + def test_constructor(self, args, kwargs, start, stop, step, name): + result = RangeIndex(*args, name=name, **kwargs) + expected = Index(np.arange(start, stop, step, dtype=np.int64), name=name) + assert isinstance(result, RangeIndex) + assert result.name is name + assert result._range == range(start, stop, step) + tm.assert_index_equal(result, expected, exact="equiv") + + def test_constructor_invalid_args(self): + msg = "RangeIndex\\(\\.\\.\\.\\) must be called with integers" + with pytest.raises(TypeError, match=msg): + RangeIndex() + + with pytest.raises(TypeError, match=msg): + RangeIndex(name="Foo") + + # we don't allow on a bare Index + msg = ( + r"Index\(\.\.\.\) must be called with a collection of some " + r"kind, 0 was passed" + ) + with pytest.raises(TypeError, match=msg): + Index(0) + + @pytest.mark.parametrize( + "args", + [ + Index(["a", "b"]), + Series(["a", "b"]), + np.array(["a", "b"]), + [], + np.arange(0, 10), + np.array([1]), + [1], + ], + ) + def test_constructor_additional_invalid_args(self, args): + msg = f"Value needs to be a scalar value, was type {type(args).__name__}" + with pytest.raises(TypeError, match=msg): + RangeIndex(args) + + @pytest.mark.parametrize("args", ["foo", datetime(2000, 1, 1, 0, 0)]) + def test_constructor_invalid_args_wrong_type(self, args): + msg = f"Wrong type {type(args)} for value {args}" + with pytest.raises(TypeError, match=msg): + RangeIndex(args) + + def test_constructor_same(self): + # pass thru w and w/o copy + index = RangeIndex(1, 5, 2) + result = RangeIndex(index, copy=False) + assert result.identical(index) + + result = RangeIndex(index, copy=True) + tm.assert_index_equal(result, index, exact=True) + + result = RangeIndex(index) + tm.assert_index_equal(result, index, exact=True) + + with pytest.raises( + ValueError, + match="Incorrect `dtype` passed: expected signed integer, received float64", + ): + RangeIndex(index, dtype="float64") + + def test_constructor_range_object(self): + result = RangeIndex(range(1, 5, 2)) + expected = RangeIndex(1, 5, 2) + tm.assert_index_equal(result, expected, exact=True) + + def test_constructor_range(self): + result = RangeIndex.from_range(range(1, 5, 2)) + expected = RangeIndex(1, 5, 2) + tm.assert_index_equal(result, expected, exact=True) + + result = RangeIndex.from_range(range(5, 6)) + expected = RangeIndex(5, 6, 1) + tm.assert_index_equal(result, expected, exact=True) + + # an invalid range + result = RangeIndex.from_range(range(5, 1)) + expected = RangeIndex(0, 0, 1) + tm.assert_index_equal(result, expected, exact=True) + + result = RangeIndex.from_range(range(5)) + expected = RangeIndex(0, 5, 1) + tm.assert_index_equal(result, expected, exact=True) + + result = Index(range(1, 5, 2)) + expected = RangeIndex(1, 5, 2) + tm.assert_index_equal(result, expected, exact=True) + + msg = ( + r"(RangeIndex.)?from_range\(\) got an unexpected keyword argument( 'copy')?" + ) + with pytest.raises(TypeError, match=msg): + RangeIndex.from_range(range(10), copy=True) + + def test_constructor_name(self): + # GH#12288 + orig = RangeIndex(10) + orig.name = "original" + + copy = RangeIndex(orig) + copy.name = "copy" + + assert orig.name == "original" + assert copy.name == "copy" + + new = Index(copy) + assert new.name == "copy" + + new.name = "new" + assert orig.name == "original" + assert copy.name == "copy" + assert new.name == "new" + + def test_constructor_corner(self): + arr = np.array([1, 2, 3, 4], dtype=object) + index = RangeIndex(1, 5) + assert index.values.dtype == np.int64 + expected = Index(arr).astype("int64") + + tm.assert_index_equal(index, expected, exact="equiv") + + # non-int raise Exception + with pytest.raises(TypeError, match=r"Wrong type \"): + RangeIndex("1", "10", "1") + with pytest.raises(TypeError, match=r"Wrong type \"): + RangeIndex(1.1, 10.2, 1.3) + + # invalid passed type + with pytest.raises( + ValueError, + match="Incorrect `dtype` passed: expected signed integer, received float64", + ): + RangeIndex(1, 5, dtype="float64") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..6202074a11d7883c6f6aa984c23d7964e9042eb0 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_indexing.py @@ -0,0 +1,137 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + RangeIndex, +) +import pandas._testing as tm + + +class TestGetIndexer: + def test_get_indexer(self): + index = RangeIndex(start=0, stop=20, step=2) + target = RangeIndex(10) + indexer = index.get_indexer(target) + expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + def test_get_indexer_pad(self): + index = RangeIndex(start=0, stop=20, step=2) + target = RangeIndex(10) + indexer = index.get_indexer(target, method="pad") + expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + def test_get_indexer_backfill(self): + index = RangeIndex(start=0, stop=20, step=2) + target = RangeIndex(10) + indexer = index.get_indexer(target, method="backfill") + expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp) + tm.assert_numpy_array_equal(indexer, expected) + + def test_get_indexer_limit(self): + # GH#28631 + idx = RangeIndex(4) + target = RangeIndex(6) + result = idx.get_indexer(target, method="pad", limit=1) + expected = np.array([0, 1, 2, 3, 3, -1], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + + @pytest.mark.parametrize("stop", [0, -1, -2]) + def test_get_indexer_decreasing(self, stop): + # GH#28678 + index = RangeIndex(7, stop, -3) + result = index.get_indexer(range(9)) + expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp) + tm.assert_numpy_array_equal(result, expected) + + +class TestTake: + def test_take_preserve_name(self): + index = RangeIndex(1, 5, name="foo") + taken = index.take([3, 0, 1]) + assert index.name == taken.name + + def test_take_fill_value(self): + # GH#12631 + idx = RangeIndex(1, 4, name="xxx") + result = idx.take(np.array([1, 0, -1])) + expected = Index([2, 1, 3], dtype=np.int64, name="xxx") + tm.assert_index_equal(result, expected) + + # fill_value + msg = "Unable to fill values because RangeIndex cannot contain NA" + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -1]), fill_value=True) + + # allow_fill=False + result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True) + expected = Index([2, 1, 3], dtype=np.int64, name="xxx") + tm.assert_index_equal(result, expected) + + msg = "Unable to fill values because RangeIndex cannot contain NA" + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + def test_take_raises_index_error(self): + idx = RangeIndex(1, 4, name="xxx") + + msg = "index -5 is out of bounds for (axis 0 with )?size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) + + msg = "index -4 is out of bounds for (axis 0 with )?size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -4])) + + # no errors + result = idx.take(np.array([1, -3])) + expected = Index([2, 1], dtype=np.int64, name="xxx") + tm.assert_index_equal(result, expected) + + def test_take_accepts_empty_array(self): + idx = RangeIndex(1, 4, name="foo") + result = idx.take(np.array([])) + expected = Index([], dtype=np.int64, name="foo") + tm.assert_index_equal(result, expected) + + # empty index + idx = RangeIndex(0, name="foo") + result = idx.take(np.array([])) + expected = Index([], dtype=np.int64, name="foo") + tm.assert_index_equal(result, expected) + + def test_take_accepts_non_int64_array(self): + idx = RangeIndex(1, 4, name="foo") + result = idx.take(np.array([2, 1], dtype=np.uint32)) + expected = Index([3, 2], dtype=np.int64, name="foo") + tm.assert_index_equal(result, expected) + + def test_take_when_index_has_step(self): + idx = RangeIndex(1, 11, 3, name="foo") # [1, 4, 7, 10] + result = idx.take(np.array([1, 0, -1, -4])) + expected = Index([4, 1, 10, 1], dtype=np.int64, name="foo") + tm.assert_index_equal(result, expected) + + def test_take_when_index_has_negative_step(self): + idx = RangeIndex(11, -4, -2, name="foo") # [11, 9, 7, 5, 3, 1, -1, -3] + result = idx.take(np.array([1, 0, -1, -8])) + expected = Index([9, 11, -3, 11], dtype=np.int64, name="foo") + tm.assert_index_equal(result, expected) + + +class TestWhere: + def test_where_putmask_range_cast(self): + # GH#43240 + idx = RangeIndex(0, 5, name="test") + + mask = np.array([True, True, False, False, False]) + result = idx.putmask(mask, 10) + expected = Index([10, 10, 2, 3, 4], dtype=np.int64, name="test") + tm.assert_index_equal(result, expected) + + result = idx.where(~mask, 10) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_join.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_join.py new file mode 100644 index 0000000000000000000000000000000000000000..682b5c8def9ff0e00b533610c1d45a093e7d7a8d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_join.py @@ -0,0 +1,177 @@ +import numpy as np + +from pandas import ( + Index, + RangeIndex, +) +import pandas._testing as tm + + +class TestJoin: + def test_join_outer(self): + # join with Index[int64] + index = RangeIndex(start=0, stop=20, step=2) + other = Index(np.arange(25, 14, -1, dtype=np.int64)) + + res, lidx, ridx = index.join(other, how="outer", return_indexers=True) + noidx_res = index.join(other, how="outer") + tm.assert_index_equal(res, noidx_res) + + eres = Index( + [0, 2, 4, 6, 8, 10, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25] + ) + elidx = np.array( + [0, 1, 2, 3, 4, 5, 6, 7, -1, 8, -1, 9, -1, -1, -1, -1, -1, -1, -1], + dtype=np.intp, + ) + eridx = np.array( + [-1, -1, -1, -1, -1, -1, -1, -1, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0], + dtype=np.intp, + ) + + assert isinstance(res, Index) and res.dtype == np.dtype(np.int64) + assert not isinstance(res, RangeIndex) + tm.assert_index_equal(res, eres, exact=True) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # join with RangeIndex + other = RangeIndex(25, 14, -1) + + res, lidx, ridx = index.join(other, how="outer", return_indexers=True) + noidx_res = index.join(other, how="outer") + tm.assert_index_equal(res, noidx_res) + + assert isinstance(res, Index) and res.dtype == np.int64 + assert not isinstance(res, RangeIndex) + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_inner(self): + # Join with non-RangeIndex + index = RangeIndex(start=0, stop=20, step=2) + other = Index(np.arange(25, 14, -1, dtype=np.int64)) + + res, lidx, ridx = index.join(other, how="inner", return_indexers=True) + + # no guarantee of sortedness, so sort for comparison purposes + ind = res.argsort() + res = res.take(ind) + lidx = lidx.take(ind) + ridx = ridx.take(ind) + + eres = Index([16, 18]) + elidx = np.array([8, 9], dtype=np.intp) + eridx = np.array([9, 7], dtype=np.intp) + + assert isinstance(res, Index) and res.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + # Join two RangeIndex + other = RangeIndex(25, 14, -1) + + res, lidx, ridx = index.join(other, how="inner", return_indexers=True) + + assert isinstance(res, RangeIndex) + tm.assert_index_equal(res, eres, exact="equiv") + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_left(self): + # Join with Index[int64] + index = RangeIndex(start=0, stop=20, step=2) + other = Index(np.arange(25, 14, -1, dtype=np.int64)) + + res, lidx, ridx = index.join(other, how="left", return_indexers=True) + eres = index + eridx = np.array([-1, -1, -1, -1, -1, -1, -1, -1, 9, 7], dtype=np.intp) + + assert isinstance(res, RangeIndex) + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + # Join withRangeIndex + other = Index(np.arange(25, 14, -1, dtype=np.int64)) + + res, lidx, ridx = index.join(other, how="left", return_indexers=True) + + assert isinstance(res, RangeIndex) + tm.assert_index_equal(res, eres) + assert lidx is None + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_right(self): + # Join with Index[int64] + index = RangeIndex(start=0, stop=20, step=2) + other = Index(np.arange(25, 14, -1, dtype=np.int64)) + + res, lidx, ridx = index.join(other, how="right", return_indexers=True) + eres = other + elidx = np.array([-1, -1, -1, -1, -1, -1, -1, 9, -1, 8, -1], dtype=np.intp) + + assert isinstance(other, Index) and other.dtype == np.int64 + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + assert ridx is None + + # Join withRangeIndex + other = RangeIndex(25, 14, -1) + + res, lidx, ridx = index.join(other, how="right", return_indexers=True) + eres = other + + assert isinstance(other, RangeIndex) + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + assert ridx is None + + def test_join_non_int_index(self): + index = RangeIndex(start=0, stop=20, step=2) + other = Index([3, 6, 7, 8, 10], dtype=object) + + outer = index.join(other, how="outer") + outer2 = other.join(index, how="outer") + expected = Index([0, 2, 3, 4, 6, 7, 8, 10, 12, 14, 16, 18]) + tm.assert_index_equal(outer, outer2) + tm.assert_index_equal(outer, expected) + + inner = index.join(other, how="inner") + inner2 = other.join(index, how="inner") + expected = Index([6, 8, 10]) + tm.assert_index_equal(inner, inner2) + tm.assert_index_equal(inner, expected) + + left = index.join(other, how="left") + tm.assert_index_equal(left, index.astype(object)) + + left2 = other.join(index, how="left") + tm.assert_index_equal(left2, other) + + right = index.join(other, how="right") + tm.assert_index_equal(right, other) + + right2 = other.join(index, how="right") + tm.assert_index_equal(right2, index.astype(object)) + + def test_join_non_unique(self): + index = RangeIndex(start=0, stop=20, step=2) + other = Index([4, 4, 3, 3]) + + res, lidx, ridx = index.join(other, return_indexers=True) + + eres = Index([0, 2, 4, 4, 6, 8, 10, 12, 14, 16, 18]) + elidx = np.array([0, 1, 2, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.intp) + eridx = np.array([-1, -1, 0, 1, -1, -1, -1, -1, -1, -1, -1], dtype=np.intp) + + tm.assert_index_equal(res, eres) + tm.assert_numpy_array_equal(lidx, elidx) + tm.assert_numpy_array_equal(ridx, eridx) + + def test_join_self(self, join_type): + index = RangeIndex(start=0, stop=20, step=2) + joined = index.join(index, how=join_type) + assert index is joined diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_range.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_range.py new file mode 100644 index 0000000000000000000000000000000000000000..06e19eeca67663318709772ff23f76675545e19b --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_range.py @@ -0,0 +1,622 @@ +import numpy as np +import pytest + +from pandas.core.dtypes.common import ensure_platform_int + +import pandas as pd +from pandas import ( + Index, + RangeIndex, +) +import pandas._testing as tm + + +class TestRangeIndex: + @pytest.fixture + def simple_index(self): + return RangeIndex(start=0, stop=20, step=2) + + def test_constructor_unwraps_index(self): + result = RangeIndex(1, 3) + expected = np.array([1, 2], dtype=np.int64) + tm.assert_numpy_array_equal(result._data, expected) + + def test_can_hold_identifiers(self, simple_index): + idx = simple_index + key = idx[0] + assert idx._can_hold_identifiers_and_holds_name(key) is False + + def test_too_many_names(self, simple_index): + index = simple_index + with pytest.raises(ValueError, match="^Length"): + index.names = ["roger", "harold"] + + @pytest.mark.parametrize( + "index, start, stop, step", + [ + (RangeIndex(5), 0, 5, 1), + (RangeIndex(0, 5), 0, 5, 1), + (RangeIndex(5, step=2), 0, 5, 2), + (RangeIndex(1, 5, 2), 1, 5, 2), + ], + ) + def test_start_stop_step_attrs(self, index, start, stop, step): + # GH 25710 + assert index.start == start + assert index.stop == stop + assert index.step == step + + def test_copy(self): + i = RangeIndex(5, name="Foo") + i_copy = i.copy() + assert i_copy is not i + assert i_copy.identical(i) + assert i_copy._range == range(0, 5, 1) + assert i_copy.name == "Foo" + + def test_repr(self): + i = RangeIndex(5, name="Foo") + result = repr(i) + expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')" + assert result == expected + + result = eval(result) + tm.assert_index_equal(result, i, exact=True) + + i = RangeIndex(5, 0, -1) + result = repr(i) + expected = "RangeIndex(start=5, stop=0, step=-1)" + assert result == expected + + result = eval(result) + tm.assert_index_equal(result, i, exact=True) + + def test_insert(self): + idx = RangeIndex(5, name="Foo") + result = idx[1:4] + + # test 0th element + tm.assert_index_equal(idx[0:4], result.insert(0, idx[0]), exact="equiv") + + # GH 18295 (test missing) + expected = Index([0, np.nan, 1, 2, 3, 4], dtype=np.float64) + for na in [np.nan, None, pd.NA]: + result = RangeIndex(5).insert(1, na) + tm.assert_index_equal(result, expected) + + result = RangeIndex(5).insert(1, pd.NaT) + expected = Index([0, pd.NaT, 1, 2, 3, 4], dtype=object) + tm.assert_index_equal(result, expected) + + def test_insert_edges_preserves_rangeindex(self): + idx = Index(range(4, 9, 2)) + + result = idx.insert(0, 2) + expected = Index(range(2, 9, 2)) + tm.assert_index_equal(result, expected, exact=True) + + result = idx.insert(3, 10) + expected = Index(range(4, 11, 2)) + tm.assert_index_equal(result, expected, exact=True) + + def test_insert_middle_preserves_rangeindex(self): + # insert in the middle + idx = Index(range(0, 3, 2)) + result = idx.insert(1, 1) + expected = Index(range(3)) + tm.assert_index_equal(result, expected, exact=True) + + idx = idx * 2 + result = idx.insert(1, 2) + expected = expected * 2 + tm.assert_index_equal(result, expected, exact=True) + + def test_delete(self): + idx = RangeIndex(5, name="Foo") + expected = idx[1:] + result = idx.delete(0) + tm.assert_index_equal(result, expected, exact=True) + assert result.name == expected.name + + expected = idx[:-1] + result = idx.delete(-1) + tm.assert_index_equal(result, expected, exact=True) + assert result.name == expected.name + + msg = "index 5 is out of bounds for axis 0 with size 5" + with pytest.raises((IndexError, ValueError), match=msg): + # either depending on numpy version + result = idx.delete(len(idx)) + + def test_delete_preserves_rangeindex(self): + idx = Index(range(2), name="foo") + + result = idx.delete([1]) + expected = Index(range(1), name="foo") + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(1) + tm.assert_index_equal(result, expected, exact=True) + + def test_delete_preserves_rangeindex_middle(self): + idx = Index(range(3), name="foo") + result = idx.delete(1) + expected = idx[::2] + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(-2) + tm.assert_index_equal(result, expected, exact=True) + + def test_delete_preserves_rangeindex_list_at_end(self): + idx = RangeIndex(0, 6, 1) + + loc = [2, 3, 4, 5] + result = idx.delete(loc) + expected = idx[:2] + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(loc[::-1]) + tm.assert_index_equal(result, expected, exact=True) + + def test_delete_preserves_rangeindex_list_middle(self): + idx = RangeIndex(0, 6, 1) + + loc = [1, 2, 3, 4] + result = idx.delete(loc) + expected = RangeIndex(0, 6, 5) + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(loc[::-1]) + tm.assert_index_equal(result, expected, exact=True) + + def test_delete_all_preserves_rangeindex(self): + idx = RangeIndex(0, 6, 1) + + loc = [0, 1, 2, 3, 4, 5] + result = idx.delete(loc) + expected = idx[:0] + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(loc[::-1]) + tm.assert_index_equal(result, expected, exact=True) + + def test_delete_not_preserving_rangeindex(self): + idx = RangeIndex(0, 6, 1) + + loc = [0, 3, 5] + result = idx.delete(loc) + expected = Index([1, 2, 4]) + tm.assert_index_equal(result, expected, exact=True) + + result = idx.delete(loc[::-1]) + tm.assert_index_equal(result, expected, exact=True) + + def test_view(self): + i = RangeIndex(0, name="Foo") + i_view = i.view() + assert i_view.name == "Foo" + + i_view = i.view("i8") + tm.assert_numpy_array_equal(i.values, i_view) + + msg = "Passing a type in RangeIndex.view is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + i_view = i.view(RangeIndex) + tm.assert_index_equal(i, i_view) + + def test_dtype(self, simple_index): + index = simple_index + assert index.dtype == np.int64 + + def test_cache(self): + # GH 26565, GH26617, GH35432, GH53387 + # This test checks whether _cache has been set. + # Calling RangeIndex._cache["_data"] creates an int64 array of the same length + # as the RangeIndex and stores it in _cache. + idx = RangeIndex(0, 100, 10) + + assert idx._cache == {} + + repr(idx) + assert idx._cache == {} + + str(idx) + assert idx._cache == {} + + idx.get_loc(20) + assert idx._cache == {} + + 90 in idx # True + assert idx._cache == {} + + 91 in idx # False + assert idx._cache == {} + + idx.all() + assert idx._cache == {} + + idx.any() + assert idx._cache == {} + + for _ in idx: + pass + assert idx._cache == {} + + msg = "RangeIndex.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + idx.format() + assert idx._cache == {} + + df = pd.DataFrame({"a": range(10)}, index=idx) + + # df.__repr__ should not populate index cache + str(df) + assert idx._cache == {} + + df.loc[50] + assert idx._cache == {} + + with pytest.raises(KeyError, match="51"): + df.loc[51] + assert idx._cache == {} + + df.loc[10:50] + assert idx._cache == {} + + df.iloc[5:10] + assert idx._cache == {} + + # after calling take, _cache may contain other keys, but not "_data" + idx.take([3, 0, 1]) + assert "_data" not in idx._cache + + df.loc[[50]] + assert "_data" not in idx._cache + + df.iloc[[5, 6, 7, 8, 9]] + assert "_data" not in idx._cache + + # idx._cache should contain a _data entry after call to idx._data + idx._data + assert isinstance(idx._data, np.ndarray) + assert idx._data is idx._data # check cached value is reused + assert "_data" in idx._cache + expected = np.arange(0, 100, 10, dtype="int64") + tm.assert_numpy_array_equal(idx._cache["_data"], expected) + + def test_is_monotonic(self): + index = RangeIndex(0, 20, 2) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index.is_monotonic_decreasing is False + assert index._is_strictly_monotonic_increasing is True + assert index._is_strictly_monotonic_decreasing is False + + index = RangeIndex(4, 0, -1) + assert index.is_monotonic_increasing is False + assert index._is_strictly_monotonic_increasing is False + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_decreasing is True + + index = RangeIndex(1, 2) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_increasing is True + assert index._is_strictly_monotonic_decreasing is True + + index = RangeIndex(2, 1) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_increasing is True + assert index._is_strictly_monotonic_decreasing is True + + index = RangeIndex(1, 1) + assert index.is_monotonic_increasing is True + assert index.is_monotonic_increasing is True + assert index.is_monotonic_decreasing is True + assert index._is_strictly_monotonic_increasing is True + assert index._is_strictly_monotonic_decreasing is True + + @pytest.mark.parametrize( + "left,right", + [ + (RangeIndex(0, 9, 2), RangeIndex(0, 10, 2)), + (RangeIndex(0), RangeIndex(1, -1, 3)), + (RangeIndex(1, 2, 3), RangeIndex(1, 3, 4)), + (RangeIndex(0, -9, -2), RangeIndex(0, -10, -2)), + ], + ) + def test_equals_range(self, left, right): + assert left.equals(right) + assert right.equals(left) + + def test_logical_compat(self, simple_index): + idx = simple_index + assert idx.all() == idx.values.all() + assert idx.any() == idx.values.any() + + def test_identical(self, simple_index): + index = simple_index + i = Index(index.copy()) + assert i.identical(index) + + # we don't allow object dtype for RangeIndex + if isinstance(index, RangeIndex): + return + + same_values_different_type = Index(i, dtype=object) + assert not i.identical(same_values_different_type) + + i = index.copy(dtype=object) + i = i.rename("foo") + same_values = Index(i, dtype=object) + assert same_values.identical(index.copy(dtype=object)) + + assert not i.identical(index) + assert Index(same_values, name="foo", dtype=object).identical(i) + + assert not index.copy(dtype=object).identical(index.copy(dtype="int64")) + + def test_nbytes(self): + # memory savings vs int index + idx = RangeIndex(0, 1000) + assert idx.nbytes < Index(idx._values).nbytes / 10 + + # constant memory usage + i2 = RangeIndex(0, 10) + assert idx.nbytes == i2.nbytes + + @pytest.mark.parametrize( + "start,stop,step", + [ + # can't + ("foo", "bar", "baz"), + # shouldn't + ("0", "1", "2"), + ], + ) + def test_cant_or_shouldnt_cast(self, start, stop, step): + msg = f"Wrong type {type(start)} for value {start}" + with pytest.raises(TypeError, match=msg): + RangeIndex(start, stop, step) + + def test_view_index(self, simple_index): + index = simple_index + msg = "Passing a type in RangeIndex.view is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + index.view(Index) + + def test_prevent_casting(self, simple_index): + index = simple_index + result = index.astype("O") + assert result.dtype == np.object_ + + def test_repr_roundtrip(self, simple_index): + index = simple_index + tm.assert_index_equal(eval(repr(index)), index) + + def test_slice_keep_name(self): + idx = RangeIndex(1, 2, name="asdf") + assert idx.name == idx[1:].name + + @pytest.mark.parametrize( + "index", + [ + RangeIndex(start=0, stop=20, step=2, name="foo"), + RangeIndex(start=18, stop=-1, step=-2, name="bar"), + ], + ids=["index_inc", "index_dec"], + ) + def test_has_duplicates(self, index): + assert index.is_unique + assert not index.has_duplicates + + def test_extended_gcd(self, simple_index): + index = simple_index + result = index._extended_gcd(6, 10) + assert result[0] == result[1] * 6 + result[2] * 10 + assert 2 == result[0] + + result = index._extended_gcd(10, 6) + assert 2 == result[1] * 10 + result[2] * 6 + assert 2 == result[0] + + def test_min_fitting_element(self): + result = RangeIndex(0, 20, 2)._min_fitting_element(1) + assert 2 == result + + result = RangeIndex(1, 6)._min_fitting_element(1) + assert 1 == result + + result = RangeIndex(18, -2, -2)._min_fitting_element(1) + assert 2 == result + + result = RangeIndex(5, 0, -1)._min_fitting_element(1) + assert 1 == result + + big_num = 500000000000000000000000 + + result = RangeIndex(5, big_num * 2, 1)._min_fitting_element(big_num) + assert big_num == result + + def test_slice_specialised(self, simple_index): + index = simple_index + index.name = "foo" + + # scalar indexing + res = index[1] + expected = 2 + assert res == expected + + res = index[-1] + expected = 18 + assert res == expected + + # slicing + # slice value completion + index_slice = index[:] + expected = index + tm.assert_index_equal(index_slice, expected) + + # positive slice values + index_slice = index[7:10:2] + expected = Index([14, 18], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + # negative slice values + index_slice = index[-1:-5:-2] + expected = Index([18, 14], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + # stop overshoot + index_slice = index[2:100:4] + expected = Index([4, 12], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + # reverse + index_slice = index[::-1] + expected = Index(index.values[::-1], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + index_slice = index[-8::-1] + expected = Index([4, 2, 0], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + index_slice = index[-40::-1] + expected = Index(np.array([], dtype=np.int64), name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + index_slice = index[40::-1] + expected = Index(index.values[40::-1], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + index_slice = index[10::-1] + expected = Index(index.values[::-1], name="foo") + tm.assert_index_equal(index_slice, expected, exact="equiv") + + @pytest.mark.parametrize("step", set(range(-5, 6)) - {0}) + def test_len_specialised(self, step): + # make sure that our len is the same as np.arange calc + start, stop = (0, 5) if step > 0 else (5, 0) + + arr = np.arange(start, stop, step) + index = RangeIndex(start, stop, step) + assert len(index) == len(arr) + + index = RangeIndex(stop, start, step) + assert len(index) == 0 + + @pytest.mark.parametrize( + "indices, expected", + [ + ([RangeIndex(1, 12, 5)], RangeIndex(1, 12, 5)), + ([RangeIndex(0, 6, 4)], RangeIndex(0, 6, 4)), + ([RangeIndex(1, 3), RangeIndex(3, 7)], RangeIndex(1, 7)), + ([RangeIndex(1, 5, 2), RangeIndex(5, 6)], RangeIndex(1, 6, 2)), + ([RangeIndex(1, 3, 2), RangeIndex(4, 7, 3)], RangeIndex(1, 7, 3)), + ([RangeIndex(-4, 3, 2), RangeIndex(4, 7, 2)], RangeIndex(-4, 7, 2)), + ([RangeIndex(-4, -8), RangeIndex(-8, -12)], RangeIndex(0, 0)), + ([RangeIndex(-4, -8), RangeIndex(3, -4)], RangeIndex(0, 0)), + ([RangeIndex(-4, -8), RangeIndex(3, 5)], RangeIndex(3, 5)), + ([RangeIndex(-4, -2), RangeIndex(3, 5)], Index([-4, -3, 3, 4])), + ([RangeIndex(-2), RangeIndex(3, 5)], RangeIndex(3, 5)), + ([RangeIndex(2), RangeIndex(2)], Index([0, 1, 0, 1])), + ([RangeIndex(2), RangeIndex(2, 5), RangeIndex(5, 8, 4)], RangeIndex(0, 6)), + ( + [RangeIndex(2), RangeIndex(3, 5), RangeIndex(5, 8, 4)], + Index([0, 1, 3, 4, 5]), + ), + ( + [RangeIndex(-2, 2), RangeIndex(2, 5), RangeIndex(5, 8, 4)], + RangeIndex(-2, 6), + ), + ([RangeIndex(3), Index([-1, 3, 15])], Index([0, 1, 2, -1, 3, 15])), + ([RangeIndex(3), Index([-1, 3.1, 15.0])], Index([0, 1, 2, -1, 3.1, 15.0])), + ([RangeIndex(3), Index(["a", None, 14])], Index([0, 1, 2, "a", None, 14])), + ([RangeIndex(3, 1), Index(["a", None, 14])], Index(["a", None, 14])), + ], + ) + def test_append(self, indices, expected): + # GH16212 + result = indices[0].append(indices[1:]) + tm.assert_index_equal(result, expected, exact=True) + + if len(indices) == 2: + # Append single item rather than list + result2 = indices[0].append(indices[1]) + tm.assert_index_equal(result2, expected, exact=True) + + def test_engineless_lookup(self): + # GH 16685 + # Standard lookup on RangeIndex should not require the engine to be + # created + idx = RangeIndex(2, 10, 3) + + assert idx.get_loc(5) == 1 + tm.assert_numpy_array_equal( + idx.get_indexer([2, 8]), ensure_platform_int(np.array([0, 2])) + ) + with pytest.raises(KeyError, match="3"): + idx.get_loc(3) + + assert "_engine" not in idx._cache + + # Different types of scalars can be excluded immediately, no need to + # use the _engine + with pytest.raises(KeyError, match="'a'"): + idx.get_loc("a") + + assert "_engine" not in idx._cache + + def test_format_empty(self): + # GH35712 + empty_idx = RangeIndex(0) + msg = r"RangeIndex\.format is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + assert empty_idx.format() == [] + with tm.assert_produces_warning(FutureWarning, match=msg): + assert empty_idx.format(name=True) == [""] + + @pytest.mark.parametrize( + "ri", + [ + RangeIndex(0, -1, -1), + RangeIndex(0, 1, 1), + RangeIndex(1, 3, 2), + RangeIndex(0, -1, -2), + RangeIndex(-3, -5, -2), + ], + ) + def test_append_len_one(self, ri): + # GH39401 + result = ri.append([]) + tm.assert_index_equal(result, ri, exact=True) + + @pytest.mark.parametrize("base", [RangeIndex(0, 2), Index([0, 1])]) + def test_isin_range(self, base): + # GH#41151 + values = RangeIndex(0, 1) + result = base.isin(values) + expected = np.array([True, False]) + tm.assert_numpy_array_equal(result, expected) + + def test_sort_values_key(self): + # GH#43666, GH#52764 + sort_order = {8: 2, 6: 0, 4: 8, 2: 10, 0: 12} + values = RangeIndex(0, 10, 2) + result = values.sort_values(key=lambda x: x.map(sort_order)) + expected = Index([6, 8, 4, 2, 0], dtype="int64") + tm.assert_index_equal(result, expected, check_exact=True) + + # check this matches the Series.sort_values behavior + ser = values.to_series() + result2 = ser.sort_values(key=lambda x: x.map(sort_order)) + tm.assert_series_equal(result2, expected.to_series(), check_exact=True) + + def test_range_index_rsub_by_const(self): + # GH#53255 + result = 3 - RangeIndex(0, 4, 1) + expected = RangeIndex(3, -1, -1) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..d417b8b743dc589bdf9d6acf5bde396a129ece23 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/ranges/test_setops.py @@ -0,0 +1,493 @@ +from datetime import ( + datetime, + timedelta, +) + +from hypothesis import ( + assume, + given, + strategies as st, +) +import numpy as np +import pytest + +from pandas import ( + Index, + RangeIndex, +) +import pandas._testing as tm + + +class TestRangeIndexSetOps: + @pytest.mark.parametrize("dtype", [None, "int64", "uint64"]) + def test_intersection_mismatched_dtype(self, dtype): + # check that we cast to float, not object + index = RangeIndex(start=0, stop=20, step=2, name="foo") + index = Index(index, dtype=dtype) + + flt = index.astype(np.float64) + + # bc index.equals(flt), we go through fastpath and get RangeIndex back + result = index.intersection(flt) + tm.assert_index_equal(result, index, exact=True) + + result = flt.intersection(index) + tm.assert_index_equal(result, flt, exact=True) + + # neither empty, not-equals + result = index.intersection(flt[1:]) + tm.assert_index_equal(result, flt[1:], exact=True) + + result = flt[1:].intersection(index) + tm.assert_index_equal(result, flt[1:], exact=True) + + # empty other + result = index.intersection(flt[:0]) + tm.assert_index_equal(result, flt[:0], exact=True) + + result = flt[:0].intersection(index) + tm.assert_index_equal(result, flt[:0], exact=True) + + def test_intersection_empty(self, sort, names): + # name retention on empty intersections + index = RangeIndex(start=0, stop=20, step=2, name=names[0]) + + # empty other + result = index.intersection(index[:0].rename(names[1]), sort=sort) + tm.assert_index_equal(result, index[:0].rename(names[2]), exact=True) + + # empty self + result = index[:0].intersection(index.rename(names[1]), sort=sort) + tm.assert_index_equal(result, index[:0].rename(names[2]), exact=True) + + def test_intersection(self, sort): + # intersect with Index with dtype int64 + index = RangeIndex(start=0, stop=20, step=2) + other = Index(np.arange(1, 6)) + result = index.intersection(other, sort=sort) + expected = Index(np.sort(np.intersect1d(index.values, other.values))) + tm.assert_index_equal(result, expected) + + result = other.intersection(index, sort=sort) + expected = Index( + np.sort(np.asarray(np.intersect1d(index.values, other.values))) + ) + tm.assert_index_equal(result, expected) + + # intersect with increasing RangeIndex + other = RangeIndex(1, 6) + result = index.intersection(other, sort=sort) + expected = Index(np.sort(np.intersect1d(index.values, other.values))) + tm.assert_index_equal(result, expected, exact="equiv") + + # intersect with decreasing RangeIndex + other = RangeIndex(5, 0, -1) + result = index.intersection(other, sort=sort) + expected = Index(np.sort(np.intersect1d(index.values, other.values))) + tm.assert_index_equal(result, expected, exact="equiv") + + # reversed (GH 17296) + result = other.intersection(index, sort=sort) + tm.assert_index_equal(result, expected, exact="equiv") + + # GH 17296: intersect two decreasing RangeIndexes + first = RangeIndex(10, -2, -2) + other = RangeIndex(5, -4, -1) + expected = first.astype(int).intersection(other.astype(int), sort=sort) + result = first.intersection(other, sort=sort).astype(int) + tm.assert_index_equal(result, expected) + + # reversed + result = other.intersection(first, sort=sort).astype(int) + tm.assert_index_equal(result, expected) + + index = RangeIndex(5, name="foo") + + # intersect of non-overlapping indices + other = RangeIndex(5, 10, 1, name="foo") + result = index.intersection(other, sort=sort) + expected = RangeIndex(0, 0, 1, name="foo") + tm.assert_index_equal(result, expected) + + other = RangeIndex(-1, -5, -1) + result = index.intersection(other, sort=sort) + expected = RangeIndex(0, 0, 1) + tm.assert_index_equal(result, expected) + + # intersection of empty indices + other = RangeIndex(0, 0, 1) + result = index.intersection(other, sort=sort) + expected = RangeIndex(0, 0, 1) + tm.assert_index_equal(result, expected) + + result = other.intersection(index, sort=sort) + tm.assert_index_equal(result, expected) + + def test_intersection_non_overlapping_gcd(self, sort, names): + # intersection of non-overlapping values based on start value and gcd + index = RangeIndex(1, 10, 2, name=names[0]) + other = RangeIndex(0, 10, 4, name=names[1]) + result = index.intersection(other, sort=sort) + expected = RangeIndex(0, 0, 1, name=names[2]) + tm.assert_index_equal(result, expected) + + def test_union_noncomparable(self, sort): + # corner case, Index with non-int64 dtype + index = RangeIndex(start=0, stop=20, step=2) + other = Index([datetime.now() + timedelta(i) for i in range(4)], dtype=object) + result = index.union(other, sort=sort) + expected = Index(np.concatenate((index, other))) + tm.assert_index_equal(result, expected) + + result = other.union(index, sort=sort) + expected = Index(np.concatenate((other, index))) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "idx1, idx2, expected_sorted, expected_notsorted", + [ + ( + RangeIndex(0, 10, 1), + RangeIndex(0, 10, 1), + RangeIndex(0, 10, 1), + RangeIndex(0, 10, 1), + ), + ( + RangeIndex(0, 10, 1), + RangeIndex(5, 20, 1), + RangeIndex(0, 20, 1), + RangeIndex(0, 20, 1), + ), + ( + RangeIndex(0, 10, 1), + RangeIndex(10, 20, 1), + RangeIndex(0, 20, 1), + RangeIndex(0, 20, 1), + ), + ( + RangeIndex(0, -10, -1), + RangeIndex(0, -10, -1), + RangeIndex(0, -10, -1), + RangeIndex(0, -10, -1), + ), + ( + RangeIndex(0, -10, -1), + RangeIndex(-10, -20, -1), + RangeIndex(-19, 1, 1), + RangeIndex(0, -20, -1), + ), + ( + RangeIndex(0, 10, 2), + RangeIndex(1, 10, 2), + RangeIndex(0, 10, 1), + Index(list(range(0, 10, 2)) + list(range(1, 10, 2))), + ), + ( + RangeIndex(0, 11, 2), + RangeIndex(1, 12, 2), + RangeIndex(0, 12, 1), + Index(list(range(0, 11, 2)) + list(range(1, 12, 2))), + ), + ( + RangeIndex(0, 21, 4), + RangeIndex(-2, 24, 4), + RangeIndex(-2, 24, 2), + Index(list(range(0, 21, 4)) + list(range(-2, 24, 4))), + ), + ( + RangeIndex(0, -20, -2), + RangeIndex(-1, -21, -2), + RangeIndex(-19, 1, 1), + Index(list(range(0, -20, -2)) + list(range(-1, -21, -2))), + ), + ( + RangeIndex(0, 100, 5), + RangeIndex(0, 100, 20), + RangeIndex(0, 100, 5), + RangeIndex(0, 100, 5), + ), + ( + RangeIndex(0, -100, -5), + RangeIndex(5, -100, -20), + RangeIndex(-95, 10, 5), + Index(list(range(0, -100, -5)) + [5]), + ), + ( + RangeIndex(0, -11, -1), + RangeIndex(1, -12, -4), + RangeIndex(-11, 2, 1), + Index(list(range(0, -11, -1)) + [1, -11]), + ), + (RangeIndex(0), RangeIndex(0), RangeIndex(0), RangeIndex(0)), + ( + RangeIndex(0, -10, -2), + RangeIndex(0), + RangeIndex(0, -10, -2), + RangeIndex(0, -10, -2), + ), + ( + RangeIndex(0, 100, 2), + RangeIndex(100, 150, 200), + RangeIndex(0, 102, 2), + RangeIndex(0, 102, 2), + ), + ( + RangeIndex(0, -100, -2), + RangeIndex(-100, 50, 102), + RangeIndex(-100, 4, 2), + Index(list(range(0, -100, -2)) + [-100, 2]), + ), + ( + RangeIndex(0, -100, -1), + RangeIndex(0, -50, -3), + RangeIndex(-99, 1, 1), + RangeIndex(0, -100, -1), + ), + ( + RangeIndex(0, 1, 1), + RangeIndex(5, 6, 10), + RangeIndex(0, 6, 5), + RangeIndex(0, 10, 5), + ), + ( + RangeIndex(0, 10, 5), + RangeIndex(-5, -6, -20), + RangeIndex(-5, 10, 5), + Index([0, 5, -5]), + ), + ( + RangeIndex(0, 3, 1), + RangeIndex(4, 5, 1), + Index([0, 1, 2, 4]), + Index([0, 1, 2, 4]), + ), + ( + RangeIndex(0, 10, 1), + Index([], dtype=np.int64), + RangeIndex(0, 10, 1), + RangeIndex(0, 10, 1), + ), + ( + RangeIndex(0), + Index([1, 5, 6]), + Index([1, 5, 6]), + Index([1, 5, 6]), + ), + # GH 43885 + ( + RangeIndex(0, 10), + RangeIndex(0, 5), + RangeIndex(0, 10), + RangeIndex(0, 10), + ), + ], + ids=lambda x: repr(x) if isinstance(x, RangeIndex) else x, + ) + def test_union_sorted(self, idx1, idx2, expected_sorted, expected_notsorted): + res1 = idx1.union(idx2, sort=None) + tm.assert_index_equal(res1, expected_sorted, exact=True) + + res1 = idx1.union(idx2, sort=False) + tm.assert_index_equal(res1, expected_notsorted, exact=True) + + res2 = idx2.union(idx1, sort=None) + res3 = Index(idx1._values, name=idx1.name).union(idx2, sort=None) + tm.assert_index_equal(res2, expected_sorted, exact=True) + tm.assert_index_equal(res3, expected_sorted, exact="equiv") + + def test_union_same_step_misaligned(self): + # GH#44019 + left = RangeIndex(range(0, 20, 4)) + right = RangeIndex(range(1, 21, 4)) + + result = left.union(right) + expected = Index([0, 1, 4, 5, 8, 9, 12, 13, 16, 17]) + tm.assert_index_equal(result, expected, exact=True) + + def test_difference(self): + # GH#12034 Cases where we operate against another RangeIndex and may + # get back another RangeIndex + obj = RangeIndex.from_range(range(1, 10), name="foo") + + result = obj.difference(obj) + expected = RangeIndex.from_range(range(0), name="foo") + tm.assert_index_equal(result, expected, exact=True) + + result = obj.difference(expected.rename("bar")) + tm.assert_index_equal(result, obj.rename(None), exact=True) + + result = obj.difference(obj[:3]) + tm.assert_index_equal(result, obj[3:], exact=True) + + result = obj.difference(obj[-3:]) + tm.assert_index_equal(result, obj[:-3], exact=True) + + # Flipping the step of 'other' doesn't affect the result, but + # flipping the stepof 'self' does when sort=None + result = obj[::-1].difference(obj[-3:]) + tm.assert_index_equal(result, obj[:-3], exact=True) + + result = obj[::-1].difference(obj[-3:], sort=False) + tm.assert_index_equal(result, obj[:-3][::-1], exact=True) + + result = obj[::-1].difference(obj[-3:][::-1]) + tm.assert_index_equal(result, obj[:-3], exact=True) + + result = obj[::-1].difference(obj[-3:][::-1], sort=False) + tm.assert_index_equal(result, obj[:-3][::-1], exact=True) + + result = obj.difference(obj[2:6]) + expected = Index([1, 2, 7, 8, 9], name="foo") + tm.assert_index_equal(result, expected, exact=True) + + def test_difference_sort(self): + # GH#44085 ensure we respect the sort keyword + + idx = Index(range(4))[::-1] + other = Index(range(3, 4)) + + result = idx.difference(other) + expected = Index(range(3)) + tm.assert_index_equal(result, expected, exact=True) + + result = idx.difference(other, sort=False) + expected = expected[::-1] + tm.assert_index_equal(result, expected, exact=True) + + # case where the intersection is empty + other = range(10, 12) + result = idx.difference(other, sort=None) + expected = idx[::-1] + tm.assert_index_equal(result, expected, exact=True) + + def test_difference_mismatched_step(self): + obj = RangeIndex.from_range(range(1, 10), name="foo") + + result = obj.difference(obj[::2]) + expected = obj[1::2] + tm.assert_index_equal(result, expected, exact=True) + + result = obj[::-1].difference(obj[::2], sort=False) + tm.assert_index_equal(result, expected[::-1], exact=True) + + result = obj.difference(obj[1::2]) + expected = obj[::2] + tm.assert_index_equal(result, expected, exact=True) + + result = obj[::-1].difference(obj[1::2], sort=False) + tm.assert_index_equal(result, expected[::-1], exact=True) + + def test_difference_interior_overlap_endpoints_preserved(self): + left = RangeIndex(range(4)) + right = RangeIndex(range(1, 3)) + + result = left.difference(right) + expected = RangeIndex(0, 4, 3) + assert expected.tolist() == [0, 3] + tm.assert_index_equal(result, expected, exact=True) + + def test_difference_endpoints_overlap_interior_preserved(self): + left = RangeIndex(-8, 20, 7) + right = RangeIndex(13, -9, -3) + + result = left.difference(right) + expected = RangeIndex(-1, 13, 7) + assert expected.tolist() == [-1, 6] + tm.assert_index_equal(result, expected, exact=True) + + def test_difference_interior_non_preserving(self): + # case with intersection of length 1 but RangeIndex is not preserved + idx = Index(range(10)) + + other = idx[3:4] + result = idx.difference(other) + expected = Index([0, 1, 2, 4, 5, 6, 7, 8, 9]) + tm.assert_index_equal(result, expected, exact=True) + + # case with other.step / self.step > 2 + other = idx[::3] + result = idx.difference(other) + expected = Index([1, 2, 4, 5, 7, 8]) + tm.assert_index_equal(result, expected, exact=True) + + # cases with only reaching one end of left + obj = Index(range(20)) + other = obj[:10:2] + result = obj.difference(other) + expected = Index([1, 3, 5, 7, 9] + list(range(10, 20))) + tm.assert_index_equal(result, expected, exact=True) + + other = obj[1:11:2] + result = obj.difference(other) + expected = Index([0, 2, 4, 6, 8, 10] + list(range(11, 20))) + tm.assert_index_equal(result, expected, exact=True) + + def test_symmetric_difference(self): + # GH#12034 Cases where we operate against another RangeIndex and may + # get back another RangeIndex + left = RangeIndex.from_range(range(1, 10), name="foo") + + result = left.symmetric_difference(left) + expected = RangeIndex.from_range(range(0), name="foo") + tm.assert_index_equal(result, expected) + + result = left.symmetric_difference(expected.rename("bar")) + tm.assert_index_equal(result, left.rename(None)) + + result = left[:-2].symmetric_difference(left[2:]) + expected = Index([1, 2, 8, 9], name="foo") + tm.assert_index_equal(result, expected, exact=True) + + right = RangeIndex.from_range(range(10, 15)) + + result = left.symmetric_difference(right) + expected = RangeIndex.from_range(range(1, 15)) + tm.assert_index_equal(result, expected) + + result = left.symmetric_difference(right[1:]) + expected = Index([1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 13, 14]) + tm.assert_index_equal(result, expected, exact=True) + + +def assert_range_or_not_is_rangelike(index): + """ + Check that we either have a RangeIndex or that this index *cannot* + be represented as a RangeIndex. + """ + if not isinstance(index, RangeIndex) and len(index) > 0: + diff = index[:-1] - index[1:] + assert not (diff == diff[0]).all() + + +@given( + st.integers(-20, 20), + st.integers(-20, 20), + st.integers(-20, 20), + st.integers(-20, 20), + st.integers(-20, 20), + st.integers(-20, 20), +) +def test_range_difference(start1, stop1, step1, start2, stop2, step2): + # test that + # a) we match Index[int64].difference and + # b) we return RangeIndex whenever it is possible to do so. + assume(step1 != 0) + assume(step2 != 0) + + left = RangeIndex(start1, stop1, step1) + right = RangeIndex(start2, stop2, step2) + + result = left.difference(right, sort=None) + assert_range_or_not_is_rangelike(result) + + left_int64 = Index(left.to_numpy()) + right_int64 = Index(right.to_numpy()) + + alt = left_int64.difference(right_int64, sort=None) + tm.assert_index_equal(result, alt, exact="equiv") + + result = left.difference(right, sort=False) + assert_range_or_not_is_rangelike(result) + + alt = left_int64.difference(right_int64, sort=False) + tm.assert_index_equal(result, alt, exact="equiv") diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c14ffe2845011fbdf05df7fae41cd7f0442852e9 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_arithmetic.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_arithmetic.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ad7e914c13ce93d4c44bbd575b0c9c606292e4df Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_arithmetic.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_constructors.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_constructors.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f6b8baae04124985bd6285c067a694c5b6b61e86 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_constructors.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_delete.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_delete.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..714746bf939abe56d369e9b534d6ea2420003809 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_delete.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_formats.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_formats.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..42dc1215dc18460f6bbbe5f67f5f54ae6b2a61f7 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_formats.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_freq_attr.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_freq_attr.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0c7077ea48c9a4128131f9b39da03bdc1bcafa50 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_freq_attr.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_indexing.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_indexing.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a3a2133e4ccaa33e5a68e7c9b8d5efc0db7a7bff Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_indexing.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_join.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_join.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0f84ee858e539c7ef5cb06fa424d117464fe3db3 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_join.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_ops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_ops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b9801c34d2b3ec53273130db6e58face8a6a6473 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_ops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_pickle.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_pickle.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9c81edaca3607613b4d10e252c0b843a859d6ca2 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_pickle.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_scalar_compat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_scalar_compat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..388963aec74e5e8dc6dc87978839c05beca1294e Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_scalar_compat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_searchsorted.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_searchsorted.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bcbcea8272ffea143cdad581dcaae703f92b81fa Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_searchsorted.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_setops.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_setops.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c5ac2908c3417d317d93c8dfaae72a979a7cf590 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_setops.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1ad241b9b6e5a45ea61c8515a4e3ee2dcf202155 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta_range.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta_range.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3d241cb37936eb0d0fd32c4069f372e02ce48111 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/__pycache__/test_timedelta_range.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__init__.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/__init__.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/__init__.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..52e91a8efc32c4e8fccdaa1dd1f4bfe94d2c64fd Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/__init__.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_astype.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_astype.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..21a383c13d18d34d733ba7d09563ed177e726d34 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_astype.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_factorize.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_factorize.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..194ade0e72c4ca71873ac5d52aa0e4cb931f4630 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_factorize.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_fillna.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_fillna.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3281f73f1be09acbb6b624416bc90be29ab22698 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_fillna.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_insert.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_insert.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f94ab5373ffa49f4f82961693a9716651bbe3007 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_insert.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_repeat.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_repeat.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2a95a80b1ac354dc50a0070baee45c0e9dcbfd6f Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_repeat.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_shift.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_shift.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f61e7f5fc1b7253f0e85bef0963f39bd8ede0381 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/__pycache__/test_shift.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_astype.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_astype.py new file mode 100644 index 0000000000000000000000000000000000000000..311f2b5c9aa598de68543825d1bde9dc814b469e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_astype.py @@ -0,0 +1,176 @@ +from datetime import timedelta + +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + NaT, + Timedelta, + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm +from pandas.core.arrays import TimedeltaArray + + +class TestTimedeltaIndex: + def test_astype_object(self): + idx = timedelta_range(start="1 days", periods=4, freq="D", name="idx") + expected_list = [ + Timedelta("1 days"), + Timedelta("2 days"), + Timedelta("3 days"), + Timedelta("4 days"), + ] + result = idx.astype(object) + expected = Index(expected_list, dtype=object, name="idx") + tm.assert_index_equal(result, expected) + assert idx.tolist() == expected_list + + def test_astype_object_with_nat(self): + idx = TimedeltaIndex( + [timedelta(days=1), timedelta(days=2), NaT, timedelta(days=4)], name="idx" + ) + expected_list = [ + Timedelta("1 days"), + Timedelta("2 days"), + NaT, + Timedelta("4 days"), + ] + result = idx.astype(object) + expected = Index(expected_list, dtype=object, name="idx") + tm.assert_index_equal(result, expected) + assert idx.tolist() == expected_list + + def test_astype(self): + # GH 13149, GH 13209 + idx = TimedeltaIndex([1e14, "NaT", NaT, np.nan], name="idx") + + result = idx.astype(object) + expected = Index( + [Timedelta("1 days 03:46:40")] + [NaT] * 3, dtype=object, name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.astype(np.int64) + expected = Index( + [100000000000000] + [-9223372036854775808] * 3, dtype=np.int64, name="idx" + ) + tm.assert_index_equal(result, expected) + + result = idx.astype(str) + expected = Index([str(x) for x in idx], name="idx", dtype=object) + tm.assert_index_equal(result, expected) + + rng = timedelta_range("1 days", periods=10) + result = rng.astype("i8") + tm.assert_index_equal(result, Index(rng.asi8)) + tm.assert_numpy_array_equal(rng.asi8, result.values) + + def test_astype_uint(self): + arr = timedelta_range("1h", periods=2) + + with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"): + arr.astype("uint64") + with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"): + arr.astype("uint32") + + def test_astype_timedelta64(self): + # GH 13149, GH 13209 + idx = TimedeltaIndex([1e14, "NaT", NaT, np.nan]) + + msg = ( + r"Cannot convert from timedelta64\[ns\] to timedelta64. " + "Supported resolutions are 's', 'ms', 'us', 'ns'" + ) + with pytest.raises(ValueError, match=msg): + idx.astype("timedelta64") + + result = idx.astype("timedelta64[ns]") + tm.assert_index_equal(result, idx) + assert result is not idx + + result = idx.astype("timedelta64[ns]", copy=False) + tm.assert_index_equal(result, idx) + assert result is idx + + def test_astype_to_td64d_raises(self, index_or_series): + # We don't support "D" reso + scalar = Timedelta(days=31) + td = index_or_series( + [scalar, scalar, scalar + timedelta(minutes=5, seconds=3), NaT], + dtype="m8[ns]", + ) + msg = ( + r"Cannot convert from timedelta64\[ns\] to timedelta64\[D\]. " + "Supported resolutions are 's', 'ms', 'us', 'ns'" + ) + with pytest.raises(ValueError, match=msg): + td.astype("timedelta64[D]") + + def test_astype_ms_to_s(self, index_or_series): + scalar = Timedelta(days=31) + td = index_or_series( + [scalar, scalar, scalar + timedelta(minutes=5, seconds=3), NaT], + dtype="m8[ns]", + ) + + exp_values = np.asarray(td).astype("m8[s]") + exp_tda = TimedeltaArray._simple_new(exp_values, dtype=exp_values.dtype) + expected = index_or_series(exp_tda) + assert expected.dtype == "m8[s]" + result = td.astype("timedelta64[s]") + tm.assert_equal(result, expected) + + def test_astype_freq_conversion(self): + # pre-2.0 td64 astype converted to float64. now for supported units + # (s, ms, us, ns) this converts to the requested dtype. + # This matches TDA and Series + tdi = timedelta_range("1 Day", periods=30) + + res = tdi.astype("m8[s]") + exp_values = np.asarray(tdi).astype("m8[s]") + exp_tda = TimedeltaArray._simple_new( + exp_values, dtype=exp_values.dtype, freq=tdi.freq + ) + expected = Index(exp_tda) + assert expected.dtype == "m8[s]" + tm.assert_index_equal(res, expected) + + # check this matches Series and TimedeltaArray + res = tdi._data.astype("m8[s]") + tm.assert_equal(res, expected._values) + + res = tdi.to_series().astype("m8[s]") + tm.assert_equal(res._values, expected._values._with_freq(None)) + + @pytest.mark.parametrize("dtype", [float, "datetime64", "datetime64[ns]"]) + def test_astype_raises(self, dtype): + # GH 13149, GH 13209 + idx = TimedeltaIndex([1e14, "NaT", NaT, np.nan]) + msg = "Cannot cast TimedeltaIndex to dtype" + with pytest.raises(TypeError, match=msg): + idx.astype(dtype) + + def test_astype_category(self): + obj = timedelta_range("1h", periods=2, freq="h") + + result = obj.astype("category") + expected = pd.CategoricalIndex([Timedelta("1h"), Timedelta("2h")]) + tm.assert_index_equal(result, expected) + + result = obj._data.astype("category") + expected = expected.values + tm.assert_categorical_equal(result, expected) + + def test_astype_array_fallback(self): + obj = timedelta_range("1h", periods=2) + result = obj.astype(bool) + expected = Index(np.array([True, True])) + tm.assert_index_equal(result, expected) + + result = obj._data.astype(bool) + expected = np.array([True, True]) + tm.assert_numpy_array_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_factorize.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_factorize.py new file mode 100644 index 0000000000000000000000000000000000000000..24ab3888412d08b54543ed22910c67ce9bdf328f --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_factorize.py @@ -0,0 +1,40 @@ +import numpy as np + +from pandas import ( + TimedeltaIndex, + factorize, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndexFactorize: + def test_factorize(self): + idx1 = TimedeltaIndex(["1 day", "1 day", "2 day", "2 day", "3 day", "3 day"]) + + exp_arr = np.array([0, 0, 1, 1, 2, 2], dtype=np.intp) + exp_idx = TimedeltaIndex(["1 day", "2 day", "3 day"]) + + arr, idx = idx1.factorize() + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) + assert idx.freq == exp_idx.freq + + arr, idx = idx1.factorize(sort=True) + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, exp_idx) + assert idx.freq == exp_idx.freq + + def test_factorize_preserves_freq(self): + # GH#38120 freq should be preserved + idx3 = timedelta_range("1 day", periods=4, freq="s") + exp_arr = np.array([0, 1, 2, 3], dtype=np.intp) + arr, idx = idx3.factorize() + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, idx3) + assert idx.freq == idx3.freq + + arr, idx = factorize(idx3) + tm.assert_numpy_array_equal(arr, exp_arr) + tm.assert_index_equal(idx, idx3) + assert idx.freq == idx3.freq diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_fillna.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_fillna.py new file mode 100644 index 0000000000000000000000000000000000000000..40aa95d0a46058d2dc3fc5208ca39328d96b23fb --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_fillna.py @@ -0,0 +1,22 @@ +from pandas import ( + Index, + NaT, + Timedelta, + TimedeltaIndex, +) +import pandas._testing as tm + + +class TestFillNA: + def test_fillna_timedelta(self): + # GH#11343 + idx = TimedeltaIndex(["1 day", NaT, "3 day"]) + + exp = TimedeltaIndex(["1 day", "2 day", "3 day"]) + tm.assert_index_equal(idx.fillna(Timedelta("2 day")), exp) + + exp = TimedeltaIndex(["1 day", "3 hour", "3 day"]) + idx.fillna(Timedelta("3 hour")) + + exp = Index([Timedelta("1 day"), "x", Timedelta("3 day")], dtype=object) + tm.assert_index_equal(idx.fillna("x"), exp) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_insert.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_insert.py new file mode 100644 index 0000000000000000000000000000000000000000..f8164102815f61ec61962524db2a2b3dd0ff6d55 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_insert.py @@ -0,0 +1,145 @@ +from datetime import timedelta + +import numpy as np +import pytest + +from pandas._libs import lib + +import pandas as pd +from pandas import ( + Index, + Timedelta, + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndexInsert: + def test_insert(self): + idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx") + + result = idx.insert(2, timedelta(days=5)) + exp = TimedeltaIndex(["4day", "1day", "5day", "2day"], name="idx") + tm.assert_index_equal(result, exp) + + # insertion of non-datetime should coerce to object index + result = idx.insert(1, "inserted") + expected = Index( + [Timedelta("4day"), "inserted", Timedelta("1day"), Timedelta("2day")], + name="idx", + ) + assert not isinstance(result, TimedeltaIndex) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + + idx = timedelta_range("1day 00:00:01", periods=3, freq="s", name="idx") + + # preserve freq + expected_0 = TimedeltaIndex( + ["1day", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"], + name="idx", + freq="s", + ) + expected_3 = TimedeltaIndex( + ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:04"], + name="idx", + freq="s", + ) + + # reset freq to None + expected_1_nofreq = TimedeltaIndex( + ["1day 00:00:01", "1day 00:00:01", "1day 00:00:02", "1day 00:00:03"], + name="idx", + freq=None, + ) + expected_3_nofreq = TimedeltaIndex( + ["1day 00:00:01", "1day 00:00:02", "1day 00:00:03", "1day 00:00:05"], + name="idx", + freq=None, + ) + + cases = [ + (0, Timedelta("1day"), expected_0), + (-3, Timedelta("1day"), expected_0), + (3, Timedelta("1day 00:00:04"), expected_3), + (1, Timedelta("1day 00:00:01"), expected_1_nofreq), + (3, Timedelta("1day 00:00:05"), expected_3_nofreq), + ] + + for n, d, expected in cases: + result = idx.insert(n, d) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + @pytest.mark.parametrize( + "null", [None, np.nan, np.timedelta64("NaT"), pd.NaT, pd.NA] + ) + def test_insert_nat(self, null): + # GH 18295 (test missing) + idx = timedelta_range("1day", "3day") + result = idx.insert(1, null) + expected = TimedeltaIndex(["1day", pd.NaT, "2day", "3day"]) + tm.assert_index_equal(result, expected) + + def test_insert_invalid_na(self): + idx = TimedeltaIndex(["4day", "1day", "2day"], name="idx") + + item = np.datetime64("NaT") + result = idx.insert(0, item) + + expected = Index([item] + list(idx), dtype=object, name="idx") + tm.assert_index_equal(result, expected) + + # Also works if we pass a different dt64nat object + item2 = np.datetime64("NaT") + result = idx.insert(0, item2) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "item", [0, np.int64(0), np.float64(0), np.array(0), np.datetime64(456, "us")] + ) + def test_insert_mismatched_types_raises(self, item): + # GH#33703 dont cast these to td64 + tdi = TimedeltaIndex(["4day", "1day", "2day"], name="idx") + + result = tdi.insert(1, item) + + expected = Index( + [tdi[0], lib.item_from_zerodim(item)] + list(tdi[1:]), + dtype=object, + name="idx", + ) + tm.assert_index_equal(result, expected) + + def test_insert_castable_str(self): + idx = timedelta_range("1day", "3day") + + result = idx.insert(0, "1 Day") + + expected = TimedeltaIndex([idx[0]] + list(idx)) + tm.assert_index_equal(result, expected) + + def test_insert_non_castable_str(self): + idx = timedelta_range("1day", "3day") + + result = idx.insert(0, "foo") + + expected = Index(["foo"] + list(idx), dtype=object) + tm.assert_index_equal(result, expected) + + def test_insert_empty(self): + # Corner case inserting with length zero doesn't raise IndexError + # GH#33573 for freq preservation + idx = timedelta_range("1 Day", periods=3) + td = idx[0] + + result = idx[:0].insert(0, td) + assert result.freq == "D" + + with pytest.raises(IndexError, match="loc must be an integer between"): + result = idx[:0].insert(1, td) + + with pytest.raises(IndexError, match="loc must be an integer between"): + result = idx[:0].insert(-1, td) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_repeat.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_repeat.py new file mode 100644 index 0000000000000000000000000000000000000000..2a9b58d1bf322938e9344d0cbacfaa79674fcf0e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_repeat.py @@ -0,0 +1,34 @@ +import numpy as np + +from pandas import ( + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +class TestRepeat: + def test_repeat(self): + index = timedelta_range("1 days", periods=2, freq="D") + exp = TimedeltaIndex(["1 days", "1 days", "2 days", "2 days"]) + for res in [index.repeat(2), np.repeat(index, 2)]: + tm.assert_index_equal(res, exp) + assert res.freq is None + + index = TimedeltaIndex(["1 days", "NaT", "3 days"]) + exp = TimedeltaIndex( + [ + "1 days", + "1 days", + "1 days", + "NaT", + "NaT", + "NaT", + "3 days", + "3 days", + "3 days", + ] + ) + for res in [index.repeat(3), np.repeat(index, 3)]: + tm.assert_index_equal(res, exp) + assert res.freq is None diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_shift.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_shift.py new file mode 100644 index 0000000000000000000000000000000000000000..a0986d1496881a2061ac8306d0a064f4393cd4e9 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/methods/test_shift.py @@ -0,0 +1,76 @@ +import pytest + +from pandas.errors import NullFrequencyError + +import pandas as pd +from pandas import TimedeltaIndex +import pandas._testing as tm + + +class TestTimedeltaIndexShift: + # ------------------------------------------------------------- + # TimedeltaIndex.shift is used by __add__/__sub__ + + def test_tdi_shift_empty(self): + # GH#9903 + idx = TimedeltaIndex([], name="xxx") + tm.assert_index_equal(idx.shift(0, freq="h"), idx) + tm.assert_index_equal(idx.shift(3, freq="h"), idx) + + def test_tdi_shift_hours(self): + # GH#9903 + idx = TimedeltaIndex(["5 hours", "6 hours", "9 hours"], name="xxx") + tm.assert_index_equal(idx.shift(0, freq="h"), idx) + exp = TimedeltaIndex(["8 hours", "9 hours", "12 hours"], name="xxx") + tm.assert_index_equal(idx.shift(3, freq="h"), exp) + exp = TimedeltaIndex(["2 hours", "3 hours", "6 hours"], name="xxx") + tm.assert_index_equal(idx.shift(-3, freq="h"), exp) + + def test_tdi_shift_minutes(self): + # GH#9903 + idx = TimedeltaIndex(["5 hours", "6 hours", "9 hours"], name="xxx") + tm.assert_index_equal(idx.shift(0, freq="min"), idx) + exp = TimedeltaIndex(["05:03:00", "06:03:00", "9:03:00"], name="xxx") + tm.assert_index_equal(idx.shift(3, freq="min"), exp) + exp = TimedeltaIndex(["04:57:00", "05:57:00", "8:57:00"], name="xxx") + tm.assert_index_equal(idx.shift(-3, freq="min"), exp) + + def test_tdi_shift_int(self): + # GH#8083 + tdi = pd.to_timedelta(range(5), unit="d") + trange = tdi._with_freq("infer") + pd.offsets.Hour(1) + result = trange.shift(1) + expected = TimedeltaIndex( + [ + "1 days 01:00:00", + "2 days 01:00:00", + "3 days 01:00:00", + "4 days 01:00:00", + "5 days 01:00:00", + ], + freq="D", + ) + tm.assert_index_equal(result, expected) + + def test_tdi_shift_nonstandard_freq(self): + # GH#8083 + tdi = pd.to_timedelta(range(5), unit="d") + trange = tdi._with_freq("infer") + pd.offsets.Hour(1) + result = trange.shift(3, freq="2D 1s") + expected = TimedeltaIndex( + [ + "6 days 01:00:03", + "7 days 01:00:03", + "8 days 01:00:03", + "9 days 01:00:03", + "10 days 01:00:03", + ], + freq="D", + ) + tm.assert_index_equal(result, expected) + + def test_shift_no_freq(self): + # GH#19147 + tdi = TimedeltaIndex(["1 days 01:00:00", "2 days 01:00:00"], freq=None) + with pytest.raises(NullFrequencyError, match="Cannot shift with no freq"): + tdi.shift(2) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_arithmetic.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_arithmetic.py new file mode 100644 index 0000000000000000000000000000000000000000..a431e10dc18ab15da0fd07f798d54b6dead26073 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_arithmetic.py @@ -0,0 +1,51 @@ +# Arithmetic tests for TimedeltaIndex are generally about the result's `freq` attribute. +# Other cases can be shared in tests.arithmetic.test_timedelta64 +import numpy as np + +from pandas import ( + NaT, + Timedelta, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndexArithmetic: + def test_arithmetic_zero_freq(self): + # GH#51575 don't get a .freq with freq.n = 0 + tdi = timedelta_range(0, periods=100, freq="ns") + result = tdi / 2 + assert result.freq is None + expected = tdi[:50].repeat(2) + tm.assert_index_equal(result, expected) + + result2 = tdi // 2 + assert result2.freq is None + expected2 = expected + tm.assert_index_equal(result2, expected2) + + result3 = tdi * 0 + assert result3.freq is None + expected3 = tdi[:1].repeat(100) + tm.assert_index_equal(result3, expected3) + + def test_tdi_division(self, index_or_series): + # doc example + + scalar = Timedelta(days=31) + td = index_or_series( + [scalar, scalar, scalar + Timedelta(minutes=5, seconds=3), NaT], + dtype="m8[ns]", + ) + + result = td / np.timedelta64(1, "D") + expected = index_or_series( + [31, 31, (31 * 86400 + 5 * 60 + 3) / 86400.0, np.nan] + ) + tm.assert_equal(result, expected) + + result = td / np.timedelta64(1, "s") + expected = index_or_series( + [31 * 86400, 31 * 86400, 31 * 86400 + 5 * 60 + 3, np.nan] + ) + tm.assert_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_constructors.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_constructors.py new file mode 100644 index 0000000000000000000000000000000000000000..0510700bb64d7a626761a67d72ecfa6ecfba9ac4 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_constructors.py @@ -0,0 +1,291 @@ +from datetime import timedelta + +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Timedelta, + TimedeltaIndex, + timedelta_range, + to_timedelta, +) +import pandas._testing as tm +from pandas.core.arrays.timedeltas import TimedeltaArray + + +class TestTimedeltaIndex: + def test_closed_deprecated(self): + # GH#52628 + msg = "The 'closed' keyword" + with tm.assert_produces_warning(FutureWarning, match=msg): + TimedeltaIndex([], closed=True) + + def test_array_of_dt64_nat_raises(self): + # GH#39462 + nat = np.datetime64("NaT", "ns") + arr = np.array([nat], dtype=object) + + msg = "Invalid type for timedelta scalar" + with pytest.raises(TypeError, match=msg): + TimedeltaIndex(arr) + + with pytest.raises(TypeError, match=msg): + TimedeltaArray._from_sequence(arr, dtype="m8[ns]") + + with pytest.raises(TypeError, match=msg): + to_timedelta(arr) + + @pytest.mark.parametrize("unit", ["Y", "y", "M"]) + def test_unit_m_y_raises(self, unit): + msg = "Units 'M', 'Y', and 'y' are no longer supported" + depr_msg = "The 'unit' keyword in TimedeltaIndex construction is deprecated" + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + TimedeltaIndex([1, 3, 7], unit) + + def test_int64_nocopy(self): + # GH#23539 check that a copy isn't made when we pass int64 data + # and copy=False + arr = np.arange(10, dtype=np.int64) + tdi = TimedeltaIndex(arr, copy=False) + assert tdi._data._ndarray.base is arr + + def test_infer_from_tdi(self): + # GH#23539 + # fast-path for inferring a frequency if the passed data already + # has one + tdi = timedelta_range("1 second", periods=10**7, freq="1s") + + result = TimedeltaIndex(tdi, freq="infer") + assert result.freq == tdi.freq + + # check that inferred_freq was not called by checking that the + # value has not been cached + assert "inferred_freq" not in getattr(result, "_cache", {}) + + def test_infer_from_tdi_mismatch(self): + # GH#23539 + # fast-path for invalidating a frequency if the passed data already + # has one and it does not match the `freq` input + tdi = timedelta_range("1 second", periods=100, freq="1s") + + depr_msg = "TimedeltaArray.__init__ is deprecated" + msg = ( + "Inferred frequency .* from passed values does " + "not conform to passed frequency" + ) + with pytest.raises(ValueError, match=msg): + TimedeltaIndex(tdi, freq="D") + + with pytest.raises(ValueError, match=msg): + # GH#23789 + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + TimedeltaArray(tdi, freq="D") + + with pytest.raises(ValueError, match=msg): + TimedeltaIndex(tdi._data, freq="D") + + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + TimedeltaArray(tdi._data, freq="D") + + def test_dt64_data_invalid(self): + # GH#23539 + # passing tz-aware DatetimeIndex raises, naive or ndarray[datetime64] + # raise as of GH#29794 + dti = pd.date_range("2016-01-01", periods=3) + + msg = "cannot be converted to timedelta64" + with pytest.raises(TypeError, match=msg): + TimedeltaIndex(dti.tz_localize("Europe/Brussels")) + + with pytest.raises(TypeError, match=msg): + TimedeltaIndex(dti) + + with pytest.raises(TypeError, match=msg): + TimedeltaIndex(np.asarray(dti)) + + def test_float64_ns_rounded(self): + # GH#23539 without specifying a unit, floats are regarded as nanos, + # and fractional portions are truncated + tdi = TimedeltaIndex([2.3, 9.7]) + expected = TimedeltaIndex([2, 9]) + tm.assert_index_equal(tdi, expected) + + # integral floats are non-lossy + tdi = TimedeltaIndex([2.0, 9.0]) + expected = TimedeltaIndex([2, 9]) + tm.assert_index_equal(tdi, expected) + + # NaNs get converted to NaT + tdi = TimedeltaIndex([2.0, np.nan]) + expected = TimedeltaIndex([Timedelta(nanoseconds=2), pd.NaT]) + tm.assert_index_equal(tdi, expected) + + def test_float64_unit_conversion(self): + # GH#23539 + tdi = to_timedelta([1.5, 2.25], unit="D") + expected = TimedeltaIndex([Timedelta(days=1.5), Timedelta(days=2.25)]) + tm.assert_index_equal(tdi, expected) + + def test_construction_base_constructor(self): + arr = [Timedelta("1 days"), pd.NaT, Timedelta("3 days")] + tm.assert_index_equal(pd.Index(arr), TimedeltaIndex(arr)) + tm.assert_index_equal(pd.Index(np.array(arr)), TimedeltaIndex(np.array(arr))) + + arr = [np.nan, pd.NaT, Timedelta("1 days")] + tm.assert_index_equal(pd.Index(arr), TimedeltaIndex(arr)) + tm.assert_index_equal(pd.Index(np.array(arr)), TimedeltaIndex(np.array(arr))) + + @pytest.mark.filterwarnings( + "ignore:The 'unit' keyword in TimedeltaIndex construction:FutureWarning" + ) + def test_constructor(self): + expected = TimedeltaIndex( + [ + "1 days", + "1 days 00:00:05", + "2 days", + "2 days 00:00:02", + "0 days 00:00:03", + ] + ) + result = TimedeltaIndex( + [ + "1 days", + "1 days, 00:00:05", + np.timedelta64(2, "D"), + timedelta(days=2, seconds=2), + pd.offsets.Second(3), + ] + ) + tm.assert_index_equal(result, expected) + + expected = TimedeltaIndex( + ["0 days 00:00:00", "0 days 00:00:01", "0 days 00:00:02"] + ) + result = TimedeltaIndex(range(3), unit="s") + tm.assert_index_equal(result, expected) + expected = TimedeltaIndex( + ["0 days 00:00:00", "0 days 00:00:05", "0 days 00:00:09"] + ) + result = TimedeltaIndex([0, 5, 9], unit="s") + tm.assert_index_equal(result, expected) + expected = TimedeltaIndex( + ["0 days 00:00:00.400", "0 days 00:00:00.450", "0 days 00:00:01.200"] + ) + result = TimedeltaIndex([400, 450, 1200], unit="ms") + tm.assert_index_equal(result, expected) + + def test_constructor_iso(self): + # GH #21877 + expected = timedelta_range("1s", periods=9, freq="s") + durations = [f"P0DT0H0M{i}S" for i in range(1, 10)] + result = to_timedelta(durations) + tm.assert_index_equal(result, expected) + + def test_timedelta_range_fractional_period(self): + msg = "Non-integer 'periods' in pd.date_range, pd.timedelta_range" + with tm.assert_produces_warning(FutureWarning, match=msg): + rng = timedelta_range("1 days", periods=10.5) + exp = timedelta_range("1 days", periods=10) + tm.assert_index_equal(rng, exp) + + def test_constructor_coverage(self): + msg = "periods must be a number, got foo" + with pytest.raises(TypeError, match=msg): + timedelta_range(start="1 days", periods="foo", freq="D") + + msg = ( + r"TimedeltaIndex\(\.\.\.\) must be called with a collection of some kind, " + "'1 days' was passed" + ) + with pytest.raises(TypeError, match=msg): + TimedeltaIndex("1 days") + + # generator expression + gen = (timedelta(i) for i in range(10)) + result = TimedeltaIndex(gen) + expected = TimedeltaIndex([timedelta(i) for i in range(10)]) + tm.assert_index_equal(result, expected) + + # NumPy string array + strings = np.array(["1 days", "2 days", "3 days"]) + result = TimedeltaIndex(strings) + expected = to_timedelta([1, 2, 3], unit="d") + tm.assert_index_equal(result, expected) + + from_ints = TimedeltaIndex(expected.asi8) + tm.assert_index_equal(from_ints, expected) + + # non-conforming freq + msg = ( + "Inferred frequency None from passed values does not conform to " + "passed frequency D" + ) + with pytest.raises(ValueError, match=msg): + TimedeltaIndex(["1 days", "2 days", "4 days"], freq="D") + + msg = ( + "Of the four parameters: start, end, periods, and freq, exactly " + "three must be specified" + ) + with pytest.raises(ValueError, match=msg): + timedelta_range(periods=10, freq="D") + + def test_constructor_name(self): + idx = timedelta_range(start="1 days", periods=1, freq="D", name="TEST") + assert idx.name == "TEST" + + # GH10025 + idx2 = TimedeltaIndex(idx, name="something else") + assert idx2.name == "something else" + + def test_constructor_no_precision_raises(self): + # GH-24753, GH-24739 + + msg = "with no precision is not allowed" + with pytest.raises(ValueError, match=msg): + TimedeltaIndex(["2000"], dtype="timedelta64") + + msg = "The 'timedelta64' dtype has no unit. Please pass in" + with pytest.raises(ValueError, match=msg): + pd.Index(["2000"], dtype="timedelta64") + + def test_constructor_wrong_precision_raises(self): + msg = "Supported timedelta64 resolutions are 's', 'ms', 'us', 'ns'" + with pytest.raises(ValueError, match=msg): + TimedeltaIndex(["2000"], dtype="timedelta64[D]") + + # "timedelta64[us]" was unsupported pre-2.0, but now this works. + tdi = TimedeltaIndex(["2000"], dtype="timedelta64[us]") + assert tdi.dtype == "m8[us]" + + def test_explicit_none_freq(self): + # Explicitly passing freq=None is respected + tdi = timedelta_range(1, periods=5) + assert tdi.freq is not None + + result = TimedeltaIndex(tdi, freq=None) + assert result.freq is None + + result = TimedeltaIndex(tdi._data, freq=None) + assert result.freq is None + + msg = "TimedeltaArray.__init__ is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + tda = TimedeltaArray(tdi, freq=None) + assert tda.freq is None + + def test_from_categorical(self): + tdi = timedelta_range(1, periods=5) + + cat = pd.Categorical(tdi) + + result = TimedeltaIndex(cat) + tm.assert_index_equal(result, tdi) + + ci = pd.CategoricalIndex(tdi) + result = TimedeltaIndex(ci) + tm.assert_index_equal(result, tdi) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_delete.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_delete.py new file mode 100644 index 0000000000000000000000000000000000000000..6e6f54702ce1a09c0fccb0c44d0cd4a474c46a8c --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_delete.py @@ -0,0 +1,71 @@ +from pandas import ( + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndexDelete: + def test_delete(self): + idx = timedelta_range(start="1 Days", periods=5, freq="D", name="idx") + + # preserve freq + expected_0 = timedelta_range(start="2 Days", periods=4, freq="D", name="idx") + expected_4 = timedelta_range(start="1 Days", periods=4, freq="D", name="idx") + + # reset freq to None + expected_1 = TimedeltaIndex( + ["1 day", "3 day", "4 day", "5 day"], freq=None, name="idx" + ) + + cases = { + 0: expected_0, + -5: expected_0, + -1: expected_4, + 4: expected_4, + 1: expected_1, + } + for n, expected in cases.items(): + result = idx.delete(n) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + with tm.external_error_raised((IndexError, ValueError)): + # either depending on numpy version + idx.delete(5) + + def test_delete_slice(self): + idx = timedelta_range(start="1 days", periods=10, freq="D", name="idx") + + # preserve freq + expected_0_2 = timedelta_range(start="4 days", periods=7, freq="D", name="idx") + expected_7_9 = timedelta_range(start="1 days", periods=7, freq="D", name="idx") + + # reset freq to None + expected_3_5 = TimedeltaIndex( + ["1 d", "2 d", "3 d", "7 d", "8 d", "9 d", "10d"], freq=None, name="idx" + ) + + cases = { + (0, 1, 2): expected_0_2, + (7, 8, 9): expected_7_9, + (3, 4, 5): expected_3_5, + } + for n, expected in cases.items(): + result = idx.delete(n) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + result = idx.delete(slice(n[0], n[-1] + 1)) + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + def test_delete_doesnt_infer_freq(self): + # GH#30655 behavior matches DatetimeIndex + + tdi = TimedeltaIndex(["1 Day", "2 Days", None, "3 Days", "4 Days"]) + result = tdi.delete(2) + assert result.freq is None diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_formats.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_formats.py new file mode 100644 index 0000000000000000000000000000000000000000..607336060cbbc2093e224e31614e26a2c03bd72f --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_formats.py @@ -0,0 +1,106 @@ +import pytest + +import pandas as pd +from pandas import ( + Series, + TimedeltaIndex, +) + + +class TestTimedeltaIndexRendering: + def test_repr_round_days_non_nano(self): + # GH#55405 + # we should get "1 days", not "1 days 00:00:00" with non-nano + tdi = TimedeltaIndex(["1 days"], freq="D").as_unit("s") + result = repr(tdi) + expected = "TimedeltaIndex(['1 days'], dtype='timedelta64[s]', freq='D')" + assert result == expected + + result2 = repr(Series(tdi)) + expected2 = "0 1 days\ndtype: timedelta64[s]" + assert result2 == expected2 + + @pytest.mark.parametrize("method", ["__repr__", "__str__"]) + def test_representation(self, method): + idx1 = TimedeltaIndex([], freq="D") + idx2 = TimedeltaIndex(["1 days"], freq="D") + idx3 = TimedeltaIndex(["1 days", "2 days"], freq="D") + idx4 = TimedeltaIndex(["1 days", "2 days", "3 days"], freq="D") + idx5 = TimedeltaIndex(["1 days 00:00:01", "2 days", "3 days"]) + + exp1 = "TimedeltaIndex([], dtype='timedelta64[ns]', freq='D')" + + exp2 = "TimedeltaIndex(['1 days'], dtype='timedelta64[ns]', freq='D')" + + exp3 = "TimedeltaIndex(['1 days', '2 days'], dtype='timedelta64[ns]', freq='D')" + + exp4 = ( + "TimedeltaIndex(['1 days', '2 days', '3 days'], " + "dtype='timedelta64[ns]', freq='D')" + ) + + exp5 = ( + "TimedeltaIndex(['1 days 00:00:01', '2 days 00:00:00', " + "'3 days 00:00:00'], dtype='timedelta64[ns]', freq=None)" + ) + + with pd.option_context("display.width", 300): + for idx, expected in zip( + [idx1, idx2, idx3, idx4, idx5], [exp1, exp2, exp3, exp4, exp5] + ): + result = getattr(idx, method)() + assert result == expected + + # TODO: this is a Series.__repr__ test + def test_representation_to_series(self): + idx1 = TimedeltaIndex([], freq="D") + idx2 = TimedeltaIndex(["1 days"], freq="D") + idx3 = TimedeltaIndex(["1 days", "2 days"], freq="D") + idx4 = TimedeltaIndex(["1 days", "2 days", "3 days"], freq="D") + idx5 = TimedeltaIndex(["1 days 00:00:01", "2 days", "3 days"]) + + exp1 = """Series([], dtype: timedelta64[ns])""" + + exp2 = "0 1 days\ndtype: timedelta64[ns]" + + exp3 = "0 1 days\n1 2 days\ndtype: timedelta64[ns]" + + exp4 = "0 1 days\n1 2 days\n2 3 days\ndtype: timedelta64[ns]" + + exp5 = ( + "0 1 days 00:00:01\n" + "1 2 days 00:00:00\n" + "2 3 days 00:00:00\n" + "dtype: timedelta64[ns]" + ) + + with pd.option_context("display.width", 300): + for idx, expected in zip( + [idx1, idx2, idx3, idx4, idx5], [exp1, exp2, exp3, exp4, exp5] + ): + result = repr(Series(idx)) + assert result == expected + + def test_summary(self): + # GH#9116 + idx1 = TimedeltaIndex([], freq="D") + idx2 = TimedeltaIndex(["1 days"], freq="D") + idx3 = TimedeltaIndex(["1 days", "2 days"], freq="D") + idx4 = TimedeltaIndex(["1 days", "2 days", "3 days"], freq="D") + idx5 = TimedeltaIndex(["1 days 00:00:01", "2 days", "3 days"]) + + exp1 = "TimedeltaIndex: 0 entries\nFreq: D" + + exp2 = "TimedeltaIndex: 1 entries, 1 days to 1 days\nFreq: D" + + exp3 = "TimedeltaIndex: 2 entries, 1 days to 2 days\nFreq: D" + + exp4 = "TimedeltaIndex: 3 entries, 1 days to 3 days\nFreq: D" + + exp5 = "TimedeltaIndex: 3 entries, 1 days 00:00:01 to 3 days 00:00:00" + + for idx, expected in zip( + [idx1, idx2, idx3, idx4, idx5], [exp1, exp2, exp3, exp4, exp5] + ): + result = idx._summary() + assert result == expected diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_freq_attr.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_freq_attr.py new file mode 100644 index 0000000000000000000000000000000000000000..1912c49d3000fcbef45dd081213778bfb387e38e --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_freq_attr.py @@ -0,0 +1,72 @@ +import pytest + +from pandas import TimedeltaIndex + +from pandas.tseries.offsets import ( + DateOffset, + Day, + Hour, + MonthEnd, +) + + +class TestFreq: + @pytest.mark.parametrize("values", [["0 days", "2 days", "4 days"], []]) + @pytest.mark.parametrize("freq", ["2D", Day(2), "48h", Hour(48)]) + def test_freq_setter(self, values, freq): + # GH#20678 + idx = TimedeltaIndex(values) + + # can set to an offset, converting from string if necessary + idx._data.freq = freq + assert idx.freq == freq + assert isinstance(idx.freq, DateOffset) + + # can reset to None + idx._data.freq = None + assert idx.freq is None + + def test_with_freq_empty_requires_tick(self): + idx = TimedeltaIndex([]) + + off = MonthEnd(1) + msg = "TimedeltaArray/Index freq must be a Tick" + with pytest.raises(TypeError, match=msg): + idx._with_freq(off) + with pytest.raises(TypeError, match=msg): + idx._data._with_freq(off) + + def test_freq_setter_errors(self): + # GH#20678 + idx = TimedeltaIndex(["0 days", "2 days", "4 days"]) + + # setting with an incompatible freq + msg = ( + "Inferred frequency 2D from passed values does not conform to " + "passed frequency 5D" + ) + with pytest.raises(ValueError, match=msg): + idx._data.freq = "5D" + + # setting with a non-fixed frequency + msg = r"<2 \* BusinessDays> is a non-fixed frequency" + with pytest.raises(ValueError, match=msg): + idx._data.freq = "2B" + + # setting with non-freq string + with pytest.raises(ValueError, match="Invalid frequency"): + idx._data.freq = "foo" + + def test_freq_view_safe(self): + # Setting the freq for one TimedeltaIndex shouldn't alter the freq + # for another that views the same data + + tdi = TimedeltaIndex(["0 days", "2 days", "4 days"], freq="2D") + tda = tdi._data + + tdi2 = TimedeltaIndex(tda)._with_freq(None) + assert tdi2.freq is None + + # Original was not altered + assert tdi.freq == "2D" + assert tda.freq == "2D" diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_indexing.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_indexing.py new file mode 100644 index 0000000000000000000000000000000000000000..397f9d9e183319f6df9335fbae7f8cb7401d6ac1 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_indexing.py @@ -0,0 +1,347 @@ +from datetime import datetime +import re + +import numpy as np +import pytest + +from pandas import ( + Index, + NaT, + Timedelta, + TimedeltaIndex, + Timestamp, + notna, + offsets, + timedelta_range, + to_timedelta, +) +import pandas._testing as tm + + +class TestGetItem: + def test_getitem_slice_keeps_name(self): + # GH#4226 + tdi = timedelta_range("1d", "5d", freq="h", name="timebucket") + assert tdi[1:].name == tdi.name + + def test_getitem(self): + idx1 = timedelta_range("1 day", "31 day", freq="D", name="idx") + + for idx in [idx1]: + result = idx[0] + assert result == Timedelta("1 day") + + result = idx[0:5] + expected = timedelta_range("1 day", "5 day", freq="D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx[0:10:2] + expected = timedelta_range("1 day", "9 day", freq="2D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx[-20:-5:3] + expected = timedelta_range("12 day", "24 day", freq="3D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx[4::-1] + expected = TimedeltaIndex( + ["5 day", "4 day", "3 day", "2 day", "1 day"], freq="-1D", name="idx" + ) + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + @pytest.mark.parametrize( + "key", + [ + Timestamp("1970-01-01"), + Timestamp("1970-01-02"), + datetime(1970, 1, 1), + Timestamp("1970-01-03").to_datetime64(), + # non-matching NA values + np.datetime64("NaT"), + ], + ) + def test_timestamp_invalid_key(self, key): + # GH#20464 + tdi = timedelta_range(0, periods=10) + with pytest.raises(KeyError, match=re.escape(repr(key))): + tdi.get_loc(key) + + +class TestGetLoc: + def test_get_loc_key_unit_mismatch(self): + idx = to_timedelta(["0 days", "1 days", "2 days"]) + key = idx[1].as_unit("ms") + loc = idx.get_loc(key) + assert loc == 1 + + def test_get_loc_key_unit_mismatch_not_castable(self): + tdi = to_timedelta(["0 days", "1 days", "2 days"]).astype("m8[s]") + assert tdi.dtype == "m8[s]" + key = tdi[0].as_unit("ns") + Timedelta(1) + + with pytest.raises(KeyError, match=r"Timedelta\('0 days 00:00:00.000000001'\)"): + tdi.get_loc(key) + + assert key not in tdi + + def test_get_loc(self): + idx = to_timedelta(["0 days", "1 days", "2 days"]) + + # GH 16909 + assert idx.get_loc(idx[1].to_timedelta64()) == 1 + + # GH 16896 + assert idx.get_loc("0 days") == 0 + + def test_get_loc_nat(self): + tidx = TimedeltaIndex(["1 days 01:00:00", "NaT", "2 days 01:00:00"]) + + assert tidx.get_loc(NaT) == 1 + assert tidx.get_loc(None) == 1 + assert tidx.get_loc(float("nan")) == 1 + assert tidx.get_loc(np.nan) == 1 + + +class TestGetIndexer: + def test_get_indexer(self): + idx = to_timedelta(["0 days", "1 days", "2 days"]) + tm.assert_numpy_array_equal( + idx.get_indexer(idx), np.array([0, 1, 2], dtype=np.intp) + ) + + target = to_timedelta(["-1 hour", "12 hours", "1 day 1 hour"]) + tm.assert_numpy_array_equal( + idx.get_indexer(target, "pad"), np.array([-1, 0, 1], dtype=np.intp) + ) + tm.assert_numpy_array_equal( + idx.get_indexer(target, "backfill"), np.array([0, 1, 2], dtype=np.intp) + ) + tm.assert_numpy_array_equal( + idx.get_indexer(target, "nearest"), np.array([0, 1, 1], dtype=np.intp) + ) + + res = idx.get_indexer(target, "nearest", tolerance=Timedelta("1 hour")) + tm.assert_numpy_array_equal(res, np.array([0, -1, 1], dtype=np.intp)) + + +class TestWhere: + def test_where_doesnt_retain_freq(self): + tdi = timedelta_range("1 day", periods=3, freq="D", name="idx") + cond = [True, True, False] + expected = TimedeltaIndex([tdi[0], tdi[1], tdi[0]], freq=None, name="idx") + + result = tdi.where(cond, tdi[::-1]) + tm.assert_index_equal(result, expected) + + def test_where_invalid_dtypes(self, fixed_now_ts): + tdi = timedelta_range("1 day", periods=3, freq="D", name="idx") + + tail = tdi[2:].tolist() + i2 = Index([NaT, NaT] + tail) + mask = notna(i2) + + expected = Index([NaT._value, NaT._value] + tail, dtype=object, name="idx") + assert isinstance(expected[0], int) + result = tdi.where(mask, i2.asi8) + tm.assert_index_equal(result, expected) + + ts = i2 + fixed_now_ts + expected = Index([ts[0], ts[1]] + tail, dtype=object, name="idx") + result = tdi.where(mask, ts) + tm.assert_index_equal(result, expected) + + per = (i2 + fixed_now_ts).to_period("D") + expected = Index([per[0], per[1]] + tail, dtype=object, name="idx") + result = tdi.where(mask, per) + tm.assert_index_equal(result, expected) + + ts = fixed_now_ts + expected = Index([ts, ts] + tail, dtype=object, name="idx") + result = tdi.where(mask, ts) + tm.assert_index_equal(result, expected) + + def test_where_mismatched_nat(self): + tdi = timedelta_range("1 day", periods=3, freq="D", name="idx") + cond = np.array([True, False, False]) + + dtnat = np.datetime64("NaT", "ns") + expected = Index([tdi[0], dtnat, dtnat], dtype=object, name="idx") + assert expected[2] is dtnat + result = tdi.where(cond, dtnat) + tm.assert_index_equal(result, expected) + + +class TestTake: + def test_take(self): + # GH 10295 + idx1 = timedelta_range("1 day", "31 day", freq="D", name="idx") + + for idx in [idx1]: + result = idx.take([0]) + assert result == Timedelta("1 day") + + result = idx.take([-1]) + assert result == Timedelta("31 day") + + result = idx.take([0, 1, 2]) + expected = timedelta_range("1 day", "3 day", freq="D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx.take([0, 2, 4]) + expected = timedelta_range("1 day", "5 day", freq="2D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx.take([7, 4, 1]) + expected = timedelta_range("8 day", "2 day", freq="-3D", name="idx") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + result = idx.take([3, 2, 5]) + expected = TimedeltaIndex(["4 day", "3 day", "6 day"], name="idx") + tm.assert_index_equal(result, expected) + assert result.freq is None + + result = idx.take([-3, 2, 5]) + expected = TimedeltaIndex(["29 day", "3 day", "6 day"], name="idx") + tm.assert_index_equal(result, expected) + assert result.freq is None + + def test_take_invalid_kwargs(self): + idx = timedelta_range("1 day", "31 day", freq="D", name="idx") + indices = [1, 6, 5, 9, 10, 13, 15, 3] + + msg = r"take\(\) got an unexpected keyword argument 'foo'" + with pytest.raises(TypeError, match=msg): + idx.take(indices, foo=2) + + msg = "the 'out' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, out=indices) + + msg = "the 'mode' parameter is not supported" + with pytest.raises(ValueError, match=msg): + idx.take(indices, mode="clip") + + def test_take_equiv_getitem(self): + tds = ["1day 02:00:00", "1 day 04:00:00", "1 day 10:00:00"] + idx = timedelta_range(start="1d", end="2d", freq="h", name="idx") + expected = TimedeltaIndex(tds, freq=None, name="idx") + + taken1 = idx.take([2, 4, 10]) + taken2 = idx[[2, 4, 10]] + + for taken in [taken1, taken2]: + tm.assert_index_equal(taken, expected) + assert isinstance(taken, TimedeltaIndex) + assert taken.freq is None + assert taken.name == expected.name + + def test_take_fill_value(self): + # GH 12631 + idx = TimedeltaIndex(["1 days", "2 days", "3 days"], name="xxx") + result = idx.take(np.array([1, 0, -1])) + expected = TimedeltaIndex(["2 days", "1 days", "3 days"], name="xxx") + tm.assert_index_equal(result, expected) + + # fill_value + result = idx.take(np.array([1, 0, -1]), fill_value=True) + expected = TimedeltaIndex(["2 days", "1 days", "NaT"], name="xxx") + tm.assert_index_equal(result, expected) + + # allow_fill=False + result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True) + expected = TimedeltaIndex(["2 days", "1 days", "3 days"], name="xxx") + tm.assert_index_equal(result, expected) + + msg = ( + "When allow_fill=True and fill_value is not None, " + "all indices must be >= -1" + ) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -2]), fill_value=True) + with pytest.raises(ValueError, match=msg): + idx.take(np.array([1, 0, -5]), fill_value=True) + + msg = "index -5 is out of bounds for (axis 0 with )?size 3" + with pytest.raises(IndexError, match=msg): + idx.take(np.array([1, -5])) + + +class TestMaybeCastSliceBound: + @pytest.fixture(params=["increasing", "decreasing", None]) + def monotonic(self, request): + return request.param + + @pytest.fixture + def tdi(self, monotonic): + tdi = timedelta_range("1 Day", periods=10) + if monotonic == "decreasing": + tdi = tdi[::-1] + elif monotonic is None: + taker = np.arange(10, dtype=np.intp) + np.random.default_rng(2).shuffle(taker) + tdi = tdi.take(taker) + return tdi + + def test_maybe_cast_slice_bound_invalid_str(self, tdi): + # test the low-level _maybe_cast_slice_bound and that we get the + # expected exception+message all the way up the stack + msg = ( + "cannot do slice indexing on TimedeltaIndex with these " + r"indexers \[foo\] of type str" + ) + with pytest.raises(TypeError, match=msg): + tdi._maybe_cast_slice_bound("foo", side="left") + with pytest.raises(TypeError, match=msg): + tdi.get_slice_bound("foo", side="left") + with pytest.raises(TypeError, match=msg): + tdi.slice_locs("foo", None, None) + + def test_slice_invalid_str_with_timedeltaindex( + self, tdi, frame_or_series, indexer_sl + ): + obj = frame_or_series(range(10), index=tdi) + + msg = ( + "cannot do slice indexing on TimedeltaIndex with these " + r"indexers \[foo\] of type str" + ) + with pytest.raises(TypeError, match=msg): + indexer_sl(obj)["foo":] + with pytest.raises(TypeError, match=msg): + indexer_sl(obj)["foo":-1] + with pytest.raises(TypeError, match=msg): + indexer_sl(obj)[:"foo"] + with pytest.raises(TypeError, match=msg): + indexer_sl(obj)[tdi[0] : "foo"] + + +class TestContains: + def test_contains_nonunique(self): + # GH#9512 + for vals in ( + [0, 1, 0], + [0, 0, -1], + [0, -1, -1], + ["00:01:00", "00:01:00", "00:02:00"], + ["00:01:00", "00:01:00", "00:00:01"], + ): + idx = TimedeltaIndex(vals) + assert idx[0] in idx + + def test_contains(self): + # Checking for any NaT-like objects + # GH#13603 + td = to_timedelta(range(5), unit="d") + offsets.Hour(1) + for v in [NaT, None, float("nan"), np.nan]: + assert v not in td + + td = to_timedelta([NaT]) + for v in [NaT, None, float("nan"), np.nan]: + assert v in td diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_join.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_join.py new file mode 100644 index 0000000000000000000000000000000000000000..cbd7a5de71b10a6004cd7a3f798fecd8e7631750 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_join.py @@ -0,0 +1,47 @@ +import numpy as np + +from pandas import ( + DataFrame, + Index, + Timedelta, + timedelta_range, +) +import pandas._testing as tm + + +class TestJoin: + def test_append_join_nondatetimeindex(self): + rng = timedelta_range("1 days", periods=10) + idx = Index(["a", "b", "c", "d"]) + + result = rng.append(idx) + assert isinstance(result[0], Timedelta) + + # it works + rng.join(idx, how="outer") + + def test_join_self(self, join_type): + index = timedelta_range("1 day", periods=10) + joined = index.join(index, how=join_type) + tm.assert_index_equal(index, joined) + + def test_does_not_convert_mixed_integer(self): + df = DataFrame(np.ones((5, 5)), columns=timedelta_range("1 day", periods=5)) + + cols = df.columns.join(df.index, how="outer") + joined = cols.join(df.columns) + assert cols.dtype == np.dtype("O") + assert cols.dtype == joined.dtype + tm.assert_index_equal(cols, joined) + + def test_join_preserves_freq(self): + # GH#32157 + tdi = timedelta_range("1 day", periods=10) + result = tdi[:5].join(tdi[5:], how="outer") + assert result.freq == tdi.freq + tm.assert_index_equal(result, tdi) + + result = tdi[:5].join(tdi[6:], how="outer") + assert result.freq is None + expected = tdi.delete(5) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_ops.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_ops.py new file mode 100644 index 0000000000000000000000000000000000000000..f6013baf86edcd566a17cd3127467a7443ac475a --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_ops.py @@ -0,0 +1,14 @@ +from pandas import ( + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndexOps: + def test_infer_freq(self, freq_sample): + # GH#11018 + idx = timedelta_range("1", freq=freq_sample, periods=10) + result = TimedeltaIndex(idx.asi8, freq="infer") + tm.assert_index_equal(idx, result) + assert result.freq == freq_sample diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_pickle.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_pickle.py new file mode 100644 index 0000000000000000000000000000000000000000..befe709728bdd4e9fac3c626f4e33986d671c86d --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_pickle.py @@ -0,0 +1,11 @@ +from pandas import timedelta_range +import pandas._testing as tm + + +class TestPickle: + def test_pickle_after_set_freq(self): + tdi = timedelta_range("1 day", periods=4, freq="s") + tdi = tdi._with_freq(None) + + res = tm.round_trip_pickle(tdi) + tm.assert_index_equal(res, tdi) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_scalar_compat.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_scalar_compat.py new file mode 100644 index 0000000000000000000000000000000000000000..9f0552f8baa901addaae9b4ca0890f6edb272715 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_scalar_compat.py @@ -0,0 +1,142 @@ +""" +Tests for TimedeltaIndex methods behaving like their Timedelta counterparts +""" + +import numpy as np +import pytest + +from pandas._libs.tslibs.offsets import INVALID_FREQ_ERR_MSG + +from pandas import ( + Index, + Series, + Timedelta, + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + + +class TestVectorizedTimedelta: + def test_tdi_total_seconds(self): + # GH#10939 + # test index + rng = timedelta_range("1 days, 10:11:12.100123456", periods=2, freq="s") + expt = [ + 1 * 86400 + 10 * 3600 + 11 * 60 + 12 + 100123456.0 / 1e9, + 1 * 86400 + 10 * 3600 + 11 * 60 + 13 + 100123456.0 / 1e9, + ] + tm.assert_almost_equal(rng.total_seconds(), Index(expt)) + + # test Series + ser = Series(rng) + s_expt = Series(expt, index=[0, 1]) + tm.assert_series_equal(ser.dt.total_seconds(), s_expt) + + # with nat + ser[1] = np.nan + s_expt = Series( + [1 * 86400 + 10 * 3600 + 11 * 60 + 12 + 100123456.0 / 1e9, np.nan], + index=[0, 1], + ) + tm.assert_series_equal(ser.dt.total_seconds(), s_expt) + + def test_tdi_total_seconds_all_nat(self): + # with both nat + ser = Series([np.nan, np.nan], dtype="timedelta64[ns]") + result = ser.dt.total_seconds() + expected = Series([np.nan, np.nan]) + tm.assert_series_equal(result, expected) + + def test_tdi_round(self): + td = timedelta_range(start="16801 days", periods=5, freq="30Min") + elt = td[1] + + expected_rng = TimedeltaIndex( + [ + Timedelta("16801 days 00:00:00"), + Timedelta("16801 days 00:00:00"), + Timedelta("16801 days 01:00:00"), + Timedelta("16801 days 02:00:00"), + Timedelta("16801 days 02:00:00"), + ] + ) + expected_elt = expected_rng[1] + + tm.assert_index_equal(td.round(freq="h"), expected_rng) + assert elt.round(freq="h") == expected_elt + + msg = INVALID_FREQ_ERR_MSG + with pytest.raises(ValueError, match=msg): + td.round(freq="foo") + with pytest.raises(ValueError, match=msg): + elt.round(freq="foo") + + msg = " is a non-fixed frequency" + with pytest.raises(ValueError, match=msg): + td.round(freq="ME") + with pytest.raises(ValueError, match=msg): + elt.round(freq="ME") + + @pytest.mark.parametrize( + "freq,msg", + [ + ("YE", " is a non-fixed frequency"), + ("ME", " is a non-fixed frequency"), + ("foobar", "Invalid frequency: foobar"), + ], + ) + def test_tdi_round_invalid(self, freq, msg): + t1 = timedelta_range("1 days", periods=3, freq="1 min 2 s 3 us") + + with pytest.raises(ValueError, match=msg): + t1.round(freq) + with pytest.raises(ValueError, match=msg): + # Same test for TimedeltaArray + t1._data.round(freq) + + # TODO: de-duplicate with test_tdi_round + def test_round(self): + t1 = timedelta_range("1 days", periods=3, freq="1 min 2 s 3 us") + t2 = -1 * t1 + t1a = timedelta_range("1 days", periods=3, freq="1 min 2 s") + t1c = TimedeltaIndex(np.array([1, 1, 1], "m8[D]")).as_unit("ns") + + # note that negative times round DOWN! so don't give whole numbers + for freq, s1, s2 in [ + ("ns", t1, t2), + ("us", t1, t2), + ( + "ms", + t1a, + TimedeltaIndex( + ["-1 days +00:00:00", "-2 days +23:58:58", "-2 days +23:57:56"] + ), + ), + ( + "s", + t1a, + TimedeltaIndex( + ["-1 days +00:00:00", "-2 days +23:58:58", "-2 days +23:57:56"] + ), + ), + ("12min", t1c, TimedeltaIndex(["-1 days", "-1 days", "-1 days"])), + ("h", t1c, TimedeltaIndex(["-1 days", "-1 days", "-1 days"])), + ("d", t1c, -1 * t1c), + ]: + r1 = t1.round(freq) + tm.assert_index_equal(r1, s1) + r2 = t2.round(freq) + tm.assert_index_equal(r2, s2) + + def test_components(self): + rng = timedelta_range("1 days, 10:11:12", periods=2, freq="s") + rng.components + + # with nat + s = Series(rng) + s[1] = np.nan + + result = s.dt.components + assert not result.iloc[0].isna().all() + assert result.iloc[1].isna().all() diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_searchsorted.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_searchsorted.py new file mode 100644 index 0000000000000000000000000000000000000000..710571ef383970097985f44e09ecba77fcf63f74 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_searchsorted.py @@ -0,0 +1,28 @@ +import numpy as np +import pytest + +from pandas import ( + TimedeltaIndex, + Timestamp, +) +import pandas._testing as tm + + +class TestSearchSorted: + def test_searchsorted_different_argument_classes(self, listlike_box): + idx = TimedeltaIndex(["1 day", "2 days", "3 days"]) + result = idx.searchsorted(listlike_box(idx)) + expected = np.arange(len(idx), dtype=result.dtype) + tm.assert_numpy_array_equal(result, expected) + + result = idx._data.searchsorted(listlike_box(idx)) + tm.assert_numpy_array_equal(result, expected) + + @pytest.mark.parametrize( + "arg", [[1, 2], ["a", "b"], [Timestamp("2020-01-01", tz="Europe/London")] * 2] + ) + def test_searchsorted_invalid_argument_dtype(self, arg): + idx = TimedeltaIndex(["1 day", "2 days", "3 days"]) + msg = "value should be a 'Timedelta', 'NaT', or array of those. Got" + with pytest.raises(TypeError, match=msg): + idx.searchsorted(arg) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_setops.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_setops.py new file mode 100644 index 0000000000000000000000000000000000000000..fce10d9176d7438e63a5e46eede1bb96b41bb8bd --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_setops.py @@ -0,0 +1,254 @@ +import numpy as np +import pytest + +import pandas as pd +from pandas import ( + Index, + TimedeltaIndex, + timedelta_range, +) +import pandas._testing as tm + +from pandas.tseries.offsets import Hour + + +class TestTimedeltaIndex: + def test_union(self): + i1 = timedelta_range("1day", periods=5) + i2 = timedelta_range("3day", periods=5) + result = i1.union(i2) + expected = timedelta_range("1day", periods=7) + tm.assert_index_equal(result, expected) + + i1 = Index(np.arange(0, 20, 2, dtype=np.int64)) + i2 = timedelta_range(start="1 day", periods=10, freq="D") + i1.union(i2) # Works + i2.union(i1) # Fails with "AttributeError: can't set attribute" + + def test_union_sort_false(self): + tdi = timedelta_range("1day", periods=5) + + left = tdi[3:] + right = tdi[:3] + + # Check that we are testing the desired code path + assert left._can_fast_union(right) + + result = left.union(right) + tm.assert_index_equal(result, tdi) + + result = left.union(right, sort=False) + expected = TimedeltaIndex(["4 Days", "5 Days", "1 Days", "2 Day", "3 Days"]) + tm.assert_index_equal(result, expected) + + def test_union_coverage(self): + idx = TimedeltaIndex(["3d", "1d", "2d"]) + ordered = TimedeltaIndex(idx.sort_values(), freq="infer") + result = ordered.union(idx) + tm.assert_index_equal(result, ordered) + + result = ordered[:0].union(ordered) + tm.assert_index_equal(result, ordered) + assert result.freq == ordered.freq + + def test_union_bug_1730(self): + rng_a = timedelta_range("1 day", periods=4, freq="3h") + rng_b = timedelta_range("1 day", periods=4, freq="4h") + + result = rng_a.union(rng_b) + exp = TimedeltaIndex(sorted(set(rng_a) | set(rng_b))) + tm.assert_index_equal(result, exp) + + def test_union_bug_1745(self): + left = TimedeltaIndex(["1 day 15:19:49.695000"]) + right = TimedeltaIndex( + ["2 day 13:04:21.322000", "1 day 15:27:24.873000", "1 day 15:31:05.350000"] + ) + + result = left.union(right) + exp = TimedeltaIndex(sorted(set(left) | set(right))) + tm.assert_index_equal(result, exp) + + def test_union_bug_4564(self): + left = timedelta_range("1 day", "30d") + right = left + pd.offsets.Minute(15) + + result = left.union(right) + exp = TimedeltaIndex(sorted(set(left) | set(right))) + tm.assert_index_equal(result, exp) + + def test_union_freq_infer(self): + # When taking the union of two TimedeltaIndexes, we infer + # a freq even if the arguments don't have freq. This matches + # DatetimeIndex behavior. + tdi = timedelta_range("1 Day", periods=5) + left = tdi[[0, 1, 3, 4]] + right = tdi[[2, 3, 1]] + + assert left.freq is None + assert right.freq is None + + result = left.union(right) + tm.assert_index_equal(result, tdi) + assert result.freq == "D" + + def test_intersection_bug_1708(self): + index_1 = timedelta_range("1 day", periods=4, freq="h") + index_2 = index_1 + pd.offsets.Hour(5) + + result = index_1.intersection(index_2) + assert len(result) == 0 + + index_1 = timedelta_range("1 day", periods=4, freq="h") + index_2 = index_1 + pd.offsets.Hour(1) + + result = index_1.intersection(index_2) + expected = timedelta_range("1 day 01:00:00", periods=3, freq="h") + tm.assert_index_equal(result, expected) + assert result.freq == expected.freq + + def test_intersection_equal(self, sort): + # GH 24471 Test intersection outcome given the sort keyword + # for equal indices intersection should return the original index + first = timedelta_range("1 day", periods=4, freq="h") + second = timedelta_range("1 day", periods=4, freq="h") + intersect = first.intersection(second, sort=sort) + if sort is None: + tm.assert_index_equal(intersect, second.sort_values()) + tm.assert_index_equal(intersect, second) + + # Corner cases + inter = first.intersection(first, sort=sort) + assert inter is first + + @pytest.mark.parametrize("period_1, period_2", [(0, 4), (4, 0)]) + def test_intersection_zero_length(self, period_1, period_2, sort): + # GH 24471 test for non overlap the intersection should be zero length + index_1 = timedelta_range("1 day", periods=period_1, freq="h") + index_2 = timedelta_range("1 day", periods=period_2, freq="h") + expected = timedelta_range("1 day", periods=0, freq="h") + result = index_1.intersection(index_2, sort=sort) + tm.assert_index_equal(result, expected) + + def test_zero_length_input_index(self, sort): + # GH 24966 test for 0-len intersections are copied + index_1 = timedelta_range("1 day", periods=0, freq="h") + index_2 = timedelta_range("1 day", periods=3, freq="h") + result = index_1.intersection(index_2, sort=sort) + assert index_1 is not result + assert index_2 is not result + tm.assert_copy(result, index_1) + + @pytest.mark.parametrize( + "rng, expected", + # if target has the same name, it is preserved + [ + ( + timedelta_range("1 day", periods=5, freq="h", name="idx"), + timedelta_range("1 day", periods=4, freq="h", name="idx"), + ), + # if target name is different, it will be reset + ( + timedelta_range("1 day", periods=5, freq="h", name="other"), + timedelta_range("1 day", periods=4, freq="h", name=None), + ), + # if no overlap exists return empty index + ( + timedelta_range("1 day", periods=10, freq="h", name="idx")[5:], + TimedeltaIndex([], freq="h", name="idx"), + ), + ], + ) + def test_intersection(self, rng, expected, sort): + # GH 4690 (with tz) + base = timedelta_range("1 day", periods=4, freq="h", name="idx") + result = base.intersection(rng, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + assert result.name == expected.name + assert result.freq == expected.freq + + @pytest.mark.parametrize( + "rng, expected", + # part intersection works + [ + ( + TimedeltaIndex(["5 hour", "2 hour", "4 hour", "9 hour"], name="idx"), + TimedeltaIndex(["2 hour", "4 hour"], name="idx"), + ), + # reordered part intersection + ( + TimedeltaIndex(["2 hour", "5 hour", "5 hour", "1 hour"], name="other"), + TimedeltaIndex(["1 hour", "2 hour"], name=None), + ), + # reversed index + ( + TimedeltaIndex(["1 hour", "2 hour", "4 hour", "3 hour"], name="idx")[ + ::-1 + ], + TimedeltaIndex(["1 hour", "2 hour", "4 hour", "3 hour"], name="idx"), + ), + ], + ) + def test_intersection_non_monotonic(self, rng, expected, sort): + # 24471 non-monotonic + base = TimedeltaIndex(["1 hour", "2 hour", "4 hour", "3 hour"], name="idx") + result = base.intersection(rng, sort=sort) + if sort is None: + expected = expected.sort_values() + tm.assert_index_equal(result, expected) + assert result.name == expected.name + + # if reversed order, frequency is still the same + if all(base == rng[::-1]) and sort is None: + assert isinstance(result.freq, Hour) + else: + assert result.freq is None + + +class TestTimedeltaIndexDifference: + def test_difference_freq(self, sort): + # GH14323: Difference of TimedeltaIndex should not preserve frequency + + index = timedelta_range("0 days", "5 days", freq="D") + + other = timedelta_range("1 days", "4 days", freq="D") + expected = TimedeltaIndex(["0 days", "5 days"], freq=None) + idx_diff = index.difference(other, sort) + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) + + # preserve frequency when the difference is a contiguous + # subset of the original range + other = timedelta_range("2 days", "5 days", freq="D") + idx_diff = index.difference(other, sort) + expected = TimedeltaIndex(["0 days", "1 days"], freq="D") + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) + + def test_difference_sort(self, sort): + index = TimedeltaIndex( + ["5 days", "3 days", "2 days", "4 days", "1 days", "0 days"] + ) + + other = timedelta_range("1 days", "4 days", freq="D") + idx_diff = index.difference(other, sort) + + expected = TimedeltaIndex(["5 days", "0 days"], freq=None) + + if sort is None: + expected = expected.sort_values() + + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) + + other = timedelta_range("2 days", "5 days", freq="D") + idx_diff = index.difference(other, sort) + expected = TimedeltaIndex(["1 days", "0 days"], freq=None) + + if sort is None: + expected = expected.sort_values() + + tm.assert_index_equal(idx_diff, expected) + tm.assert_attr_equal("freq", idx_diff, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta.py new file mode 100644 index 0000000000000000000000000000000000000000..3120066741ffa292dc1533056438ebf481cb1849 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta.py @@ -0,0 +1,61 @@ +import numpy as np +import pytest + +from pandas import ( + Index, + Series, + Timedelta, + timedelta_range, +) +import pandas._testing as tm + + +class TestTimedeltaIndex: + def test_misc_coverage(self): + rng = timedelta_range("1 day", periods=5) + result = rng.groupby(rng.days) + assert isinstance(next(iter(result.values()))[0], Timedelta) + + def test_map(self): + # test_map_dictlike generally tests + + rng = timedelta_range("1 day", periods=10) + + f = lambda x: x.days + result = rng.map(f) + exp = Index([f(x) for x in rng], dtype=np.int64) + tm.assert_index_equal(result, exp) + + def test_fields(self): + rng = timedelta_range("1 days, 10:11:12.100123456", periods=2, freq="s") + tm.assert_index_equal(rng.days, Index([1, 1], dtype=np.int64)) + tm.assert_index_equal( + rng.seconds, + Index([10 * 3600 + 11 * 60 + 12, 10 * 3600 + 11 * 60 + 13], dtype=np.int32), + ) + tm.assert_index_equal( + rng.microseconds, + Index([100 * 1000 + 123, 100 * 1000 + 123], dtype=np.int32), + ) + tm.assert_index_equal(rng.nanoseconds, Index([456, 456], dtype=np.int32)) + + msg = "'TimedeltaIndex' object has no attribute '{}'" + with pytest.raises(AttributeError, match=msg.format("hours")): + rng.hours + with pytest.raises(AttributeError, match=msg.format("minutes")): + rng.minutes + with pytest.raises(AttributeError, match=msg.format("milliseconds")): + rng.milliseconds + + # with nat + s = Series(rng) + s[1] = np.nan + + tm.assert_series_equal(s.dt.days, Series([1, np.nan], index=[0, 1])) + tm.assert_series_equal( + s.dt.seconds, Series([10 * 3600 + 11 * 60 + 12, np.nan], index=[0, 1]) + ) + + # preserve name (GH15589) + rng.name = "name" + assert rng.days.name == "name" diff --git a/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta_range.py b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta_range.py new file mode 100644 index 0000000000000000000000000000000000000000..f22bdb7a90516a7162ebdb1cc2d8cbfd9531b9e7 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/indexes/timedeltas/test_timedelta_range.py @@ -0,0 +1,173 @@ +import numpy as np +import pytest + +from pandas import ( + Timedelta, + TimedeltaIndex, + timedelta_range, + to_timedelta, +) +import pandas._testing as tm + +from pandas.tseries.offsets import ( + Day, + Second, +) + + +class TestTimedeltas: + def test_timedelta_range_unit(self): + # GH#49824 + tdi = timedelta_range("0 Days", periods=10, freq="100000D", unit="s") + exp_arr = (np.arange(10, dtype="i8") * 100_000).view("m8[D]").astype("m8[s]") + tm.assert_numpy_array_equal(tdi.to_numpy(), exp_arr) + + def test_timedelta_range(self): + expected = to_timedelta(np.arange(5), unit="D") + result = timedelta_range("0 days", periods=5, freq="D") + tm.assert_index_equal(result, expected) + + expected = to_timedelta(np.arange(11), unit="D") + result = timedelta_range("0 days", "10 days", freq="D") + tm.assert_index_equal(result, expected) + + expected = to_timedelta(np.arange(5), unit="D") + Second(2) + Day() + result = timedelta_range("1 days, 00:00:02", "5 days, 00:00:02", freq="D") + tm.assert_index_equal(result, expected) + + expected = to_timedelta([1, 3, 5, 7, 9], unit="D") + Second(2) + result = timedelta_range("1 days, 00:00:02", periods=5, freq="2D") + tm.assert_index_equal(result, expected) + + expected = to_timedelta(np.arange(50), unit="min") * 30 + result = timedelta_range("0 days", freq="30min", periods=50) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "depr_unit, unit", + [ + ("H", "hour"), + ("T", "minute"), + ("t", "minute"), + ("S", "second"), + ("L", "millisecond"), + ("l", "millisecond"), + ("U", "microsecond"), + ("u", "microsecond"), + ("N", "nanosecond"), + ("n", "nanosecond"), + ], + ) + def test_timedelta_units_H_T_S_L_U_N_deprecated(self, depr_unit, unit): + # GH#52536 + depr_msg = ( + f"'{depr_unit}' is deprecated and will be removed in a future version." + ) + + expected = to_timedelta(np.arange(5), unit=unit) + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + result = to_timedelta(np.arange(5), unit=depr_unit) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "periods, freq", [(3, "2D"), (5, "D"), (6, "19h12min"), (7, "16h"), (9, "12h")] + ) + def test_linspace_behavior(self, periods, freq): + # GH 20976 + result = timedelta_range(start="0 days", end="4 days", periods=periods) + expected = timedelta_range(start="0 days", end="4 days", freq=freq) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("msg_freq, freq", [("H", "19H12min"), ("T", "19h12T")]) + def test_timedelta_range_H_T_deprecated(self, freq, msg_freq): + # GH#52536 + msg = f"'{msg_freq}' is deprecated and will be removed in a future version." + + result = timedelta_range(start="0 days", end="4 days", periods=6) + with tm.assert_produces_warning(FutureWarning, match=msg): + expected = timedelta_range(start="0 days", end="4 days", freq=freq) + tm.assert_index_equal(result, expected) + + def test_errors(self): + # not enough params + msg = ( + "Of the four parameters: start, end, periods, and freq, " + "exactly three must be specified" + ) + with pytest.raises(ValueError, match=msg): + timedelta_range(start="0 days") + + with pytest.raises(ValueError, match=msg): + timedelta_range(end="5 days") + + with pytest.raises(ValueError, match=msg): + timedelta_range(periods=2) + + with pytest.raises(ValueError, match=msg): + timedelta_range() + + # too many params + with pytest.raises(ValueError, match=msg): + timedelta_range(start="0 days", end="5 days", periods=10, freq="h") + + @pytest.mark.parametrize( + "start, end, freq, expected_periods", + [ + ("1D", "10D", "2D", (10 - 1) // 2 + 1), + ("2D", "30D", "3D", (30 - 2) // 3 + 1), + ("2s", "50s", "5s", (50 - 2) // 5 + 1), + # tests that worked before GH 33498: + ("4D", "16D", "3D", (16 - 4) // 3 + 1), + ("8D", "16D", "40s", (16 * 3600 * 24 - 8 * 3600 * 24) // 40 + 1), + ], + ) + def test_timedelta_range_freq_divide_end(self, start, end, freq, expected_periods): + # GH 33498 only the cases where `(end % freq) == 0` used to fail + res = timedelta_range(start=start, end=end, freq=freq) + assert Timedelta(start) == res[0] + assert Timedelta(end) >= res[-1] + assert len(res) == expected_periods + + def test_timedelta_range_infer_freq(self): + # https://github.com/pandas-dev/pandas/issues/35897 + result = timedelta_range("0s", "1s", periods=31) + assert result.freq is None + + @pytest.mark.parametrize( + "freq_depr, start, end, expected_values, expected_freq", + [ + ( + "3.5S", + "05:03:01", + "05:03:10", + ["0 days 05:03:01", "0 days 05:03:04.500000", "0 days 05:03:08"], + "3500ms", + ), + ( + "2.5T", + "5 hours", + "5 hours 8 minutes", + [ + "0 days 05:00:00", + "0 days 05:02:30", + "0 days 05:05:00", + "0 days 05:07:30", + ], + "150s", + ), + ], + ) + def test_timedelta_range_deprecated_freq( + self, freq_depr, start, end, expected_values, expected_freq + ): + # GH#52536 + msg = ( + f"'{freq_depr[-1]}' is deprecated and will be removed in a future version." + ) + + with tm.assert_produces_warning(FutureWarning, match=msg): + result = timedelta_range(start=start, end=end, freq=freq_depr) + expected = TimedeltaIndex( + expected_values, dtype="timedelta64[ns]", freq=expected_freq + ) + tm.assert_index_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/tools/__init__.py b/lib/python3.12/site-packages/pandas/tests/tools/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_numeric.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_numeric.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..95f88e2ba20b85ad9dbd3086d0f58e2546757d93 Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_numeric.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_timedelta.cpython-312.pyc b/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_timedelta.cpython-312.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7a2cbda55e8da5b5ff8458f6d03aacd2141094af Binary files /dev/null and b/lib/python3.12/site-packages/pandas/tests/tools/__pycache__/test_to_timedelta.cpython-312.pyc differ diff --git a/lib/python3.12/site-packages/pandas/tests/tools/test_to_datetime.py b/lib/python3.12/site-packages/pandas/tests/tools/test_to_datetime.py new file mode 100644 index 0000000000000000000000000000000000000000..ede38ce9c9a09e705a20eae2dd42bde8216f19cb --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/tools/test_to_datetime.py @@ -0,0 +1,3911 @@ +""" test to_datetime """ + +import calendar +from collections import deque +from datetime import ( + date, + datetime, + timedelta, + timezone, +) +from decimal import Decimal +import locale + +from dateutil.parser import parse +from dateutil.tz.tz import tzoffset +import numpy as np +import pytest +import pytz + +from pandas._libs import tslib +from pandas._libs.tslibs import ( + iNaT, + parsing, +) +from pandas.errors import ( + OutOfBoundsDatetime, + OutOfBoundsTimedelta, +) +import pandas.util._test_decorators as td + +from pandas.core.dtypes.common import is_datetime64_ns_dtype + +import pandas as pd +from pandas import ( + DataFrame, + DatetimeIndex, + Index, + NaT, + Series, + Timestamp, + date_range, + isna, + to_datetime, +) +import pandas._testing as tm +from pandas.core.arrays import DatetimeArray +from pandas.core.tools import datetimes as tools +from pandas.core.tools.datetimes import start_caching_at + +PARSING_ERR_MSG = ( + r"You might want to try:\n" + r" - passing `format` if your strings have a consistent format;\n" + r" - passing `format=\'ISO8601\'` if your strings are all ISO8601 " + r"but not necessarily in exactly the same format;\n" + r" - passing `format=\'mixed\'`, and the format will be inferred " + r"for each element individually. You might want to use `dayfirst` " + r"alongside this." +) + +pytestmark = pytest.mark.filterwarnings( + "ignore:errors='ignore' is deprecated:FutureWarning" +) + + +@pytest.fixture(params=[True, False]) +def cache(request): + """ + cache keyword to pass to to_datetime. + """ + return request.param + + +class TestTimeConversionFormats: + @pytest.mark.parametrize("readonly", [True, False]) + def test_to_datetime_readonly(self, readonly): + # GH#34857 + arr = np.array([], dtype=object) + if readonly: + arr.setflags(write=False) + result = to_datetime(arr) + expected = to_datetime([]) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "format, expected", + [ + [ + "%d/%m/%Y", + [Timestamp("20000101"), Timestamp("20000201"), Timestamp("20000301")], + ], + [ + "%m/%d/%Y", + [Timestamp("20000101"), Timestamp("20000102"), Timestamp("20000103")], + ], + ], + ) + def test_to_datetime_format(self, cache, index_or_series, format, expected): + values = index_or_series(["1/1/2000", "1/2/2000", "1/3/2000"]) + result = to_datetime(values, format=format, cache=cache) + expected = index_or_series(expected) + tm.assert_equal(result, expected) + + @pytest.mark.parametrize( + "arg, expected, format", + [ + ["1/1/2000", "20000101", "%d/%m/%Y"], + ["1/1/2000", "20000101", "%m/%d/%Y"], + ["1/2/2000", "20000201", "%d/%m/%Y"], + ["1/2/2000", "20000102", "%m/%d/%Y"], + ["1/3/2000", "20000301", "%d/%m/%Y"], + ["1/3/2000", "20000103", "%m/%d/%Y"], + ], + ) + def test_to_datetime_format_scalar(self, cache, arg, expected, format): + result = to_datetime(arg, format=format, cache=cache) + expected = Timestamp(expected) + assert result == expected + + def test_to_datetime_format_YYYYMMDD(self, cache): + ser = Series([19801222, 19801222] + [19810105] * 5) + expected = Series([Timestamp(x) for x in ser.apply(str)]) + + result = to_datetime(ser, format="%Y%m%d", cache=cache) + tm.assert_series_equal(result, expected) + + result = to_datetime(ser.apply(str), format="%Y%m%d", cache=cache) + tm.assert_series_equal(result, expected) + + def test_to_datetime_format_YYYYMMDD_with_nat(self, cache): + # Explicit cast to float to explicit cast when setting np.nan + ser = Series([19801222, 19801222] + [19810105] * 5, dtype="float") + # with NaT + expected = Series( + [Timestamp("19801222"), Timestamp("19801222")] + [Timestamp("19810105")] * 5 + ) + expected[2] = np.nan + ser[2] = np.nan + + result = to_datetime(ser, format="%Y%m%d", cache=cache) + tm.assert_series_equal(result, expected) + + # string with NaT + ser2 = ser.apply(str) + ser2[2] = "nat" + with pytest.raises( + ValueError, + match=( + 'unconverted data remains when parsing with format "%Y%m%d": ".0", ' + "at position 0" + ), + ): + # https://github.com/pandas-dev/pandas/issues/50051 + to_datetime(ser2, format="%Y%m%d", cache=cache) + + def test_to_datetime_format_YYYYMM_with_nat(self, cache): + # https://github.com/pandas-dev/pandas/issues/50237 + # Explicit cast to float to explicit cast when setting np.nan + ser = Series([198012, 198012] + [198101] * 5, dtype="float") + expected = Series( + [Timestamp("19801201"), Timestamp("19801201")] + [Timestamp("19810101")] * 5 + ) + expected[2] = np.nan + ser[2] = np.nan + result = to_datetime(ser, format="%Y%m", cache=cache) + tm.assert_series_equal(result, expected) + + def test_to_datetime_format_YYYYMMDD_ignore(self, cache): + # coercion + # GH 7930, GH 14487 + ser = Series([20121231, 20141231, 99991231]) + result = to_datetime(ser, format="%Y%m%d", errors="ignore", cache=cache) + expected = Series( + [20121231, 20141231, 99991231], + dtype=object, + ) + tm.assert_series_equal(result, expected) + + def test_to_datetime_format_YYYYMMDD_ignore_with_outofbounds(self, cache): + # https://github.com/pandas-dev/pandas/issues/26493 + result = to_datetime( + ["15010101", "20150101", np.nan], + format="%Y%m%d", + errors="ignore", + cache=cache, + ) + expected = Index(["15010101", "20150101", np.nan], dtype=object) + tm.assert_index_equal(result, expected) + + def test_to_datetime_format_YYYYMMDD_coercion(self, cache): + # coercion + # GH 7930 + ser = Series([20121231, 20141231, 99991231]) + result = to_datetime(ser, format="%Y%m%d", errors="coerce", cache=cache) + expected = Series(["20121231", "20141231", "NaT"], dtype="M8[ns]") + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "input_s", + [ + # Null values with Strings + ["19801222", "20010112", None], + ["19801222", "20010112", np.nan], + ["19801222", "20010112", NaT], + ["19801222", "20010112", "NaT"], + # Null values with Integers + [19801222, 20010112, None], + [19801222, 20010112, np.nan], + [19801222, 20010112, NaT], + [19801222, 20010112, "NaT"], + ], + ) + def test_to_datetime_format_YYYYMMDD_with_none(self, input_s): + # GH 30011 + # format='%Y%m%d' + # with None + expected = Series([Timestamp("19801222"), Timestamp("20010112"), NaT]) + result = Series(to_datetime(input_s, format="%Y%m%d")) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "input_s, expected", + [ + # NaN before strings with invalid date values + [ + Series(["19801222", np.nan, "20010012", "10019999"]), + Series([Timestamp("19801222"), np.nan, np.nan, np.nan]), + ], + # NaN after strings with invalid date values + [ + Series(["19801222", "20010012", "10019999", np.nan]), + Series([Timestamp("19801222"), np.nan, np.nan, np.nan]), + ], + # NaN before integers with invalid date values + [ + Series([20190813, np.nan, 20010012, 20019999]), + Series([Timestamp("20190813"), np.nan, np.nan, np.nan]), + ], + # NaN after integers with invalid date values + [ + Series([20190813, 20010012, np.nan, 20019999]), + Series([Timestamp("20190813"), np.nan, np.nan, np.nan]), + ], + ], + ) + def test_to_datetime_format_YYYYMMDD_overflow(self, input_s, expected): + # GH 25512 + # format='%Y%m%d', errors='coerce' + result = to_datetime(input_s, format="%Y%m%d", errors="coerce") + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "data, format, expected", + [ + ([pd.NA], "%Y%m%d%H%M%S", DatetimeIndex(["NaT"])), + ([pd.NA], None, DatetimeIndex(["NaT"])), + ( + [pd.NA, "20210202202020"], + "%Y%m%d%H%M%S", + DatetimeIndex(["NaT", "2021-02-02 20:20:20"]), + ), + (["201010", pd.NA], "%y%m%d", DatetimeIndex(["2020-10-10", "NaT"])), + (["201010", pd.NA], "%d%m%y", DatetimeIndex(["2010-10-20", "NaT"])), + ([None, np.nan, pd.NA], None, DatetimeIndex(["NaT", "NaT", "NaT"])), + ([None, np.nan, pd.NA], "%Y%m%d", DatetimeIndex(["NaT", "NaT", "NaT"])), + ], + ) + def test_to_datetime_with_NA(self, data, format, expected): + # GH#42957 + result = to_datetime(data, format=format) + tm.assert_index_equal(result, expected) + + def test_to_datetime_with_NA_with_warning(self): + # GH#42957 + result = to_datetime(["201010", pd.NA]) + expected = DatetimeIndex(["2010-10-20", "NaT"]) + tm.assert_index_equal(result, expected) + + def test_to_datetime_format_integer(self, cache): + # GH 10178 + ser = Series([2000, 2001, 2002]) + expected = Series([Timestamp(x) for x in ser.apply(str)]) + + result = to_datetime(ser, format="%Y", cache=cache) + tm.assert_series_equal(result, expected) + + ser = Series([200001, 200105, 200206]) + expected = Series([Timestamp(x[:4] + "-" + x[4:]) for x in ser.apply(str)]) + + result = to_datetime(ser, format="%Y%m", cache=cache) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "int_date, expected", + [ + # valid date, length == 8 + [20121030, datetime(2012, 10, 30)], + # short valid date, length == 6 + [199934, datetime(1999, 3, 4)], + # long integer date partially parsed to datetime(2012,1,1), length > 8 + [2012010101, 2012010101], + # invalid date partially parsed to datetime(2012,9,9), length == 8 + [20129930, 20129930], + # short integer date partially parsed to datetime(2012,9,9), length < 8 + [2012993, 2012993], + # short invalid date, length == 4 + [2121, 2121], + ], + ) + def test_int_to_datetime_format_YYYYMMDD_typeerror(self, int_date, expected): + # GH 26583 + result = to_datetime(int_date, format="%Y%m%d", errors="ignore") + assert result == expected + + def test_to_datetime_format_microsecond(self, cache): + month_abbr = calendar.month_abbr[4] + val = f"01-{month_abbr}-2011 00:00:01.978" + + format = "%d-%b-%Y %H:%M:%S.%f" + result = to_datetime(val, format=format, cache=cache) + exp = datetime.strptime(val, format) + assert result == exp + + @pytest.mark.parametrize( + "value, format, dt", + [ + ["01/10/2010 15:20", "%m/%d/%Y %H:%M", Timestamp("2010-01-10 15:20")], + ["01/10/2010 05:43", "%m/%d/%Y %I:%M", Timestamp("2010-01-10 05:43")], + [ + "01/10/2010 13:56:01", + "%m/%d/%Y %H:%M:%S", + Timestamp("2010-01-10 13:56:01"), + ], + # The 3 tests below are locale-dependent. + # They pass, except when the machine locale is zh_CN or it_IT . + pytest.param( + "01/10/2010 08:14 PM", + "%m/%d/%Y %I:%M %p", + Timestamp("2010-01-10 20:14"), + marks=pytest.mark.xfail( + locale.getlocale()[0] in ("zh_CN", "it_IT"), + reason="fail on a CI build with LC_ALL=zh_CN.utf8/it_IT.utf8", + strict=False, + ), + ), + pytest.param( + "01/10/2010 07:40 AM", + "%m/%d/%Y %I:%M %p", + Timestamp("2010-01-10 07:40"), + marks=pytest.mark.xfail( + locale.getlocale()[0] in ("zh_CN", "it_IT"), + reason="fail on a CI build with LC_ALL=zh_CN.utf8/it_IT.utf8", + strict=False, + ), + ), + pytest.param( + "01/10/2010 09:12:56 AM", + "%m/%d/%Y %I:%M:%S %p", + Timestamp("2010-01-10 09:12:56"), + marks=pytest.mark.xfail( + locale.getlocale()[0] in ("zh_CN", "it_IT"), + reason="fail on a CI build with LC_ALL=zh_CN.utf8/it_IT.utf8", + strict=False, + ), + ), + ], + ) + def test_to_datetime_format_time(self, cache, value, format, dt): + assert to_datetime(value, format=format, cache=cache) == dt + + @td.skip_if_not_us_locale + def test_to_datetime_with_non_exact(self, cache): + # GH 10834 + # 8904 + # exact kw + ser = Series( + ["19MAY11", "foobar19MAY11", "19MAY11:00:00:00", "19MAY11 00:00:00Z"] + ) + result = to_datetime(ser, format="%d%b%y", exact=False, cache=cache) + expected = to_datetime( + ser.str.extract(r"(\d+\w+\d+)", expand=False), format="%d%b%y", cache=cache + ) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "format, expected", + [ + ("%Y-%m-%d", Timestamp(2000, 1, 3)), + ("%Y-%d-%m", Timestamp(2000, 3, 1)), + ("%Y-%m-%d %H", Timestamp(2000, 1, 3, 12)), + ("%Y-%d-%m %H", Timestamp(2000, 3, 1, 12)), + ("%Y-%m-%d %H:%M", Timestamp(2000, 1, 3, 12, 34)), + ("%Y-%d-%m %H:%M", Timestamp(2000, 3, 1, 12, 34)), + ("%Y-%m-%d %H:%M:%S", Timestamp(2000, 1, 3, 12, 34, 56)), + ("%Y-%d-%m %H:%M:%S", Timestamp(2000, 3, 1, 12, 34, 56)), + ("%Y-%m-%d %H:%M:%S.%f", Timestamp(2000, 1, 3, 12, 34, 56, 123456)), + ("%Y-%d-%m %H:%M:%S.%f", Timestamp(2000, 3, 1, 12, 34, 56, 123456)), + ( + "%Y-%m-%d %H:%M:%S.%f%z", + Timestamp(2000, 1, 3, 12, 34, 56, 123456, tz="UTC+01:00"), + ), + ( + "%Y-%d-%m %H:%M:%S.%f%z", + Timestamp(2000, 3, 1, 12, 34, 56, 123456, tz="UTC+01:00"), + ), + ], + ) + def test_non_exact_doesnt_parse_whole_string(self, cache, format, expected): + # https://github.com/pandas-dev/pandas/issues/50412 + # the formats alternate between ISO8601 and non-ISO8601 to check both paths + result = to_datetime( + "2000-01-03 12:34:56.123456+01:00", format=format, exact=False + ) + assert result == expected + + @pytest.mark.parametrize( + "arg", + [ + "2012-01-01 09:00:00.000000001", + "2012-01-01 09:00:00.000001", + "2012-01-01 09:00:00.001", + "2012-01-01 09:00:00.001000", + "2012-01-01 09:00:00.001000000", + ], + ) + def test_parse_nanoseconds_with_formula(self, cache, arg): + # GH8989 + # truncating the nanoseconds when a format was provided + expected = to_datetime(arg, cache=cache) + result = to_datetime(arg, format="%Y-%m-%d %H:%M:%S.%f", cache=cache) + assert result == expected + + @pytest.mark.parametrize( + "value,fmt,expected", + [ + ["2009324", "%Y%W%w", Timestamp("2009-08-13")], + ["2013020", "%Y%U%w", Timestamp("2013-01-13")], + ], + ) + def test_to_datetime_format_weeks(self, value, fmt, expected, cache): + assert to_datetime(value, format=fmt, cache=cache) == expected + + @pytest.mark.parametrize( + "fmt,dates,expected_dates", + [ + [ + "%Y-%m-%d %H:%M:%S %Z", + ["2010-01-01 12:00:00 UTC"] * 2, + [Timestamp("2010-01-01 12:00:00", tz="UTC")] * 2, + ], + [ + "%Y-%m-%d %H:%M:%S%z", + ["2010-01-01 12:00:00+0100"] * 2, + [ + Timestamp( + "2010-01-01 12:00:00", tzinfo=timezone(timedelta(minutes=60)) + ) + ] + * 2, + ], + [ + "%Y-%m-%d %H:%M:%S %z", + ["2010-01-01 12:00:00 +0100"] * 2, + [ + Timestamp( + "2010-01-01 12:00:00", tzinfo=timezone(timedelta(minutes=60)) + ) + ] + * 2, + ], + [ + "%Y-%m-%d %H:%M:%S %z", + ["2010-01-01 12:00:00 Z", "2010-01-01 12:00:00 Z"], + [ + Timestamp( + "2010-01-01 12:00:00", tzinfo=pytz.FixedOffset(0) + ), # pytz coerces to UTC + Timestamp("2010-01-01 12:00:00", tzinfo=pytz.FixedOffset(0)), + ], + ], + ], + ) + def test_to_datetime_parse_tzname_or_tzoffset(self, fmt, dates, expected_dates): + # GH 13486 + result = to_datetime(dates, format=fmt) + expected = Index(expected_dates) + tm.assert_equal(result, expected) + + @pytest.mark.parametrize( + "fmt,dates,expected_dates", + [ + [ + "%Y-%m-%d %H:%M:%S %Z", + [ + "2010-01-01 12:00:00 UTC", + "2010-01-01 12:00:00 GMT", + "2010-01-01 12:00:00 US/Pacific", + ], + [ + Timestamp("2010-01-01 12:00:00", tz="UTC"), + Timestamp("2010-01-01 12:00:00", tz="GMT"), + Timestamp("2010-01-01 12:00:00", tz="US/Pacific"), + ], + ], + [ + "%Y-%m-%d %H:%M:%S %z", + ["2010-01-01 12:00:00 +0100", "2010-01-01 12:00:00 -0100"], + [ + Timestamp( + "2010-01-01 12:00:00", tzinfo=timezone(timedelta(minutes=60)) + ), + Timestamp( + "2010-01-01 12:00:00", tzinfo=timezone(timedelta(minutes=-60)) + ), + ], + ], + ], + ) + def test_to_datetime_parse_tzname_or_tzoffset_utc_false_deprecated( + self, fmt, dates, expected_dates + ): + # GH 13486, 50887 + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime(dates, format=fmt) + expected = Index(expected_dates) + tm.assert_equal(result, expected) + + def test_to_datetime_parse_tzname_or_tzoffset_different_tz_to_utc(self): + # GH 32792 + dates = [ + "2010-01-01 12:00:00 +0100", + "2010-01-01 12:00:00 -0100", + "2010-01-01 12:00:00 +0300", + "2010-01-01 12:00:00 +0400", + ] + expected_dates = [ + "2010-01-01 11:00:00+00:00", + "2010-01-01 13:00:00+00:00", + "2010-01-01 09:00:00+00:00", + "2010-01-01 08:00:00+00:00", + ] + fmt = "%Y-%m-%d %H:%M:%S %z" + + result = to_datetime(dates, format=fmt, utc=True) + expected = DatetimeIndex(expected_dates) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "offset", ["+0", "-1foo", "UTCbar", ":10", "+01:000:01", ""] + ) + def test_to_datetime_parse_timezone_malformed(self, offset): + fmt = "%Y-%m-%d %H:%M:%S %z" + date = "2010-01-01 12:00:00 " + offset + + msg = "|".join( + [ + r'^time data ".*" doesn\'t match format ".*", at position 0. ' + f"{PARSING_ERR_MSG}$", + r'^unconverted data remains when parsing with format ".*": ".*", ' + f"at position 0. {PARSING_ERR_MSG}$", + ] + ) + with pytest.raises(ValueError, match=msg): + to_datetime([date], format=fmt) + + def test_to_datetime_parse_timezone_keeps_name(self): + # GH 21697 + fmt = "%Y-%m-%d %H:%M:%S %z" + arg = Index(["2010-01-01 12:00:00 Z"], name="foo") + result = to_datetime(arg, format=fmt) + expected = DatetimeIndex(["2010-01-01 12:00:00"], tz="UTC", name="foo") + tm.assert_index_equal(result, expected) + + +class TestToDatetime: + @pytest.mark.filterwarnings("ignore:Could not infer format") + def test_to_datetime_overflow(self): + # we should get an OutOfBoundsDatetime, NOT OverflowError + # TODO: Timestamp raises ValueError("could not convert string to Timestamp") + # can we make these more consistent? + arg = "08335394550" + msg = 'Parsing "08335394550" to datetime overflows, at position 0' + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(arg) + + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime([arg]) + + res = to_datetime(arg, errors="coerce") + assert res is NaT + res = to_datetime([arg], errors="coerce") + tm.assert_index_equal(res, Index([NaT])) + + res = to_datetime(arg, errors="ignore") + assert isinstance(res, str) and res == arg + res = to_datetime([arg], errors="ignore") + tm.assert_index_equal(res, Index([arg], dtype=object)) + + def test_to_datetime_mixed_datetime_and_string(self): + # GH#47018 adapted old doctest with new behavior + d1 = datetime(2020, 1, 1, 17, tzinfo=timezone(-timedelta(hours=1))) + d2 = datetime(2020, 1, 1, 18, tzinfo=timezone(-timedelta(hours=1))) + res = to_datetime(["2020-01-01 17:00 -0100", d2]) + expected = to_datetime([d1, d2]).tz_convert(timezone(timedelta(minutes=-60))) + tm.assert_index_equal(res, expected) + + def test_to_datetime_mixed_string_and_numeric(self): + # GH#55780 np.array(vals) would incorrectly cast the number to str + vals = ["2016-01-01", 0] + expected = DatetimeIndex([Timestamp(x) for x in vals]) + result = to_datetime(vals, format="mixed") + result2 = to_datetime(vals[::-1], format="mixed")[::-1] + result3 = DatetimeIndex(vals) + result4 = DatetimeIndex(vals[::-1])[::-1] + + tm.assert_index_equal(result, expected) + tm.assert_index_equal(result2, expected) + tm.assert_index_equal(result3, expected) + tm.assert_index_equal(result4, expected) + + @pytest.mark.parametrize( + "format", ["%Y-%m-%d", "%Y-%d-%m"], ids=["ISO8601", "non-ISO8601"] + ) + def test_to_datetime_mixed_date_and_string(self, format): + # https://github.com/pandas-dev/pandas/issues/50108 + d1 = date(2020, 1, 2) + res = to_datetime(["2020-01-01", d1], format=format) + expected = DatetimeIndex(["2020-01-01", "2020-01-02"], dtype="M8[ns]") + tm.assert_index_equal(res, expected) + + @pytest.mark.parametrize( + "fmt", + ["%Y-%d-%m %H:%M:%S%z", "%Y-%m-%d %H:%M:%S%z"], + ids=["non-ISO8601 format", "ISO8601 format"], + ) + @pytest.mark.parametrize( + "utc, args, expected", + [ + pytest.param( + True, + ["2000-01-01 01:00:00-08:00", "2000-01-01 02:00:00-08:00"], + DatetimeIndex( + ["2000-01-01 09:00:00+00:00", "2000-01-01 10:00:00+00:00"], + dtype="datetime64[ns, UTC]", + ), + id="all tz-aware, with utc", + ), + pytest.param( + False, + ["2000-01-01 01:00:00+00:00", "2000-01-01 02:00:00+00:00"], + DatetimeIndex( + ["2000-01-01 01:00:00+00:00", "2000-01-01 02:00:00+00:00"], + ), + id="all tz-aware, without utc", + ), + pytest.param( + True, + ["2000-01-01 01:00:00-08:00", "2000-01-01 02:00:00+00:00"], + DatetimeIndex( + ["2000-01-01 09:00:00+00:00", "2000-01-01 02:00:00+00:00"], + dtype="datetime64[ns, UTC]", + ), + id="all tz-aware, mixed offsets, with utc", + ), + pytest.param( + True, + ["2000-01-01 01:00:00", "2000-01-01 02:00:00+00:00"], + DatetimeIndex( + ["2000-01-01 01:00:00+00:00", "2000-01-01 02:00:00+00:00"], + dtype="datetime64[ns, UTC]", + ), + id="tz-aware string, naive pydatetime, with utc", + ), + ], + ) + @pytest.mark.parametrize( + "constructor", + [Timestamp, lambda x: Timestamp(x).to_pydatetime()], + ) + def test_to_datetime_mixed_datetime_and_string_with_format( + self, fmt, utc, args, expected, constructor + ): + # https://github.com/pandas-dev/pandas/issues/49298 + # https://github.com/pandas-dev/pandas/issues/50254 + # note: ISO8601 formats go down a fastpath, so we need to check both + # a ISO8601 format and a non-ISO8601 one + ts1 = constructor(args[0]) + ts2 = args[1] + result = to_datetime([ts1, ts2], format=fmt, utc=utc) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "fmt", + ["%Y-%d-%m %H:%M:%S%z", "%Y-%m-%d %H:%M:%S%z"], + ids=["non-ISO8601 format", "ISO8601 format"], + ) + @pytest.mark.parametrize( + "constructor", + [Timestamp, lambda x: Timestamp(x).to_pydatetime()], + ) + def test_to_datetime_mixed_datetime_and_string_with_format_mixed_offsets_utc_false( + self, fmt, constructor + ): + # https://github.com/pandas-dev/pandas/issues/49298 + # https://github.com/pandas-dev/pandas/issues/50254 + # note: ISO8601 formats go down a fastpath, so we need to check both + # a ISO8601 format and a non-ISO8601 one + args = ["2000-01-01 01:00:00", "2000-01-01 02:00:00+00:00"] + ts1 = constructor(args[0]) + ts2 = args[1] + msg = "parsing datetimes with mixed time zones will raise an error" + + expected = Index( + [ + Timestamp("2000-01-01 01:00:00"), + Timestamp("2000-01-01 02:00:00+0000", tz="UTC"), + ], + ) + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime([ts1, ts2], format=fmt, utc=False) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "fmt, expected", + [ + pytest.param( + "%Y-%m-%d %H:%M:%S%z", + Index( + [ + Timestamp("2000-01-01 09:00:00+0100", tz="UTC+01:00"), + Timestamp("2000-01-02 02:00:00+0200", tz="UTC+02:00"), + NaT, + ] + ), + id="ISO8601, non-UTC", + ), + pytest.param( + "%Y-%d-%m %H:%M:%S%z", + Index( + [ + Timestamp("2000-01-01 09:00:00+0100", tz="UTC+01:00"), + Timestamp("2000-02-01 02:00:00+0200", tz="UTC+02:00"), + NaT, + ] + ), + id="non-ISO8601, non-UTC", + ), + ], + ) + def test_to_datetime_mixed_offsets_with_none_tz(self, fmt, expected): + # https://github.com/pandas-dev/pandas/issues/50071 + msg = "parsing datetimes with mixed time zones will raise an error" + + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime( + ["2000-01-01 09:00:00+01:00", "2000-01-02 02:00:00+02:00", None], + format=fmt, + utc=False, + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "fmt, expected", + [ + pytest.param( + "%Y-%m-%d %H:%M:%S%z", + DatetimeIndex( + ["2000-01-01 08:00:00+00:00", "2000-01-02 00:00:00+00:00", "NaT"], + dtype="datetime64[ns, UTC]", + ), + id="ISO8601, UTC", + ), + pytest.param( + "%Y-%d-%m %H:%M:%S%z", + DatetimeIndex( + ["2000-01-01 08:00:00+00:00", "2000-02-01 00:00:00+00:00", "NaT"], + dtype="datetime64[ns, UTC]", + ), + id="non-ISO8601, UTC", + ), + ], + ) + def test_to_datetime_mixed_offsets_with_none(self, fmt, expected): + # https://github.com/pandas-dev/pandas/issues/50071 + result = to_datetime( + ["2000-01-01 09:00:00+01:00", "2000-01-02 02:00:00+02:00", None], + format=fmt, + utc=True, + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "fmt", + ["%Y-%d-%m %H:%M:%S%z", "%Y-%m-%d %H:%M:%S%z"], + ids=["non-ISO8601 format", "ISO8601 format"], + ) + @pytest.mark.parametrize( + "args", + [ + pytest.param( + ["2000-01-01 01:00:00-08:00", "2000-01-01 02:00:00-07:00"], + id="all tz-aware, mixed timezones, without utc", + ), + ], + ) + @pytest.mark.parametrize( + "constructor", + [Timestamp, lambda x: Timestamp(x).to_pydatetime()], + ) + def test_to_datetime_mixed_datetime_and_string_with_format_raises( + self, fmt, args, constructor + ): + # https://github.com/pandas-dev/pandas/issues/49298 + # note: ISO8601 formats go down a fastpath, so we need to check both + # a ISO8601 format and a non-ISO8601 one + ts1 = constructor(args[0]) + ts2 = constructor(args[1]) + with pytest.raises( + ValueError, match="cannot be converted to datetime64 unless utc=True" + ): + to_datetime([ts1, ts2], format=fmt, utc=False) + + def test_to_datetime_np_str(self): + # GH#32264 + # GH#48969 + value = np.str_("2019-02-04 10:18:46.297000+0000") + + ser = Series([value]) + + exp = Timestamp("2019-02-04 10:18:46.297000", tz="UTC") + + assert to_datetime(value) == exp + assert to_datetime(ser.iloc[0]) == exp + + res = to_datetime([value]) + expected = Index([exp]) + tm.assert_index_equal(res, expected) + + res = to_datetime(ser) + expected = Series(expected) + tm.assert_series_equal(res, expected) + + @pytest.mark.parametrize( + "s, _format, dt", + [ + ["2015-1-1", "%G-%V-%u", datetime(2014, 12, 29, 0, 0)], + ["2015-1-4", "%G-%V-%u", datetime(2015, 1, 1, 0, 0)], + ["2015-1-7", "%G-%V-%u", datetime(2015, 1, 4, 0, 0)], + ], + ) + def test_to_datetime_iso_week_year_format(self, s, _format, dt): + # See GH#16607 + assert to_datetime(s, format=_format) == dt + + @pytest.mark.parametrize( + "msg, s, _format", + [ + [ + "ISO week directive '%V' is incompatible with the year directive " + "'%Y'. Use the ISO year '%G' instead.", + "1999 50", + "%Y %V", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 51", + "%G %V", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 Monday", + "%G %A", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 Mon", + "%G %a", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 6", + "%G %w", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 6", + "%G %u", + ], + [ + "ISO year directive '%G' must be used with the ISO week directive " + "'%V' and a weekday directive '%A', '%a', '%w', or '%u'.", + "2051", + "%G", + ], + [ + "Day of the year directive '%j' is not compatible with ISO year " + "directive '%G'. Use '%Y' instead.", + "1999 51 6 256", + "%G %V %u %j", + ], + [ + "ISO week directive '%V' is incompatible with the year directive " + "'%Y'. Use the ISO year '%G' instead.", + "1999 51 Sunday", + "%Y %V %A", + ], + [ + "ISO week directive '%V' is incompatible with the year directive " + "'%Y'. Use the ISO year '%G' instead.", + "1999 51 Sun", + "%Y %V %a", + ], + [ + "ISO week directive '%V' is incompatible with the year directive " + "'%Y'. Use the ISO year '%G' instead.", + "1999 51 1", + "%Y %V %w", + ], + [ + "ISO week directive '%V' is incompatible with the year directive " + "'%Y'. Use the ISO year '%G' instead.", + "1999 51 1", + "%Y %V %u", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "20", + "%V", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 51 Sunday", + "%V %A", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 51 Sun", + "%V %a", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 51 1", + "%V %w", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "1999 51 1", + "%V %u", + ], + [ + "Day of the year directive '%j' is not compatible with ISO year " + "directive '%G'. Use '%Y' instead.", + "1999 50", + "%G %j", + ], + [ + "ISO week directive '%V' must be used with the ISO year directive " + "'%G' and a weekday directive '%A', '%a', '%w', or '%u'.", + "20 Monday", + "%V %A", + ], + ], + ) + @pytest.mark.parametrize("errors", ["raise", "coerce", "ignore"]) + def test_error_iso_week_year(self, msg, s, _format, errors): + # See GH#16607, GH#50308 + # This test checks for errors thrown when giving the wrong format + # However, as discussed on PR#25541, overriding the locale + # causes a different error to be thrown due to the format being + # locale specific, but the test data is in english. + # Therefore, the tests only run when locale is not overwritten, + # as a sort of solution to this problem. + if locale.getlocale() != ("zh_CN", "UTF-8") and locale.getlocale() != ( + "it_IT", + "UTF-8", + ): + with pytest.raises(ValueError, match=msg): + to_datetime(s, format=_format, errors=errors) + + @pytest.mark.parametrize("tz", [None, "US/Central"]) + def test_to_datetime_dtarr(self, tz): + # DatetimeArray + dti = date_range("1965-04-03", periods=19, freq="2W", tz=tz) + arr = dti._data + + result = to_datetime(arr) + assert result is arr + + # Doesn't work on Windows since tzpath not set correctly + @td.skip_if_windows + @pytest.mark.parametrize("arg_class", [Series, Index]) + @pytest.mark.parametrize("utc", [True, False]) + @pytest.mark.parametrize("tz", [None, "US/Central"]) + def test_to_datetime_arrow(self, tz, utc, arg_class): + pa = pytest.importorskip("pyarrow") + + dti = date_range("1965-04-03", periods=19, freq="2W", tz=tz) + dti = arg_class(dti) + + dti_arrow = dti.astype(pd.ArrowDtype(pa.timestamp(unit="ns", tz=tz))) + + result = to_datetime(dti_arrow, utc=utc) + expected = to_datetime(dti, utc=utc).astype( + pd.ArrowDtype(pa.timestamp(unit="ns", tz=tz if not utc else "UTC")) + ) + if not utc and arg_class is not Series: + # Doesn't hold for utc=True, since that will astype + # to_datetime also returns a new object for series + assert result is dti_arrow + if arg_class is Series: + tm.assert_series_equal(result, expected) + else: + tm.assert_index_equal(result, expected) + + def test_to_datetime_pydatetime(self): + actual = to_datetime(datetime(2008, 1, 15)) + assert actual == datetime(2008, 1, 15) + + def test_to_datetime_YYYYMMDD(self): + actual = to_datetime("20080115") + assert actual == datetime(2008, 1, 15) + + def test_to_datetime_unparsable_ignore(self): + # unparsable + ser = "Month 1, 1999" + assert to_datetime(ser, errors="ignore") == ser + + @td.skip_if_windows # `tm.set_timezone` does not work in windows + def test_to_datetime_now(self): + # See GH#18666 + with tm.set_timezone("US/Eastern"): + # GH#18705 + now = Timestamp("now").as_unit("ns") + pdnow = to_datetime("now") + pdnow2 = to_datetime(["now"])[0] + + # These should all be equal with infinite perf; this gives + # a generous margin of 10 seconds + assert abs(pdnow._value - now._value) < 1e10 + assert abs(pdnow2._value - now._value) < 1e10 + + assert pdnow.tzinfo is None + assert pdnow2.tzinfo is None + + @td.skip_if_windows # `tm.set_timezone` does not work in windows + @pytest.mark.parametrize("tz", ["Pacific/Auckland", "US/Samoa"]) + def test_to_datetime_today(self, tz): + # See GH#18666 + # Test with one timezone far ahead of UTC and another far behind, so + # one of these will _almost_ always be in a different day from UTC. + # Unfortunately this test between 12 and 1 AM Samoa time + # this both of these timezones _and_ UTC will all be in the same day, + # so this test will not detect the regression introduced in #18666. + with tm.set_timezone(tz): + nptoday = np.datetime64("today").astype("datetime64[ns]").astype(np.int64) + pdtoday = to_datetime("today") + pdtoday2 = to_datetime(["today"])[0] + + tstoday = Timestamp("today").as_unit("ns") + tstoday2 = Timestamp.today().as_unit("ns") + + # These should all be equal with infinite perf; this gives + # a generous margin of 10 seconds + assert abs(pdtoday.normalize()._value - nptoday) < 1e10 + assert abs(pdtoday2.normalize()._value - nptoday) < 1e10 + assert abs(pdtoday._value - tstoday._value) < 1e10 + assert abs(pdtoday._value - tstoday2._value) < 1e10 + + assert pdtoday.tzinfo is None + assert pdtoday2.tzinfo is None + + @pytest.mark.parametrize("arg", ["now", "today"]) + def test_to_datetime_today_now_unicode_bytes(self, arg): + to_datetime([arg]) + + @pytest.mark.parametrize( + "format, expected_ds", + [ + ("%Y-%m-%d %H:%M:%S%z", "2020-01-03"), + ("%Y-%d-%m %H:%M:%S%z", "2020-03-01"), + (None, "2020-01-03"), + ], + ) + @pytest.mark.parametrize( + "string, attribute", + [ + ("now", "utcnow"), + ("today", "today"), + ], + ) + def test_to_datetime_now_with_format(self, format, expected_ds, string, attribute): + # https://github.com/pandas-dev/pandas/issues/50359 + result = to_datetime(["2020-01-03 00:00:00Z", string], format=format, utc=True) + expected = DatetimeIndex( + [expected_ds, getattr(Timestamp, attribute)()], dtype="datetime64[ns, UTC]" + ) + assert (expected - result).max().total_seconds() < 1 + + @pytest.mark.parametrize( + "dt", [np.datetime64("2000-01-01"), np.datetime64("2000-01-02")] + ) + def test_to_datetime_dt64s(self, cache, dt): + assert to_datetime(dt, cache=cache) == Timestamp(dt) + + @pytest.mark.parametrize( + "arg, format", + [ + ("2001-01-01", "%Y-%m-%d"), + ("01-01-2001", "%d-%m-%Y"), + ], + ) + def test_to_datetime_dt64s_and_str(self, arg, format): + # https://github.com/pandas-dev/pandas/issues/50036 + result = to_datetime([arg, np.datetime64("2020-01-01")], format=format) + expected = DatetimeIndex(["2001-01-01", "2020-01-01"]) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "dt", [np.datetime64("1000-01-01"), np.datetime64("5000-01-02")] + ) + @pytest.mark.parametrize("errors", ["raise", "ignore", "coerce"]) + def test_to_datetime_dt64s_out_of_ns_bounds(self, cache, dt, errors): + # GH#50369 We cast to the nearest supported reso, i.e. "s" + ts = to_datetime(dt, errors=errors, cache=cache) + assert isinstance(ts, Timestamp) + assert ts.unit == "s" + assert ts.asm8 == dt + + ts = Timestamp(dt) + assert ts.unit == "s" + assert ts.asm8 == dt + + @pytest.mark.skip_ubsan + def test_to_datetime_dt64d_out_of_bounds(self, cache): + dt64 = np.datetime64(np.iinfo(np.int64).max, "D") + + msg = "Out of bounds second timestamp: 25252734927768524-07-27" + with pytest.raises(OutOfBoundsDatetime, match=msg): + Timestamp(dt64) + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(dt64, errors="raise", cache=cache) + + assert to_datetime(dt64, errors="coerce", cache=cache) is NaT + + @pytest.mark.parametrize("unit", ["s", "D"]) + def test_to_datetime_array_of_dt64s(self, cache, unit): + # https://github.com/pandas-dev/pandas/issues/31491 + # Need at least 50 to ensure cache is used. + dts = [ + np.datetime64("2000-01-01", unit), + np.datetime64("2000-01-02", unit), + ] * 30 + # Assuming all datetimes are in bounds, to_datetime() returns + # an array that is equal to Timestamp() parsing + result = to_datetime(dts, cache=cache) + if cache: + # FIXME: behavior should not depend on cache + expected = DatetimeIndex([Timestamp(x).asm8 for x in dts], dtype="M8[s]") + else: + expected = DatetimeIndex([Timestamp(x).asm8 for x in dts], dtype="M8[ns]") + + tm.assert_index_equal(result, expected) + + # A list of datetimes where the last one is out of bounds + dts_with_oob = dts + [np.datetime64("9999-01-01")] + + # As of GH#51978 we do not raise in this case + to_datetime(dts_with_oob, errors="raise") + + result = to_datetime(dts_with_oob, errors="coerce", cache=cache) + if not cache: + # FIXME: shouldn't depend on cache! + expected = DatetimeIndex( + [Timestamp(dts_with_oob[0]).asm8, Timestamp(dts_with_oob[1]).asm8] * 30 + + [NaT], + ) + else: + expected = DatetimeIndex(np.array(dts_with_oob, dtype="M8[s]")) + tm.assert_index_equal(result, expected) + + # With errors='ignore', out of bounds datetime64s + # are converted to their .item(), which depending on the version of + # numpy is either a python datetime.datetime or datetime.date + result = to_datetime(dts_with_oob, errors="ignore", cache=cache) + if not cache: + # FIXME: shouldn't depend on cache! + expected = Index(dts_with_oob) + tm.assert_index_equal(result, expected) + + def test_out_of_bounds_errors_ignore(self): + # https://github.com/pandas-dev/pandas/issues/50587 + result = to_datetime(np.datetime64("9999-01-01"), errors="ignore") + expected = np.datetime64("9999-01-01") + assert result == expected + + def test_out_of_bounds_errors_ignore2(self): + # GH#12424 + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + res = to_datetime( + Series(["2362-01-01", np.nan], dtype=object), errors="ignore" + ) + exp = Series(["2362-01-01", np.nan], dtype=object) + tm.assert_series_equal(res, exp) + + def test_to_datetime_tz(self, cache): + # xref 8260 + # uniform returns a DatetimeIndex + arr = [ + Timestamp("2013-01-01 13:00:00-0800", tz="US/Pacific"), + Timestamp("2013-01-02 14:00:00-0800", tz="US/Pacific"), + ] + result = to_datetime(arr, cache=cache) + expected = DatetimeIndex( + ["2013-01-01 13:00:00", "2013-01-02 14:00:00"], tz="US/Pacific" + ) + tm.assert_index_equal(result, expected) + + def test_to_datetime_tz_mixed(self, cache): + # mixed tzs will raise if errors='raise' + # https://github.com/pandas-dev/pandas/issues/50585 + arr = [ + Timestamp("2013-01-01 13:00:00", tz="US/Pacific"), + Timestamp("2013-01-02 14:00:00", tz="US/Eastern"), + ] + msg = ( + "Tz-aware datetime.datetime cannot be " + "converted to datetime64 unless utc=True" + ) + with pytest.raises(ValueError, match=msg): + to_datetime(arr, cache=cache) + + depr_msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + result = to_datetime(arr, cache=cache, errors="ignore") + expected = Index( + [ + Timestamp("2013-01-01 13:00:00-08:00"), + Timestamp("2013-01-02 14:00:00-05:00"), + ], + dtype="object", + ) + tm.assert_index_equal(result, expected) + result = to_datetime(arr, cache=cache, errors="coerce") + expected = DatetimeIndex( + ["2013-01-01 13:00:00-08:00", "NaT"], dtype="datetime64[ns, US/Pacific]" + ) + tm.assert_index_equal(result, expected) + + def test_to_datetime_different_offsets(self, cache): + # inspired by asv timeseries.ToDatetimeNONISO8601 benchmark + # see GH-26097 for more + ts_string_1 = "March 1, 2018 12:00:00+0400" + ts_string_2 = "March 1, 2018 12:00:00+0500" + arr = [ts_string_1] * 5 + [ts_string_2] * 5 + expected = Index([parse(x) for x in arr]) + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime(arr, cache=cache) + tm.assert_index_equal(result, expected) + + def test_to_datetime_tz_pytz(self, cache): + # see gh-8260 + us_eastern = pytz.timezone("US/Eastern") + arr = np.array( + [ + us_eastern.localize( + datetime(year=2000, month=1, day=1, hour=3, minute=0) + ), + us_eastern.localize( + datetime(year=2000, month=6, day=1, hour=3, minute=0) + ), + ], + dtype=object, + ) + result = to_datetime(arr, utc=True, cache=cache) + expected = DatetimeIndex( + ["2000-01-01 08:00:00+00:00", "2000-06-01 07:00:00+00:00"], + dtype="datetime64[ns, UTC]", + freq=None, + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "init_constructor, end_constructor", + [ + (Index, DatetimeIndex), + (list, DatetimeIndex), + (np.array, DatetimeIndex), + (Series, Series), + ], + ) + def test_to_datetime_utc_true(self, cache, init_constructor, end_constructor): + # See gh-11934 & gh-6415 + data = ["20100102 121314", "20100102 121315"] + expected_data = [ + Timestamp("2010-01-02 12:13:14", tz="utc"), + Timestamp("2010-01-02 12:13:15", tz="utc"), + ] + + result = to_datetime( + init_constructor(data), format="%Y%m%d %H%M%S", utc=True, cache=cache + ) + expected = end_constructor(expected_data) + tm.assert_equal(result, expected) + + @pytest.mark.parametrize( + "scalar, expected", + [ + ["20100102 121314", Timestamp("2010-01-02 12:13:14", tz="utc")], + ["20100102 121315", Timestamp("2010-01-02 12:13:15", tz="utc")], + ], + ) + def test_to_datetime_utc_true_scalar(self, cache, scalar, expected): + # Test scalar case as well + result = to_datetime(scalar, format="%Y%m%d %H%M%S", utc=True, cache=cache) + assert result == expected + + def test_to_datetime_utc_true_with_series_single_value(self, cache): + # GH 15760 UTC=True with Series + ts = 1.5e18 + result = to_datetime(Series([ts]), utc=True, cache=cache) + expected = Series([Timestamp(ts, tz="utc")]) + tm.assert_series_equal(result, expected) + + def test_to_datetime_utc_true_with_series_tzaware_string(self, cache): + ts = "2013-01-01 00:00:00-01:00" + expected_ts = "2013-01-01 01:00:00" + data = Series([ts] * 3) + result = to_datetime(data, utc=True, cache=cache) + expected = Series([Timestamp(expected_ts, tz="utc")] * 3) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "date, dtype", + [ + ("2013-01-01 01:00:00", "datetime64[ns]"), + ("2013-01-01 01:00:00", "datetime64[ns, UTC]"), + ], + ) + def test_to_datetime_utc_true_with_series_datetime_ns(self, cache, date, dtype): + expected = Series( + [Timestamp("2013-01-01 01:00:00", tz="UTC")], dtype="M8[ns, UTC]" + ) + result = to_datetime(Series([date], dtype=dtype), utc=True, cache=cache) + tm.assert_series_equal(result, expected) + + def test_to_datetime_tz_psycopg2(self, request, cache): + # xref 8260 + psycopg2_tz = pytest.importorskip("psycopg2.tz") + + # misc cases + tz1 = psycopg2_tz.FixedOffsetTimezone(offset=-300, name=None) + tz2 = psycopg2_tz.FixedOffsetTimezone(offset=-240, name=None) + arr = np.array( + [ + datetime(2000, 1, 1, 3, 0, tzinfo=tz1), + datetime(2000, 6, 1, 3, 0, tzinfo=tz2), + ], + dtype=object, + ) + + result = to_datetime(arr, errors="coerce", utc=True, cache=cache) + expected = DatetimeIndex( + ["2000-01-01 08:00:00+00:00", "2000-06-01 07:00:00+00:00"], + dtype="datetime64[ns, UTC]", + freq=None, + ) + tm.assert_index_equal(result, expected) + + # dtype coercion + i = DatetimeIndex( + ["2000-01-01 08:00:00"], + tz=psycopg2_tz.FixedOffsetTimezone(offset=-300, name=None), + ) + assert is_datetime64_ns_dtype(i) + + # tz coercion + result = to_datetime(i, errors="coerce", cache=cache) + tm.assert_index_equal(result, i) + + result = to_datetime(i, errors="coerce", utc=True, cache=cache) + expected = DatetimeIndex(["2000-01-01 13:00:00"], dtype="datetime64[ns, UTC]") + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("arg", [True, False]) + def test_datetime_bool(self, cache, arg): + # GH13176 + msg = r"dtype bool cannot be converted to datetime64\[ns\]" + with pytest.raises(TypeError, match=msg): + to_datetime(arg) + assert to_datetime(arg, errors="coerce", cache=cache) is NaT + assert to_datetime(arg, errors="ignore", cache=cache) is arg + + def test_datetime_bool_arrays_mixed(self, cache): + msg = f"{type(cache)} is not convertible to datetime" + with pytest.raises(TypeError, match=msg): + to_datetime([False, datetime.today()], cache=cache) + with pytest.raises( + ValueError, + match=( + r'^time data "True" doesn\'t match format "%Y%m%d", ' + f"at position 1. {PARSING_ERR_MSG}$" + ), + ): + to_datetime(["20130101", True], cache=cache) + tm.assert_index_equal( + to_datetime([0, False, NaT, 0.0], errors="coerce", cache=cache), + DatetimeIndex( + [to_datetime(0, cache=cache), NaT, NaT, to_datetime(0, cache=cache)] + ), + ) + + @pytest.mark.parametrize("arg", [bool, to_datetime]) + def test_datetime_invalid_datatype(self, arg): + # GH13176 + msg = "is not convertible to datetime" + with pytest.raises(TypeError, match=msg): + to_datetime(arg) + + @pytest.mark.parametrize("errors", ["coerce", "raise", "ignore"]) + def test_invalid_format_raises(self, errors): + # https://github.com/pandas-dev/pandas/issues/50255 + with pytest.raises( + ValueError, match="':' is a bad directive in format 'H%:M%:S%" + ): + to_datetime(["00:00:00"], format="H%:M%:S%", errors=errors) + + @pytest.mark.parametrize("value", ["a", "00:01:99"]) + @pytest.mark.parametrize("format", [None, "%H:%M:%S"]) + def test_datetime_invalid_scalar(self, value, format): + # GH24763 + res = to_datetime(value, errors="ignore", format=format) + assert res == value + + res = to_datetime(value, errors="coerce", format=format) + assert res is NaT + + msg = "|".join( + [ + r'^time data "a" doesn\'t match format "%H:%M:%S", at position 0. ' + f"{PARSING_ERR_MSG}$", + r'^Given date string "a" not likely a datetime, at position 0$', + r'^unconverted data remains when parsing with format "%H:%M:%S": "9", ' + f"at position 0. {PARSING_ERR_MSG}$", + r"^second must be in 0..59: 00:01:99, at position 0$", + ] + ) + with pytest.raises(ValueError, match=msg): + to_datetime(value, errors="raise", format=format) + + @pytest.mark.parametrize("value", ["3000/12/11 00:00:00"]) + @pytest.mark.parametrize("format", [None, "%H:%M:%S"]) + def test_datetime_outofbounds_scalar(self, value, format): + # GH24763 + res = to_datetime(value, errors="ignore", format=format) + assert res == value + + res = to_datetime(value, errors="coerce", format=format) + assert res is NaT + + if format is not None: + msg = r'^time data ".*" doesn\'t match format ".*", at position 0.' + with pytest.raises(ValueError, match=msg): + to_datetime(value, errors="raise", format=format) + else: + msg = "^Out of bounds .*, at position 0$" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(value, errors="raise", format=format) + + @pytest.mark.parametrize( + ("values"), [(["a"]), (["00:01:99"]), (["a", "b", "99:00:00"])] + ) + @pytest.mark.parametrize("format", [(None), ("%H:%M:%S")]) + def test_datetime_invalid_index(self, values, format): + # GH24763 + # Not great to have logic in tests, but this one's hard to + # parametrise over + if format is None and len(values) > 1: + warn = UserWarning + else: + warn = None + with tm.assert_produces_warning( + warn, match="Could not infer format", raise_on_extra_warnings=False + ): + res = to_datetime(values, errors="ignore", format=format) + tm.assert_index_equal(res, Index(values, dtype=object)) + + with tm.assert_produces_warning( + warn, match="Could not infer format", raise_on_extra_warnings=False + ): + res = to_datetime(values, errors="coerce", format=format) + tm.assert_index_equal(res, DatetimeIndex([NaT] * len(values))) + + msg = "|".join( + [ + r'^Given date string "a" not likely a datetime, at position 0$', + r'^time data "a" doesn\'t match format "%H:%M:%S", at position 0. ' + f"{PARSING_ERR_MSG}$", + r'^unconverted data remains when parsing with format "%H:%M:%S": "9", ' + f"at position 0. {PARSING_ERR_MSG}$", + r"^second must be in 0..59: 00:01:99, at position 0$", + ] + ) + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning( + warn, match="Could not infer format", raise_on_extra_warnings=False + ): + to_datetime(values, errors="raise", format=format) + + @pytest.mark.parametrize("utc", [True, None]) + @pytest.mark.parametrize("format", ["%Y%m%d %H:%M:%S", None]) + @pytest.mark.parametrize("constructor", [list, tuple, np.array, Index, deque]) + def test_to_datetime_cache(self, utc, format, constructor): + date = "20130101 00:00:00" + test_dates = [date] * 10**5 + data = constructor(test_dates) + + result = to_datetime(data, utc=utc, format=format, cache=True) + expected = to_datetime(data, utc=utc, format=format, cache=False) + + tm.assert_index_equal(result, expected) + + def test_to_datetime_from_deque(self): + # GH 29403 + result = to_datetime(deque([Timestamp("2010-06-02 09:30:00")] * 51)) + expected = to_datetime([Timestamp("2010-06-02 09:30:00")] * 51) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("utc", [True, None]) + @pytest.mark.parametrize("format", ["%Y%m%d %H:%M:%S", None]) + def test_to_datetime_cache_series(self, utc, format): + date = "20130101 00:00:00" + test_dates = [date] * 10**5 + data = Series(test_dates) + result = to_datetime(data, utc=utc, format=format, cache=True) + expected = to_datetime(data, utc=utc, format=format, cache=False) + tm.assert_series_equal(result, expected) + + def test_to_datetime_cache_scalar(self): + date = "20130101 00:00:00" + result = to_datetime(date, cache=True) + expected = Timestamp("20130101 00:00:00") + assert result == expected + + @pytest.mark.parametrize( + "datetimelikes,expected_values", + ( + ( + (None, np.nan) + (NaT,) * start_caching_at, + (NaT,) * (start_caching_at + 2), + ), + ( + (None, Timestamp("2012-07-26")) + (NaT,) * start_caching_at, + (NaT, Timestamp("2012-07-26")) + (NaT,) * start_caching_at, + ), + ( + (None,) + + (NaT,) * start_caching_at + + ("2012 July 26", Timestamp("2012-07-26")), + (NaT,) * (start_caching_at + 1) + + (Timestamp("2012-07-26"), Timestamp("2012-07-26")), + ), + ), + ) + def test_convert_object_to_datetime_with_cache( + self, datetimelikes, expected_values + ): + # GH#39882 + ser = Series( + datetimelikes, + dtype="object", + ) + result_series = to_datetime(ser, errors="coerce") + expected_series = Series( + expected_values, + dtype="datetime64[ns]", + ) + tm.assert_series_equal(result_series, expected_series) + + @pytest.mark.parametrize("cache", [True, False]) + @pytest.mark.parametrize( + "input", + [ + Series([NaT] * 20 + [None] * 20, dtype="object"), + Series([NaT] * 60 + [None] * 60, dtype="object"), + Series([None] * 20), + Series([None] * 60), + Series([""] * 20), + Series([""] * 60), + Series([pd.NA] * 20), + Series([pd.NA] * 60), + Series([np.nan] * 20), + Series([np.nan] * 60), + ], + ) + def test_to_datetime_converts_null_like_to_nat(self, cache, input): + # GH35888 + expected = Series([NaT] * len(input), dtype="M8[ns]") + result = to_datetime(input, cache=cache) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "date, format", + [ + ("2017-20", "%Y-%W"), + ("20 Sunday", "%W %A"), + ("20 Sun", "%W %a"), + ("2017-21", "%Y-%U"), + ("20 Sunday", "%U %A"), + ("20 Sun", "%U %a"), + ], + ) + def test_week_without_day_and_calendar_year(self, date, format): + # GH16774 + + msg = "Cannot use '%W' or '%U' without day and year" + with pytest.raises(ValueError, match=msg): + to_datetime(date, format=format) + + def test_to_datetime_coerce(self): + # GH 26122 + ts_strings = [ + "March 1, 2018 12:00:00+0400", + "March 1, 2018 12:00:00+0500", + "20100240", + ] + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime(ts_strings, errors="coerce") + expected = Index( + [ + datetime(2018, 3, 1, 12, 0, tzinfo=tzoffset(None, 14400)), + datetime(2018, 3, 1, 12, 0, tzinfo=tzoffset(None, 18000)), + NaT, + ] + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "string_arg, format", + [("March 1, 2018", "%B %d, %Y"), ("2018-03-01", "%Y-%m-%d")], + ) + @pytest.mark.parametrize( + "outofbounds", + [ + datetime(9999, 1, 1), + date(9999, 1, 1), + np.datetime64("9999-01-01"), + "January 1, 9999", + "9999-01-01", + ], + ) + def test_to_datetime_coerce_oob(self, string_arg, format, outofbounds): + # https://github.com/pandas-dev/pandas/issues/50255 + ts_strings = [string_arg, outofbounds] + result = to_datetime(ts_strings, errors="coerce", format=format) + expected = DatetimeIndex([datetime(2018, 3, 1), NaT]) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "errors, expected", + [ + ("coerce", Index([NaT, NaT])), + ("ignore", Index(["200622-12-31", "111111-24-11"], dtype=object)), + ], + ) + def test_to_datetime_malformed_no_raise(self, errors, expected): + # GH 28299 + # GH 48633 + ts_strings = ["200622-12-31", "111111-24-11"] + with tm.assert_produces_warning( + UserWarning, match="Could not infer format", raise_on_extra_warnings=False + ): + result = to_datetime(ts_strings, errors=errors) + tm.assert_index_equal(result, expected) + + def test_to_datetime_malformed_raise(self): + # GH 48633 + ts_strings = ["200622-12-31", "111111-24-11"] + msg = ( + 'Parsed string "200622-12-31" gives an invalid tzoffset, which must ' + r"be between -timedelta\(hours=24\) and timedelta\(hours=24\), " + "at position 0" + ) + with pytest.raises( + ValueError, + match=msg, + ): + with tm.assert_produces_warning( + UserWarning, match="Could not infer format" + ): + to_datetime( + ts_strings, + errors="raise", + ) + + def test_iso_8601_strings_with_same_offset(self): + # GH 17697, 11736 + ts_str = "2015-11-18 15:30:00+05:30" + result = to_datetime(ts_str) + expected = Timestamp(ts_str) + assert result == expected + + expected = DatetimeIndex([Timestamp(ts_str)] * 2) + result = to_datetime([ts_str] * 2) + tm.assert_index_equal(result, expected) + + result = DatetimeIndex([ts_str] * 2) + tm.assert_index_equal(result, expected) + + def test_iso_8601_strings_with_different_offsets(self): + # GH 17697, 11736, 50887 + ts_strings = ["2015-11-18 15:30:00+05:30", "2015-11-18 16:30:00+06:30", NaT] + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_datetime(ts_strings) + expected = np.array( + [ + datetime(2015, 11, 18, 15, 30, tzinfo=tzoffset(None, 19800)), + datetime(2015, 11, 18, 16, 30, tzinfo=tzoffset(None, 23400)), + NaT, + ], + dtype=object, + ) + # GH 21864 + expected = Index(expected) + tm.assert_index_equal(result, expected) + + def test_iso_8601_strings_with_different_offsets_utc(self): + ts_strings = ["2015-11-18 15:30:00+05:30", "2015-11-18 16:30:00+06:30", NaT] + result = to_datetime(ts_strings, utc=True) + expected = DatetimeIndex( + [Timestamp(2015, 11, 18, 10), Timestamp(2015, 11, 18, 10), NaT], tz="UTC" + ) + tm.assert_index_equal(result, expected) + + def test_mixed_offsets_with_native_datetime_raises(self): + # GH 25978 + + vals = [ + "nan", + Timestamp("1990-01-01"), + "2015-03-14T16:15:14.123-08:00", + "2019-03-04T21:56:32.620-07:00", + None, + "today", + "now", + ] + ser = Series(vals) + assert all(ser[i] is vals[i] for i in range(len(vals))) # GH#40111 + + now = Timestamp("now") + today = Timestamp("today") + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + mixed = to_datetime(ser) + expected = Series( + [ + "NaT", + Timestamp("1990-01-01"), + Timestamp("2015-03-14T16:15:14.123-08:00").to_pydatetime(), + Timestamp("2019-03-04T21:56:32.620-07:00").to_pydatetime(), + None, + ], + dtype=object, + ) + tm.assert_series_equal(mixed[:-2], expected) + # we'll check mixed[-1] and mixed[-2] match now and today to within + # call-timing tolerances + assert (now - mixed.iloc[-1]).total_seconds() <= 0.1 + assert (today - mixed.iloc[-2]).total_seconds() <= 0.1 + + with pytest.raises(ValueError, match="Tz-aware datetime.datetime"): + to_datetime(mixed) + + def test_non_iso_strings_with_tz_offset(self): + result = to_datetime(["March 1, 2018 12:00:00+0400"] * 2) + expected = DatetimeIndex( + [datetime(2018, 3, 1, 12, tzinfo=timezone(timedelta(minutes=240)))] * 2 + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "ts, expected", + [ + (Timestamp("2018-01-01"), Timestamp("2018-01-01", tz="UTC")), + ( + Timestamp("2018-01-01", tz="US/Pacific"), + Timestamp("2018-01-01 08:00", tz="UTC"), + ), + ], + ) + def test_timestamp_utc_true(self, ts, expected): + # GH 24415 + result = to_datetime(ts, utc=True) + assert result == expected + + @pytest.mark.parametrize("dt_str", ["00010101", "13000101", "30000101", "99990101"]) + def test_to_datetime_with_format_out_of_bounds(self, dt_str): + # GH 9107 + msg = "Out of bounds nanosecond timestamp" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(dt_str, format="%Y%m%d") + + def test_to_datetime_utc(self): + arr = np.array([parse("2012-06-13T01:39:00Z")], dtype=object) + + result = to_datetime(arr, utc=True) + assert result.tz is timezone.utc + + def test_to_datetime_fixed_offset(self): + from pandas.tests.indexes.datetimes.test_timezones import FixedOffset + + fixed_off = FixedOffset(-420, "-07:00") + + dates = [ + datetime(2000, 1, 1, tzinfo=fixed_off), + datetime(2000, 1, 2, tzinfo=fixed_off), + datetime(2000, 1, 3, tzinfo=fixed_off), + ] + result = to_datetime(dates) + assert result.tz == fixed_off + + @pytest.mark.parametrize( + "date", + [ + ["2020-10-26 00:00:00+06:00", "2020-10-26 00:00:00+01:00"], + ["2020-10-26 00:00:00+06:00", Timestamp("2018-01-01", tz="US/Pacific")], + [ + "2020-10-26 00:00:00+06:00", + datetime(2020, 1, 1, 18, tzinfo=pytz.timezone("Australia/Melbourne")), + ], + ], + ) + def test_to_datetime_mixed_offsets_with_utc_false_deprecated(self, date): + # GH 50887 + msg = "parsing datetimes with mixed time zones will raise an error" + with tm.assert_produces_warning(FutureWarning, match=msg): + to_datetime(date, utc=False) + + +class TestToDatetimeUnit: + @pytest.mark.parametrize("unit", ["Y", "M"]) + @pytest.mark.parametrize("item", [150, float(150)]) + def test_to_datetime_month_or_year_unit_int(self, cache, unit, item, request): + # GH#50870 Note we have separate tests that pd.Timestamp gets these right + ts = Timestamp(item, unit=unit) + expected = DatetimeIndex([ts], dtype="M8[ns]") + + result = to_datetime([item], unit=unit, cache=cache) + tm.assert_index_equal(result, expected) + + result = to_datetime(np.array([item], dtype=object), unit=unit, cache=cache) + tm.assert_index_equal(result, expected) + + result = to_datetime(np.array([item]), unit=unit, cache=cache) + tm.assert_index_equal(result, expected) + + # with a nan! + result = to_datetime(np.array([item, np.nan]), unit=unit, cache=cache) + assert result.isna()[1] + tm.assert_index_equal(result[:1], expected) + + @pytest.mark.parametrize("unit", ["Y", "M"]) + def test_to_datetime_month_or_year_unit_non_round_float(self, cache, unit): + # GH#50301 + # Match Timestamp behavior in disallowing non-round floats with + # Y or M unit + warn_msg = "strings will be parsed as datetime strings" + msg = f"Conversion of non-round float with unit={unit} is ambiguous" + with pytest.raises(ValueError, match=msg): + to_datetime([1.5], unit=unit, errors="raise") + with pytest.raises(ValueError, match=msg): + to_datetime(np.array([1.5]), unit=unit, errors="raise") + with pytest.raises(ValueError, match=msg): + with tm.assert_produces_warning(FutureWarning, match=warn_msg): + to_datetime(["1.5"], unit=unit, errors="raise") + + # with errors="ignore" we also end up raising within the Timestamp + # constructor; this may not be ideal + with pytest.raises(ValueError, match=msg): + to_datetime([1.5], unit=unit, errors="ignore") + + res = to_datetime([1.5], unit=unit, errors="coerce") + expected = Index([NaT], dtype="M8[ns]") + tm.assert_index_equal(res, expected) + + with tm.assert_produces_warning(FutureWarning, match=warn_msg): + res = to_datetime(["1.5"], unit=unit, errors="coerce") + tm.assert_index_equal(res, expected) + + # round floats are OK + res = to_datetime([1.0], unit=unit) + expected = to_datetime([1], unit=unit) + tm.assert_index_equal(res, expected) + + def test_unit(self, cache): + # GH 11758 + # test proper behavior with errors + msg = "cannot specify both format and unit" + with pytest.raises(ValueError, match=msg): + to_datetime([1], unit="D", format="%Y%m%d", cache=cache) + + def test_unit_str(self, cache): + # GH 57051 + # Test that strs aren't dropping precision to 32-bit accidentally. + with tm.assert_produces_warning(FutureWarning): + res = to_datetime(["1704660000"], unit="s", origin="unix") + expected = to_datetime([1704660000], unit="s", origin="unix") + tm.assert_index_equal(res, expected) + + def test_unit_array_mixed_nans(self, cache): + values = [11111111111111111, 1, 1.0, iNaT, NaT, np.nan, "NaT", ""] + result = to_datetime(values, unit="D", errors="ignore", cache=cache) + expected = Index( + [ + 11111111111111111, + Timestamp("1970-01-02"), + Timestamp("1970-01-02"), + NaT, + NaT, + NaT, + NaT, + NaT, + ], + dtype=object, + ) + tm.assert_index_equal(result, expected) + + result = to_datetime(values, unit="D", errors="coerce", cache=cache) + expected = DatetimeIndex( + ["NaT", "1970-01-02", "1970-01-02", "NaT", "NaT", "NaT", "NaT", "NaT"], + dtype="M8[ns]", + ) + tm.assert_index_equal(result, expected) + + msg = "cannot convert input 11111111111111111 with the unit 'D'" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(values, unit="D", errors="raise", cache=cache) + + def test_unit_array_mixed_nans_large_int(self, cache): + values = [1420043460000000000000000, iNaT, NaT, np.nan, "NaT"] + + result = to_datetime(values, errors="ignore", unit="s", cache=cache) + expected = Index([1420043460000000000000000, NaT, NaT, NaT, NaT], dtype=object) + tm.assert_index_equal(result, expected) + + result = to_datetime(values, errors="coerce", unit="s", cache=cache) + expected = DatetimeIndex(["NaT", "NaT", "NaT", "NaT", "NaT"], dtype="M8[ns]") + tm.assert_index_equal(result, expected) + + msg = "cannot convert input 1420043460000000000000000 with the unit 's'" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(values, errors="raise", unit="s", cache=cache) + + def test_to_datetime_invalid_str_not_out_of_bounds_valuerror(self, cache): + # if we have a string, then we raise a ValueError + # and NOT an OutOfBoundsDatetime + msg = "non convertible value foo with the unit 's'" + with pytest.raises(ValueError, match=msg): + to_datetime("foo", errors="raise", unit="s", cache=cache) + + @pytest.mark.parametrize("error", ["raise", "coerce", "ignore"]) + def test_unit_consistency(self, cache, error): + # consistency of conversions + expected = Timestamp("1970-05-09 14:25:11") + result = to_datetime(11111111, unit="s", errors=error, cache=cache) + assert result == expected + assert isinstance(result, Timestamp) + + @pytest.mark.parametrize("errors", ["ignore", "raise", "coerce"]) + @pytest.mark.parametrize("dtype", ["float64", "int64"]) + def test_unit_with_numeric(self, cache, errors, dtype): + # GH 13180 + # coercions from floats/ints are ok + expected = DatetimeIndex( + ["2015-06-19 05:33:20", "2015-05-27 22:33:20"], dtype="M8[ns]" + ) + arr = np.array([1.434692e18, 1.432766e18]).astype(dtype) + result = to_datetime(arr, errors=errors, cache=cache) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "exp, arr, warning", + [ + [ + ["NaT", "2015-06-19 05:33:20", "2015-05-27 22:33:20"], + ["foo", 1.434692e18, 1.432766e18], + UserWarning, + ], + [ + ["2015-06-19 05:33:20", "2015-05-27 22:33:20", "NaT", "NaT"], + [1.434692e18, 1.432766e18, "foo", "NaT"], + None, + ], + ], + ) + def test_unit_with_numeric_coerce(self, cache, exp, arr, warning): + # but we want to make sure that we are coercing + # if we have ints/strings + expected = DatetimeIndex(exp, dtype="M8[ns]") + with tm.assert_produces_warning(warning, match="Could not infer format"): + result = to_datetime(arr, errors="coerce", cache=cache) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "arr", + [ + [Timestamp("20130101"), 1.434692e18, 1.432766e18], + [1.434692e18, 1.432766e18, Timestamp("20130101")], + ], + ) + def test_unit_mixed(self, cache, arr): + # GH#50453 pre-2.0 with mixed numeric/datetimes and errors="coerce" + # the numeric entries would be coerced to NaT, was never clear exactly + # why. + # mixed integers/datetimes + expected = Index([Timestamp(x) for x in arr], dtype="M8[ns]") + result = to_datetime(arr, errors="coerce", cache=cache) + tm.assert_index_equal(result, expected) + + # GH#49037 pre-2.0 this raised, but it always worked with Series, + # was never clear why it was disallowed + result = to_datetime(arr, errors="raise", cache=cache) + tm.assert_index_equal(result, expected) + + result = DatetimeIndex(arr) + tm.assert_index_equal(result, expected) + + def test_unit_rounding(self, cache): + # GH 14156 & GH 20445: argument will incur floating point errors + # but no premature rounding + value = 1434743731.8770001 + result = to_datetime(value, unit="s", cache=cache) + expected = Timestamp("2015-06-19 19:55:31.877000093") + assert result == expected + + alt = Timestamp(value, unit="s") + assert alt == result + + def test_unit_ignore_keeps_name(self, cache): + # GH 21697 + expected = Index([15e9] * 2, name="name") + result = to_datetime(expected, errors="ignore", unit="s", cache=cache) + tm.assert_index_equal(result, expected) + + def test_to_datetime_errors_ignore_utc_true(self): + # GH#23758 + result = to_datetime([1], unit="s", utc=True, errors="ignore") + expected = DatetimeIndex(["1970-01-01 00:00:01"], dtype="M8[ns, UTC]") + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("dtype", [int, float]) + def test_to_datetime_unit(self, dtype): + epoch = 1370745748 + ser = Series([epoch + t for t in range(20)]).astype(dtype) + result = to_datetime(ser, unit="s") + expected = Series( + [ + Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t) + for t in range(20) + ], + dtype="M8[ns]", + ) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize("null", [iNaT, np.nan]) + def test_to_datetime_unit_with_nulls(self, null): + epoch = 1370745748 + ser = Series([epoch + t for t in range(20)] + [null]) + result = to_datetime(ser, unit="s") + expected = Series( + [Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t) for t in range(20)] + + [NaT], + dtype="M8[ns]", + ) + tm.assert_series_equal(result, expected) + + def test_to_datetime_unit_fractional_seconds(self): + # GH13834 + epoch = 1370745748 + ser = Series([epoch + t for t in np.arange(0, 2, 0.25)] + [iNaT]).astype(float) + result = to_datetime(ser, unit="s") + expected = Series( + [ + Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t) + for t in np.arange(0, 2, 0.25) + ] + + [NaT], + dtype="M8[ns]", + ) + # GH20455 argument will incur floating point errors but no premature rounding + result = result.round("ms") + tm.assert_series_equal(result, expected) + + def test_to_datetime_unit_na_values(self): + result = to_datetime([1, 2, "NaT", NaT, np.nan], unit="D") + expected = DatetimeIndex( + [Timestamp("1970-01-02"), Timestamp("1970-01-03")] + ["NaT"] * 3, + dtype="M8[ns]", + ) + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize("bad_val", ["foo", 111111111]) + def test_to_datetime_unit_invalid(self, bad_val): + msg = f"{bad_val} with the unit 'D'" + with pytest.raises(ValueError, match=msg): + to_datetime([1, 2, bad_val], unit="D") + + @pytest.mark.parametrize("bad_val", ["foo", 111111111]) + def test_to_timestamp_unit_coerce(self, bad_val): + # coerce we can process + expected = DatetimeIndex( + [Timestamp("1970-01-02"), Timestamp("1970-01-03")] + ["NaT"] * 1, + dtype="M8[ns]", + ) + result = to_datetime([1, 2, bad_val], unit="D", errors="coerce") + tm.assert_index_equal(result, expected) + + def test_float_to_datetime_raise_near_bounds(self): + # GH50183 + msg = "cannot convert input with unit 'D'" + oneday_in_ns = 1e9 * 60 * 60 * 24 + tsmax_in_days = 2**63 / oneday_in_ns # 2**63 ns, in days + # just in bounds + should_succeed = Series( + [0, tsmax_in_days - 0.005, -tsmax_in_days + 0.005], dtype=float + ) + expected = (should_succeed * oneday_in_ns).astype(np.int64) + for error_mode in ["raise", "coerce", "ignore"]: + result1 = to_datetime(should_succeed, unit="D", errors=error_mode) + # Cast to `np.float64` so that `rtol` and inexact checking kick in + # (`check_exact` doesn't take place for integer dtypes) + tm.assert_almost_equal( + result1.astype(np.int64).astype(np.float64), + expected.astype(np.float64), + rtol=1e-10, + ) + # just out of bounds + should_fail1 = Series([0, tsmax_in_days + 0.005], dtype=float) + should_fail2 = Series([0, -tsmax_in_days - 0.005], dtype=float) + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(should_fail1, unit="D", errors="raise") + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(should_fail2, unit="D", errors="raise") + + +class TestToDatetimeDataFrame: + @pytest.fixture + def df(self): + return DataFrame( + { + "year": [2015, 2016], + "month": [2, 3], + "day": [4, 5], + "hour": [6, 7], + "minute": [58, 59], + "second": [10, 11], + "ms": [1, 1], + "us": [2, 2], + "ns": [3, 3], + } + ) + + def test_dataframe(self, df, cache): + result = to_datetime( + {"year": df["year"], "month": df["month"], "day": df["day"]}, cache=cache + ) + expected = Series( + [Timestamp("20150204 00:00:00"), Timestamp("20160305 00:0:00")] + ) + tm.assert_series_equal(result, expected) + + # dict-like + result = to_datetime(df[["year", "month", "day"]].to_dict(), cache=cache) + tm.assert_series_equal(result, expected) + + def test_dataframe_dict_with_constructable(self, df, cache): + # dict but with constructable + df2 = df[["year", "month", "day"]].to_dict() + df2["month"] = 2 + result = to_datetime(df2, cache=cache) + expected2 = Series( + [Timestamp("20150204 00:00:00"), Timestamp("20160205 00:0:00")] + ) + tm.assert_series_equal(result, expected2) + + @pytest.mark.parametrize( + "unit", + [ + { + "year": "years", + "month": "months", + "day": "days", + "hour": "hours", + "minute": "minutes", + "second": "seconds", + }, + { + "year": "year", + "month": "month", + "day": "day", + "hour": "hour", + "minute": "minute", + "second": "second", + }, + ], + ) + def test_dataframe_field_aliases_column_subset(self, df, cache, unit): + # unit mappings + result = to_datetime(df[list(unit.keys())].rename(columns=unit), cache=cache) + expected = Series( + [Timestamp("20150204 06:58:10"), Timestamp("20160305 07:59:11")], + dtype="M8[ns]", + ) + tm.assert_series_equal(result, expected) + + def test_dataframe_field_aliases(self, df, cache): + d = { + "year": "year", + "month": "month", + "day": "day", + "hour": "hour", + "minute": "minute", + "second": "second", + "ms": "ms", + "us": "us", + "ns": "ns", + } + + result = to_datetime(df.rename(columns=d), cache=cache) + expected = Series( + [ + Timestamp("20150204 06:58:10.001002003"), + Timestamp("20160305 07:59:11.001002003"), + ] + ) + tm.assert_series_equal(result, expected) + + def test_dataframe_str_dtype(self, df, cache): + # coerce back to int + result = to_datetime(df.astype(str), cache=cache) + expected = Series( + [ + Timestamp("20150204 06:58:10.001002003"), + Timestamp("20160305 07:59:11.001002003"), + ] + ) + tm.assert_series_equal(result, expected) + + def test_dataframe_coerce(self, cache): + # passing coerce + df2 = DataFrame({"year": [2015, 2016], "month": [2, 20], "day": [4, 5]}) + + msg = ( + r'^cannot assemble the datetimes: time data ".+" doesn\'t ' + r'match format "%Y%m%d", at position 1\.' + ) + with pytest.raises(ValueError, match=msg): + to_datetime(df2, cache=cache) + + result = to_datetime(df2, errors="coerce", cache=cache) + expected = Series([Timestamp("20150204 00:00:00"), NaT]) + tm.assert_series_equal(result, expected) + + def test_dataframe_extra_keys_raisesm(self, df, cache): + # extra columns + msg = r"extra keys have been passed to the datetime assemblage: \[foo\]" + with pytest.raises(ValueError, match=msg): + df2 = df.copy() + df2["foo"] = 1 + to_datetime(df2, cache=cache) + + @pytest.mark.parametrize( + "cols", + [ + ["year"], + ["year", "month"], + ["year", "month", "second"], + ["month", "day"], + ["year", "day", "second"], + ], + ) + def test_dataframe_missing_keys_raises(self, df, cache, cols): + # not enough + msg = ( + r"to assemble mappings requires at least that \[year, month, " + r"day\] be specified: \[.+\] is missing" + ) + with pytest.raises(ValueError, match=msg): + to_datetime(df[cols], cache=cache) + + def test_dataframe_duplicate_columns_raises(self, cache): + # duplicates + msg = "cannot assemble with duplicate keys" + df2 = DataFrame({"year": [2015, 2016], "month": [2, 20], "day": [4, 5]}) + df2.columns = ["year", "year", "day"] + with pytest.raises(ValueError, match=msg): + to_datetime(df2, cache=cache) + + df2 = DataFrame( + {"year": [2015, 2016], "month": [2, 20], "day": [4, 5], "hour": [4, 5]} + ) + df2.columns = ["year", "month", "day", "day"] + with pytest.raises(ValueError, match=msg): + to_datetime(df2, cache=cache) + + def test_dataframe_int16(self, cache): + # GH#13451 + df = DataFrame({"year": [2015, 2016], "month": [2, 3], "day": [4, 5]}) + + # int16 + result = to_datetime(df.astype("int16"), cache=cache) + expected = Series( + [Timestamp("20150204 00:00:00"), Timestamp("20160305 00:00:00")] + ) + tm.assert_series_equal(result, expected) + + def test_dataframe_mixed(self, cache): + # mixed dtypes + df = DataFrame({"year": [2015, 2016], "month": [2, 3], "day": [4, 5]}) + df["month"] = df["month"].astype("int8") + df["day"] = df["day"].astype("int8") + result = to_datetime(df, cache=cache) + expected = Series( + [Timestamp("20150204 00:00:00"), Timestamp("20160305 00:00:00")] + ) + tm.assert_series_equal(result, expected) + + def test_dataframe_float(self, cache): + # float + df = DataFrame({"year": [2000, 2001], "month": [1.5, 1], "day": [1, 1]}) + msg = ( + r"^cannot assemble the datetimes: unconverted data remains when parsing " + r'with format ".*": "1", at position 0.' + ) + with pytest.raises(ValueError, match=msg): + to_datetime(df, cache=cache) + + def test_dataframe_utc_true(self): + # GH#23760 + df = DataFrame({"year": [2015, 2016], "month": [2, 3], "day": [4, 5]}) + result = to_datetime(df, utc=True) + expected = Series( + np.array(["2015-02-04", "2016-03-05"], dtype="datetime64[ns]") + ).dt.tz_localize("UTC") + tm.assert_series_equal(result, expected) + + +class TestToDatetimeMisc: + def test_to_datetime_barely_out_of_bounds(self): + # GH#19529 + # GH#19382 close enough to bounds that dropping nanos would result + # in an in-bounds datetime + arr = np.array(["2262-04-11 23:47:16.854775808"], dtype=object) + + msg = "^Out of bounds nanosecond timestamp: .*, at position 0" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime(arr) + + @pytest.mark.parametrize( + "arg, exp_str", + [ + ["2012-01-01 00:00:00", "2012-01-01 00:00:00"], + ["20121001", "2012-10-01"], # bad iso 8601 + ], + ) + def test_to_datetime_iso8601(self, cache, arg, exp_str): + result = to_datetime([arg], cache=cache) + exp = Timestamp(exp_str) + assert result[0] == exp + + @pytest.mark.parametrize( + "input, format", + [ + ("2012", "%Y-%m"), + ("2012-01", "%Y-%m-%d"), + ("2012-01-01", "%Y-%m-%d %H"), + ("2012-01-01 10", "%Y-%m-%d %H:%M"), + ("2012-01-01 10:00", "%Y-%m-%d %H:%M:%S"), + ("2012-01-01 10:00:00", "%Y-%m-%d %H:%M:%S.%f"), + ("2012-01-01 10:00:00.123", "%Y-%m-%d %H:%M:%S.%f%z"), + (0, "%Y-%m-%d"), + ], + ) + @pytest.mark.parametrize("exact", [True, False]) + def test_to_datetime_iso8601_fails(self, input, format, exact): + # https://github.com/pandas-dev/pandas/issues/12649 + # `format` is longer than the string, so this fails regardless of `exact` + with pytest.raises( + ValueError, + match=( + rf"time data \"{input}\" doesn't match format " + rf"\"{format}\", at position 0" + ), + ): + to_datetime(input, format=format, exact=exact) + + @pytest.mark.parametrize( + "input, format", + [ + ("2012-01-01", "%Y-%m"), + ("2012-01-01 10", "%Y-%m-%d"), + ("2012-01-01 10:00", "%Y-%m-%d %H"), + ("2012-01-01 10:00:00", "%Y-%m-%d %H:%M"), + (0, "%Y-%m-%d"), + ], + ) + def test_to_datetime_iso8601_exact_fails(self, input, format): + # https://github.com/pandas-dev/pandas/issues/12649 + # `format` is shorter than the date string, so only fails with `exact=True` + msg = "|".join( + [ + '^unconverted data remains when parsing with format ".*": ".*"' + f", at position 0. {PARSING_ERR_MSG}$", + f'^time data ".*" doesn\'t match format ".*", at position 0. ' + f"{PARSING_ERR_MSG}$", + ] + ) + with pytest.raises( + ValueError, + match=(msg), + ): + to_datetime(input, format=format) + + @pytest.mark.parametrize( + "input, format", + [ + ("2012-01-01", "%Y-%m"), + ("2012-01-01 00", "%Y-%m-%d"), + ("2012-01-01 00:00", "%Y-%m-%d %H"), + ("2012-01-01 00:00:00", "%Y-%m-%d %H:%M"), + ], + ) + def test_to_datetime_iso8601_non_exact(self, input, format): + # https://github.com/pandas-dev/pandas/issues/12649 + expected = Timestamp(2012, 1, 1) + result = to_datetime(input, format=format, exact=False) + assert result == expected + + @pytest.mark.parametrize( + "input, format", + [ + ("2020-01", "%Y/%m"), + ("2020-01-01", "%Y/%m/%d"), + ("2020-01-01 00", "%Y/%m/%dT%H"), + ("2020-01-01T00", "%Y/%m/%d %H"), + ("2020-01-01 00:00", "%Y/%m/%dT%H:%M"), + ("2020-01-01T00:00", "%Y/%m/%d %H:%M"), + ("2020-01-01 00:00:00", "%Y/%m/%dT%H:%M:%S"), + ("2020-01-01T00:00:00", "%Y/%m/%d %H:%M:%S"), + ], + ) + def test_to_datetime_iso8601_separator(self, input, format): + # https://github.com/pandas-dev/pandas/issues/12649 + with pytest.raises( + ValueError, + match=( + rf"time data \"{input}\" doesn\'t match format " + rf"\"{format}\", at position 0" + ), + ): + to_datetime(input, format=format) + + @pytest.mark.parametrize( + "input, format", + [ + ("2020-01", "%Y-%m"), + ("2020-01-01", "%Y-%m-%d"), + ("2020-01-01 00", "%Y-%m-%d %H"), + ("2020-01-01T00", "%Y-%m-%dT%H"), + ("2020-01-01 00:00", "%Y-%m-%d %H:%M"), + ("2020-01-01T00:00", "%Y-%m-%dT%H:%M"), + ("2020-01-01 00:00:00", "%Y-%m-%d %H:%M:%S"), + ("2020-01-01T00:00:00", "%Y-%m-%dT%H:%M:%S"), + ("2020-01-01T00:00:00.000", "%Y-%m-%dT%H:%M:%S.%f"), + ("2020-01-01T00:00:00.000000", "%Y-%m-%dT%H:%M:%S.%f"), + ("2020-01-01T00:00:00.000000000", "%Y-%m-%dT%H:%M:%S.%f"), + ], + ) + def test_to_datetime_iso8601_valid(self, input, format): + # https://github.com/pandas-dev/pandas/issues/12649 + expected = Timestamp(2020, 1, 1) + result = to_datetime(input, format=format) + assert result == expected + + @pytest.mark.parametrize( + "input, format", + [ + ("2020-1", "%Y-%m"), + ("2020-1-1", "%Y-%m-%d"), + ("2020-1-1 0", "%Y-%m-%d %H"), + ("2020-1-1T0", "%Y-%m-%dT%H"), + ("2020-1-1 0:0", "%Y-%m-%d %H:%M"), + ("2020-1-1T0:0", "%Y-%m-%dT%H:%M"), + ("2020-1-1 0:0:0", "%Y-%m-%d %H:%M:%S"), + ("2020-1-1T0:0:0", "%Y-%m-%dT%H:%M:%S"), + ("2020-1-1T0:0:0.000", "%Y-%m-%dT%H:%M:%S.%f"), + ("2020-1-1T0:0:0.000000", "%Y-%m-%dT%H:%M:%S.%f"), + ("2020-1-1T0:0:0.000000000", "%Y-%m-%dT%H:%M:%S.%f"), + ], + ) + def test_to_datetime_iso8601_non_padded(self, input, format): + # https://github.com/pandas-dev/pandas/issues/21422 + expected = Timestamp(2020, 1, 1) + result = to_datetime(input, format=format) + assert result == expected + + @pytest.mark.parametrize( + "input, format", + [ + ("2020-01-01T00:00:00.000000000+00:00", "%Y-%m-%dT%H:%M:%S.%f%z"), + ("2020-01-01T00:00:00+00:00", "%Y-%m-%dT%H:%M:%S%z"), + ("2020-01-01T00:00:00Z", "%Y-%m-%dT%H:%M:%S%z"), + ], + ) + def test_to_datetime_iso8601_with_timezone_valid(self, input, format): + # https://github.com/pandas-dev/pandas/issues/12649 + expected = Timestamp(2020, 1, 1, tzinfo=pytz.UTC) + result = to_datetime(input, format=format) + assert result == expected + + def test_to_datetime_default(self, cache): + rs = to_datetime("2001", cache=cache) + xp = datetime(2001, 1, 1) + assert rs == xp + + @pytest.mark.xfail(reason="fails to enforce dayfirst=True, which would raise") + def test_to_datetime_respects_dayfirst(self, cache): + # dayfirst is essentially broken + + # The msg here is not important since it isn't actually raised yet. + msg = "Invalid date specified" + with pytest.raises(ValueError, match=msg): + # if dayfirst is respected, then this would parse as month=13, which + # would raise + with tm.assert_produces_warning(UserWarning, match="Provide format"): + to_datetime("01-13-2012", dayfirst=True, cache=cache) + + def test_to_datetime_on_datetime64_series(self, cache): + # #2699 + ser = Series(date_range("1/1/2000", periods=10)) + + result = to_datetime(ser, cache=cache) + assert result[0] == ser[0] + + def test_to_datetime_with_space_in_series(self, cache): + # GH 6428 + ser = Series(["10/18/2006", "10/18/2008", " "]) + msg = ( + r'^time data " " doesn\'t match format "%m/%d/%Y", ' + rf"at position 2. {PARSING_ERR_MSG}$" + ) + with pytest.raises(ValueError, match=msg): + to_datetime(ser, errors="raise", cache=cache) + result_coerce = to_datetime(ser, errors="coerce", cache=cache) + expected_coerce = Series([datetime(2006, 10, 18), datetime(2008, 10, 18), NaT]) + tm.assert_series_equal(result_coerce, expected_coerce) + result_ignore = to_datetime(ser, errors="ignore", cache=cache) + tm.assert_series_equal(result_ignore, ser) + + @td.skip_if_not_us_locale + def test_to_datetime_with_apply(self, cache): + # this is only locale tested with US/None locales + # GH 5195 + # with a format and coerce a single item to_datetime fails + td = Series(["May 04", "Jun 02", "Dec 11"], index=[1, 2, 3]) + expected = to_datetime(td, format="%b %y", cache=cache) + result = td.apply(to_datetime, format="%b %y", cache=cache) + tm.assert_series_equal(result, expected) + + def test_to_datetime_timezone_name(self): + # https://github.com/pandas-dev/pandas/issues/49748 + result = to_datetime("2020-01-01 00:00:00UTC", format="%Y-%m-%d %H:%M:%S%Z") + expected = Timestamp(2020, 1, 1).tz_localize("UTC") + assert result == expected + + @td.skip_if_not_us_locale + @pytest.mark.parametrize("errors", ["raise", "coerce", "ignore"]) + def test_to_datetime_with_apply_with_empty_str(self, cache, errors): + # this is only locale tested with US/None locales + # GH 5195, GH50251 + # with a format and coerce a single item to_datetime fails + td = Series(["May 04", "Jun 02", ""], index=[1, 2, 3]) + expected = to_datetime(td, format="%b %y", errors=errors, cache=cache) + + result = td.apply( + lambda x: to_datetime(x, format="%b %y", errors="coerce", cache=cache) + ) + tm.assert_series_equal(result, expected) + + def test_to_datetime_empty_stt(self, cache): + # empty string + result = to_datetime("", cache=cache) + assert result is NaT + + def test_to_datetime_empty_str_list(self, cache): + result = to_datetime(["", ""], cache=cache) + assert isna(result).all() + + def test_to_datetime_zero(self, cache): + # ints + result = Timestamp(0) + expected = to_datetime(0, cache=cache) + assert result == expected + + def test_to_datetime_strings(self, cache): + # GH 3888 (strings) + expected = to_datetime(["2012"], cache=cache)[0] + result = to_datetime("2012", cache=cache) + assert result == expected + + def test_to_datetime_strings_variation(self, cache): + array = ["2012", "20120101", "20120101 12:01:01"] + expected = [to_datetime(dt_str, cache=cache) for dt_str in array] + result = [Timestamp(date_str) for date_str in array] + tm.assert_almost_equal(result, expected) + + @pytest.mark.parametrize("result", [Timestamp("2012"), to_datetime("2012")]) + def test_to_datetime_strings_vs_constructor(self, result): + expected = Timestamp(2012, 1, 1) + assert result == expected + + def test_to_datetime_unprocessable_input(self, cache): + # GH 4928 + # GH 21864 + result = to_datetime([1, "1"], errors="ignore", cache=cache) + + expected = Index(np.array([1, "1"], dtype="O")) + tm.assert_equal(result, expected) + msg = '^Given date string "1" not likely a datetime, at position 1$' + with pytest.raises(ValueError, match=msg): + to_datetime([1, "1"], errors="raise", cache=cache) + + def test_to_datetime_unhashable_input(self, cache): + series = Series([["a"]] * 100) + result = to_datetime(series, errors="ignore", cache=cache) + tm.assert_series_equal(series, result) + + def test_to_datetime_other_datetime64_units(self): + # 5/25/2012 + scalar = np.int64(1337904000000000).view("M8[us]") + as_obj = scalar.astype("O") + + index = DatetimeIndex([scalar]) + assert index[0] == scalar.astype("O") + + value = Timestamp(scalar) + assert value == as_obj + + def test_to_datetime_list_of_integers(self): + rng = date_range("1/1/2000", periods=20) + rng = DatetimeIndex(rng.values) + + ints = list(rng.asi8) + + result = DatetimeIndex(ints) + + tm.assert_index_equal(rng, result) + + def test_to_datetime_overflow(self): + # gh-17637 + # we are overflowing Timedelta range here + msg = "Cannot cast 139999 days 00:00:00 to unit='ns' without overflow" + with pytest.raises(OutOfBoundsTimedelta, match=msg): + date_range(start="1/1/1700", freq="B", periods=100000) + + def test_string_invalid_operation(self, cache): + invalid = np.array(["87156549591102612381000001219H5"], dtype=object) + # GH #51084 + + with pytest.raises(ValueError, match="Unknown datetime string format"): + to_datetime(invalid, errors="raise", cache=cache) + + def test_string_na_nat_conversion(self, cache): + # GH #999, #858 + + strings = np.array(["1/1/2000", "1/2/2000", np.nan, "1/4/2000"], dtype=object) + + expected = np.empty(4, dtype="M8[ns]") + for i, val in enumerate(strings): + if isna(val): + expected[i] = iNaT + else: + expected[i] = parse(val) + + result = tslib.array_to_datetime(strings)[0] + tm.assert_almost_equal(result, expected) + + result2 = to_datetime(strings, cache=cache) + assert isinstance(result2, DatetimeIndex) + tm.assert_numpy_array_equal(result, result2.values) + + def test_string_na_nat_conversion_malformed(self, cache): + malformed = np.array(["1/100/2000", np.nan], dtype=object) + + # GH 10636, default is now 'raise' + msg = r"Unknown datetime string format" + with pytest.raises(ValueError, match=msg): + to_datetime(malformed, errors="raise", cache=cache) + + result = to_datetime(malformed, errors="ignore", cache=cache) + # GH 21864 + expected = Index(malformed, dtype=object) + tm.assert_index_equal(result, expected) + + with pytest.raises(ValueError, match=msg): + to_datetime(malformed, errors="raise", cache=cache) + + def test_string_na_nat_conversion_with_name(self, cache): + idx = ["a", "b", "c", "d", "e"] + series = Series( + ["1/1/2000", np.nan, "1/3/2000", np.nan, "1/5/2000"], index=idx, name="foo" + ) + dseries = Series( + [ + to_datetime("1/1/2000", cache=cache), + np.nan, + to_datetime("1/3/2000", cache=cache), + np.nan, + to_datetime("1/5/2000", cache=cache), + ], + index=idx, + name="foo", + ) + + result = to_datetime(series, cache=cache) + dresult = to_datetime(dseries, cache=cache) + + expected = Series(np.empty(5, dtype="M8[ns]"), index=idx) + for i in range(5): + x = series.iloc[i] + if isna(x): + expected.iloc[i] = NaT + else: + expected.iloc[i] = to_datetime(x, cache=cache) + + tm.assert_series_equal(result, expected, check_names=False) + assert result.name == "foo" + + tm.assert_series_equal(dresult, expected, check_names=False) + assert dresult.name == "foo" + + @pytest.mark.parametrize( + "unit", + ["h", "m", "s", "ms", "us", "ns"], + ) + def test_dti_constructor_numpy_timeunits(self, cache, unit): + # GH 9114 + dtype = np.dtype(f"M8[{unit}]") + base = to_datetime(["2000-01-01T00:00", "2000-01-02T00:00", "NaT"], cache=cache) + + values = base.values.astype(dtype) + + if unit in ["h", "m"]: + # we cast to closest supported unit + unit = "s" + exp_dtype = np.dtype(f"M8[{unit}]") + expected = DatetimeIndex(base.astype(exp_dtype)) + assert expected.dtype == exp_dtype + + tm.assert_index_equal(DatetimeIndex(values), expected) + tm.assert_index_equal(to_datetime(values, cache=cache), expected) + + def test_dayfirst(self, cache): + # GH 5917 + arr = ["10/02/2014", "11/02/2014", "12/02/2014"] + expected = DatetimeIndex( + [datetime(2014, 2, 10), datetime(2014, 2, 11), datetime(2014, 2, 12)] + ) + idx1 = DatetimeIndex(arr, dayfirst=True) + idx2 = DatetimeIndex(np.array(arr), dayfirst=True) + idx3 = to_datetime(arr, dayfirst=True, cache=cache) + idx4 = to_datetime(np.array(arr), dayfirst=True, cache=cache) + idx5 = DatetimeIndex(Index(arr), dayfirst=True) + idx6 = DatetimeIndex(Series(arr), dayfirst=True) + tm.assert_index_equal(expected, idx1) + tm.assert_index_equal(expected, idx2) + tm.assert_index_equal(expected, idx3) + tm.assert_index_equal(expected, idx4) + tm.assert_index_equal(expected, idx5) + tm.assert_index_equal(expected, idx6) + + def test_dayfirst_warnings_valid_input(self): + # GH 12585 + warning_msg = ( + "Parsing dates in .* format when dayfirst=.* was specified. " + "Pass `dayfirst=.*` or specify a format to silence this warning." + ) + + # CASE 1: valid input + arr = ["31/12/2014", "10/03/2011"] + expected = DatetimeIndex( + ["2014-12-31", "2011-03-10"], dtype="datetime64[ns]", freq=None + ) + + # A. dayfirst arg correct, no warning + res1 = to_datetime(arr, dayfirst=True) + tm.assert_index_equal(expected, res1) + + # B. dayfirst arg incorrect, warning + with tm.assert_produces_warning(UserWarning, match=warning_msg): + res2 = to_datetime(arr, dayfirst=False) + tm.assert_index_equal(expected, res2) + + def test_dayfirst_warnings_invalid_input(self): + # CASE 2: invalid input + # cannot consistently process with single format + # ValueError *always* raised + + # first in DD/MM/YYYY, second in MM/DD/YYYY + arr = ["31/12/2014", "03/30/2011"] + + with pytest.raises( + ValueError, + match=( + r'^time data "03/30/2011" doesn\'t match format ' + rf'"%d/%m/%Y", at position 1. {PARSING_ERR_MSG}$' + ), + ): + to_datetime(arr, dayfirst=True) + + @pytest.mark.parametrize("klass", [DatetimeIndex, DatetimeArray._from_sequence]) + def test_to_datetime_dta_tz(self, klass): + # GH#27733 + dti = date_range("2015-04-05", periods=3).rename("foo") + expected = dti.tz_localize("UTC") + + obj = klass(dti) + expected = klass(expected) + + result = to_datetime(obj, utc=True) + tm.assert_equal(result, expected) + + +class TestGuessDatetimeFormat: + @pytest.mark.parametrize( + "test_list", + [ + [ + "2011-12-30 00:00:00.000000", + "2011-12-30 00:00:00.000000", + "2011-12-30 00:00:00.000000", + ], + [np.nan, np.nan, "2011-12-30 00:00:00.000000"], + ["", "2011-12-30 00:00:00.000000"], + ["NaT", "2011-12-30 00:00:00.000000"], + ["2011-12-30 00:00:00.000000", "random_string"], + ["now", "2011-12-30 00:00:00.000000"], + ["today", "2011-12-30 00:00:00.000000"], + ], + ) + def test_guess_datetime_format_for_array(self, test_list): + expected_format = "%Y-%m-%d %H:%M:%S.%f" + test_array = np.array(test_list, dtype=object) + assert tools._guess_datetime_format_for_array(test_array) == expected_format + + @td.skip_if_not_us_locale + def test_guess_datetime_format_for_array_all_nans(self): + format_for_string_of_nans = tools._guess_datetime_format_for_array( + np.array([np.nan, np.nan, np.nan], dtype="O") + ) + assert format_for_string_of_nans is None + + +class TestToDatetimeInferFormat: + @pytest.mark.parametrize( + "test_format", ["%m-%d-%Y", "%m/%d/%Y %H:%M:%S.%f", "%Y-%m-%dT%H:%M:%S.%f"] + ) + def test_to_datetime_infer_datetime_format_consistent_format( + self, cache, test_format + ): + ser = Series(date_range("20000101", periods=50, freq="h")) + + s_as_dt_strings = ser.apply(lambda x: x.strftime(test_format)) + + with_format = to_datetime(s_as_dt_strings, format=test_format, cache=cache) + without_format = to_datetime(s_as_dt_strings, cache=cache) + + # Whether the format is explicitly passed, or + # it is inferred, the results should all be the same + tm.assert_series_equal(with_format, without_format) + + def test_to_datetime_inconsistent_format(self, cache): + data = ["01/01/2011 00:00:00", "01-02-2011 00:00:00", "2011-01-03T00:00:00"] + ser = Series(np.array(data)) + msg = ( + r'^time data "01-02-2011 00:00:00" doesn\'t match format ' + rf'"%m/%d/%Y %H:%M:%S", at position 1. {PARSING_ERR_MSG}$' + ) + with pytest.raises(ValueError, match=msg): + to_datetime(ser, cache=cache) + + def test_to_datetime_consistent_format(self, cache): + data = ["Jan/01/2011", "Feb/01/2011", "Mar/01/2011"] + ser = Series(np.array(data)) + result = to_datetime(ser, cache=cache) + expected = Series( + ["2011-01-01", "2011-02-01", "2011-03-01"], dtype="datetime64[ns]" + ) + tm.assert_series_equal(result, expected) + + def test_to_datetime_series_with_nans(self, cache): + ser = Series( + np.array( + ["01/01/2011 00:00:00", np.nan, "01/03/2011 00:00:00", np.nan], + dtype=object, + ) + ) + result = to_datetime(ser, cache=cache) + expected = Series( + ["2011-01-01", NaT, "2011-01-03", NaT], dtype="datetime64[ns]" + ) + tm.assert_series_equal(result, expected) + + def test_to_datetime_series_start_with_nans(self, cache): + ser = Series( + np.array( + [ + np.nan, + np.nan, + "01/01/2011 00:00:00", + "01/02/2011 00:00:00", + "01/03/2011 00:00:00", + ], + dtype=object, + ) + ) + + result = to_datetime(ser, cache=cache) + expected = Series( + [NaT, NaT, "2011-01-01", "2011-01-02", "2011-01-03"], dtype="datetime64[ns]" + ) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "tz_name, offset", + [("UTC", 0), ("UTC-3", 180), ("UTC+3", -180)], + ) + def test_infer_datetime_format_tz_name(self, tz_name, offset): + # GH 33133 + ser = Series([f"2019-02-02 08:07:13 {tz_name}"]) + result = to_datetime(ser) + tz = timezone(timedelta(minutes=offset)) + expected = Series([Timestamp("2019-02-02 08:07:13").tz_localize(tz)]) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "ts,zero_tz", + [ + ("2019-02-02 08:07:13", "Z"), + ("2019-02-02 08:07:13", ""), + ("2019-02-02 08:07:13.012345", "Z"), + ("2019-02-02 08:07:13.012345", ""), + ], + ) + def test_infer_datetime_format_zero_tz(self, ts, zero_tz): + # GH 41047 + ser = Series([ts + zero_tz]) + result = to_datetime(ser) + tz = pytz.utc if zero_tz == "Z" else None + expected = Series([Timestamp(ts, tz=tz)]) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize("format", [None, "%Y-%m-%d"]) + def test_to_datetime_iso8601_noleading_0s(self, cache, format): + # GH 11871 + ser = Series(["2014-1-1", "2014-2-2", "2015-3-3"]) + expected = Series( + [ + Timestamp("2014-01-01"), + Timestamp("2014-02-02"), + Timestamp("2015-03-03"), + ] + ) + result = to_datetime(ser, format=format, cache=cache) + tm.assert_series_equal(result, expected) + + def test_parse_dates_infer_datetime_format_warning(self): + # GH 49024 + with tm.assert_produces_warning( + UserWarning, + match="The argument 'infer_datetime_format' is deprecated", + ): + to_datetime(["10-10-2000"], infer_datetime_format=True) + + +class TestDaysInMonth: + # tests for issue #10154 + + @pytest.mark.parametrize( + "arg, format", + [ + ["2015-02-29", None], + ["2015-02-29", "%Y-%m-%d"], + ["2015-02-32", "%Y-%m-%d"], + ["2015-04-31", "%Y-%m-%d"], + ], + ) + def test_day_not_in_month_coerce(self, cache, arg, format): + assert isna(to_datetime(arg, errors="coerce", format=format, cache=cache)) + + def test_day_not_in_month_raise(self, cache): + msg = "day is out of range for month: 2015-02-29, at position 0" + with pytest.raises(ValueError, match=msg): + to_datetime("2015-02-29", errors="raise", cache=cache) + + @pytest.mark.parametrize( + "arg, format, msg", + [ + ( + "2015-02-29", + "%Y-%m-%d", + f"^day is out of range for month, at position 0. {PARSING_ERR_MSG}$", + ), + ( + "2015-29-02", + "%Y-%d-%m", + f"^day is out of range for month, at position 0. {PARSING_ERR_MSG}$", + ), + ( + "2015-02-32", + "%Y-%m-%d", + '^unconverted data remains when parsing with format "%Y-%m-%d": "2", ' + f"at position 0. {PARSING_ERR_MSG}$", + ), + ( + "2015-32-02", + "%Y-%d-%m", + '^time data "2015-32-02" doesn\'t match format "%Y-%d-%m", ' + f"at position 0. {PARSING_ERR_MSG}$", + ), + ( + "2015-04-31", + "%Y-%m-%d", + f"^day is out of range for month, at position 0. {PARSING_ERR_MSG}$", + ), + ( + "2015-31-04", + "%Y-%d-%m", + f"^day is out of range for month, at position 0. {PARSING_ERR_MSG}$", + ), + ], + ) + def test_day_not_in_month_raise_value(self, cache, arg, format, msg): + # https://github.com/pandas-dev/pandas/issues/50462 + with pytest.raises(ValueError, match=msg): + to_datetime(arg, errors="raise", format=format, cache=cache) + + @pytest.mark.parametrize( + "expected, format", + [ + ["2015-02-29", None], + ["2015-02-29", "%Y-%m-%d"], + ["2015-02-29", "%Y-%m-%d"], + ["2015-04-31", "%Y-%m-%d"], + ], + ) + def test_day_not_in_month_ignore(self, cache, expected, format): + result = to_datetime(expected, errors="ignore", format=format, cache=cache) + assert result == expected + + +class TestDatetimeParsingWrappers: + @pytest.mark.parametrize( + "date_str, expected", + [ + ("2011-01-01", datetime(2011, 1, 1)), + ("2Q2005", datetime(2005, 4, 1)), + ("2Q05", datetime(2005, 4, 1)), + ("2005Q1", datetime(2005, 1, 1)), + ("05Q1", datetime(2005, 1, 1)), + ("2011Q3", datetime(2011, 7, 1)), + ("11Q3", datetime(2011, 7, 1)), + ("3Q2011", datetime(2011, 7, 1)), + ("3Q11", datetime(2011, 7, 1)), + # quarterly without space + ("2000Q4", datetime(2000, 10, 1)), + ("00Q4", datetime(2000, 10, 1)), + ("4Q2000", datetime(2000, 10, 1)), + ("4Q00", datetime(2000, 10, 1)), + ("2000q4", datetime(2000, 10, 1)), + ("2000-Q4", datetime(2000, 10, 1)), + ("00-Q4", datetime(2000, 10, 1)), + ("4Q-2000", datetime(2000, 10, 1)), + ("4Q-00", datetime(2000, 10, 1)), + ("00q4", datetime(2000, 10, 1)), + ("2005", datetime(2005, 1, 1)), + ("2005-11", datetime(2005, 11, 1)), + ("2005 11", datetime(2005, 11, 1)), + ("11-2005", datetime(2005, 11, 1)), + ("11 2005", datetime(2005, 11, 1)), + ("200511", datetime(2020, 5, 11)), + ("20051109", datetime(2005, 11, 9)), + ("20051109 10:15", datetime(2005, 11, 9, 10, 15)), + ("20051109 08H", datetime(2005, 11, 9, 8, 0)), + ("2005-11-09 10:15", datetime(2005, 11, 9, 10, 15)), + ("2005-11-09 08H", datetime(2005, 11, 9, 8, 0)), + ("2005/11/09 10:15", datetime(2005, 11, 9, 10, 15)), + ("2005/11/09 10:15:32", datetime(2005, 11, 9, 10, 15, 32)), + ("2005/11/09 10:15:32 AM", datetime(2005, 11, 9, 10, 15, 32)), + ("2005/11/09 10:15:32 PM", datetime(2005, 11, 9, 22, 15, 32)), + ("2005/11/09 08H", datetime(2005, 11, 9, 8, 0)), + ("Thu Sep 25 10:36:28 2003", datetime(2003, 9, 25, 10, 36, 28)), + ("Thu Sep 25 2003", datetime(2003, 9, 25)), + ("Sep 25 2003", datetime(2003, 9, 25)), + ("January 1 2014", datetime(2014, 1, 1)), + # GH#10537 + ("2014-06", datetime(2014, 6, 1)), + ("06-2014", datetime(2014, 6, 1)), + ("2014-6", datetime(2014, 6, 1)), + ("6-2014", datetime(2014, 6, 1)), + ("20010101 12", datetime(2001, 1, 1, 12)), + ("20010101 1234", datetime(2001, 1, 1, 12, 34)), + ("20010101 123456", datetime(2001, 1, 1, 12, 34, 56)), + ], + ) + def test_parsers(self, date_str, expected, cache): + # dateutil >= 2.5.0 defaults to yearfirst=True + # https://github.com/dateutil/dateutil/issues/217 + yearfirst = True + + result1, _ = parsing.parse_datetime_string_with_reso( + date_str, yearfirst=yearfirst + ) + result2 = to_datetime(date_str, yearfirst=yearfirst) + result3 = to_datetime([date_str], yearfirst=yearfirst) + # result5 is used below + result4 = to_datetime( + np.array([date_str], dtype=object), yearfirst=yearfirst, cache=cache + ) + result6 = DatetimeIndex([date_str], yearfirst=yearfirst) + # result7 is used below + result8 = DatetimeIndex(Index([date_str]), yearfirst=yearfirst) + result9 = DatetimeIndex(Series([date_str]), yearfirst=yearfirst) + + for res in [result1, result2]: + assert res == expected + for res in [result3, result4, result6, result8, result9]: + exp = DatetimeIndex([Timestamp(expected)]) + tm.assert_index_equal(res, exp) + + # these really need to have yearfirst, but we don't support + if not yearfirst: + result5 = Timestamp(date_str) + assert result5 == expected + result7 = date_range(date_str, freq="S", periods=1, yearfirst=yearfirst) + assert result7 == expected + + def test_na_values_with_cache( + self, cache, unique_nulls_fixture, unique_nulls_fixture2 + ): + # GH22305 + expected = Index([NaT, NaT], dtype="datetime64[ns]") + result = to_datetime([unique_nulls_fixture, unique_nulls_fixture2], cache=cache) + tm.assert_index_equal(result, expected) + + def test_parsers_nat(self): + # Test that each of several string-accepting methods return pd.NaT + result1, _ = parsing.parse_datetime_string_with_reso("NaT") + result2 = to_datetime("NaT") + result3 = Timestamp("NaT") + result4 = DatetimeIndex(["NaT"])[0] + assert result1 is NaT + assert result2 is NaT + assert result3 is NaT + assert result4 is NaT + + @pytest.mark.parametrize( + "date_str, dayfirst, yearfirst, expected", + [ + ("10-11-12", False, False, datetime(2012, 10, 11)), + ("10-11-12", True, False, datetime(2012, 11, 10)), + ("10-11-12", False, True, datetime(2010, 11, 12)), + ("10-11-12", True, True, datetime(2010, 12, 11)), + ("20/12/21", False, False, datetime(2021, 12, 20)), + ("20/12/21", True, False, datetime(2021, 12, 20)), + ("20/12/21", False, True, datetime(2020, 12, 21)), + ("20/12/21", True, True, datetime(2020, 12, 21)), + ], + ) + def test_parsers_dayfirst_yearfirst( + self, cache, date_str, dayfirst, yearfirst, expected + ): + # OK + # 2.5.1 10-11-12 [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00 + # 2.5.2 10-11-12 [dayfirst=0, yearfirst=1] -> 2012-10-11 00:00:00 + # 2.5.3 10-11-12 [dayfirst=0, yearfirst=0] -> 2012-10-11 00:00:00 + + # OK + # 2.5.1 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00 + # 2.5.2 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00 + # 2.5.3 10-11-12 [dayfirst=0, yearfirst=1] -> 2010-11-12 00:00:00 + + # bug fix in 2.5.2 + # 2.5.1 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-11-12 00:00:00 + # 2.5.2 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00 + # 2.5.3 10-11-12 [dayfirst=1, yearfirst=1] -> 2010-12-11 00:00:00 + + # OK + # 2.5.1 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00 + # 2.5.2 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00 + # 2.5.3 10-11-12 [dayfirst=1, yearfirst=0] -> 2012-11-10 00:00:00 + + # OK + # 2.5.1 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00 + # 2.5.2 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00 + # 2.5.3 20/12/21 [dayfirst=0, yearfirst=0] -> 2021-12-20 00:00:00 + + # OK + # 2.5.1 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00 + # 2.5.2 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00 + # 2.5.3 20/12/21 [dayfirst=0, yearfirst=1] -> 2020-12-21 00:00:00 + + # revert of bug in 2.5.2 + # 2.5.1 20/12/21 [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00 + # 2.5.2 20/12/21 [dayfirst=1, yearfirst=1] -> month must be in 1..12 + # 2.5.3 20/12/21 [dayfirst=1, yearfirst=1] -> 2020-12-21 00:00:00 + + # OK + # 2.5.1 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00 + # 2.5.2 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00 + # 2.5.3 20/12/21 [dayfirst=1, yearfirst=0] -> 2021-12-20 00:00:00 + + # str : dayfirst, yearfirst, expected + + # compare with dateutil result + dateutil_result = parse(date_str, dayfirst=dayfirst, yearfirst=yearfirst) + assert dateutil_result == expected + + result1, _ = parsing.parse_datetime_string_with_reso( + date_str, dayfirst=dayfirst, yearfirst=yearfirst + ) + + # we don't support dayfirst/yearfirst here: + if not dayfirst and not yearfirst: + result2 = Timestamp(date_str) + assert result2 == expected + + result3 = to_datetime( + date_str, dayfirst=dayfirst, yearfirst=yearfirst, cache=cache + ) + + result4 = DatetimeIndex([date_str], dayfirst=dayfirst, yearfirst=yearfirst)[0] + + assert result1 == expected + assert result3 == expected + assert result4 == expected + + @pytest.mark.parametrize( + "date_str, exp_def", + [["10:15", datetime(1, 1, 1, 10, 15)], ["9:05", datetime(1, 1, 1, 9, 5)]], + ) + def test_parsers_timestring(self, date_str, exp_def): + # must be the same as dateutil result + exp_now = parse(date_str) + + result1, _ = parsing.parse_datetime_string_with_reso(date_str) + result2 = to_datetime(date_str) + result3 = to_datetime([date_str]) + result4 = Timestamp(date_str) + result5 = DatetimeIndex([date_str])[0] + # parse time string return time string based on default date + # others are not, and can't be changed because it is used in + # time series plot + assert result1 == exp_def + assert result2 == exp_now + assert result3 == exp_now + assert result4 == exp_now + assert result5 == exp_now + + @pytest.mark.parametrize( + "dt_string, tz, dt_string_repr", + [ + ( + "2013-01-01 05:45+0545", + timezone(timedelta(minutes=345)), + "Timestamp('2013-01-01 05:45:00+0545', tz='UTC+05:45')", + ), + ( + "2013-01-01 05:30+0530", + timezone(timedelta(minutes=330)), + "Timestamp('2013-01-01 05:30:00+0530', tz='UTC+05:30')", + ), + ], + ) + def test_parsers_timezone_minute_offsets_roundtrip( + self, cache, dt_string, tz, dt_string_repr + ): + # GH11708 + base = to_datetime("2013-01-01 00:00:00", cache=cache) + base = base.tz_localize("UTC").tz_convert(tz) + dt_time = to_datetime(dt_string, cache=cache) + assert base == dt_time + assert dt_string_repr == repr(dt_time) + + +@pytest.fixture(params=["D", "s", "ms", "us", "ns"]) +def units(request): + """Day and some time units. + + * D + * s + * ms + * us + * ns + """ + return request.param + + +@pytest.fixture +def epoch_1960(): + """Timestamp at 1960-01-01.""" + return Timestamp("1960-01-01") + + +@pytest.fixture +def units_from_epochs(): + return list(range(5)) + + +@pytest.fixture(params=["timestamp", "pydatetime", "datetime64", "str_1960"]) +def epochs(epoch_1960, request): + """Timestamp at 1960-01-01 in various forms. + + * Timestamp + * datetime.datetime + * numpy.datetime64 + * str + """ + assert request.param in {"timestamp", "pydatetime", "datetime64", "str_1960"} + if request.param == "timestamp": + return epoch_1960 + elif request.param == "pydatetime": + return epoch_1960.to_pydatetime() + elif request.param == "datetime64": + return epoch_1960.to_datetime64() + else: + return str(epoch_1960) + + +@pytest.fixture +def julian_dates(): + return date_range("2014-1-1", periods=10).to_julian_date().values + + +class TestOrigin: + def test_origin_and_unit(self): + # GH#42624 + ts = to_datetime(1, unit="s", origin=1) + expected = Timestamp("1970-01-01 00:00:02") + assert ts == expected + + ts = to_datetime(1, unit="s", origin=1_000_000_000) + expected = Timestamp("2001-09-09 01:46:41") + assert ts == expected + + def test_julian(self, julian_dates): + # gh-11276, gh-11745 + # for origin as julian + + result = Series(to_datetime(julian_dates, unit="D", origin="julian")) + expected = Series( + to_datetime(julian_dates - Timestamp(0).to_julian_date(), unit="D") + ) + tm.assert_series_equal(result, expected) + + def test_unix(self): + result = Series(to_datetime([0, 1, 2], unit="D", origin="unix")) + expected = Series( + [Timestamp("1970-01-01"), Timestamp("1970-01-02"), Timestamp("1970-01-03")], + dtype="M8[ns]", + ) + tm.assert_series_equal(result, expected) + + def test_julian_round_trip(self): + result = to_datetime(2456658, origin="julian", unit="D") + assert result.to_julian_date() == 2456658 + + # out-of-bounds + msg = "1 is Out of Bounds for origin='julian'" + with pytest.raises(ValueError, match=msg): + to_datetime(1, origin="julian", unit="D") + + def test_invalid_unit(self, units, julian_dates): + # checking for invalid combination of origin='julian' and unit != D + if units != "D": + msg = "unit must be 'D' for origin='julian'" + with pytest.raises(ValueError, match=msg): + to_datetime(julian_dates, unit=units, origin="julian") + + @pytest.mark.parametrize("unit", ["ns", "D"]) + def test_invalid_origin(self, unit): + # need to have a numeric specified + msg = "it must be numeric with a unit specified" + with pytest.raises(ValueError, match=msg): + to_datetime("2005-01-01", origin="1960-01-01", unit=unit) + + @pytest.mark.parametrize( + "epochs", + [ + Timestamp(1960, 1, 1), + datetime(1960, 1, 1), + "1960-01-01", + np.datetime64("1960-01-01"), + ], + ) + def test_epoch(self, units, epochs): + epoch_1960 = Timestamp(1960, 1, 1) + units_from_epochs = np.arange(5, dtype=np.int64) + expected = Series( + [pd.Timedelta(x, unit=units) + epoch_1960 for x in units_from_epochs] + ) + + result = Series(to_datetime(units_from_epochs, unit=units, origin=epochs)) + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + "origin, exc", + [ + ("random_string", ValueError), + ("epoch", ValueError), + ("13-24-1990", ValueError), + (datetime(1, 1, 1), OutOfBoundsDatetime), + ], + ) + def test_invalid_origins(self, origin, exc, units, units_from_epochs): + msg = "|".join( + [ + f"origin {origin} is Out of Bounds", + f"origin {origin} cannot be converted to a Timestamp", + "Cannot cast .* to unit='ns' without overflow", + ] + ) + with pytest.raises(exc, match=msg): + to_datetime(units_from_epochs, unit=units, origin=origin) + + def test_invalid_origins_tzinfo(self): + # GH16842 + with pytest.raises(ValueError, match="must be tz-naive"): + to_datetime(1, unit="D", origin=datetime(2000, 1, 1, tzinfo=pytz.utc)) + + def test_incorrect_value_exception(self): + # GH47495 + msg = ( + "Unknown datetime string format, unable to parse: yesterday, at position 1" + ) + with pytest.raises(ValueError, match=msg): + to_datetime(["today", "yesterday"]) + + @pytest.mark.parametrize( + "format, warning", + [ + (None, UserWarning), + ("%Y-%m-%d %H:%M:%S", None), + ("%Y-%d-%m %H:%M:%S", None), + ], + ) + def test_to_datetime_out_of_bounds_with_format_arg(self, format, warning): + # see gh-23830 + msg = r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00, at position 0" + with pytest.raises(OutOfBoundsDatetime, match=msg): + to_datetime("2417-10-10 00:00:00", format=format) + + @pytest.mark.parametrize( + "arg, origin, expected_str", + [ + [200 * 365, "unix", "2169-11-13 00:00:00"], + [200 * 365, "1870-01-01", "2069-11-13 00:00:00"], + [300 * 365, "1870-01-01", "2169-10-20 00:00:00"], + ], + ) + def test_processing_order(self, arg, origin, expected_str): + # make sure we handle out-of-bounds *before* + # constructing the dates + + result = to_datetime(arg, unit="D", origin=origin) + expected = Timestamp(expected_str) + assert result == expected + + result = to_datetime(200 * 365, unit="D", origin="1870-01-01") + expected = Timestamp("2069-11-13 00:00:00") + assert result == expected + + result = to_datetime(300 * 365, unit="D", origin="1870-01-01") + expected = Timestamp("2169-10-20 00:00:00") + assert result == expected + + @pytest.mark.parametrize( + "offset,utc,exp", + [ + ["Z", True, "2019-01-01T00:00:00.000Z"], + ["Z", None, "2019-01-01T00:00:00.000Z"], + ["-01:00", True, "2019-01-01T01:00:00.000Z"], + ["-01:00", None, "2019-01-01T00:00:00.000-01:00"], + ], + ) + def test_arg_tz_ns_unit(self, offset, utc, exp): + # GH 25546 + arg = "2019-01-01T00:00:00.000" + offset + result = to_datetime([arg], unit="ns", utc=utc) + expected = to_datetime([exp]).as_unit("ns") + tm.assert_index_equal(result, expected) + + +class TestShouldCache: + @pytest.mark.parametrize( + "listlike,do_caching", + [ + ([1, 2, 3, 4, 5, 6, 7, 8, 9, 0], False), + ([1, 1, 1, 1, 4, 5, 6, 7, 8, 9], True), + ], + ) + def test_should_cache(self, listlike, do_caching): + assert ( + tools.should_cache(listlike, check_count=len(listlike), unique_share=0.7) + == do_caching + ) + + @pytest.mark.parametrize( + "unique_share,check_count, err_message", + [ + (0.5, 11, r"check_count must be in next bounds: \[0; len\(arg\)\]"), + (10, 2, r"unique_share must be in next bounds: \(0; 1\)"), + ], + ) + def test_should_cache_errors(self, unique_share, check_count, err_message): + arg = [5] * 10 + + with pytest.raises(AssertionError, match=err_message): + tools.should_cache(arg, unique_share, check_count) + + @pytest.mark.parametrize( + "listlike", + [ + (deque([Timestamp("2010-06-02 09:30:00")] * 51)), + ([Timestamp("2010-06-02 09:30:00")] * 51), + (tuple([Timestamp("2010-06-02 09:30:00")] * 51)), + ], + ) + def test_no_slicing_errors_in_should_cache(self, listlike): + # GH#29403 + assert tools.should_cache(listlike) is True + + +def test_nullable_integer_to_datetime(): + # Test for #30050 + ser = Series([1, 2, None, 2**61, None]) + ser = ser.astype("Int64") + ser_copy = ser.copy() + + res = to_datetime(ser, unit="ns") + + expected = Series( + [ + np.datetime64("1970-01-01 00:00:00.000000001"), + np.datetime64("1970-01-01 00:00:00.000000002"), + np.datetime64("NaT"), + np.datetime64("2043-01-25 23:56:49.213693952"), + np.datetime64("NaT"), + ] + ) + tm.assert_series_equal(res, expected) + # Check that ser isn't mutated + tm.assert_series_equal(ser, ser_copy) + + +@pytest.mark.parametrize("klass", [np.array, list]) +def test_na_to_datetime(nulls_fixture, klass): + if isinstance(nulls_fixture, Decimal): + with pytest.raises(TypeError, match="not convertible to datetime"): + to_datetime(klass([nulls_fixture])) + + else: + result = to_datetime(klass([nulls_fixture])) + + assert result[0] is NaT + + +@pytest.mark.parametrize("errors", ["raise", "coerce", "ignore"]) +@pytest.mark.parametrize( + "args, format", + [ + (["03/24/2016", "03/25/2016", ""], "%m/%d/%Y"), + (["2016-03-24", "2016-03-25", ""], "%Y-%m-%d"), + ], + ids=["non-ISO8601", "ISO8601"], +) +def test_empty_string_datetime(errors, args, format): + # GH13044, GH50251 + td = Series(args) + + # coerce empty string to pd.NaT + result = to_datetime(td, format=format, errors=errors) + expected = Series(["2016-03-24", "2016-03-25", NaT], dtype="datetime64[ns]") + tm.assert_series_equal(expected, result) + + +def test_empty_string_datetime_coerce__unit(): + # GH13044 + # coerce empty string to pd.NaT + result = to_datetime([1, ""], unit="s", errors="coerce") + expected = DatetimeIndex(["1970-01-01 00:00:01", "NaT"], dtype="datetime64[ns]") + tm.assert_index_equal(expected, result) + + # verify that no exception is raised even when errors='raise' is set + result = to_datetime([1, ""], unit="s", errors="raise") + tm.assert_index_equal(expected, result) + + +@pytest.mark.parametrize("cache", [True, False]) +def test_to_datetime_monotonic_increasing_index(cache): + # GH28238 + cstart = start_caching_at + times = date_range(Timestamp("1980"), periods=cstart, freq="YS") + times = times.to_frame(index=False, name="DT").sample(n=cstart, random_state=1) + times.index = times.index.to_series().astype(float) / 1000 + result = to_datetime(times.iloc[:, 0], cache=cache) + expected = times.iloc[:, 0] + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "series_length", + [40, start_caching_at, (start_caching_at + 1), (start_caching_at + 5)], +) +def test_to_datetime_cache_coerce_50_lines_outofbounds(series_length): + # GH#45319 + ser = Series( + [datetime.fromisoformat("1446-04-12 00:00:00+00:00")] + + ([datetime.fromisoformat("1991-10-20 00:00:00+00:00")] * series_length), + dtype=object, + ) + result1 = to_datetime(ser, errors="coerce", utc=True) + + expected1 = Series( + [NaT] + ([Timestamp("1991-10-20 00:00:00+00:00")] * series_length) + ) + + tm.assert_series_equal(result1, expected1) + + result2 = to_datetime(ser, errors="ignore", utc=True) + + expected2 = Series( + [datetime.fromisoformat("1446-04-12 00:00:00+00:00")] + + ([datetime.fromisoformat("1991-10-20 00:00:00+00:00")] * series_length) + ) + + tm.assert_series_equal(result2, expected2) + + with pytest.raises(OutOfBoundsDatetime, match="Out of bounds nanosecond timestamp"): + to_datetime(ser, errors="raise", utc=True) + + +def test_to_datetime_format_f_parse_nanos(): + # GH 48767 + timestamp = "15/02/2020 02:03:04.123456789" + timestamp_format = "%d/%m/%Y %H:%M:%S.%f" + result = to_datetime(timestamp, format=timestamp_format) + expected = Timestamp( + year=2020, + month=2, + day=15, + hour=2, + minute=3, + second=4, + microsecond=123456, + nanosecond=789, + ) + assert result == expected + + +def test_to_datetime_mixed_iso8601(): + # https://github.com/pandas-dev/pandas/issues/50411 + result = to_datetime(["2020-01-01", "2020-01-01 05:00:00"], format="ISO8601") + expected = DatetimeIndex(["2020-01-01 00:00:00", "2020-01-01 05:00:00"]) + tm.assert_index_equal(result, expected) + + +def test_to_datetime_mixed_other(): + # https://github.com/pandas-dev/pandas/issues/50411 + result = to_datetime(["01/11/2000", "12 January 2000"], format="mixed") + expected = DatetimeIndex(["2000-01-11", "2000-01-12"]) + tm.assert_index_equal(result, expected) + + +@pytest.mark.parametrize("exact", [True, False]) +@pytest.mark.parametrize("format", ["ISO8601", "mixed"]) +def test_to_datetime_mixed_or_iso_exact(exact, format): + msg = "Cannot use 'exact' when 'format' is 'mixed' or 'ISO8601'" + with pytest.raises(ValueError, match=msg): + to_datetime(["2020-01-01"], exact=exact, format=format) + + +def test_to_datetime_mixed_not_necessarily_iso8601_raise(): + # https://github.com/pandas-dev/pandas/issues/50411 + with pytest.raises( + ValueError, match="Time data 01-01-2000 is not ISO8601 format, at position 1" + ): + to_datetime(["2020-01-01", "01-01-2000"], format="ISO8601") + + +@pytest.mark.parametrize( + ("errors", "expected"), + [ + ("coerce", DatetimeIndex(["2020-01-01 00:00:00", NaT])), + ("ignore", Index(["2020-01-01", "01-01-2000"], dtype=object)), + ], +) +def test_to_datetime_mixed_not_necessarily_iso8601_coerce(errors, expected): + # https://github.com/pandas-dev/pandas/issues/50411 + result = to_datetime(["2020-01-01", "01-01-2000"], format="ISO8601", errors=errors) + tm.assert_index_equal(result, expected) + + +def test_ignoring_unknown_tz_deprecated(): + # GH#18702, GH#51476 + dtstr = "2014 Jan 9 05:15 FAKE" + msg = 'un-recognized timezone "FAKE". Dropping unrecognized timezones is deprecated' + with tm.assert_produces_warning(FutureWarning, match=msg): + res = Timestamp(dtstr) + assert res == Timestamp(dtstr[:-5]) + + with tm.assert_produces_warning(FutureWarning): + res = to_datetime(dtstr) + assert res == to_datetime(dtstr[:-5]) + with tm.assert_produces_warning(FutureWarning): + res = to_datetime([dtstr]) + tm.assert_index_equal(res, to_datetime([dtstr[:-5]])) + + +def test_from_numeric_arrow_dtype(any_numeric_ea_dtype): + # GH 52425 + pytest.importorskip("pyarrow") + ser = Series([1, 2], dtype=f"{any_numeric_ea_dtype.lower()}[pyarrow]") + result = to_datetime(ser) + expected = Series([1, 2], dtype="datetime64[ns]") + tm.assert_series_equal(result, expected) + + +def test_to_datetime_with_empty_str_utc_false_format_mixed(): + # GH 50887 + vals = ["2020-01-01 00:00+00:00", ""] + result = to_datetime(vals, format="mixed") + expected = Index([Timestamp("2020-01-01 00:00+00:00"), "NaT"], dtype="M8[ns, UTC]") + tm.assert_index_equal(result, expected) + + # Check that a couple of other similar paths work the same way + alt = to_datetime(vals) + tm.assert_index_equal(alt, expected) + alt2 = DatetimeIndex(vals) + tm.assert_index_equal(alt2, expected) + + +def test_to_datetime_with_empty_str_utc_false_offsets_and_format_mixed(): + # GH 50887 + msg = "parsing datetimes with mixed time zones will raise an error" + + with tm.assert_produces_warning(FutureWarning, match=msg): + to_datetime( + ["2020-01-01 00:00+00:00", "2020-01-01 00:00+02:00", ""], format="mixed" + ) + + +def test_to_datetime_mixed_tzs_mixed_types(): + # GH#55793, GH#55693 mismatched tzs but one is str and other is + # datetime object + ts = Timestamp("2016-01-02 03:04:05", tz="US/Pacific") + dtstr = "2023-10-30 15:06+01" + arr = [ts, dtstr] + + msg = ( + "Mixed timezones detected. pass utc=True in to_datetime or tz='UTC' " + "in DatetimeIndex to convert to a common timezone" + ) + with pytest.raises(ValueError, match=msg): + to_datetime(arr) + with pytest.raises(ValueError, match=msg): + to_datetime(arr, format="mixed") + with pytest.raises(ValueError, match=msg): + DatetimeIndex(arr) + + +def test_to_datetime_mixed_types_matching_tzs(): + # GH#55793 + dtstr = "2023-11-01 09:22:03-07:00" + ts = Timestamp(dtstr) + arr = [ts, dtstr] + res1 = to_datetime(arr) + res2 = to_datetime(arr[::-1])[::-1] + res3 = to_datetime(arr, format="mixed") + res4 = DatetimeIndex(arr) + + expected = DatetimeIndex([ts, ts]) + tm.assert_index_equal(res1, expected) + tm.assert_index_equal(res2, expected) + tm.assert_index_equal(res3, expected) + tm.assert_index_equal(res4, expected) + + +dtstr = "2020-01-01 00:00+00:00" +ts = Timestamp(dtstr) + + +@pytest.mark.filterwarnings("ignore:Could not infer format:UserWarning") +@pytest.mark.parametrize( + "aware_val", + [dtstr, Timestamp(dtstr)], + ids=lambda x: type(x).__name__, +) +@pytest.mark.parametrize( + "naive_val", + [dtstr[:-6], ts.tz_localize(None), ts.date(), ts.asm8, ts.value, float(ts.value)], + ids=lambda x: type(x).__name__, +) +@pytest.mark.parametrize("naive_first", [True, False]) +def test_to_datetime_mixed_awareness_mixed_types(aware_val, naive_val, naive_first): + # GH#55793, GH#55693 + # Empty string parses to NaT + vals = [aware_val, naive_val, ""] + + vec = vals + if naive_first: + # alas, the behavior is order-dependent, so we test both ways + vec = [naive_val, aware_val, ""] + + # both_strs-> paths that were previously already deprecated with warning + # issued in _array_to_datetime_object + both_strs = isinstance(aware_val, str) and isinstance(naive_val, str) + has_numeric = isinstance(naive_val, (int, float)) + + depr_msg = "In a future version of pandas, parsing datetimes with mixed time zones" + + first_non_null = next(x for x in vec if x != "") + # if first_non_null is a not a string, _guess_datetime_format_for_array + # doesn't guess a format so we don't go through array_strptime + if not isinstance(first_non_null, str): + # that case goes through array_strptime which has different behavior + msg = "Cannot mix tz-aware with tz-naive values" + if naive_first and isinstance(aware_val, Timestamp): + if isinstance(naive_val, Timestamp): + msg = "Tz-aware datetime.datetime cannot be converted to datetime64" + with pytest.raises(ValueError, match=msg): + to_datetime(vec) + else: + with pytest.raises(ValueError, match=msg): + to_datetime(vec) + + # No warning/error with utc=True + to_datetime(vec, utc=True) + + elif has_numeric and vec.index(aware_val) < vec.index(naive_val): + msg = "time data .* doesn't match format" + with pytest.raises(ValueError, match=msg): + to_datetime(vec) + with pytest.raises(ValueError, match=msg): + to_datetime(vec, utc=True) + + elif both_strs and vec.index(aware_val) < vec.index(naive_val): + msg = r"time data \"2020-01-01 00:00\" doesn't match format" + with pytest.raises(ValueError, match=msg): + to_datetime(vec) + with pytest.raises(ValueError, match=msg): + to_datetime(vec, utc=True) + + elif both_strs and vec.index(naive_val) < vec.index(aware_val): + msg = "unconverted data remains when parsing with format" + with pytest.raises(ValueError, match=msg): + to_datetime(vec) + with pytest.raises(ValueError, match=msg): + to_datetime(vec, utc=True) + + else: + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + to_datetime(vec) + + # No warning/error with utc=True + to_datetime(vec, utc=True) + + if both_strs: + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + to_datetime(vec, format="mixed") + with tm.assert_produces_warning(FutureWarning, match=depr_msg): + msg = "DatetimeIndex has mixed timezones" + with pytest.raises(TypeError, match=msg): + DatetimeIndex(vec) + else: + msg = "Cannot mix tz-aware with tz-naive values" + if naive_first and isinstance(aware_val, Timestamp): + if isinstance(naive_val, Timestamp): + msg = "Tz-aware datetime.datetime cannot be converted to datetime64" + with pytest.raises(ValueError, match=msg): + to_datetime(vec, format="mixed") + with pytest.raises(ValueError, match=msg): + DatetimeIndex(vec) + else: + with pytest.raises(ValueError, match=msg): + to_datetime(vec, format="mixed") + with pytest.raises(ValueError, match=msg): + DatetimeIndex(vec) diff --git a/lib/python3.12/site-packages/pandas/tests/tools/test_to_numeric.py b/lib/python3.12/site-packages/pandas/tests/tools/test_to_numeric.py new file mode 100644 index 0000000000000000000000000000000000000000..c452382ec572bd24cf704c445f24f9af87947141 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/tools/test_to_numeric.py @@ -0,0 +1,978 @@ +import decimal + +import numpy as np +from numpy import iinfo +import pytest + +import pandas.util._test_decorators as td + +import pandas as pd +from pandas import ( + ArrowDtype, + DataFrame, + Index, + Series, + option_context, + to_numeric, +) +import pandas._testing as tm + + +@pytest.fixture(params=[None, "ignore", "raise", "coerce"]) +def errors(request): + return request.param + + +@pytest.fixture(params=[True, False]) +def signed(request): + return request.param + + +@pytest.fixture(params=[lambda x: x, str], ids=["identity", "str"]) +def transform(request): + return request.param + + +@pytest.fixture(params=[47393996303418497800, 100000000000000000000]) +def large_val(request): + return request.param + + +@pytest.fixture(params=[True, False]) +def multiple_elts(request): + return request.param + + +@pytest.fixture( + params=[ + (lambda x: Index(x, name="idx"), tm.assert_index_equal), + (lambda x: Series(x, name="ser"), tm.assert_series_equal), + (lambda x: np.array(Index(x).values), tm.assert_numpy_array_equal), + ] +) +def transform_assert_equal(request): + return request.param + + +@pytest.mark.parametrize( + "input_kwargs,result_kwargs", + [ + ({}, {"dtype": np.int64}), + ({"errors": "coerce", "downcast": "integer"}, {"dtype": np.int8}), + ], +) +def test_empty(input_kwargs, result_kwargs): + # see gh-16302 + ser = Series([], dtype=object) + result = to_numeric(ser, **input_kwargs) + + expected = Series([], **result_kwargs) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "infer_string", [False, pytest.param(True, marks=td.skip_if_no("pyarrow"))] +) +@pytest.mark.parametrize("last_val", ["7", 7]) +def test_series(last_val, infer_string): + with option_context("future.infer_string", infer_string): + ser = Series(["1", "-3.14", last_val]) + result = to_numeric(ser) + + expected = Series([1, -3.14, 7]) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "data", + [ + [1, 3, 4, 5], + [1.0, 3.0, 4.0, 5.0], + # Bool is regarded as numeric. + [True, False, True, True], + ], +) +def test_series_numeric(data): + ser = Series(data, index=list("ABCD"), name="EFG") + + result = to_numeric(ser) + tm.assert_series_equal(result, ser) + + +@pytest.mark.parametrize( + "data,msg", + [ + ([1, -3.14, "apple"], 'Unable to parse string "apple" at position 2'), + ( + ["orange", 1, -3.14, "apple"], + 'Unable to parse string "orange" at position 0', + ), + ], +) +def test_error(data, msg): + ser = Series(data) + + with pytest.raises(ValueError, match=msg): + to_numeric(ser, errors="raise") + + +@pytest.mark.parametrize( + "errors,exp_data", [("ignore", [1, -3.14, "apple"]), ("coerce", [1, -3.14, np.nan])] +) +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_ignore_error(errors, exp_data): + ser = Series([1, -3.14, "apple"]) + result = to_numeric(ser, errors=errors) + + expected = Series(exp_data) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "errors,exp", + [ + ("raise", 'Unable to parse string "apple" at position 2'), + ("ignore", [True, False, "apple"]), + # Coerces to float. + ("coerce", [1.0, 0.0, np.nan]), + ], +) +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_bool_handling(errors, exp): + ser = Series([True, False, "apple"]) + + if isinstance(exp, str): + with pytest.raises(ValueError, match=exp): + to_numeric(ser, errors=errors) + else: + result = to_numeric(ser, errors=errors) + expected = Series(exp) + + tm.assert_series_equal(result, expected) + + +def test_list(): + ser = ["1", "-3.14", "7"] + res = to_numeric(ser) + + expected = np.array([1, -3.14, 7]) + tm.assert_numpy_array_equal(res, expected) + + +@pytest.mark.parametrize( + "data,arr_kwargs", + [ + ([1, 3, 4, 5], {"dtype": np.int64}), + ([1.0, 3.0, 4.0, 5.0], {}), + # Boolean is regarded as numeric. + ([True, False, True, True], {}), + ], +) +def test_list_numeric(data, arr_kwargs): + result = to_numeric(data) + expected = np.array(data, **arr_kwargs) + tm.assert_numpy_array_equal(result, expected) + + +@pytest.mark.parametrize("kwargs", [{"dtype": "O"}, {}]) +def test_numeric(kwargs): + data = [1, -3.14, 7] + + ser = Series(data, **kwargs) + result = to_numeric(ser) + + expected = Series(data) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "columns", + [ + # One column. + "a", + # Multiple columns. + ["a", "b"], + ], +) +def test_numeric_df_columns(columns): + # see gh-14827 + df = DataFrame( + { + "a": [1.2, decimal.Decimal(3.14), decimal.Decimal("infinity"), "0.1"], + "b": [1.0, 2.0, 3.0, 4.0], + } + ) + + expected = DataFrame({"a": [1.2, 3.14, np.inf, 0.1], "b": [1.0, 2.0, 3.0, 4.0]}) + + df_copy = df.copy() + df_copy[columns] = df_copy[columns].apply(to_numeric) + + tm.assert_frame_equal(df_copy, expected) + + +@pytest.mark.parametrize( + "data,exp_data", + [ + ( + [[decimal.Decimal(3.14), 1.0], decimal.Decimal(1.6), 0.1], + [[3.14, 1.0], 1.6, 0.1], + ), + ([np.array([decimal.Decimal(3.14), 1.0]), 0.1], [[3.14, 1.0], 0.1]), + ], +) +def test_numeric_embedded_arr_likes(data, exp_data): + # Test to_numeric with embedded lists and arrays + df = DataFrame({"a": data}) + df["a"] = df["a"].apply(to_numeric) + + expected = DataFrame({"a": exp_data}) + tm.assert_frame_equal(df, expected) + + +def test_all_nan(): + ser = Series(["a", "b", "c"]) + result = to_numeric(ser, errors="coerce") + + expected = Series([np.nan, np.nan, np.nan]) + tm.assert_series_equal(result, expected) + + +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_type_check(errors): + # see gh-11776 + df = DataFrame({"a": [1, -3.14, 7], "b": ["4", "5", "6"]}) + kwargs = {"errors": errors} if errors is not None else {} + with pytest.raises(TypeError, match="1-d array"): + to_numeric(df, **kwargs) + + +@pytest.mark.parametrize("val", [1, 1.1, 20001]) +def test_scalar(val, signed, transform): + val = -val if signed else val + assert to_numeric(transform(val)) == float(val) + + +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_really_large_scalar(large_val, signed, transform, errors): + # see gh-24910 + kwargs = {"errors": errors} if errors is not None else {} + val = -large_val if signed else large_val + + val = transform(val) + val_is_string = isinstance(val, str) + + if val_is_string and errors in (None, "raise"): + msg = "Integer out of range. at position 0" + with pytest.raises(ValueError, match=msg): + to_numeric(val, **kwargs) + else: + expected = float(val) if (errors == "coerce" and val_is_string) else val + tm.assert_almost_equal(to_numeric(val, **kwargs), expected) + + +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_really_large_in_arr(large_val, signed, transform, multiple_elts, errors): + # see gh-24910 + kwargs = {"errors": errors} if errors is not None else {} + val = -large_val if signed else large_val + val = transform(val) + + extra_elt = "string" + arr = [val] + multiple_elts * [extra_elt] + + val_is_string = isinstance(val, str) + coercing = errors == "coerce" + + if errors in (None, "raise") and (val_is_string or multiple_elts): + if val_is_string: + msg = "Integer out of range. at position 0" + else: + msg = 'Unable to parse string "string" at position 1' + + with pytest.raises(ValueError, match=msg): + to_numeric(arr, **kwargs) + else: + result = to_numeric(arr, **kwargs) + + exp_val = float(val) if (coercing and val_is_string) else val + expected = [exp_val] + + if multiple_elts: + if coercing: + expected.append(np.nan) + exp_dtype = float + else: + expected.append(extra_elt) + exp_dtype = object + else: + exp_dtype = float if isinstance(exp_val, (int, float)) else object + + tm.assert_almost_equal(result, np.array(expected, dtype=exp_dtype)) + + +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_really_large_in_arr_consistent(large_val, signed, multiple_elts, errors): + # see gh-24910 + # + # Even if we discover that we have to hold float, does not mean + # we should be lenient on subsequent elements that fail to be integer. + kwargs = {"errors": errors} if errors is not None else {} + arr = [str(-large_val if signed else large_val)] + + if multiple_elts: + arr.insert(0, large_val) + + if errors in (None, "raise"): + index = int(multiple_elts) + msg = f"Integer out of range. at position {index}" + + with pytest.raises(ValueError, match=msg): + to_numeric(arr, **kwargs) + else: + result = to_numeric(arr, **kwargs) + + if errors == "coerce": + expected = [float(i) for i in arr] + exp_dtype = float + else: + expected = arr + exp_dtype = object + + tm.assert_almost_equal(result, np.array(expected, dtype=exp_dtype)) + + +@pytest.mark.parametrize( + "errors,checker", + [ + ("raise", 'Unable to parse string "fail" at position 0'), + ("ignore", lambda x: x == "fail"), + ("coerce", lambda x: np.isnan(x)), + ], +) +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_scalar_fail(errors, checker): + scalar = "fail" + + if isinstance(checker, str): + with pytest.raises(ValueError, match=checker): + to_numeric(scalar, errors=errors) + else: + assert checker(to_numeric(scalar, errors=errors)) + + +@pytest.mark.parametrize("data", [[1, 2, 3], [1.0, np.nan, 3, np.nan]]) +def test_numeric_dtypes(data, transform_assert_equal): + transform, assert_equal = transform_assert_equal + data = transform(data) + + result = to_numeric(data) + assert_equal(result, data) + + +@pytest.mark.parametrize( + "data,exp", + [ + (["1", "2", "3"], np.array([1, 2, 3], dtype="int64")), + (["1.5", "2.7", "3.4"], np.array([1.5, 2.7, 3.4])), + ], +) +def test_str(data, exp, transform_assert_equal): + transform, assert_equal = transform_assert_equal + result = to_numeric(transform(data)) + + expected = transform(exp) + assert_equal(result, expected) + + +def test_datetime_like(tz_naive_fixture, transform_assert_equal): + transform, assert_equal = transform_assert_equal + idx = pd.date_range("20130101", periods=3, tz=tz_naive_fixture) + + result = to_numeric(transform(idx)) + expected = transform(idx.asi8) + assert_equal(result, expected) + + +def test_timedelta(transform_assert_equal): + transform, assert_equal = transform_assert_equal + idx = pd.timedelta_range("1 days", periods=3, freq="D") + + result = to_numeric(transform(idx)) + expected = transform(idx.asi8) + assert_equal(result, expected) + + +def test_period(request, transform_assert_equal): + transform, assert_equal = transform_assert_equal + + idx = pd.period_range("2011-01", periods=3, freq="M", name="") + inp = transform(idx) + + if not isinstance(inp, Index): + request.applymarker( + pytest.mark.xfail(reason="Missing PeriodDtype support in to_numeric") + ) + result = to_numeric(inp) + expected = transform(idx.asi8) + assert_equal(result, expected) + + +@pytest.mark.parametrize( + "errors,expected", + [ + ("raise", "Invalid object type at position 0"), + ("ignore", Series([[10.0, 2], 1.0, "apple"])), + ("coerce", Series([np.nan, 1.0, np.nan])), + ], +) +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_non_hashable(errors, expected): + # see gh-13324 + ser = Series([[10.0, 2], 1.0, "apple"]) + + if isinstance(expected, str): + with pytest.raises(TypeError, match=expected): + to_numeric(ser, errors=errors) + else: + result = to_numeric(ser, errors=errors) + tm.assert_series_equal(result, expected) + + +def test_downcast_invalid_cast(): + # see gh-13352 + data = ["1", 2, 3] + invalid_downcast = "unsigned-integer" + msg = "invalid downcasting method provided" + + with pytest.raises(ValueError, match=msg): + to_numeric(data, downcast=invalid_downcast) + + +def test_errors_invalid_value(): + # see gh-26466 + data = ["1", 2, 3] + invalid_error_value = "invalid" + msg = "invalid error value specified" + + with pytest.raises(ValueError, match=msg): + to_numeric(data, errors=invalid_error_value) + + +@pytest.mark.parametrize( + "data", + [ + ["1", 2, 3], + [1, 2, 3], + np.array(["1970-01-02", "1970-01-03", "1970-01-04"], dtype="datetime64[D]"), + ], +) +@pytest.mark.parametrize( + "kwargs,exp_dtype", + [ + # Basic function tests. + ({}, np.int64), + ({"downcast": None}, np.int64), + # Support below np.float32 is rare and far between. + ({"downcast": "float"}, np.dtype(np.float32).char), + # Basic dtype support. + ({"downcast": "unsigned"}, np.dtype(np.typecodes["UnsignedInteger"][0])), + ], +) +def test_downcast_basic(data, kwargs, exp_dtype): + # see gh-13352 + result = to_numeric(data, **kwargs) + expected = np.array([1, 2, 3], dtype=exp_dtype) + tm.assert_numpy_array_equal(result, expected) + + +@pytest.mark.parametrize("signed_downcast", ["integer", "signed"]) +@pytest.mark.parametrize( + "data", + [ + ["1", 2, 3], + [1, 2, 3], + np.array(["1970-01-02", "1970-01-03", "1970-01-04"], dtype="datetime64[D]"), + ], +) +def test_signed_downcast(data, signed_downcast): + # see gh-13352 + smallest_int_dtype = np.dtype(np.typecodes["Integer"][0]) + expected = np.array([1, 2, 3], dtype=smallest_int_dtype) + + res = to_numeric(data, downcast=signed_downcast) + tm.assert_numpy_array_equal(res, expected) + + +def test_ignore_downcast_invalid_data(): + # If we can't successfully cast the given + # data to a numeric dtype, do not bother + # with the downcast parameter. + data = ["foo", 2, 3] + expected = np.array(data, dtype=object) + + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + res = to_numeric(data, errors="ignore", downcast="unsigned") + tm.assert_numpy_array_equal(res, expected) + + +def test_ignore_downcast_neg_to_unsigned(): + # Cannot cast to an unsigned integer + # because we have a negative number. + data = ["-1", 2, 3] + expected = np.array([-1, 2, 3], dtype=np.int64) + + res = to_numeric(data, downcast="unsigned") + tm.assert_numpy_array_equal(res, expected) + + +# Warning in 32 bit platforms +@pytest.mark.filterwarnings("ignore:invalid value encountered in cast:RuntimeWarning") +@pytest.mark.parametrize("downcast", ["integer", "signed", "unsigned"]) +@pytest.mark.parametrize( + "data,expected", + [ + (["1.1", 2, 3], np.array([1.1, 2, 3], dtype=np.float64)), + ( + [10000.0, 20000, 3000, 40000.36, 50000, 50000.00], + np.array( + [10000.0, 20000, 3000, 40000.36, 50000, 50000.00], dtype=np.float64 + ), + ), + ], +) +def test_ignore_downcast_cannot_convert_float(data, expected, downcast): + # Cannot cast to an integer (signed or unsigned) + # because we have a float number. + res = to_numeric(data, downcast=downcast) + tm.assert_numpy_array_equal(res, expected) + + +@pytest.mark.parametrize( + "downcast,expected_dtype", + [("integer", np.int16), ("signed", np.int16), ("unsigned", np.uint16)], +) +def test_downcast_not8bit(downcast, expected_dtype): + # the smallest integer dtype need not be np.(u)int8 + data = ["256", 257, 258] + + expected = np.array([256, 257, 258], dtype=expected_dtype) + res = to_numeric(data, downcast=downcast) + tm.assert_numpy_array_equal(res, expected) + + +@pytest.mark.parametrize( + "dtype,downcast,min_max", + [ + ("int8", "integer", [iinfo(np.int8).min, iinfo(np.int8).max]), + ("int16", "integer", [iinfo(np.int16).min, iinfo(np.int16).max]), + ("int32", "integer", [iinfo(np.int32).min, iinfo(np.int32).max]), + ("int64", "integer", [iinfo(np.int64).min, iinfo(np.int64).max]), + ("uint8", "unsigned", [iinfo(np.uint8).min, iinfo(np.uint8).max]), + ("uint16", "unsigned", [iinfo(np.uint16).min, iinfo(np.uint16).max]), + ("uint32", "unsigned", [iinfo(np.uint32).min, iinfo(np.uint32).max]), + ("uint64", "unsigned", [iinfo(np.uint64).min, iinfo(np.uint64).max]), + ("int16", "integer", [iinfo(np.int8).min, iinfo(np.int8).max + 1]), + ("int32", "integer", [iinfo(np.int16).min, iinfo(np.int16).max + 1]), + ("int64", "integer", [iinfo(np.int32).min, iinfo(np.int32).max + 1]), + ("int16", "integer", [iinfo(np.int8).min - 1, iinfo(np.int16).max]), + ("int32", "integer", [iinfo(np.int16).min - 1, iinfo(np.int32).max]), + ("int64", "integer", [iinfo(np.int32).min - 1, iinfo(np.int64).max]), + ("uint16", "unsigned", [iinfo(np.uint8).min, iinfo(np.uint8).max + 1]), + ("uint32", "unsigned", [iinfo(np.uint16).min, iinfo(np.uint16).max + 1]), + ("uint64", "unsigned", [iinfo(np.uint32).min, iinfo(np.uint32).max + 1]), + ], +) +def test_downcast_limits(dtype, downcast, min_max): + # see gh-14404: test the limits of each downcast. + series = to_numeric(Series(min_max), downcast=downcast) + assert series.dtype == dtype + + +def test_downcast_float64_to_float32(): + # GH-43693: Check float64 preservation when >= 16,777,217 + series = Series([16777217.0, np.finfo(np.float64).max, np.nan], dtype=np.float64) + result = to_numeric(series, downcast="float") + + assert series.dtype == result.dtype + + +@pytest.mark.parametrize( + "ser,expected", + [ + ( + Series([0, 9223372036854775808]), + Series([0, 9223372036854775808], dtype=np.uint64), + ) + ], +) +def test_downcast_uint64(ser, expected): + # see gh-14422: + # BUG: to_numeric doesn't work uint64 numbers + + result = to_numeric(ser, downcast="unsigned") + + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "data,exp_data", + [ + ( + [200, 300, "", "NaN", 30000000000000000000], + [200, 300, np.nan, np.nan, 30000000000000000000], + ), + ( + ["12345678901234567890", "1234567890", "ITEM"], + [12345678901234567890, 1234567890, np.nan], + ), + ], +) +def test_coerce_uint64_conflict(data, exp_data): + # see gh-17007 and gh-17125 + # + # Still returns float despite the uint64-nan conflict, + # which would normally force the casting to object. + result = to_numeric(Series(data), errors="coerce") + expected = Series(exp_data, dtype=float) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "errors,exp", + [ + ("ignore", Series(["12345678901234567890", "1234567890", "ITEM"])), + ("raise", "Unable to parse string"), + ], +) +@pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") +def test_non_coerce_uint64_conflict(errors, exp): + # see gh-17007 and gh-17125 + # + # For completeness. + ser = Series(["12345678901234567890", "1234567890", "ITEM"]) + + if isinstance(exp, str): + with pytest.raises(ValueError, match=exp): + to_numeric(ser, errors=errors) + else: + result = to_numeric(ser, errors=errors) + tm.assert_series_equal(result, ser) + + +@pytest.mark.parametrize("dc1", ["integer", "float", "unsigned"]) +@pytest.mark.parametrize("dc2", ["integer", "float", "unsigned"]) +def test_downcast_empty(dc1, dc2): + # GH32493 + + tm.assert_numpy_array_equal( + to_numeric([], downcast=dc1), + to_numeric([], downcast=dc2), + check_dtype=False, + ) + + +def test_failure_to_convert_uint64_string_to_NaN(): + # GH 32394 + result = to_numeric("uint64", errors="coerce") + assert np.isnan(result) + + ser = Series([32, 64, np.nan]) + result = to_numeric(Series(["32", "64", "uint64"]), errors="coerce") + tm.assert_series_equal(result, ser) + + +@pytest.mark.parametrize( + "strrep", + [ + "243.164", + "245.968", + "249.585", + "259.745", + "265.742", + "272.567", + "279.196", + "280.366", + "275.034", + "271.351", + "272.889", + "270.627", + "280.828", + "290.383", + "308.153", + "319.945", + "336.0", + "344.09", + "351.385", + "356.178", + "359.82", + "361.03", + "367.701", + "380.812", + "387.98", + "391.749", + "391.171", + "385.97", + "385.345", + "386.121", + "390.996", + "399.734", + "413.073", + "421.532", + "430.221", + "437.092", + "439.746", + "446.01", + "451.191", + "460.463", + "469.779", + "472.025", + "479.49", + "474.864", + "467.54", + "471.978", + ], +) +def test_precision_float_conversion(strrep): + # GH 31364 + result = to_numeric(strrep) + + assert result == float(strrep) + + +@pytest.mark.parametrize( + "values, expected", + [ + (["1", "2", None], Series([1, 2, np.nan], dtype="Int64")), + (["1", "2", "3"], Series([1, 2, 3], dtype="Int64")), + (["1", "2", 3], Series([1, 2, 3], dtype="Int64")), + (["1", "2", 3.5], Series([1, 2, 3.5], dtype="Float64")), + (["1", None, 3.5], Series([1, np.nan, 3.5], dtype="Float64")), + (["1", "2", "3.5"], Series([1, 2, 3.5], dtype="Float64")), + ], +) +def test_to_numeric_from_nullable_string(values, nullable_string_dtype, expected): + # https://github.com/pandas-dev/pandas/issues/37262 + s = Series(values, dtype=nullable_string_dtype) + result = to_numeric(s) + tm.assert_series_equal(result, expected) + + +def test_to_numeric_from_nullable_string_coerce(nullable_string_dtype): + # GH#52146 + values = ["a", "1"] + ser = Series(values, dtype=nullable_string_dtype) + result = to_numeric(ser, errors="coerce") + expected = Series([pd.NA, 1], dtype="Int64") + tm.assert_series_equal(result, expected) + + +def test_to_numeric_from_nullable_string_ignore(nullable_string_dtype): + # GH#52146 + values = ["a", "1"] + ser = Series(values, dtype=nullable_string_dtype) + expected = ser.copy() + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_numeric(ser, errors="ignore") + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "data, input_dtype, downcast, expected_dtype", + ( + ([1, 1], "Int64", "integer", "Int8"), + ([1.0, pd.NA], "Float64", "integer", "Int8"), + ([1.0, 1.1], "Float64", "integer", "Float64"), + ([1, pd.NA], "Int64", "integer", "Int8"), + ([450, 300], "Int64", "integer", "Int16"), + ([1, 1], "Float64", "integer", "Int8"), + ([np.iinfo(np.int64).max - 1, 1], "Int64", "integer", "Int64"), + ([1, 1], "Int64", "signed", "Int8"), + ([1.0, 1.0], "Float32", "signed", "Int8"), + ([1.0, 1.1], "Float64", "signed", "Float64"), + ([1, pd.NA], "Int64", "signed", "Int8"), + ([450, -300], "Int64", "signed", "Int16"), + ([np.iinfo(np.uint64).max - 1, 1], "UInt64", "signed", "UInt64"), + ([1, 1], "Int64", "unsigned", "UInt8"), + ([1.0, 1.0], "Float32", "unsigned", "UInt8"), + ([1.0, 1.1], "Float64", "unsigned", "Float64"), + ([1, pd.NA], "Int64", "unsigned", "UInt8"), + ([450, -300], "Int64", "unsigned", "Int64"), + ([-1, -1], "Int32", "unsigned", "Int32"), + ([1, 1], "Float64", "float", "Float32"), + ([1, 1.1], "Float64", "float", "Float32"), + ([1, 1], "Float32", "float", "Float32"), + ([1, 1.1], "Float32", "float", "Float32"), + ), +) +def test_downcast_nullable_numeric(data, input_dtype, downcast, expected_dtype): + arr = pd.array(data, dtype=input_dtype) + result = to_numeric(arr, downcast=downcast) + expected = pd.array(data, dtype=expected_dtype) + tm.assert_extension_array_equal(result, expected) + + +def test_downcast_nullable_mask_is_copied(): + # GH38974 + + arr = pd.array([1, 2, pd.NA], dtype="Int64") + + result = to_numeric(arr, downcast="integer") + expected = pd.array([1, 2, pd.NA], dtype="Int8") + tm.assert_extension_array_equal(result, expected) + + arr[1] = pd.NA # should not modify result + tm.assert_extension_array_equal(result, expected) + + +def test_to_numeric_scientific_notation(): + # GH 15898 + result = to_numeric("1.7e+308") + expected = np.float64(1.7e308) + assert result == expected + + +@pytest.mark.parametrize("val", [9876543210.0, 2.0**128]) +def test_to_numeric_large_float_not_downcast_to_float_32(val): + # GH 19729 + expected = Series([val]) + result = to_numeric(expected, downcast="float") + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "val, dtype", [(1, "Int64"), (1.5, "Float64"), (True, "boolean")] +) +def test_to_numeric_dtype_backend(val, dtype): + # GH#50505 + ser = Series([val], dtype=object) + result = to_numeric(ser, dtype_backend="numpy_nullable") + expected = Series([val], dtype=dtype) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "val, dtype", + [ + (1, "Int64"), + (1.5, "Float64"), + (True, "boolean"), + (1, "int64[pyarrow]"), + (1.5, "float64[pyarrow]"), + (True, "bool[pyarrow]"), + ], +) +def test_to_numeric_dtype_backend_na(val, dtype): + # GH#50505 + if "pyarrow" in dtype: + pytest.importorskip("pyarrow") + dtype_backend = "pyarrow" + else: + dtype_backend = "numpy_nullable" + ser = Series([val, None], dtype=object) + result = to_numeric(ser, dtype_backend=dtype_backend) + expected = Series([val, pd.NA], dtype=dtype) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "val, dtype, downcast", + [ + (1, "Int8", "integer"), + (1.5, "Float32", "float"), + (1, "Int8", "signed"), + (1, "int8[pyarrow]", "integer"), + (1.5, "float[pyarrow]", "float"), + (1, "int8[pyarrow]", "signed"), + ], +) +def test_to_numeric_dtype_backend_downcasting(val, dtype, downcast): + # GH#50505 + if "pyarrow" in dtype: + pytest.importorskip("pyarrow") + dtype_backend = "pyarrow" + else: + dtype_backend = "numpy_nullable" + ser = Series([val, None], dtype=object) + result = to_numeric(ser, dtype_backend=dtype_backend, downcast=downcast) + expected = Series([val, pd.NA], dtype=dtype) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "smaller, dtype_backend", + [["UInt8", "numpy_nullable"], ["uint8[pyarrow]", "pyarrow"]], +) +def test_to_numeric_dtype_backend_downcasting_uint(smaller, dtype_backend): + # GH#50505 + if dtype_backend == "pyarrow": + pytest.importorskip("pyarrow") + ser = Series([1, pd.NA], dtype="UInt64") + result = to_numeric(ser, dtype_backend=dtype_backend, downcast="unsigned") + expected = Series([1, pd.NA], dtype=smaller) + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize( + "dtype", + [ + "Int64", + "UInt64", + "Float64", + "boolean", + "int64[pyarrow]", + "uint64[pyarrow]", + "float64[pyarrow]", + "bool[pyarrow]", + ], +) +def test_to_numeric_dtype_backend_already_nullable(dtype): + # GH#50505 + if "pyarrow" in dtype: + pytest.importorskip("pyarrow") + ser = Series([1, pd.NA], dtype=dtype) + result = to_numeric(ser, dtype_backend="numpy_nullable") + expected = Series([1, pd.NA], dtype=dtype) + tm.assert_series_equal(result, expected) + + +def test_to_numeric_dtype_backend_error(dtype_backend): + # GH#50505 + ser = Series(["a", "b", ""]) + expected = ser.copy() + with pytest.raises(ValueError, match="Unable to parse string"): + to_numeric(ser, dtype_backend=dtype_backend) + + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_numeric(ser, dtype_backend=dtype_backend, errors="ignore") + tm.assert_series_equal(result, expected) + + result = to_numeric(ser, dtype_backend=dtype_backend, errors="coerce") + if dtype_backend == "pyarrow": + dtype = "double[pyarrow]" + else: + dtype = "Float64" + expected = Series([np.nan, np.nan, np.nan], dtype=dtype) + tm.assert_series_equal(result, expected) + + +def test_invalid_dtype_backend(): + ser = Series([1, 2, 3]) + msg = ( + "dtype_backend numpy is invalid, only 'numpy_nullable' and " + "'pyarrow' are allowed." + ) + with pytest.raises(ValueError, match=msg): + to_numeric(ser, dtype_backend="numpy") + + +def test_coerce_pyarrow_backend(): + # GH 52588 + pa = pytest.importorskip("pyarrow") + ser = Series(list("12x"), dtype=ArrowDtype(pa.string())) + result = to_numeric(ser, errors="coerce", dtype_backend="pyarrow") + expected = Series([1, 2, None], dtype=ArrowDtype(pa.int64())) + tm.assert_series_equal(result, expected) diff --git a/lib/python3.12/site-packages/pandas/tests/tools/test_to_time.py b/lib/python3.12/site-packages/pandas/tests/tools/test_to_time.py new file mode 100644 index 0000000000000000000000000000000000000000..b673bd9c2ec7168971ae0ed802336e4f03ff63a7 --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/tools/test_to_time.py @@ -0,0 +1,72 @@ +from datetime import time +import locale + +import numpy as np +import pytest + +from pandas.compat import PY311 + +from pandas import Series +import pandas._testing as tm +from pandas.core.tools.times import to_time + +# The tests marked with this are locale-dependent. +# They pass, except when the machine locale is zh_CN or it_IT. +fails_on_non_english = pytest.mark.xfail( + locale.getlocale()[0] in ("zh_CN", "it_IT"), + reason="fail on a CI build with LC_ALL=zh_CN.utf8/it_IT.utf8", + strict=False, +) + + +class TestToTime: + @pytest.mark.parametrize( + "time_string", + [ + "14:15", + "1415", + pytest.param("2:15pm", marks=fails_on_non_english), + pytest.param("0215pm", marks=fails_on_non_english), + "14:15:00", + "141500", + pytest.param("2:15:00pm", marks=fails_on_non_english), + pytest.param("021500pm", marks=fails_on_non_english), + time(14, 15), + ], + ) + def test_parsers_time(self, time_string): + # GH#11818 + assert to_time(time_string) == time(14, 15) + + def test_odd_format(self): + new_string = "14.15" + msg = r"Cannot convert arg \['14\.15'\] to a time" + if not PY311: + with pytest.raises(ValueError, match=msg): + to_time(new_string) + assert to_time(new_string, format="%H.%M") == time(14, 15) + + def test_arraylike(self): + arg = ["14:15", "20:20"] + expected_arr = [time(14, 15), time(20, 20)] + assert to_time(arg) == expected_arr + assert to_time(arg, format="%H:%M") == expected_arr + assert to_time(arg, infer_time_format=True) == expected_arr + assert to_time(arg, format="%I:%M%p", errors="coerce") == [None, None] + + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + res = to_time(arg, format="%I:%M%p", errors="ignore") + tm.assert_numpy_array_equal(res, np.array(arg, dtype=np.object_)) + + msg = "Cannot convert.+to a time with given format" + with pytest.raises(ValueError, match=msg): + to_time(arg, format="%I:%M%p", errors="raise") + + tm.assert_series_equal( + to_time(Series(arg, name="test")), Series(expected_arr, name="test") + ) + + res = to_time(np.array(arg)) + assert isinstance(res, list) + assert res == expected_arr diff --git a/lib/python3.12/site-packages/pandas/tests/tools/test_to_timedelta.py b/lib/python3.12/site-packages/pandas/tests/tools/test_to_timedelta.py new file mode 100644 index 0000000000000000000000000000000000000000..b67694f1c58c7016221ed629358e8867b2a1534a --- /dev/null +++ b/lib/python3.12/site-packages/pandas/tests/tools/test_to_timedelta.py @@ -0,0 +1,340 @@ +from datetime import ( + time, + timedelta, +) + +import numpy as np +import pytest + +from pandas.compat import IS64 +from pandas.errors import OutOfBoundsTimedelta + +import pandas as pd +from pandas import ( + Series, + TimedeltaIndex, + isna, + to_timedelta, +) +import pandas._testing as tm +from pandas.core.arrays import TimedeltaArray + + +class TestTimedeltas: + def test_to_timedelta_dt64_raises(self): + # Passing datetime64-dtype data to TimedeltaIndex is no longer + # supported GH#29794 + msg = r"dtype datetime64\[ns\] cannot be converted to timedelta64\[ns\]" + + ser = Series([pd.NaT]) + with pytest.raises(TypeError, match=msg): + to_timedelta(ser) + with pytest.raises(TypeError, match=msg): + ser.to_frame().apply(to_timedelta) + + @pytest.mark.parametrize("readonly", [True, False]) + def test_to_timedelta_readonly(self, readonly): + # GH#34857 + arr = np.array([], dtype=object) + if readonly: + arr.setflags(write=False) + result = to_timedelta(arr) + expected = to_timedelta([]) + tm.assert_index_equal(result, expected) + + def test_to_timedelta_null(self): + result = to_timedelta(["", ""]) + assert isna(result).all() + + def test_to_timedelta_same_np_timedelta64(self): + # pass thru + result = to_timedelta(np.array([np.timedelta64(1, "s")])) + expected = pd.Index(np.array([np.timedelta64(1, "s")])) + tm.assert_index_equal(result, expected) + + def test_to_timedelta_series(self): + # Series + expected = Series([timedelta(days=1), timedelta(days=1, seconds=1)]) + result = to_timedelta(Series(["1d", "1days 00:00:01"])) + tm.assert_series_equal(result, expected) + + def test_to_timedelta_units(self): + # with units + result = TimedeltaIndex( + [np.timedelta64(0, "ns"), np.timedelta64(10, "s").astype("m8[ns]")] + ) + expected = to_timedelta([0, 10], unit="s") + tm.assert_index_equal(result, expected) + + @pytest.mark.parametrize( + "dtype, unit", + [ + ["int64", "s"], + ["int64", "m"], + ["int64", "h"], + ["timedelta64[s]", "s"], + ["timedelta64[D]", "D"], + ], + ) + def test_to_timedelta_units_dtypes(self, dtype, unit): + # arrays of various dtypes + arr = np.array([1] * 5, dtype=dtype) + result = to_timedelta(arr, unit=unit) + exp_dtype = "m8[ns]" if dtype == "int64" else "m8[s]" + expected = TimedeltaIndex([np.timedelta64(1, unit)] * 5, dtype=exp_dtype) + tm.assert_index_equal(result, expected) + + def test_to_timedelta_oob_non_nano(self): + arr = np.array([pd.NaT._value + 1], dtype="timedelta64[m]") + + msg = ( + "Cannot convert -9223372036854775807 minutes to " + r"timedelta64\[s\] without overflow" + ) + with pytest.raises(OutOfBoundsTimedelta, match=msg): + to_timedelta(arr) + + with pytest.raises(OutOfBoundsTimedelta, match=msg): + TimedeltaIndex(arr) + + with pytest.raises(OutOfBoundsTimedelta, match=msg): + TimedeltaArray._from_sequence(arr, dtype="m8[s]") + + @pytest.mark.parametrize( + "arg", [np.arange(10).reshape(2, 5), pd.DataFrame(np.arange(10).reshape(2, 5))] + ) + @pytest.mark.parametrize("errors", ["ignore", "raise", "coerce"]) + @pytest.mark.filterwarnings("ignore:errors='ignore' is deprecated:FutureWarning") + def test_to_timedelta_dataframe(self, arg, errors): + # GH 11776 + with pytest.raises(TypeError, match="1-d array"): + to_timedelta(arg, errors=errors) + + def test_to_timedelta_invalid_errors(self): + # bad value for errors parameter + msg = "errors must be one of" + with pytest.raises(ValueError, match=msg): + to_timedelta(["foo"], errors="never") + + @pytest.mark.parametrize("arg", [[1, 2], 1]) + def test_to_timedelta_invalid_unit(self, arg): + # these will error + msg = "invalid unit abbreviation: foo" + with pytest.raises(ValueError, match=msg): + to_timedelta(arg, unit="foo") + + def test_to_timedelta_time(self): + # time not supported ATM + msg = ( + "Value must be Timedelta, string, integer, float, timedelta or convertible" + ) + with pytest.raises(ValueError, match=msg): + to_timedelta(time(second=1)) + assert to_timedelta(time(second=1), errors="coerce") is pd.NaT + + def test_to_timedelta_bad_value(self): + msg = "Could not convert 'foo' to NumPy timedelta" + with pytest.raises(ValueError, match=msg): + to_timedelta(["foo", "bar"]) + + def test_to_timedelta_bad_value_coerce(self): + tm.assert_index_equal( + TimedeltaIndex([pd.NaT, pd.NaT]), + to_timedelta(["foo", "bar"], errors="coerce"), + ) + + tm.assert_index_equal( + TimedeltaIndex(["1 day", pd.NaT, "1 min"]), + to_timedelta(["1 day", "bar", "1 min"], errors="coerce"), + ) + + def test_to_timedelta_invalid_errors_ignore(self): + # gh-13613: these should not error because errors='ignore' + msg = "errors='ignore' is deprecated" + invalid_data = "apple" + + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_timedelta(invalid_data, errors="ignore") + assert invalid_data == result + + invalid_data = ["apple", "1 days"] + expected = np.array(invalid_data, dtype=object) + + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_timedelta(invalid_data, errors="ignore") + tm.assert_numpy_array_equal(expected, result) + + invalid_data = pd.Index(["apple", "1 days"]) + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_timedelta(invalid_data, errors="ignore") + tm.assert_index_equal(invalid_data, result) + + invalid_data = Series(["apple", "1 days"]) + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_timedelta(invalid_data, errors="ignore") + tm.assert_series_equal(invalid_data, result) + + @pytest.mark.parametrize( + "val, errors", + [ + ("1M", True), + ("1 M", True), + ("1Y", True), + ("1 Y", True), + ("1y", True), + ("1 y", True), + ("1m", False), + ("1 m", False), + ("1 day", False), + ("2day", False), + ], + ) + def test_unambiguous_timedelta_values(self, val, errors): + # GH36666 Deprecate use of strings denoting units with 'M', 'Y', 'm' or 'y' + # in pd.to_timedelta + msg = "Units 'M', 'Y' and 'y' do not represent unambiguous timedelta" + if errors: + with pytest.raises(ValueError, match=msg): + to_timedelta(val) + else: + # check it doesn't raise + to_timedelta(val) + + def test_to_timedelta_via_apply(self): + # GH 5458 + expected = Series([np.timedelta64(1, "s")]) + result = Series(["00:00:01"]).apply(to_timedelta) + tm.assert_series_equal(result, expected) + + result = Series([to_timedelta("00:00:01")]) + tm.assert_series_equal(result, expected) + + def test_to_timedelta_inference_without_warning(self): + # GH#41731 inference produces a warning in the Series constructor, + # but _not_ in to_timedelta + vals = ["00:00:01", pd.NaT] + with tm.assert_produces_warning(None): + result = to_timedelta(vals) + + expected = TimedeltaIndex([pd.Timedelta(seconds=1), pd.NaT]) + tm.assert_index_equal(result, expected) + + def test_to_timedelta_on_missing_values(self): + # GH5438 + timedelta_NaT = np.timedelta64("NaT") + + actual = to_timedelta(Series(["00:00:01", np.nan])) + expected = Series( + [np.timedelta64(1000000000, "ns"), timedelta_NaT], + dtype=f"{tm.ENDIAN}m8[ns]", + ) + tm.assert_series_equal(actual, expected) + + ser = Series(["00:00:01", pd.NaT], dtype="m8[ns]") + actual = to_timedelta(ser) + tm.assert_series_equal(actual, expected) + + @pytest.mark.parametrize("val", [np.nan, pd.NaT, pd.NA]) + def test_to_timedelta_on_missing_values_scalar(self, val): + actual = to_timedelta(val) + assert actual._value == np.timedelta64("NaT").astype("int64") + + @pytest.mark.parametrize("val", [np.nan, pd.NaT, pd.NA]) + def test_to_timedelta_on_missing_values_list(self, val): + actual = to_timedelta([val]) + assert actual[0]._value == np.timedelta64("NaT").astype("int64") + + @pytest.mark.xfail(not IS64, reason="Floating point error") + def test_to_timedelta_float(self): + # https://github.com/pandas-dev/pandas/issues/25077 + arr = np.arange(0, 1, 1e-6)[-10:] + result = to_timedelta(arr, unit="s") + expected_asi8 = np.arange(999990000, 10**9, 1000, dtype="int64") + tm.assert_numpy_array_equal(result.asi8, expected_asi8) + + def test_to_timedelta_coerce_strings_unit(self): + arr = np.array([1, 2, "error"], dtype=object) + result = to_timedelta(arr, unit="ns", errors="coerce") + expected = to_timedelta([1, 2, pd.NaT], unit="ns") + tm.assert_index_equal(result, expected) + + def test_to_timedelta_ignore_strings_unit(self): + arr = np.array([1, 2, "error"], dtype=object) + msg = "errors='ignore' is deprecated" + with tm.assert_produces_warning(FutureWarning, match=msg): + result = to_timedelta(arr, unit="ns", errors="ignore") + tm.assert_numpy_array_equal(result, arr) + + @pytest.mark.parametrize( + "expected_val, result_val", [[timedelta(days=2), 2], [None, None]] + ) + def test_to_timedelta_nullable_int64_dtype(self, expected_val, result_val): + # GH 35574 + expected = Series([timedelta(days=1), expected_val]) + result = to_timedelta(Series([1, result_val], dtype="Int64"), unit="days") + + tm.assert_series_equal(result, expected) + + @pytest.mark.parametrize( + ("input", "expected"), + [ + ("8:53:08.71800000001", "8:53:08.718"), + ("8:53:08.718001", "8:53:08.718001"), + ("8:53:08.7180000001", "8:53:08.7180000001"), + ("-8:53:08.71800000001", "-8:53:08.718"), + ("8:53:08.7180000089", "8:53:08.718000008"), + ], + ) + @pytest.mark.parametrize("func", [pd.Timedelta, to_timedelta]) + def test_to_timedelta_precision_over_nanos(self, input, expected, func): + # GH: 36738 + expected = pd.Timedelta(expected) + result = func(input) + assert result == expected + + def test_to_timedelta_zerodim(self, fixed_now_ts): + # ndarray.item() incorrectly returns int for dt64[ns] and td64[ns] + dt64 = fixed_now_ts.to_datetime64() + arg = np.array(dt64) + + msg = ( + "Value must be Timedelta, string, integer, float, timedelta " + "or convertible, not datetime64" + ) + with pytest.raises(ValueError, match=msg): + to_timedelta(arg) + + arg2 = arg.view("m8[ns]") + result = to_timedelta(arg2) + assert isinstance(result, pd.Timedelta) + assert result._value == dt64.view("i8") + + def test_to_timedelta_numeric_ea(self, any_numeric_ea_dtype): + # GH#48796 + ser = Series([1, pd.NA], dtype=any_numeric_ea_dtype) + result = to_timedelta(ser) + expected = Series([pd.Timedelta(1, unit="ns"), pd.NaT]) + tm.assert_series_equal(result, expected) + + def test_to_timedelta_fraction(self): + result = to_timedelta(1.0 / 3, unit="h") + expected = pd.Timedelta("0 days 00:19:59.999999998") + assert result == expected + + +def test_from_numeric_arrow_dtype(any_numeric_ea_dtype): + # GH 52425 + pytest.importorskip("pyarrow") + ser = Series([1, 2], dtype=f"{any_numeric_ea_dtype.lower()}[pyarrow]") + result = to_timedelta(ser) + expected = Series([1, 2], dtype="timedelta64[ns]") + tm.assert_series_equal(result, expected) + + +@pytest.mark.parametrize("unit", ["ns", "ms"]) +def test_from_timedelta_arrow_dtype(unit): + # GH 54298 + pytest.importorskip("pyarrow") + expected = Series([timedelta(1)], dtype=f"duration[{unit}][pyarrow]") + result = to_timedelta(expected) + tm.assert_series_equal(result, expected)