Add files using upload-large-folder tool

py311/lib/python3.11/site-packages/pandas/tests/indexes/base_class/test_constructors.py

@@ -0,0 +1,78 @@
+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
+        expected = Index(["a", "b"], dtype=pd.StringDtype(na_value=np.nan))
+        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

py311/lib/python3.11/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_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_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_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

py311/lib/python3.11/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)

py311/lib/python3.11/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)

py311/lib/python3.11/site-packages/pandas/tests/indexes/base_class/test_reshape.py

@@ -0,0 +1,97 @@
+"""
+Tests for ndarray-like method on the base Index class
+"""
+import numpy as np
+import pytest
+
+import pandas as pd
+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"]), null_index.insert(0, "a"))
+
+    def test_insert_missing(self, request, nulls_fixture, using_infer_string):
+        if using_infer_string and nulls_fixture is pd.NA:
+            request.applymarker(pytest.mark.xfail(reason="TODO(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, string_dtype_no_object):
+        # GH#55365
+        index = Index(["a", "b", "c"], dtype=string_dtype_no_object)
+        result = index.insert(-1, None)
+        expected = Index(["a", "b", None, "c"], dtype=string_dtype_no_object)
+        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)

py311/lib/python3.11/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)

py311/lib/python3.11/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)

py311/lib/python3.11/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")

py311/lib/python3.11/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)

py311/lib/python3.11/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)

py311/lib/python3.11/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

py311/lib/python3.11/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")

py311/lib/python3.11/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)

py311/lib/python3.11/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)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_astype.py

@@ -0,0 +1,254 @@
+import re
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import (
+    CategoricalDtype,
+    IntervalDtype,
+)
+
+from pandas import (
+    CategoricalIndex,
+    Index,
+    IntervalIndex,
+    NaT,
+    Timedelta,
+    Timestamp,
+    interval_range,
+)
+import pandas._testing as tm
+
+
+class AstypeTests:
+    """Tests common to IntervalIndex with any subtype"""
+
+    def test_astype_idempotent(self, index):
+        result = index.astype("interval")
+        tm.assert_index_equal(result, index)
+
+        result = index.astype(index.dtype)
+        tm.assert_index_equal(result, index)
+
+    def test_astype_object(self, index):
+        result = index.astype(object)
+        expected = Index(index.values, dtype="object")
+        tm.assert_index_equal(result, expected)
+        assert not result.equals(index)
+
+    def test_astype_category(self, index):
+        result = index.astype("category")
+        expected = CategoricalIndex(index.values)
+        tm.assert_index_equal(result, expected)
+
+        result = index.astype(CategoricalDtype())
+        tm.assert_index_equal(result, expected)
+
+        # non-default params
+        categories = index.dropna().unique().values[:-1]
+        dtype = CategoricalDtype(categories=categories, ordered=True)
+        result = index.astype(dtype)
+        expected = CategoricalIndex(index.values, categories=categories, ordered=True)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "dtype",
+        [
+            "int64",
+            "uint64",
+            "float64",
+            "complex128",
+            "period[M]",
+            "timedelta64",
+            "timedelta64[ns]",
+            "datetime64",
+            "datetime64[ns]",
+            "datetime64[ns, US/Eastern]",
+        ],
+    )
+    def test_astype_cannot_cast(self, index, dtype):
+        msg = "Cannot cast IntervalIndex to dtype"
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+    def test_astype_invalid_dtype(self, index):
+        msg = "data type [\"']fake_dtype[\"'] not understood"
+        with pytest.raises(TypeError, match=msg):
+            index.astype("fake_dtype")
+
+
+class TestIntSubtype(AstypeTests):
+    """Tests specific to IntervalIndex with integer-like subtype"""
+
+    indexes = [
+        IntervalIndex.from_breaks(np.arange(-10, 11, dtype="int64")),
+        IntervalIndex.from_breaks(np.arange(100, dtype="uint64"), closed="left"),
+    ]
+
+    @pytest.fixture(params=indexes)
+    def index(self, request):
+        return request.param
+
+    @pytest.mark.parametrize(
+        "subtype", ["float64", "datetime64[ns]", "timedelta64[ns]"]
+    )
+    def test_subtype_conversion(self, index, subtype):
+        dtype = IntervalDtype(subtype, index.closed)
+        result = index.astype(dtype)
+        expected = IntervalIndex.from_arrays(
+            index.left.astype(subtype), index.right.astype(subtype), closed=index.closed
+        )
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "subtype_start, subtype_end", [("int64", "uint64"), ("uint64", "int64")]
+    )
+    def test_subtype_integer(self, subtype_start, subtype_end):
+        index = IntervalIndex.from_breaks(np.arange(100, dtype=subtype_start))
+        dtype = IntervalDtype(subtype_end, index.closed)
+        result = index.astype(dtype)
+        expected = IntervalIndex.from_arrays(
+            index.left.astype(subtype_end),
+            index.right.astype(subtype_end),
+            closed=index.closed,
+        )
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.xfail(reason="GH#15832")
+    def test_subtype_integer_errors(self):
+        # int64 -> uint64 fails with negative values
+        index = interval_range(-10, 10)
+        dtype = IntervalDtype("uint64", "right")
+
+        # Until we decide what the exception message _should_ be, we
+        #  assert something that it should _not_ be.
+        #  We should _not_ be getting a message suggesting that the -10
+        #  has been wrapped around to a large-positive integer
+        msg = "^(?!(left side of interval must be <= right side))"
+        with pytest.raises(ValueError, match=msg):
+            index.astype(dtype)
+
+
+class TestFloatSubtype(AstypeTests):
+    """Tests specific to IntervalIndex with float subtype"""
+
+    indexes = [
+        interval_range(-10.0, 10.0, closed="neither"),
+        IntervalIndex.from_arrays(
+            [-1.5, np.nan, 0.0, 0.0, 1.5], [-0.5, np.nan, 1.0, 1.0, 3.0], closed="both"
+        ),
+    ]
+
+    @pytest.fixture(params=indexes)
+    def index(self, request):
+        return request.param
+
+    @pytest.mark.parametrize("subtype", ["int64", "uint64"])
+    def test_subtype_integer(self, subtype):
+        index = interval_range(0.0, 10.0)
+        dtype = IntervalDtype(subtype, "right")
+        result = index.astype(dtype)
+        expected = IntervalIndex.from_arrays(
+            index.left.astype(subtype), index.right.astype(subtype), closed=index.closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # raises with NA
+        msg = r"Cannot convert non-finite values \(NA or inf\) to integer"
+        with pytest.raises(ValueError, match=msg):
+            index.insert(0, np.nan).astype(dtype)
+
+    @pytest.mark.parametrize("subtype", ["int64", "uint64"])
+    def test_subtype_integer_with_non_integer_borders(self, subtype):
+        index = interval_range(0.0, 3.0, freq=0.25)
+        dtype = IntervalDtype(subtype, "right")
+        result = index.astype(dtype)
+        expected = IntervalIndex.from_arrays(
+            index.left.astype(subtype), index.right.astype(subtype), closed=index.closed
+        )
+        tm.assert_index_equal(result, expected)
+
+    def test_subtype_integer_errors(self):
+        # float64 -> uint64 fails with negative values
+        index = interval_range(-10.0, 10.0)
+        dtype = IntervalDtype("uint64", "right")
+        msg = re.escape(
+            "Cannot convert interval[float64, right] to interval[uint64, right]; "
+            "subtypes are incompatible"
+        )
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+    @pytest.mark.parametrize("subtype", ["datetime64[ns]", "timedelta64[ns]"])
+    def test_subtype_datetimelike(self, index, subtype):
+        dtype = IntervalDtype(subtype, "right")
+        msg = "Cannot convert .* to .*; subtypes are incompatible"
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+    @pytest.mark.filterwarnings(
+        "ignore:invalid value encountered in cast:RuntimeWarning"
+    )
+    def test_astype_category(self, index):
+        super().test_astype_category(index)
+
+
+class TestDatetimelikeSubtype(AstypeTests):
+    """Tests specific to IntervalIndex with datetime-like subtype"""
+
+    indexes = [
+        interval_range(Timestamp("2018-01-01"), periods=10, closed="neither"),
+        interval_range(Timestamp("2018-01-01"), periods=10).insert(2, NaT),
+        interval_range(Timestamp("2018-01-01", tz="US/Eastern"), periods=10),
+        interval_range(Timedelta("0 days"), periods=10, closed="both"),
+        interval_range(Timedelta("0 days"), periods=10).insert(2, NaT),
+    ]
+
+    @pytest.fixture(params=indexes)
+    def index(self, request):
+        return request.param
+
+    @pytest.mark.parametrize("subtype", ["int64", "uint64"])
+    def test_subtype_integer(self, index, subtype):
+        dtype = IntervalDtype(subtype, "right")
+
+        if subtype != "int64":
+            msg = (
+                r"Cannot convert interval\[(timedelta64|datetime64)\[ns.*\], .*\] "
+                r"to interval\[uint64, .*\]"
+            )
+            with pytest.raises(TypeError, match=msg):
+                index.astype(dtype)
+            return
+
+        result = index.astype(dtype)
+        new_left = index.left.astype(subtype)
+        new_right = index.right.astype(subtype)
+
+        expected = IntervalIndex.from_arrays(new_left, new_right, closed=index.closed)
+        tm.assert_index_equal(result, expected)
+
+    def test_subtype_float(self, index):
+        dtype = IntervalDtype("float64", "right")
+        msg = "Cannot convert .* to .*; subtypes are incompatible"
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+    def test_subtype_datetimelike(self):
+        # datetime -> timedelta raises
+        dtype = IntervalDtype("timedelta64[ns]", "right")
+        msg = "Cannot convert .* to .*; subtypes are incompatible"
+
+        index = interval_range(Timestamp("2018-01-01"), periods=10)
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+        index = interval_range(Timestamp("2018-01-01", tz="CET"), periods=10)
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)
+
+        # timedelta -> datetime raises
+        dtype = IntervalDtype("datetime64[ns]", "right")
+        index = interval_range(Timedelta("0 days"), periods=10)
+        with pytest.raises(TypeError, match=msg):
+            index.astype(dtype)

py311/lib/python3.11/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), "<M8[ns]"),
+            (
+                date_range("20180101", periods=10, tz="US/Eastern"),
+                "datetime64[ns, US/Eastern]",
+            ),
+            (timedelta_range("1 day", periods=10), "<m8[ns]"),
+        ]
+    )
+    def breaks_and_expected_subtype(self, request):
+        return request.param
+
+    def test_constructor(self, constructor, breaks_and_expected_subtype, closed, name):
+        breaks, expected_subtype = breaks_and_expected_subtype
+
+        result_kwargs = self.get_kwargs_from_breaks(breaks, closed)
+
+        result = constructor(closed=closed, name=name, **result_kwargs)
+
+        assert result.closed == closed
+        assert result.name == name
+        assert result.dtype.subtype == expected_subtype
+        tm.assert_index_equal(result.left, Index(breaks[:-1], dtype=expected_subtype))
+        tm.assert_index_equal(result.right, Index(breaks[1:], dtype=expected_subtype))
+
+    @pytest.mark.parametrize(
+        "breaks, subtype",
+        [
+            (Index([0, 1, 2, 3, 4], dtype=np.int64), "float64"),
+            (Index([0, 1, 2, 3, 4], dtype=np.int64), "datetime64[ns]"),
+            (Index([0, 1, 2, 3, 4], dtype=np.int64), "timedelta64[ns]"),
+            (Index([0, 1, 2, 3, 4], dtype=np.float64), "int64"),
+            (date_range("2017-01-01", periods=5), "int64"),
+            (timedelta_range("1 day", periods=5), "int64"),
+        ],
+    )
+    def test_constructor_dtype(self, constructor, breaks, subtype):
+        # GH 19262: conversion via dtype parameter
+        expected_kwargs = self.get_kwargs_from_breaks(breaks.astype(subtype))
+        expected = constructor(**expected_kwargs)
+
+        result_kwargs = self.get_kwargs_from_breaks(breaks)
+        iv_dtype = IntervalDtype(subtype, "right")
+        for dtype in (iv_dtype, str(iv_dtype)):
+            result = constructor(dtype=dtype, **result_kwargs)
+            tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            Index([0, 1, 2, 3, 4], dtype=np.int64),
+            Index([0, 1, 2, 3, 4], dtype=np.uint64),
+            Index([0, 1, 2, 3, 4], dtype=np.float64),
+            date_range("2017-01-01", periods=5),
+            timedelta_range("1 day", periods=5),
+        ],
+    )
+    def test_constructor_pass_closed(self, constructor, breaks):
+        # not passing closed to IntervalDtype, but to IntervalArray constructor
+        iv_dtype = IntervalDtype(breaks.dtype)
+
+        result_kwargs = self.get_kwargs_from_breaks(breaks)
+
+        for dtype in (iv_dtype, str(iv_dtype)):
+            with tm.assert_produces_warning(None):
+                result = constructor(dtype=dtype, closed="left", **result_kwargs)
+            assert result.dtype.closed == "left"
+
+    @pytest.mark.parametrize("breaks", [[np.nan] * 2, [np.nan] * 4, [np.nan] * 50])
+    def test_constructor_nan(self, constructor, breaks, closed):
+        # GH 18421
+        result_kwargs = self.get_kwargs_from_breaks(breaks)
+        result = constructor(closed=closed, **result_kwargs)
+
+        expected_subtype = np.float64
+        expected_values = np.array(breaks[:-1], dtype=object)
+
+        assert result.closed == closed
+        assert result.dtype.subtype == expected_subtype
+        tm.assert_numpy_array_equal(np.array(result), expected_values)
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            [],
+            np.array([], dtype="int64"),
+            np.array([], dtype="uint64"),
+            np.array([], dtype="float64"),
+            np.array([], dtype="datetime64[ns]"),
+            np.array([], dtype="timedelta64[ns]"),
+        ],
+    )
+    def test_constructor_empty(self, constructor, breaks, closed):
+        # GH 18421
+        result_kwargs = self.get_kwargs_from_breaks(breaks)
+        result = constructor(closed=closed, **result_kwargs)
+
+        expected_values = np.array([], dtype=object)
+        expected_subtype = getattr(breaks, "dtype", np.int64)
+
+        assert result.empty
+        assert result.closed == closed
+        assert result.dtype.subtype == expected_subtype
+        tm.assert_numpy_array_equal(np.array(result), expected_values)
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            tuple("0123456789"),
+            list("abcdefghij"),
+            np.array(list("abcdefghij"), dtype=object),
+            np.array(list("abcdefghij"), dtype="<U1"),
+        ],
+    )
+    def test_constructor_string(self, constructor, breaks):
+        # GH 19016
+        msg = (
+            "category, object, and string subtypes are not supported "
+            "for IntervalIndex"
+        )
+        with pytest.raises(TypeError, match=msg):
+            constructor(**self.get_kwargs_from_breaks(breaks))
+
+    @pytest.mark.parametrize("cat_constructor", [Categorical, CategoricalIndex])
+    def test_constructor_categorical_valid(self, constructor, cat_constructor):
+        # GH 21243/21253
+
+        breaks = np.arange(10, dtype="int64")
+        expected = IntervalIndex.from_breaks(breaks)
+
+        cat_breaks = cat_constructor(breaks)
+        result_kwargs = self.get_kwargs_from_breaks(cat_breaks)
+        result = constructor(**result_kwargs)
+        tm.assert_index_equal(result, expected)
+
+    def test_generic_errors(self, constructor):
+        # filler input data to be used when supplying invalid kwargs
+        filler = self.get_kwargs_from_breaks(range(10))
+
+        # invalid closed
+        msg = "closed must be one of 'right', 'left', 'both', 'neither'"
+        with pytest.raises(ValueError, match=msg):
+            constructor(closed="invalid", **filler)
+
+        # unsupported dtype
+        msg = "dtype must be an IntervalDtype, got int64"
+        with pytest.raises(TypeError, match=msg):
+            constructor(dtype="int64", **filler)
+
+        # invalid dtype
+        msg = "data type [\"']invalid[\"'] not understood"
+        with pytest.raises(TypeError, match=msg):
+            constructor(dtype="invalid", **filler)
+
+        # no point in nesting periods in an IntervalIndex
+        periods = period_range("2000-01-01", periods=10)
+        periods_kwargs = self.get_kwargs_from_breaks(periods)
+        msg = "Period dtypes are not supported, use a PeriodIndex instead"
+        with pytest.raises(ValueError, match=msg):
+            constructor(**periods_kwargs)
+
+        # decreasing values
+        decreasing_kwargs = self.get_kwargs_from_breaks(range(10, -1, -1))
+        msg = "left side of interval must be <= right side"
+        with pytest.raises(ValueError, match=msg):
+            constructor(**decreasing_kwargs)
+
+
+class TestFromArrays(ConstructorTests):
+    """Tests specific to IntervalIndex.from_arrays"""
+
+    @pytest.fixture
+    def constructor(self):
+        return IntervalIndex.from_arrays
+
+    def get_kwargs_from_breaks(self, breaks, closed="right"):
+        """
+        converts intervals in breaks format to a dictionary of kwargs to
+        specific to the format expected by IntervalIndex.from_arrays
+        """
+        return {"left": breaks[:-1], "right": breaks[1:]}
+
+    def test_constructor_errors(self):
+        # GH 19016: categorical data
+        data = Categorical(list("01234abcde"), ordered=True)
+        msg = (
+            "category, object, and string subtypes are not supported "
+            "for IntervalIndex"
+        )
+        with pytest.raises(TypeError, match=msg):
+            IntervalIndex.from_arrays(data[:-1], data[1:])
+
+        # unequal length
+        left = [0, 1, 2]
+        right = [2, 3]
+        msg = "left and right must have the same length"
+        with pytest.raises(ValueError, match=msg):
+            IntervalIndex.from_arrays(left, right)
+
+    @pytest.mark.parametrize(
+        "left_subtype, right_subtype", [(np.int64, np.float64), (np.float64, np.int64)]
+    )
+    def test_mixed_float_int(self, left_subtype, right_subtype):
+        """mixed int/float left/right results in float for both sides"""
+        left = np.arange(9, dtype=left_subtype)
+        right = np.arange(1, 10, dtype=right_subtype)
+        result = IntervalIndex.from_arrays(left, right)
+
+        expected_left = Index(left, dtype=np.float64)
+        expected_right = Index(right, dtype=np.float64)
+        expected_subtype = np.float64
+
+        tm.assert_index_equal(result.left, expected_left)
+        tm.assert_index_equal(result.right, expected_right)
+        assert result.dtype.subtype == expected_subtype
+
+    @pytest.mark.parametrize("interval_cls", [IntervalArray, IntervalIndex])
+    def test_from_arrays_mismatched_datetimelike_resos(self, interval_cls):
+        # GH#55714
+        left = date_range("2016-01-01", periods=3, unit="s")
+        right = date_range("2017-01-01", periods=3, unit="ms")
+        result = interval_cls.from_arrays(left, right)
+        expected = interval_cls.from_arrays(left.as_unit("ms"), right)
+        tm.assert_equal(result, expected)
+
+        # td64
+        left2 = left - left[0]
+        right2 = right - left[0]
+        result2 = interval_cls.from_arrays(left2, right2)
+        expected2 = interval_cls.from_arrays(left2.as_unit("ms"), right2)
+        tm.assert_equal(result2, expected2)
+
+        # dt64tz
+        left3 = left.tz_localize("UTC")
+        right3 = right.tz_localize("UTC")
+        result3 = interval_cls.from_arrays(left3, right3)
+        expected3 = interval_cls.from_arrays(left3.as_unit("ms"), right3)
+        tm.assert_equal(result3, expected3)
+
+
+class TestFromBreaks(ConstructorTests):
+    """Tests specific to IntervalIndex.from_breaks"""
+
+    @pytest.fixture
+    def constructor(self):
+        return IntervalIndex.from_breaks
+
+    def get_kwargs_from_breaks(self, breaks, closed="right"):
+        """
+        converts intervals in breaks format to a dictionary of kwargs to
+        specific to the format expected by IntervalIndex.from_breaks
+        """
+        return {"breaks": breaks}
+
+    def test_constructor_errors(self):
+        # GH 19016: categorical data
+        data = Categorical(list("01234abcde"), ordered=True)
+        msg = (
+            "category, object, and string subtypes are not supported "
+            "for IntervalIndex"
+        )
+        with pytest.raises(TypeError, match=msg):
+            IntervalIndex.from_breaks(data)
+
+    def test_length_one(self):
+        """breaks of length one produce an empty IntervalIndex"""
+        breaks = [0]
+        result = IntervalIndex.from_breaks(breaks)
+        expected = IntervalIndex.from_breaks([])
+        tm.assert_index_equal(result, expected)
+
+    def test_left_right_dont_share_data(self):
+        # GH#36310
+        breaks = np.arange(5)
+        result = IntervalIndex.from_breaks(breaks)._data
+        assert result._left.base is None or result._left.base is not result._right.base
+
+
+class TestFromTuples(ConstructorTests):
+    """Tests specific to IntervalIndex.from_tuples"""
+
+    @pytest.fixture
+    def constructor(self):
+        return IntervalIndex.from_tuples
+
+    def get_kwargs_from_breaks(self, breaks, closed="right"):
+        """
+        converts intervals in breaks format to a dictionary of kwargs to
+        specific to the format expected by IntervalIndex.from_tuples
+        """
+        if is_unsigned_integer_dtype(breaks):
+            pytest.skip(f"{breaks.dtype} not relevant IntervalIndex.from_tuples tests")
+
+        if len(breaks) == 0:
+            return {"data": breaks}
+
+        tuples = list(zip(breaks[:-1], breaks[1:]))
+        if isinstance(breaks, (list, tuple)):
+            return {"data": tuples}
+        elif isinstance(getattr(breaks, "dtype", None), CategoricalDtype):
+            return {"data": breaks._constructor(tuples)}
+        return {"data": com.asarray_tuplesafe(tuples)}
+
+    def test_constructor_errors(self):
+        # non-tuple
+        tuples = [(0, 1), 2, (3, 4)]
+        msg = "IntervalIndex.from_tuples received an invalid item, 2"
+        with pytest.raises(TypeError, match=msg.format(t=tuples)):
+            IntervalIndex.from_tuples(tuples)
+
+        # too few/many items
+        tuples = [(0, 1), (2,), (3, 4)]
+        msg = "IntervalIndex.from_tuples requires tuples of length 2, got {t}"
+        with pytest.raises(ValueError, match=msg.format(t=tuples)):
+            IntervalIndex.from_tuples(tuples)
+
+        tuples = [(0, 1), (2, 3, 4), (5, 6)]
+        with pytest.raises(ValueError, match=msg.format(t=tuples)):
+            IntervalIndex.from_tuples(tuples)
+
+    def test_na_tuples(self):
+        # tuple (NA, NA) evaluates the same as NA as an element
+        na_tuple = [(0, 1), (np.nan, np.nan), (2, 3)]
+        idx_na_tuple = IntervalIndex.from_tuples(na_tuple)
+        idx_na_element = IntervalIndex.from_tuples([(0, 1), np.nan, (2, 3)])
+        tm.assert_index_equal(idx_na_tuple, idx_na_element)
+
+
+class TestClassConstructors(ConstructorTests):
+    """Tests specific to the IntervalIndex/Index constructors"""
+
+    @pytest.fixture(
+        params=[IntervalIndex, partial(Index, dtype="interval")],
+        ids=["IntervalIndex", "Index"],
+    )
+    def klass(self, request):
+        # We use a separate fixture here to include Index.__new__ with dtype kwarg
+        return request.param
+
+    @pytest.fixture
+    def constructor(self):
+        return IntervalIndex
+
+    def get_kwargs_from_breaks(self, breaks, closed="right"):
+        """
+        converts intervals in breaks format to a dictionary of kwargs to
+        specific to the format expected by the IntervalIndex/Index constructors
+        """
+        if is_unsigned_integer_dtype(breaks):
+            pytest.skip(f"{breaks.dtype} not relevant for class constructor tests")
+
+        if len(breaks) == 0:
+            return {"data": breaks}
+
+        ivs = [
+            Interval(left, right, closed) if notna(left) else left
+            for left, right in zip(breaks[:-1], breaks[1:])
+        ]
+
+        if isinstance(breaks, list):
+            return {"data": ivs}
+        elif isinstance(getattr(breaks, "dtype", None), CategoricalDtype):
+            return {"data": breaks._constructor(ivs)}
+        return {"data": np.array(ivs, dtype=object)}
+
+    def test_generic_errors(self, constructor):
+        """
+        override the base class implementation since errors are handled
+        differently; checks unnecessary since caught at the Interval level
+        """
+
+    def test_constructor_string(self):
+        # GH23013
+        # When forming the interval from breaks,
+        # the interval of strings is already forbidden.
+        pass
+
+    def test_constructor_errors(self, klass):
+        # mismatched closed within intervals with no constructor override
+        ivs = [Interval(0, 1, closed="right"), Interval(2, 3, closed="left")]
+        msg = "intervals must all be closed on the same side"
+        with pytest.raises(ValueError, match=msg):
+            klass(ivs)
+
+        # scalar
+        msg = (
+            r"(IntervalIndex|Index)\(...\) must be called with a collection of "
+            "some kind, 5 was passed"
+        )
+        with pytest.raises(TypeError, match=msg):
+            klass(5)
+
+        # not an interval; dtype depends on 32bit/windows builds
+        msg = "type <class 'numpy.int(32|64)'> with value 0 is not an interval"
+        with pytest.raises(TypeError, match=msg):
+            klass([0, 1])
+
+    @pytest.mark.parametrize(
+        "data, closed",
+        [
+            ([], "both"),
+            ([np.nan, np.nan], "neither"),
+            (
+                [Interval(0, 3, closed="neither"), Interval(2, 5, closed="neither")],
+                "left",
+            ),
+            (
+                [Interval(0, 3, closed="left"), Interval(2, 5, closed="right")],
+                "neither",
+            ),
+            (IntervalIndex.from_breaks(range(5), closed="both"), "right"),
+        ],
+    )
+    def test_override_inferred_closed(self, constructor, data, closed):
+        # GH 19370
+        if isinstance(data, IntervalIndex):
+            tuples = data.to_tuples()
+        else:
+            tuples = [(iv.left, iv.right) if notna(iv) else iv for iv in data]
+        expected = IntervalIndex.from_tuples(tuples, closed=closed)
+        result = constructor(data, closed=closed)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "values_constructor", [list, np.array, IntervalIndex, IntervalArray]
+    )
+    def test_index_object_dtype(self, values_constructor):
+        # Index(intervals, dtype=object) is an Index (not an IntervalIndex)
+        intervals = [Interval(0, 1), Interval(1, 2), Interval(2, 3)]
+        values = values_constructor(intervals)
+        result = Index(values, dtype=object)
+
+        assert type(result) is Index
+        tm.assert_numpy_array_equal(result.values, np.array(values))
+
+    def test_index_mixed_closed(self):
+        # GH27172
+        intervals = [
+            Interval(0, 1, closed="left"),
+            Interval(1, 2, closed="right"),
+            Interval(2, 3, closed="neither"),
+            Interval(3, 4, closed="both"),
+        ]
+        result = Index(intervals)
+        expected = Index(intervals, dtype=object)
+        tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize("timezone", ["UTC", "US/Pacific", "GMT"])
+def test_interval_index_subtype(timezone, inclusive_endpoints_fixture):
+    # GH#46999
+    dates = date_range("2022", periods=3, tz=timezone)
+    dtype = f"interval[datetime64[ns, {timezone}], {inclusive_endpoints_fixture}]"
+    result = IntervalIndex.from_arrays(
+        ["2022-01-01", "2022-01-02"],
+        ["2022-01-02", "2022-01-03"],
+        closed=inclusive_endpoints_fixture,
+        dtype=dtype,
+    )
+    expected = IntervalIndex.from_arrays(
+        dates[:-1], dates[1:], closed=inclusive_endpoints_fixture
+    )
+    tm.assert_index_equal(result, expected)
+
+
+def test_dtype_closed_mismatch():
+    # GH#38394 closed specified in both dtype and IntervalIndex constructor
+
+    dtype = IntervalDtype(np.int64, "left")
+
+    msg = "closed keyword does not match dtype.closed"
+    with pytest.raises(ValueError, match=msg):
+        IntervalIndex([], dtype=dtype, closed="neither")
+
+    with pytest.raises(ValueError, match=msg):
+        IntervalArray([], dtype=dtype, closed="neither")
+
+
+@pytest.mark.parametrize(
+    "dtype",
+    ["Float64", pytest.param("float64[pyarrow]", marks=td.skip_if_no("pyarrow"))],
+)
+def test_ea_dtype(dtype):
+    # GH#56765
+    bins = [(0.0, 0.4), (0.4, 0.6)]
+    interval_dtype = IntervalDtype(subtype=dtype, closed="left")
+    result = IntervalIndex.from_tuples(bins, closed="left", dtype=interval_dtype)
+    assert result.dtype == interval_dtype
+    expected = IntervalIndex.from_tuples(bins, closed="left").astype(interval_dtype)
+    tm.assert_index_equal(result, expected)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_equals.py

@@ -0,0 +1,36 @@
+import numpy as np
+
+from pandas import (
+    IntervalIndex,
+    date_range,
+)
+
+
+class TestEquals:
+    def test_equals(self, closed):
+        expected = IntervalIndex.from_breaks(np.arange(5), closed=closed)
+        assert expected.equals(expected)
+        assert expected.equals(expected.copy())
+
+        assert not expected.equals(expected.astype(object))
+        assert not expected.equals(np.array(expected))
+        assert not expected.equals(list(expected))
+
+        assert not expected.equals([1, 2])
+        assert not expected.equals(np.array([1, 2]))
+        assert not expected.equals(date_range("20130101", periods=2))
+
+        expected_name1 = IntervalIndex.from_breaks(
+            np.arange(5), closed=closed, name="foo"
+        )
+        expected_name2 = IntervalIndex.from_breaks(
+            np.arange(5), closed=closed, name="bar"
+        )
+        assert expected.equals(expected_name1)
+        assert expected_name1.equals(expected_name2)
+
+        for other_closed in {"left", "right", "both", "neither"} - {closed}:
+            expected_other_closed = IntervalIndex.from_breaks(
+                np.arange(5), closed=other_closed
+            )
+            assert not expected.equals(expected_other_closed)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_formats.py

@@ -0,0 +1,119 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    DataFrame,
+    DatetimeIndex,
+    Index,
+    Interval,
+    IntervalIndex,
+    Series,
+    Timedelta,
+    Timestamp,
+)
+import pandas._testing as tm
+
+
+class TestIntervalIndexRendering:
+    # TODO: this is a test for DataFrame/Series, not IntervalIndex
+    @pytest.mark.parametrize(
+        "constructor,expected",
+        [
+            (
+                Series,
+                (
+                    "(0.0, 1.0]    a\n"
+                    "NaN           b\n"
+                    "(2.0, 3.0]    c\n"
+                    "dtype: object"
+                ),
+            ),
+            (DataFrame, ("            0\n(0.0, 1.0]  a\nNaN         b\n(2.0, 3.0]  c")),
+        ],
+    )
+    def test_repr_missing(self, constructor, expected, using_infer_string, request):
+        # GH 25984
+        if using_infer_string and constructor is Series:
+            request.applymarker(pytest.mark.xfail(reason="repr different"))
+        index = IntervalIndex.from_tuples([(0, 1), np.nan, (2, 3)])
+        obj = constructor(list("abc"), index=index)
+        result = repr(obj)
+        assert result == expected
+
+    def test_repr_floats(self):
+        # GH 32553
+
+        markers = Series(
+            [1, 2],
+            index=IntervalIndex(
+                [
+                    Interval(left, right)
+                    for left, right in zip(
+                        Index([329.973, 345.137], dtype="float64"),
+                        Index([345.137, 360.191], dtype="float64"),
+                    )
+                ]
+            ),
+        )
+        result = str(markers)
+        expected = "(329.973, 345.137]    1\n(345.137, 360.191]    2\ndtype: int64"
+        assert result == expected
+
+    @pytest.mark.filterwarnings(
+        "ignore:invalid value encountered in cast:RuntimeWarning"
+    )
+    @pytest.mark.parametrize(
+        "tuples, closed, expected_data",
+        [
+            ([(0, 1), (1, 2), (2, 3)], "left", ["[0, 1)", "[1, 2)", "[2, 3)"]),
+            (
+                [(0.5, 1.0), np.nan, (2.0, 3.0)],
+                "right",
+                ["(0.5, 1.0]", "NaN", "(2.0, 3.0]"],
+            ),
+            (
+                [
+                    (Timestamp("20180101"), Timestamp("20180102")),
+                    np.nan,
+                    ((Timestamp("20180102"), Timestamp("20180103"))),
+                ],
+                "both",
+                [
+                    "[2018-01-01 00:00:00, 2018-01-02 00:00:00]",
+                    "NaN",
+                    "[2018-01-02 00:00:00, 2018-01-03 00:00:00]",
+                ],
+            ),
+            (
+                [
+                    (Timedelta("0 days"), Timedelta("1 days")),
+                    (Timedelta("1 days"), Timedelta("2 days")),
+                    np.nan,
+                ],
+                "neither",
+                [
+                    "(0 days 00:00:00, 1 days 00:00:00)",
+                    "(1 days 00:00:00, 2 days 00:00:00)",
+                    "NaN",
+                ],
+            ),
+        ],
+    )
+    def test_get_values_for_csv(self, tuples, closed, expected_data):
+        # GH 28210
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        result = index._get_values_for_csv(na_rep="NaN")
+        expected = np.array(expected_data)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_timestamp_with_timezone(self, unit):
+        # GH 55035
+        left = DatetimeIndex(["2020-01-01"], dtype=f"M8[{unit}, UTC]")
+        right = DatetimeIndex(["2020-01-02"], dtype=f"M8[{unit}, UTC]")
+        index = IntervalIndex.from_arrays(left, right)
+        result = repr(index)
+        expected = (
+            "IntervalIndex([(2020-01-01 00:00:00+00:00, 2020-01-02 00:00:00+00:00]], "
+            f"dtype='interval[datetime64[{unit}, UTC], right]')"
+        )
+        assert result == expected

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_indexing.py

@@ -0,0 +1,674 @@
+import re
+
+import numpy as np
+import pytest
+
+from pandas.errors import InvalidIndexError
+
+from pandas import (
+    NA,
+    CategoricalIndex,
+    DatetimeIndex,
+    Index,
+    Interval,
+    IntervalIndex,
+    MultiIndex,
+    NaT,
+    Timedelta,
+    Timestamp,
+    array,
+    date_range,
+    interval_range,
+    isna,
+    period_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+
+
+class TestGetItem:
+    def test_getitem(self, closed):
+        idx = IntervalIndex.from_arrays((0, 1, np.nan), (1, 2, np.nan), closed=closed)
+        assert idx[0] == Interval(0.0, 1.0, closed=closed)
+        assert idx[1] == Interval(1.0, 2.0, closed=closed)
+        assert isna(idx[2])
+
+        result = idx[0:1]
+        expected = IntervalIndex.from_arrays((0.0,), (1.0,), closed=closed)
+        tm.assert_index_equal(result, expected)
+
+        result = idx[0:2]
+        expected = IntervalIndex.from_arrays((0.0, 1), (1.0, 2.0), closed=closed)
+        tm.assert_index_equal(result, expected)
+
+        result = idx[1:3]
+        expected = IntervalIndex.from_arrays(
+            (1.0, np.nan), (2.0, np.nan), closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+    def test_getitem_2d_deprecated(self):
+        # GH#30588 multi-dim indexing is deprecated, but raising is also acceptable
+        idx = IntervalIndex.from_breaks(range(11), closed="right")
+        with pytest.raises(ValueError, match="multi-dimensional indexing not allowed"):
+            idx[:, None]
+        with pytest.raises(ValueError, match="multi-dimensional indexing not allowed"):
+            # GH#44051
+            idx[True]
+        with pytest.raises(ValueError, match="multi-dimensional indexing not allowed"):
+            # GH#44051
+            idx[False]
+
+
+class TestWhere:
+    def test_where(self, listlike_box):
+        klass = listlike_box
+
+        idx = IntervalIndex.from_breaks(range(11), closed="right")
+        cond = [True] * len(idx)
+        expected = idx
+        result = expected.where(klass(cond))
+        tm.assert_index_equal(result, expected)
+
+        cond = [False] + [True] * len(idx[1:])
+        expected = IntervalIndex([np.nan] + idx[1:].tolist())
+        result = idx.where(klass(cond))
+        tm.assert_index_equal(result, expected)
+
+
+class TestTake:
+    def test_take(self, closed):
+        index = IntervalIndex.from_breaks(range(11), closed=closed)
+
+        result = index.take(range(10))
+        tm.assert_index_equal(result, index)
+
+        result = index.take([0, 0, 1])
+        expected = IntervalIndex.from_arrays([0, 0, 1], [1, 1, 2], closed=closed)
+        tm.assert_index_equal(result, expected)
+
+
+class TestGetLoc:
+    @pytest.mark.parametrize("side", ["right", "left", "both", "neither"])
+    def test_get_loc_interval(self, closed, side):
+        idx = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
+
+        for bound in [[0, 1], [1, 2], [2, 3], [3, 4], [0, 2], [2.5, 3], [-1, 4]]:
+            # if get_loc is supplied an interval, it should only search
+            # for exact matches, not overlaps or covers, else KeyError.
+            msg = re.escape(f"Interval({bound[0]}, {bound[1]}, closed='{side}')")
+            if closed == side:
+                if bound == [0, 1]:
+                    assert idx.get_loc(Interval(0, 1, closed=side)) == 0
+                elif bound == [2, 3]:
+                    assert idx.get_loc(Interval(2, 3, closed=side)) == 1
+                else:
+                    with pytest.raises(KeyError, match=msg):
+                        idx.get_loc(Interval(*bound, closed=side))
+            else:
+                with pytest.raises(KeyError, match=msg):
+                    idx.get_loc(Interval(*bound, closed=side))
+
+    @pytest.mark.parametrize("scalar", [-0.5, 0, 0.5, 1, 1.5, 2, 2.5, 3, 3.5])
+    def test_get_loc_scalar(self, closed, scalar):
+        # correct = {side: {query: answer}}.
+        # If query is not in the dict, that query should raise a KeyError
+        correct = {
+            "right": {0.5: 0, 1: 0, 2.5: 1, 3: 1},
+            "left": {0: 0, 0.5: 0, 2: 1, 2.5: 1},
+            "both": {0: 0, 0.5: 0, 1: 0, 2: 1, 2.5: 1, 3: 1},
+            "neither": {0.5: 0, 2.5: 1},
+        }
+
+        idx = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
+
+        # if get_loc is supplied a scalar, it should return the index of
+        # the interval which contains the scalar, or KeyError.
+        if scalar in correct[closed].keys():
+            assert idx.get_loc(scalar) == correct[closed][scalar]
+        else:
+            with pytest.raises(KeyError, match=str(scalar)):
+                idx.get_loc(scalar)
+
+    @pytest.mark.parametrize("scalar", [-1, 0, 0.5, 3, 4.5, 5, 6])
+    def test_get_loc_length_one_scalar(self, scalar, closed):
+        # GH 20921
+        index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
+        if scalar in index[0]:
+            result = index.get_loc(scalar)
+            assert result == 0
+        else:
+            with pytest.raises(KeyError, match=str(scalar)):
+                index.get_loc(scalar)
+
+    @pytest.mark.parametrize("other_closed", ["left", "right", "both", "neither"])
+    @pytest.mark.parametrize("left, right", [(0, 5), (-1, 4), (-1, 6), (6, 7)])
+    def test_get_loc_length_one_interval(self, left, right, closed, other_closed):
+        # GH 20921
+        index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
+        interval = Interval(left, right, closed=other_closed)
+        if interval == index[0]:
+            result = index.get_loc(interval)
+            assert result == 0
+        else:
+            with pytest.raises(
+                KeyError,
+                match=re.escape(f"Interval({left}, {right}, closed='{other_closed}')"),
+            ):
+                index.get_loc(interval)
+
+    # Make consistent with test_interval_new.py (see #16316, #16386)
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            date_range("20180101", periods=4),
+            date_range("20180101", periods=4, tz="US/Eastern"),
+            timedelta_range("0 days", periods=4),
+        ],
+        ids=lambda x: str(x.dtype),
+    )
+    def test_get_loc_datetimelike_nonoverlapping(self, breaks):
+        # GH 20636
+        # nonoverlapping = IntervalIndex method and no i8 conversion
+        index = IntervalIndex.from_breaks(breaks)
+
+        value = index[0].mid
+        result = index.get_loc(value)
+        expected = 0
+        assert result == expected
+
+        interval = Interval(index[0].left, index[0].right)
+        result = index.get_loc(interval)
+        expected = 0
+        assert result == expected
+
+    @pytest.mark.parametrize(
+        "arrays",
+        [
+            (date_range("20180101", periods=4), date_range("20180103", periods=4)),
+            (
+                date_range("20180101", periods=4, tz="US/Eastern"),
+                date_range("20180103", periods=4, tz="US/Eastern"),
+            ),
+            (
+                timedelta_range("0 days", periods=4),
+                timedelta_range("2 days", periods=4),
+            ),
+        ],
+        ids=lambda x: str(x[0].dtype),
+    )
+    def test_get_loc_datetimelike_overlapping(self, arrays):
+        # GH 20636
+        index = IntervalIndex.from_arrays(*arrays)
+
+        value = index[0].mid + Timedelta("12 hours")
+        result = index.get_loc(value)
+        expected = slice(0, 2, None)
+        assert result == expected
+
+        interval = Interval(index[0].left, index[0].right)
+        result = index.get_loc(interval)
+        expected = 0
+        assert result == expected
+
+    @pytest.mark.parametrize(
+        "values",
+        [
+            date_range("2018-01-04", periods=4, freq="-1D"),
+            date_range("2018-01-04", periods=4, freq="-1D", tz="US/Eastern"),
+            timedelta_range("3 days", periods=4, freq="-1D"),
+            np.arange(3.0, -1.0, -1.0),
+            np.arange(3, -1, -1),
+        ],
+        ids=lambda x: str(x.dtype),
+    )
+    def test_get_loc_decreasing(self, values):
+        # GH 25860
+        index = IntervalIndex.from_arrays(values[1:], values[:-1])
+        result = index.get_loc(index[0])
+        expected = 0
+        assert result == expected
+
+    @pytest.mark.parametrize("key", [[5], (2, 3)])
+    def test_get_loc_non_scalar_errors(self, key):
+        # GH 31117
+        idx = IntervalIndex.from_tuples([(1, 3), (2, 4), (3, 5), (7, 10), (3, 10)])
+
+        msg = str(key)
+        with pytest.raises(InvalidIndexError, match=msg):
+            idx.get_loc(key)
+
+    def test_get_indexer_with_nans(self):
+        # GH#41831
+        index = IntervalIndex([np.nan, Interval(1, 2), np.nan])
+
+        expected = np.array([True, False, True])
+        for key in [None, np.nan, NA]:
+            assert key in index
+            result = index.get_loc(key)
+            tm.assert_numpy_array_equal(result, expected)
+
+        for key in [NaT, np.timedelta64("NaT", "ns"), np.datetime64("NaT", "ns")]:
+            with pytest.raises(KeyError, match=str(key)):
+                index.get_loc(key)
+
+
+class TestGetIndexer:
+    @pytest.mark.parametrize(
+        "query, expected",
+        [
+            ([Interval(2, 4, closed="right")], [1]),
+            ([Interval(2, 4, closed="left")], [-1]),
+            ([Interval(2, 4, closed="both")], [-1]),
+            ([Interval(2, 4, closed="neither")], [-1]),
+            ([Interval(1, 4, closed="right")], [-1]),
+            ([Interval(0, 4, closed="right")], [-1]),
+            ([Interval(0.5, 1.5, closed="right")], [-1]),
+            ([Interval(2, 4, closed="right"), Interval(0, 1, closed="right")], [1, -1]),
+            ([Interval(2, 4, closed="right"), Interval(2, 4, closed="right")], [1, 1]),
+            ([Interval(5, 7, closed="right"), Interval(2, 4, closed="right")], [2, 1]),
+            ([Interval(2, 4, closed="right"), Interval(2, 4, closed="left")], [1, -1]),
+        ],
+    )
+    def test_get_indexer_with_interval(self, query, expected):
+        tuples = [(0, 2), (2, 4), (5, 7)]
+        index = IntervalIndex.from_tuples(tuples, closed="right")
+
+        result = index.get_indexer(query)
+        expected = np.array(expected, dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "query, expected",
+        [
+            ([-0.5], [-1]),
+            ([0], [-1]),
+            ([0.5], [0]),
+            ([1], [0]),
+            ([1.5], [1]),
+            ([2], [1]),
+            ([2.5], [-1]),
+            ([3], [-1]),
+            ([3.5], [2]),
+            ([4], [2]),
+            ([4.5], [-1]),
+            ([1, 2], [0, 1]),
+            ([1, 2, 3], [0, 1, -1]),
+            ([1, 2, 3, 4], [0, 1, -1, 2]),
+            ([1, 2, 3, 4, 2], [0, 1, -1, 2, 1]),
+        ],
+    )
+    def test_get_indexer_with_int_and_float(self, query, expected):
+        tuples = [(0, 1), (1, 2), (3, 4)]
+        index = IntervalIndex.from_tuples(tuples, closed="right")
+
+        result = index.get_indexer(query)
+        expected = np.array(expected, dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("item", [[3], np.arange(0.5, 5, 0.5)])
+    def test_get_indexer_length_one(self, item, closed):
+        # GH 17284
+        index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
+        result = index.get_indexer(item)
+        expected = np.array([0] * len(item), dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("size", [1, 5])
+    def test_get_indexer_length_one_interval(self, size, closed):
+        # GH 17284
+        index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
+        result = index.get_indexer([Interval(0, 5, closed)] * size)
+        expected = np.array([0] * size, dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "target",
+        [
+            IntervalIndex.from_tuples([(7, 8), (1, 2), (3, 4), (0, 1)]),
+            IntervalIndex.from_tuples([(0, 1), (1, 2), (3, 4), np.nan]),
+            IntervalIndex.from_tuples([(0, 1), (1, 2), (3, 4)], closed="both"),
+            [-1, 0, 0.5, 1, 2, 2.5, np.nan],
+            ["foo", "foo", "bar", "baz"],
+        ],
+    )
+    def test_get_indexer_categorical(self, target, ordered):
+        # GH 30063: categorical and non-categorical results should be consistent
+        index = IntervalIndex.from_tuples([(0, 1), (1, 2), (3, 4)])
+        categorical_target = CategoricalIndex(target, ordered=ordered)
+
+        result = index.get_indexer(categorical_target)
+        expected = index.get_indexer(target)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.filterwarnings(
+        "ignore:invalid value encountered in cast:RuntimeWarning"
+    )
+    def test_get_indexer_categorical_with_nans(self):
+        # GH#41934 nans in both index and in target
+        ii = IntervalIndex.from_breaks(range(5))
+        ii2 = ii.append(IntervalIndex([np.nan]))
+        ci2 = CategoricalIndex(ii2)
+
+        result = ii2.get_indexer(ci2)
+        expected = np.arange(5, dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # not-all-matches
+        result = ii2[1:].get_indexer(ci2[::-1])
+        expected = np.array([3, 2, 1, 0, -1], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # non-unique target, non-unique nans
+        result = ii2.get_indexer(ci2.append(ci2))
+        expected = np.array([0, 1, 2, 3, 4, 0, 1, 2, 3, 4], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_get_indexer_datetime(self):
+        ii = IntervalIndex.from_breaks(date_range("2018-01-01", periods=4))
+        # TODO: with mismatched resolution get_indexer currently raises;
+        #  this should probably coerce?
+        target = DatetimeIndex(["2018-01-02"], dtype="M8[ns]")
+        result = ii.get_indexer(target)
+        expected = np.array([0], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = ii.get_indexer(target.astype(str))
+        tm.assert_numpy_array_equal(result, expected)
+
+        # https://github.com/pandas-dev/pandas/issues/47772
+        result = ii.get_indexer(target.asi8)
+        expected = np.array([-1], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "tuples, closed",
+        [
+            ([(0, 2), (1, 3), (3, 4)], "neither"),
+            ([(0, 5), (1, 4), (6, 7)], "left"),
+            ([(0, 1), (0, 1), (1, 2)], "right"),
+            ([(0, 1), (2, 3), (3, 4)], "both"),
+        ],
+    )
+    def test_get_indexer_errors(self, tuples, closed):
+        # IntervalIndex needs non-overlapping for uniqueness when querying
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+
+        msg = (
+            "cannot handle overlapping indices; use "
+            "IntervalIndex.get_indexer_non_unique"
+        )
+        with pytest.raises(InvalidIndexError, match=msg):
+            index.get_indexer([0, 2])
+
+    @pytest.mark.parametrize(
+        "query, expected",
+        [
+            ([-0.5], ([-1], [0])),
+            ([0], ([0], [])),
+            ([0.5], ([0], [])),
+            ([1], ([0, 1], [])),
+            ([1.5], ([0, 1], [])),
+            ([2], ([0, 1, 2], [])),
+            ([2.5], ([1, 2], [])),
+            ([3], ([2], [])),
+            ([3.5], ([2], [])),
+            ([4], ([-1], [0])),
+            ([4.5], ([-1], [0])),
+            ([1, 2], ([0, 1, 0, 1, 2], [])),
+            ([1, 2, 3], ([0, 1, 0, 1, 2, 2], [])),
+            ([1, 2, 3, 4], ([0, 1, 0, 1, 2, 2, -1], [3])),
+            ([1, 2, 3, 4, 2], ([0, 1, 0, 1, 2, 2, -1, 0, 1, 2], [3])),
+        ],
+    )
+    def test_get_indexer_non_unique_with_int_and_float(self, query, expected):
+        tuples = [(0, 2.5), (1, 3), (2, 4)]
+        index = IntervalIndex.from_tuples(tuples, closed="left")
+
+        result_indexer, result_missing = index.get_indexer_non_unique(query)
+        expected_indexer = np.array(expected[0], dtype="intp")
+        expected_missing = np.array(expected[1], dtype="intp")
+
+        tm.assert_numpy_array_equal(result_indexer, expected_indexer)
+        tm.assert_numpy_array_equal(result_missing, expected_missing)
+
+        # TODO we may also want to test get_indexer for the case when
+        # the intervals are duplicated, decreasing, non-monotonic, etc..
+
+    def test_get_indexer_non_monotonic(self):
+        # GH 16410
+        idx1 = IntervalIndex.from_tuples([(2, 3), (4, 5), (0, 1)])
+        idx2 = IntervalIndex.from_tuples([(0, 1), (2, 3), (6, 7), (8, 9)])
+        result = idx1.get_indexer(idx2)
+        expected = np.array([2, 0, -1, -1], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = idx1.get_indexer(idx1[1:])
+        expected = np.array([1, 2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_get_indexer_with_nans(self):
+        # GH#41831
+        index = IntervalIndex([np.nan, np.nan])
+        other = IntervalIndex([np.nan])
+
+        assert not index._index_as_unique
+
+        result = index.get_indexer_for(other)
+        expected = np.array([0, 1], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_get_index_non_unique_non_monotonic(self):
+        # GH#44084 (root cause)
+        index = IntervalIndex.from_tuples(
+            [(0.0, 1.0), (1.0, 2.0), (0.0, 1.0), (1.0, 2.0)]
+        )
+
+        result, _ = index.get_indexer_non_unique([Interval(1.0, 2.0)])
+        expected = np.array([1, 3], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_get_indexer_multiindex_with_intervals(self):
+        # GH#44084 (MultiIndex case as reported)
+        interval_index = IntervalIndex.from_tuples(
+            [(2.0, 3.0), (0.0, 1.0), (1.0, 2.0)], name="interval"
+        )
+        foo_index = Index([1, 2, 3], name="foo")
+
+        multi_index = MultiIndex.from_product([foo_index, interval_index])
+
+        result = multi_index.get_level_values("interval").get_indexer_for(
+            [Interval(0.0, 1.0)]
+        )
+        expected = np.array([1, 4, 7], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("box", [IntervalIndex, array, list])
+    def test_get_indexer_interval_index(self, box):
+        # GH#30178
+        rng = period_range("2022-07-01", freq="D", periods=3)
+        idx = box(interval_range(Timestamp("2022-07-01"), freq="3D", periods=3))
+
+        actual = rng.get_indexer(idx)
+        expected = np.array([-1, -1, -1], dtype=np.intp)
+        tm.assert_numpy_array_equal(actual, expected)
+
+    def test_get_indexer_read_only(self):
+        idx = interval_range(start=0, end=5)
+        arr = np.array([1, 2])
+        arr.flags.writeable = False
+        result = idx.get_indexer(arr)
+        expected = np.array([0, 1])
+        tm.assert_numpy_array_equal(result, expected, check_dtype=False)
+
+        result = idx.get_indexer_non_unique(arr)[0]
+        tm.assert_numpy_array_equal(result, expected, check_dtype=False)
+
+
+class TestSliceLocs:
+    def test_slice_locs_with_interval(self):
+        # increasing monotonically
+        index = IntervalIndex.from_tuples([(0, 2), (1, 3), (2, 4)])
+
+        assert index.slice_locs(start=Interval(0, 2), end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(start=Interval(0, 2)) == (0, 3)
+        assert index.slice_locs(end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(end=Interval(0, 2)) == (0, 1)
+        assert index.slice_locs(start=Interval(2, 4), end=Interval(0, 2)) == (2, 1)
+
+        # decreasing monotonically
+        index = IntervalIndex.from_tuples([(2, 4), (1, 3), (0, 2)])
+
+        assert index.slice_locs(start=Interval(0, 2), end=Interval(2, 4)) == (2, 1)
+        assert index.slice_locs(start=Interval(0, 2)) == (2, 3)
+        assert index.slice_locs(end=Interval(2, 4)) == (0, 1)
+        assert index.slice_locs(end=Interval(0, 2)) == (0, 3)
+        assert index.slice_locs(start=Interval(2, 4), end=Interval(0, 2)) == (0, 3)
+
+        # sorted duplicates
+        index = IntervalIndex.from_tuples([(0, 2), (0, 2), (2, 4)])
+
+        assert index.slice_locs(start=Interval(0, 2), end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(start=Interval(0, 2)) == (0, 3)
+        assert index.slice_locs(end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(end=Interval(0, 2)) == (0, 2)
+        assert index.slice_locs(start=Interval(2, 4), end=Interval(0, 2)) == (2, 2)
+
+        # unsorted duplicates
+        index = IntervalIndex.from_tuples([(0, 2), (2, 4), (0, 2)])
+
+        with pytest.raises(
+            KeyError,
+            match=re.escape(
+                '"Cannot get left slice bound for non-unique label: '
+                "Interval(0, 2, closed='right')\""
+            ),
+        ):
+            index.slice_locs(start=Interval(0, 2), end=Interval(2, 4))
+
+        with pytest.raises(
+            KeyError,
+            match=re.escape(
+                '"Cannot get left slice bound for non-unique label: '
+                "Interval(0, 2, closed='right')\""
+            ),
+        ):
+            index.slice_locs(start=Interval(0, 2))
+
+        assert index.slice_locs(end=Interval(2, 4)) == (0, 2)
+
+        with pytest.raises(
+            KeyError,
+            match=re.escape(
+                '"Cannot get right slice bound for non-unique label: '
+                "Interval(0, 2, closed='right')\""
+            ),
+        ):
+            index.slice_locs(end=Interval(0, 2))
+
+        with pytest.raises(
+            KeyError,
+            match=re.escape(
+                '"Cannot get right slice bound for non-unique label: '
+                "Interval(0, 2, closed='right')\""
+            ),
+        ):
+            index.slice_locs(start=Interval(2, 4), end=Interval(0, 2))
+
+        # another unsorted duplicates
+        index = IntervalIndex.from_tuples([(0, 2), (0, 2), (2, 4), (1, 3)])
+
+        assert index.slice_locs(start=Interval(0, 2), end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(start=Interval(0, 2)) == (0, 4)
+        assert index.slice_locs(end=Interval(2, 4)) == (0, 3)
+        assert index.slice_locs(end=Interval(0, 2)) == (0, 2)
+        assert index.slice_locs(start=Interval(2, 4), end=Interval(0, 2)) == (2, 2)
+
+    def test_slice_locs_with_ints_and_floats_succeeds(self):
+        # increasing non-overlapping
+        index = IntervalIndex.from_tuples([(0, 1), (1, 2), (3, 4)])
+
+        assert index.slice_locs(0, 1) == (0, 1)
+        assert index.slice_locs(0, 2) == (0, 2)
+        assert index.slice_locs(0, 3) == (0, 2)
+        assert index.slice_locs(3, 1) == (2, 1)
+        assert index.slice_locs(3, 4) == (2, 3)
+        assert index.slice_locs(0, 4) == (0, 3)
+
+        # decreasing non-overlapping
+        index = IntervalIndex.from_tuples([(3, 4), (1, 2), (0, 1)])
+        assert index.slice_locs(0, 1) == (3, 3)
+        assert index.slice_locs(0, 2) == (3, 2)
+        assert index.slice_locs(0, 3) == (3, 1)
+        assert index.slice_locs(3, 1) == (1, 3)
+        assert index.slice_locs(3, 4) == (1, 1)
+        assert index.slice_locs(0, 4) == (3, 1)
+
+    @pytest.mark.parametrize("query", [[0, 1], [0, 2], [0, 3], [0, 4]])
+    @pytest.mark.parametrize(
+        "tuples",
+        [
+            [(0, 2), (1, 3), (2, 4)],
+            [(2, 4), (1, 3), (0, 2)],
+            [(0, 2), (0, 2), (2, 4)],
+            [(0, 2), (2, 4), (0, 2)],
+            [(0, 2), (0, 2), (2, 4), (1, 3)],
+        ],
+    )
+    def test_slice_locs_with_ints_and_floats_errors(self, tuples, query):
+        start, stop = query
+        index = IntervalIndex.from_tuples(tuples)
+        with pytest.raises(
+            KeyError,
+            match=(
+                "'can only get slices from an IntervalIndex if bounds are "
+                "non-overlapping and all monotonic increasing or decreasing'"
+            ),
+        ):
+            index.slice_locs(start, stop)
+
+
+class TestPutmask:
+    @pytest.mark.parametrize("tz", ["US/Pacific", None])
+    def test_putmask_dt64(self, tz):
+        # GH#37968
+        dti = date_range("2016-01-01", periods=9, tz=tz)
+        idx = IntervalIndex.from_breaks(dti)
+        mask = np.zeros(idx.shape, dtype=bool)
+        mask[0:3] = True
+
+        result = idx.putmask(mask, idx[-1])
+        expected = IntervalIndex([idx[-1]] * 3 + list(idx[3:]))
+        tm.assert_index_equal(result, expected)
+
+    def test_putmask_td64(self):
+        # GH#37968
+        dti = date_range("2016-01-01", periods=9)
+        tdi = dti - dti[0]
+        idx = IntervalIndex.from_breaks(tdi)
+        mask = np.zeros(idx.shape, dtype=bool)
+        mask[0:3] = True
+
+        result = idx.putmask(mask, idx[-1])
+        expected = IntervalIndex([idx[-1]] * 3 + list(idx[3:]))
+        tm.assert_index_equal(result, expected)
+
+
+class TestContains:
+    # .__contains__, not .contains
+
+    def test_contains_dunder(self):
+        index = IntervalIndex.from_arrays([0, 1], [1, 2], closed="right")
+
+        # __contains__ requires perfect matches to intervals.
+        assert 0 not in index
+        assert 1 not in index
+        assert 2 not in index
+
+        assert Interval(0, 1, closed="right") in index
+        assert Interval(0, 2, closed="right") not in index
+        assert Interval(0, 0.5, closed="right") not in index
+        assert Interval(3, 5, closed="right") not in index
+        assert Interval(-1, 0, closed="left") not in index
+        assert Interval(0, 1, closed="left") not in index
+        assert Interval(0, 1, closed="both") not in index

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_interval.py

@@ -0,0 +1,918 @@
+from itertools import permutations
+import re
+
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    Index,
+    Interval,
+    IntervalIndex,
+    Timedelta,
+    Timestamp,
+    date_range,
+    interval_range,
+    isna,
+    notna,
+    timedelta_range,
+)
+import pandas._testing as tm
+import pandas.core.common as com
+
+
+@pytest.fixture(params=[None, "foo"])
+def name(request):
+    return request.param
+
+
+class TestIntervalIndex:
+    index = IntervalIndex.from_arrays([0, 1], [1, 2])
+
+    def create_index(self, closed="right"):
+        return IntervalIndex.from_breaks(range(11), closed=closed)
+
+    def create_index_with_nan(self, closed="right"):
+        mask = [True, False] + [True] * 8
+        return IntervalIndex.from_arrays(
+            np.where(mask, np.arange(10), np.nan),
+            np.where(mask, np.arange(1, 11), np.nan),
+            closed=closed,
+        )
+
+    def test_properties(self, closed):
+        index = self.create_index(closed=closed)
+        assert len(index) == 10
+        assert index.size == 10
+        assert index.shape == (10,)
+
+        tm.assert_index_equal(index.left, Index(np.arange(10, dtype=np.int64)))
+        tm.assert_index_equal(index.right, Index(np.arange(1, 11, dtype=np.int64)))
+        tm.assert_index_equal(index.mid, Index(np.arange(0.5, 10.5, dtype=np.float64)))
+
+        assert index.closed == closed
+
+        ivs = [
+            Interval(left, right, closed)
+            for left, right in zip(range(10), range(1, 11))
+        ]
+        expected = np.array(ivs, dtype=object)
+        tm.assert_numpy_array_equal(np.asarray(index), expected)
+
+        # with nans
+        index = self.create_index_with_nan(closed=closed)
+        assert len(index) == 10
+        assert index.size == 10
+        assert index.shape == (10,)
+
+        expected_left = Index([0, np.nan, 2, 3, 4, 5, 6, 7, 8, 9])
+        expected_right = expected_left + 1
+        expected_mid = expected_left + 0.5
+        tm.assert_index_equal(index.left, expected_left)
+        tm.assert_index_equal(index.right, expected_right)
+        tm.assert_index_equal(index.mid, expected_mid)
+
+        assert index.closed == closed
+
+        ivs = [
+            Interval(left, right, closed) if notna(left) else np.nan
+            for left, right in zip(expected_left, expected_right)
+        ]
+        expected = np.array(ivs, dtype=object)
+        tm.assert_numpy_array_equal(np.asarray(index), expected)
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            [1, 1, 2, 5, 15, 53, 217, 1014, 5335, 31240, 201608],
+            [-np.inf, -100, -10, 0.5, 1, 1.5, 3.8, 101, 202, np.inf],
+            date_range("2017-01-01", "2017-01-04"),
+            pytest.param(
+                date_range("2017-01-01", "2017-01-04", unit="s"),
+                marks=pytest.mark.xfail(reason="mismatched result unit"),
+            ),
+            pd.to_timedelta(["1ns", "2ms", "3s", "4min", "5h", "6D"]),
+        ],
+    )
+    def test_length(self, closed, breaks):
+        # GH 18789
+        index = IntervalIndex.from_breaks(breaks, closed=closed)
+        result = index.length
+        expected = Index(iv.length for iv in index)
+        tm.assert_index_equal(result, expected)
+
+        # with NA
+        index = index.insert(1, np.nan)
+        result = index.length
+        expected = Index(iv.length if notna(iv) else iv for iv in index)
+        tm.assert_index_equal(result, expected)
+
+    def test_with_nans(self, closed):
+        index = self.create_index(closed=closed)
+        assert index.hasnans is False
+
+        result = index.isna()
+        expected = np.zeros(len(index), dtype=bool)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = index.notna()
+        expected = np.ones(len(index), dtype=bool)
+        tm.assert_numpy_array_equal(result, expected)
+
+        index = self.create_index_with_nan(closed=closed)
+        assert index.hasnans is True
+
+        result = index.isna()
+        expected = np.array([False, True] + [False] * (len(index) - 2))
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = index.notna()
+        expected = np.array([True, False] + [True] * (len(index) - 2))
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_copy(self, closed):
+        expected = self.create_index(closed=closed)
+
+        result = expected.copy()
+        assert result.equals(expected)
+
+        result = expected.copy(deep=True)
+        assert result.equals(expected)
+        assert result.left is not expected.left
+
+    def test_ensure_copied_data(self, closed):
+        # exercise the copy flag in the constructor
+
+        # not copying
+        index = self.create_index(closed=closed)
+        result = IntervalIndex(index, copy=False)
+        tm.assert_numpy_array_equal(
+            index.left.values, result.left.values, check_same="same"
+        )
+        tm.assert_numpy_array_equal(
+            index.right.values, result.right.values, check_same="same"
+        )
+
+        # by-definition make a copy
+        result = IntervalIndex(np.array(index), copy=False)
+        tm.assert_numpy_array_equal(
+            index.left.values, result.left.values, check_same="copy"
+        )
+        tm.assert_numpy_array_equal(
+            index.right.values, result.right.values, check_same="copy"
+        )
+
+    def test_delete(self, closed):
+        breaks = np.arange(1, 11, dtype=np.int64)
+        expected = IntervalIndex.from_breaks(breaks, closed=closed)
+        result = self.create_index(closed=closed).delete(0)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "data",
+        [
+            interval_range(0, periods=10, closed="neither"),
+            interval_range(1.7, periods=8, freq=2.5, closed="both"),
+            interval_range(Timestamp("20170101"), periods=12, closed="left"),
+            interval_range(Timedelta("1 day"), periods=6, closed="right"),
+        ],
+    )
+    def test_insert(self, data):
+        item = data[0]
+        idx_item = IntervalIndex([item])
+
+        # start
+        expected = idx_item.append(data)
+        result = data.insert(0, item)
+        tm.assert_index_equal(result, expected)
+
+        # end
+        expected = data.append(idx_item)
+        result = data.insert(len(data), item)
+        tm.assert_index_equal(result, expected)
+
+        # mid
+        expected = data[:3].append(idx_item).append(data[3:])
+        result = data.insert(3, item)
+        tm.assert_index_equal(result, expected)
+
+        # invalid type
+        res = data.insert(1, "foo")
+        expected = data.astype(object).insert(1, "foo")
+        tm.assert_index_equal(res, expected)
+
+        msg = "can only insert Interval objects and NA into an IntervalArray"
+        with pytest.raises(TypeError, match=msg):
+            data._data.insert(1, "foo")
+
+        # invalid closed
+        msg = "'value.closed' is 'left', expected 'right'."
+        for closed in {"left", "right", "both", "neither"} - {item.closed}:
+            msg = f"'value.closed' is '{closed}', expected '{item.closed}'."
+            bad_item = Interval(item.left, item.right, closed=closed)
+            res = data.insert(1, bad_item)
+            expected = data.astype(object).insert(1, bad_item)
+            tm.assert_index_equal(res, expected)
+            with pytest.raises(ValueError, match=msg):
+                data._data.insert(1, bad_item)
+
+        # GH 18295 (test missing)
+        na_idx = IntervalIndex([np.nan], closed=data.closed)
+        for na in [np.nan, None, pd.NA]:
+            expected = data[:1].append(na_idx).append(data[1:])
+            result = data.insert(1, na)
+            tm.assert_index_equal(result, expected)
+
+        if data.left.dtype.kind not in ["m", "M"]:
+            # trying to insert pd.NaT into a numeric-dtyped Index should cast
+            expected = data.astype(object).insert(1, pd.NaT)
+
+            msg = "can only insert Interval objects and NA into an IntervalArray"
+            with pytest.raises(TypeError, match=msg):
+                data._data.insert(1, pd.NaT)
+
+        result = data.insert(1, pd.NaT)
+        tm.assert_index_equal(result, expected)
+
+    def test_is_unique_interval(self, closed):
+        """
+        Interval specific tests for is_unique in addition to base class tests
+        """
+        # unique overlapping - distinct endpoints
+        idx = IntervalIndex.from_tuples([(0, 1), (0.5, 1.5)], closed=closed)
+        assert idx.is_unique is True
+
+        # unique overlapping - shared endpoints
+        idx = IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
+        assert idx.is_unique is True
+
+        # unique nested
+        idx = IntervalIndex.from_tuples([(-1, 1), (-2, 2)], closed=closed)
+        assert idx.is_unique is True
+
+        # unique NaN
+        idx = IntervalIndex.from_tuples([(np.nan, np.nan)], closed=closed)
+        assert idx.is_unique is True
+
+        # non-unique NaN
+        idx = IntervalIndex.from_tuples(
+            [(np.nan, np.nan), (np.nan, np.nan)], closed=closed
+        )
+        assert idx.is_unique is False
+
+    def test_monotonic(self, closed):
+        # increasing non-overlapping
+        idx = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)], closed=closed)
+        assert idx.is_monotonic_increasing is True
+        assert idx._is_strictly_monotonic_increasing is True
+        assert idx.is_monotonic_decreasing is False
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # decreasing non-overlapping
+        idx = IntervalIndex.from_tuples([(4, 5), (2, 3), (1, 2)], closed=closed)
+        assert idx.is_monotonic_increasing is False
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is True
+        assert idx._is_strictly_monotonic_decreasing is True
+
+        # unordered non-overlapping
+        idx = IntervalIndex.from_tuples([(0, 1), (4, 5), (2, 3)], closed=closed)
+        assert idx.is_monotonic_increasing is False
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is False
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # increasing overlapping
+        idx = IntervalIndex.from_tuples([(0, 2), (0.5, 2.5), (1, 3)], closed=closed)
+        assert idx.is_monotonic_increasing is True
+        assert idx._is_strictly_monotonic_increasing is True
+        assert idx.is_monotonic_decreasing is False
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # decreasing overlapping
+        idx = IntervalIndex.from_tuples([(1, 3), (0.5, 2.5), (0, 2)], closed=closed)
+        assert idx.is_monotonic_increasing is False
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is True
+        assert idx._is_strictly_monotonic_decreasing is True
+
+        # unordered overlapping
+        idx = IntervalIndex.from_tuples([(0.5, 2.5), (0, 2), (1, 3)], closed=closed)
+        assert idx.is_monotonic_increasing is False
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is False
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # increasing overlapping shared endpoints
+        idx = IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)], closed=closed)
+        assert idx.is_monotonic_increasing is True
+        assert idx._is_strictly_monotonic_increasing is True
+        assert idx.is_monotonic_decreasing is False
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # decreasing overlapping shared endpoints
+        idx = IntervalIndex.from_tuples([(2, 3), (1, 3), (1, 2)], closed=closed)
+        assert idx.is_monotonic_increasing is False
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is True
+        assert idx._is_strictly_monotonic_decreasing is True
+
+        # stationary
+        idx = IntervalIndex.from_tuples([(0, 1), (0, 1)], closed=closed)
+        assert idx.is_monotonic_increasing is True
+        assert idx._is_strictly_monotonic_increasing is False
+        assert idx.is_monotonic_decreasing is True
+        assert idx._is_strictly_monotonic_decreasing is False
+
+        # empty
+        idx = IntervalIndex([], closed=closed)
+        assert idx.is_monotonic_increasing is True
+        assert idx._is_strictly_monotonic_increasing is True
+        assert idx.is_monotonic_decreasing is True
+        assert idx._is_strictly_monotonic_decreasing is True
+
+    def test_is_monotonic_with_nans(self):
+        # GH#41831
+        index = IntervalIndex([np.nan, np.nan])
+
+        assert not index.is_monotonic_increasing
+        assert not index._is_strictly_monotonic_increasing
+        assert not index.is_monotonic_increasing
+        assert not index._is_strictly_monotonic_decreasing
+        assert not index.is_monotonic_decreasing
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [
+            date_range("20180101", periods=4),
+            date_range("20180101", periods=4, tz="US/Eastern"),
+            timedelta_range("0 days", periods=4),
+        ],
+        ids=lambda x: str(x.dtype),
+    )
+    def test_maybe_convert_i8(self, breaks):
+        # GH 20636
+        index = IntervalIndex.from_breaks(breaks)
+
+        # intervalindex
+        result = index._maybe_convert_i8(index)
+        expected = IntervalIndex.from_breaks(breaks.asi8)
+        tm.assert_index_equal(result, expected)
+
+        # interval
+        interval = Interval(breaks[0], breaks[1])
+        result = index._maybe_convert_i8(interval)
+        expected = Interval(breaks[0]._value, breaks[1]._value)
+        assert result == expected
+
+        # datetimelike index
+        result = index._maybe_convert_i8(breaks)
+        expected = Index(breaks.asi8)
+        tm.assert_index_equal(result, expected)
+
+        # datetimelike scalar
+        result = index._maybe_convert_i8(breaks[0])
+        expected = breaks[0]._value
+        assert result == expected
+
+        # list-like of datetimelike scalars
+        result = index._maybe_convert_i8(list(breaks))
+        expected = Index(breaks.asi8)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "breaks",
+        [date_range("2018-01-01", periods=5), timedelta_range("0 days", periods=5)],
+    )
+    def test_maybe_convert_i8_nat(self, breaks):
+        # GH 20636
+        index = IntervalIndex.from_breaks(breaks)
+
+        to_convert = breaks._constructor([pd.NaT] * 3).as_unit("ns")
+        expected = Index([np.nan] * 3, dtype=np.float64)
+        result = index._maybe_convert_i8(to_convert)
+        tm.assert_index_equal(result, expected)
+
+        to_convert = to_convert.insert(0, breaks[0])
+        expected = expected.insert(0, float(breaks[0]._value))
+        result = index._maybe_convert_i8(to_convert)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "make_key",
+        [lambda breaks: breaks, list],
+        ids=["lambda", "list"],
+    )
+    def test_maybe_convert_i8_numeric(self, make_key, any_real_numpy_dtype):
+        # GH 20636
+        breaks = np.arange(5, dtype=any_real_numpy_dtype)
+        index = IntervalIndex.from_breaks(breaks)
+        key = make_key(breaks)
+
+        result = index._maybe_convert_i8(key)
+        kind = breaks.dtype.kind
+        expected_dtype = {"i": np.int64, "u": np.uint64, "f": np.float64}[kind]
+        expected = Index(key, dtype=expected_dtype)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "make_key",
+        [
+            IntervalIndex.from_breaks,
+            lambda breaks: Interval(breaks[0], breaks[1]),
+            lambda breaks: breaks[0],
+        ],
+        ids=["IntervalIndex", "Interval", "scalar"],
+    )
+    def test_maybe_convert_i8_numeric_identical(self, make_key, any_real_numpy_dtype):
+        # GH 20636
+        breaks = np.arange(5, dtype=any_real_numpy_dtype)
+        index = IntervalIndex.from_breaks(breaks)
+        key = make_key(breaks)
+
+        # test if _maybe_convert_i8 won't change key if an Interval or IntervalIndex
+        result = index._maybe_convert_i8(key)
+        assert result is key
+
+    @pytest.mark.parametrize(
+        "breaks1, breaks2",
+        permutations(
+            [
+                date_range("20180101", periods=4),
+                date_range("20180101", periods=4, tz="US/Eastern"),
+                timedelta_range("0 days", periods=4),
+            ],
+            2,
+        ),
+        ids=lambda x: str(x.dtype),
+    )
+    @pytest.mark.parametrize(
+        "make_key",
+        [
+            IntervalIndex.from_breaks,
+            lambda breaks: Interval(breaks[0], breaks[1]),
+            lambda breaks: breaks,
+            lambda breaks: breaks[0],
+            list,
+        ],
+        ids=["IntervalIndex", "Interval", "Index", "scalar", "list"],
+    )
+    def test_maybe_convert_i8_errors(self, breaks1, breaks2, make_key):
+        # GH 20636
+        index = IntervalIndex.from_breaks(breaks1)
+        key = make_key(breaks2)
+
+        msg = (
+            f"Cannot index an IntervalIndex of subtype {breaks1.dtype} with "
+            f"values of dtype {breaks2.dtype}"
+        )
+        msg = re.escape(msg)
+        with pytest.raises(ValueError, match=msg):
+            index._maybe_convert_i8(key)
+
+    def test_contains_method(self):
+        # can select values that are IN the range of a value
+        i = IntervalIndex.from_arrays([0, 1], [1, 2])
+
+        expected = np.array([False, False], dtype="bool")
+        actual = i.contains(0)
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = i.contains(3)
+        tm.assert_numpy_array_equal(actual, expected)
+
+        expected = np.array([True, False], dtype="bool")
+        actual = i.contains(0.5)
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = i.contains(1)
+        tm.assert_numpy_array_equal(actual, expected)
+
+        # __contains__ not implemented for "interval in interval", follow
+        # that for the contains method for now
+        with pytest.raises(
+            NotImplementedError, match="contains not implemented for two"
+        ):
+            i.contains(Interval(0, 1))
+
+    def test_dropna(self, closed):
+        expected = IntervalIndex.from_tuples([(0.0, 1.0), (1.0, 2.0)], closed=closed)
+
+        ii = IntervalIndex.from_tuples([(0, 1), (1, 2), np.nan], closed=closed)
+        result = ii.dropna()
+        tm.assert_index_equal(result, expected)
+
+        ii = IntervalIndex.from_arrays([0, 1, np.nan], [1, 2, np.nan], closed=closed)
+        result = ii.dropna()
+        tm.assert_index_equal(result, expected)
+
+    def test_non_contiguous(self, closed):
+        index = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
+        target = [0.5, 1.5, 2.5]
+        actual = index.get_indexer(target)
+        expected = np.array([0, -1, 1], dtype="intp")
+        tm.assert_numpy_array_equal(actual, expected)
+
+        assert 1.5 not in index
+
+    def test_isin(self, closed):
+        index = self.create_index(closed=closed)
+
+        expected = np.array([True] + [False] * (len(index) - 1))
+        result = index.isin(index[:1])
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = index.isin([index[0]])
+        tm.assert_numpy_array_equal(result, expected)
+
+        other = IntervalIndex.from_breaks(np.arange(-2, 10), closed=closed)
+        expected = np.array([True] * (len(index) - 1) + [False])
+        result = index.isin(other)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = index.isin(other.tolist())
+        tm.assert_numpy_array_equal(result, expected)
+
+        for other_closed in ["right", "left", "both", "neither"]:
+            other = self.create_index(closed=other_closed)
+            expected = np.repeat(closed == other_closed, len(index))
+            result = index.isin(other)
+            tm.assert_numpy_array_equal(result, expected)
+
+            result = index.isin(other.tolist())
+            tm.assert_numpy_array_equal(result, expected)
+
+    def test_comparison(self):
+        actual = Interval(0, 1) < self.index
+        expected = np.array([False, True])
+        tm.assert_numpy_array_equal(actual, expected)
+
+        actual = Interval(0.5, 1.5) < self.index
+        expected = np.array([False, True])
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = self.index > Interval(0.5, 1.5)
+        tm.assert_numpy_array_equal(actual, expected)
+
+        actual = self.index == self.index
+        expected = np.array([True, True])
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = self.index <= self.index
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = self.index >= self.index
+        tm.assert_numpy_array_equal(actual, expected)
+
+        actual = self.index < self.index
+        expected = np.array([False, False])
+        tm.assert_numpy_array_equal(actual, expected)
+        actual = self.index > self.index
+        tm.assert_numpy_array_equal(actual, expected)
+
+        actual = self.index == IntervalIndex.from_breaks([0, 1, 2], "left")
+        tm.assert_numpy_array_equal(actual, expected)
+
+        actual = self.index == self.index.values
+        tm.assert_numpy_array_equal(actual, np.array([True, True]))
+        actual = self.index.values == self.index
+        tm.assert_numpy_array_equal(actual, np.array([True, True]))
+        actual = self.index <= self.index.values
+        tm.assert_numpy_array_equal(actual, np.array([True, True]))
+        actual = self.index != self.index.values
+        tm.assert_numpy_array_equal(actual, np.array([False, False]))
+        actual = self.index > self.index.values
+        tm.assert_numpy_array_equal(actual, np.array([False, False]))
+        actual = self.index.values > self.index
+        tm.assert_numpy_array_equal(actual, np.array([False, False]))
+
+        # invalid comparisons
+        actual = self.index == 0
+        tm.assert_numpy_array_equal(actual, np.array([False, False]))
+        actual = self.index == self.index.left
+        tm.assert_numpy_array_equal(actual, np.array([False, False]))
+
+        msg = "|".join(
+            [
+                "not supported between instances of 'int' and '.*.Interval'",
+                r"Invalid comparison between dtype=interval\[int64, right\] and ",
+            ]
+        )
+        with pytest.raises(TypeError, match=msg):
+            self.index > 0
+        with pytest.raises(TypeError, match=msg):
+            self.index <= 0
+        with pytest.raises(TypeError, match=msg):
+            self.index > np.arange(2)
+
+        msg = "Lengths must match to compare"
+        with pytest.raises(ValueError, match=msg):
+            self.index > np.arange(3)
+
+    def test_missing_values(self, closed):
+        idx = Index(
+            [np.nan, Interval(0, 1, closed=closed), Interval(1, 2, closed=closed)]
+        )
+        idx2 = IntervalIndex.from_arrays([np.nan, 0, 1], [np.nan, 1, 2], closed=closed)
+        assert idx.equals(idx2)
+
+        msg = (
+            "missing values must be missing in the same location both left "
+            "and right sides"
+        )
+        with pytest.raises(ValueError, match=msg):
+            IntervalIndex.from_arrays(
+                [np.nan, 0, 1], np.array([0, 1, 2]), closed=closed
+            )
+
+        tm.assert_numpy_array_equal(isna(idx), np.array([True, False, False]))
+
+    def test_sort_values(self, closed):
+        index = self.create_index(closed=closed)
+
+        result = index.sort_values()
+        tm.assert_index_equal(result, index)
+
+        result = index.sort_values(ascending=False)
+        tm.assert_index_equal(result, index[::-1])
+
+        # with nan
+        index = IntervalIndex([Interval(1, 2), np.nan, Interval(0, 1)])
+
+        result = index.sort_values()
+        expected = IntervalIndex([Interval(0, 1), Interval(1, 2), np.nan])
+        tm.assert_index_equal(result, expected)
+
+        result = index.sort_values(ascending=False, na_position="first")
+        expected = IntervalIndex([np.nan, Interval(1, 2), Interval(0, 1)])
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("tz", [None, "US/Eastern"])
+    def test_datetime(self, tz):
+        start = Timestamp("2000-01-01", tz=tz)
+        dates = date_range(start=start, periods=10)
+        index = IntervalIndex.from_breaks(dates)
+
+        # test mid
+        start = Timestamp("2000-01-01T12:00", tz=tz)
+        expected = date_range(start=start, periods=9)
+        tm.assert_index_equal(index.mid, expected)
+
+        # __contains__ doesn't check individual points
+        assert Timestamp("2000-01-01", tz=tz) not in index
+        assert Timestamp("2000-01-01T12", tz=tz) not in index
+        assert Timestamp("2000-01-02", tz=tz) not in index
+        iv_true = Interval(
+            Timestamp("2000-01-02", tz=tz), Timestamp("2000-01-03", tz=tz)
+        )
+        iv_false = Interval(
+            Timestamp("1999-12-31", tz=tz), Timestamp("2000-01-01", tz=tz)
+        )
+        assert iv_true in index
+        assert iv_false not in index
+
+        # .contains does check individual points
+        assert not index.contains(Timestamp("2000-01-01", tz=tz)).any()
+        assert index.contains(Timestamp("2000-01-01T12", tz=tz)).any()
+        assert index.contains(Timestamp("2000-01-02", tz=tz)).any()
+
+        # test get_indexer
+        start = Timestamp("1999-12-31T12:00", tz=tz)
+        target = date_range(start=start, periods=7, freq="12h")
+        actual = index.get_indexer(target)
+        expected = np.array([-1, -1, 0, 0, 1, 1, 2], dtype="intp")
+        tm.assert_numpy_array_equal(actual, expected)
+
+        start = Timestamp("2000-01-08T18:00", tz=tz)
+        target = date_range(start=start, periods=7, freq="6h")
+        actual = index.get_indexer(target)
+        expected = np.array([7, 7, 8, 8, 8, 8, -1], dtype="intp")
+        tm.assert_numpy_array_equal(actual, expected)
+
+    def test_append(self, closed):
+        index1 = IntervalIndex.from_arrays([0, 1], [1, 2], closed=closed)
+        index2 = IntervalIndex.from_arrays([1, 2], [2, 3], closed=closed)
+
+        result = index1.append(index2)
+        expected = IntervalIndex.from_arrays([0, 1, 1, 2], [1, 2, 2, 3], closed=closed)
+        tm.assert_index_equal(result, expected)
+
+        result = index1.append([index1, index2])
+        expected = IntervalIndex.from_arrays(
+            [0, 1, 0, 1, 1, 2], [1, 2, 1, 2, 2, 3], closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        for other_closed in {"left", "right", "both", "neither"} - {closed}:
+            index_other_closed = IntervalIndex.from_arrays(
+                [0, 1], [1, 2], closed=other_closed
+            )
+            result = index1.append(index_other_closed)
+            expected = index1.astype(object).append(index_other_closed.astype(object))
+            tm.assert_index_equal(result, expected)
+
+    def test_is_non_overlapping_monotonic(self, closed):
+        # Should be True in all cases
+        tpls = [(0, 1), (2, 3), (4, 5), (6, 7)]
+        idx = IntervalIndex.from_tuples(tpls, closed=closed)
+        assert idx.is_non_overlapping_monotonic is True
+
+        idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
+        assert idx.is_non_overlapping_monotonic is True
+
+        # Should be False in all cases (overlapping)
+        tpls = [(0, 2), (1, 3), (4, 5), (6, 7)]
+        idx = IntervalIndex.from_tuples(tpls, closed=closed)
+        assert idx.is_non_overlapping_monotonic is False
+
+        idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
+        assert idx.is_non_overlapping_monotonic is False
+
+        # Should be False in all cases (non-monotonic)
+        tpls = [(0, 1), (2, 3), (6, 7), (4, 5)]
+        idx = IntervalIndex.from_tuples(tpls, closed=closed)
+        assert idx.is_non_overlapping_monotonic is False
+
+        idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
+        assert idx.is_non_overlapping_monotonic is False
+
+        # Should be False for closed='both', otherwise True (GH16560)
+        if closed == "both":
+            idx = IntervalIndex.from_breaks(range(4), closed=closed)
+            assert idx.is_non_overlapping_monotonic is False
+        else:
+            idx = IntervalIndex.from_breaks(range(4), closed=closed)
+            assert idx.is_non_overlapping_monotonic is True
+
+    @pytest.mark.parametrize(
+        "start, shift, na_value",
+        [
+            (0, 1, np.nan),
+            (Timestamp("2018-01-01"), Timedelta("1 day"), pd.NaT),
+            (Timedelta("0 days"), Timedelta("1 day"), pd.NaT),
+        ],
+    )
+    def test_is_overlapping(self, start, shift, na_value, closed):
+        # GH 23309
+        # see test_interval_tree.py for extensive tests; interface tests here
+
+        # non-overlapping
+        tuples = [(start + n * shift, start + (n + 1) * shift) for n in (0, 2, 4)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        assert index.is_overlapping is False
+
+        # non-overlapping with NA
+        tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        assert index.is_overlapping is False
+
+        # overlapping
+        tuples = [(start + n * shift, start + (n + 2) * shift) for n in range(3)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        assert index.is_overlapping is True
+
+        # overlapping with NA
+        tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        assert index.is_overlapping is True
+
+        # common endpoints
+        tuples = [(start + n * shift, start + (n + 1) * shift) for n in range(3)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        result = index.is_overlapping
+        expected = closed == "both"
+        assert result is expected
+
+        # common endpoints with NA
+        tuples = [(na_value, na_value)] + tuples + [(na_value, na_value)]
+        index = IntervalIndex.from_tuples(tuples, closed=closed)
+        result = index.is_overlapping
+        assert result is expected
+
+        # intervals with duplicate left values
+        a = [10, 15, 20, 25, 30, 35, 40, 45, 45, 50, 55, 60, 65, 70, 75, 80, 85]
+        b = [15, 20, 25, 30, 35, 40, 45, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90]
+        index = IntervalIndex.from_arrays(a, b, closed="right")
+        result = index.is_overlapping
+        assert result is False
+
+    @pytest.mark.parametrize(
+        "tuples",
+        [
+            list(zip(range(10), range(1, 11))),
+            list(
+                zip(
+                    date_range("20170101", periods=10),
+                    date_range("20170101", periods=10),
+                )
+            ),
+            list(
+                zip(
+                    timedelta_range("0 days", periods=10),
+                    timedelta_range("1 day", periods=10),
+                )
+            ),
+        ],
+    )
+    def test_to_tuples(self, tuples):
+        # GH 18756
+        idx = IntervalIndex.from_tuples(tuples)
+        result = idx.to_tuples()
+        expected = Index(com.asarray_tuplesafe(tuples))
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "tuples",
+        [
+            list(zip(range(10), range(1, 11))) + [np.nan],
+            list(
+                zip(
+                    date_range("20170101", periods=10),
+                    date_range("20170101", periods=10),
+                )
+            )
+            + [np.nan],
+            list(
+                zip(
+                    timedelta_range("0 days", periods=10),
+                    timedelta_range("1 day", periods=10),
+                )
+            )
+            + [np.nan],
+        ],
+    )
+    @pytest.mark.parametrize("na_tuple", [True, False])
+    def test_to_tuples_na(self, tuples, na_tuple):
+        # GH 18756
+        idx = IntervalIndex.from_tuples(tuples)
+        result = idx.to_tuples(na_tuple=na_tuple)
+
+        # check the non-NA portion
+        expected_notna = Index(com.asarray_tuplesafe(tuples[:-1]))
+        result_notna = result[:-1]
+        tm.assert_index_equal(result_notna, expected_notna)
+
+        # check the NA portion
+        result_na = result[-1]
+        if na_tuple:
+            assert isinstance(result_na, tuple)
+            assert len(result_na) == 2
+            assert all(isna(x) for x in result_na)
+        else:
+            assert isna(result_na)
+
+    def test_nbytes(self):
+        # GH 19209
+        left = np.arange(0, 4, dtype="i8")
+        right = np.arange(1, 5, dtype="i8")
+
+        result = IntervalIndex.from_arrays(left, right).nbytes
+        expected = 64  # 4 * 8 * 2
+        assert result == expected
+
+    @pytest.mark.parametrize("new_closed", ["left", "right", "both", "neither"])
+    def test_set_closed(self, name, closed, new_closed):
+        # GH 21670
+        index = interval_range(0, 5, closed=closed, name=name)
+        result = index.set_closed(new_closed)
+        expected = interval_range(0, 5, closed=new_closed, name=name)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("bad_closed", ["foo", 10, "LEFT", True, False])
+    def test_set_closed_errors(self, bad_closed):
+        # GH 21670
+        index = interval_range(0, 5)
+        msg = f"invalid option for 'closed': {bad_closed}"
+        with pytest.raises(ValueError, match=msg):
+            index.set_closed(bad_closed)
+
+    def test_is_all_dates(self):
+        # GH 23576
+        year_2017 = Interval(
+            Timestamp("2017-01-01 00:00:00"), Timestamp("2018-01-01 00:00:00")
+        )
+        year_2017_index = IntervalIndex([year_2017])
+        assert not year_2017_index._is_all_dates
+
+
+def test_dir():
+    # GH#27571 dir(interval_index) should not raise
+    index = IntervalIndex.from_arrays([0, 1], [1, 2])
+    result = dir(index)
+    assert "str" not in result
+
+
+def test_searchsorted_different_argument_classes(listlike_box):
+    # https://github.com/pandas-dev/pandas/issues/32762
+    values = IntervalIndex([Interval(0, 1), Interval(1, 2)])
+    result = values.searchsorted(listlike_box(values))
+    expected = np.array([0, 1], dtype=result.dtype)
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = values._data.searchsorted(listlike_box(values))
+    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(arg):
+    values = IntervalIndex([Interval(0, 1), Interval(1, 2)])
+    msg = "'<' not supported between instances of 'pandas._libs.interval.Interval' and "
+    with pytest.raises(TypeError, match=msg):
+        values.searchsorted(arg)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_interval_range.py

@@ -0,0 +1,369 @@
+from datetime import timedelta
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.common import is_integer
+
+from pandas import (
+    DateOffset,
+    Interval,
+    IntervalIndex,
+    Timedelta,
+    Timestamp,
+    date_range,
+    interval_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+
+from pandas.tseries.offsets import Day
+
+
+@pytest.fixture(params=[None, "foo"])
+def name(request):
+    return request.param
+
+
+class TestIntervalRange:
+    @pytest.mark.parametrize("freq, periods", [(1, 100), (2.5, 40), (5, 20), (25, 4)])
+    def test_constructor_numeric(self, closed, name, freq, periods):
+        start, end = 0, 100
+        breaks = np.arange(101, step=freq)
+        expected = IntervalIndex.from_breaks(breaks, name=name, closed=closed)
+
+        # defined from start/end/freq
+        result = interval_range(
+            start=start, end=end, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from start/periods/freq
+        result = interval_range(
+            start=start, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from end/periods/freq
+        result = interval_range(
+            end=end, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # GH 20976: linspace behavior defined from start/end/periods
+        result = interval_range(
+            start=start, end=end, periods=periods, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("tz", [None, "US/Eastern"])
+    @pytest.mark.parametrize(
+        "freq, periods", [("D", 364), ("2D", 182), ("22D18h", 16), ("ME", 11)]
+    )
+    def test_constructor_timestamp(self, closed, name, freq, periods, tz):
+        start, end = Timestamp("20180101", tz=tz), Timestamp("20181231", tz=tz)
+        breaks = date_range(start=start, end=end, freq=freq)
+        expected = IntervalIndex.from_breaks(breaks, name=name, closed=closed)
+
+        # defined from start/end/freq
+        result = interval_range(
+            start=start, end=end, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from start/periods/freq
+        result = interval_range(
+            start=start, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from end/periods/freq
+        result = interval_range(
+            end=end, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # GH 20976: linspace behavior defined from start/end/periods
+        if not breaks.freq.n == 1 and tz is None:
+            result = interval_range(
+                start=start, end=end, periods=periods, name=name, closed=closed
+            )
+            tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "freq, periods", [("D", 100), ("2D12h", 40), ("5D", 20), ("25D", 4)]
+    )
+    def test_constructor_timedelta(self, closed, name, freq, periods):
+        start, end = Timedelta("0 days"), Timedelta("100 days")
+        breaks = timedelta_range(start=start, end=end, freq=freq)
+        expected = IntervalIndex.from_breaks(breaks, name=name, closed=closed)
+
+        # defined from start/end/freq
+        result = interval_range(
+            start=start, end=end, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from start/periods/freq
+        result = interval_range(
+            start=start, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # defined from end/periods/freq
+        result = interval_range(
+            end=end, periods=periods, freq=freq, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+        # GH 20976: linspace behavior defined from start/end/periods
+        result = interval_range(
+            start=start, end=end, periods=periods, name=name, closed=closed
+        )
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "start, end, freq, expected_endpoint",
+        [
+            (0, 10, 3, 9),
+            (0, 10, 1.5, 9),
+            (0.5, 10, 3, 9.5),
+            (Timedelta("0D"), Timedelta("10D"), "2D4h", Timedelta("8D16h")),
+            (
+                Timestamp("2018-01-01"),
+                Timestamp("2018-02-09"),
+                "MS",
+                Timestamp("2018-02-01"),
+            ),
+            (
+                Timestamp("2018-01-01", tz="US/Eastern"),
+                Timestamp("2018-01-20", tz="US/Eastern"),
+                "5D12h",
+                Timestamp("2018-01-17 12:00:00", tz="US/Eastern"),
+            ),
+        ],
+    )
+    def test_early_truncation(self, start, end, freq, expected_endpoint):
+        # index truncates early if freq causes end to be skipped
+        result = interval_range(start=start, end=end, freq=freq)
+        result_endpoint = result.right[-1]
+        assert result_endpoint == expected_endpoint
+
+    @pytest.mark.parametrize(
+        "start, end, freq",
+        [(0.5, None, None), (None, 4.5, None), (0.5, None, 1.5), (None, 6.5, 1.5)],
+    )
+    def test_no_invalid_float_truncation(self, start, end, freq):
+        # GH 21161
+        if freq is None:
+            breaks = [0.5, 1.5, 2.5, 3.5, 4.5]
+        else:
+            breaks = [0.5, 2.0, 3.5, 5.0, 6.5]
+        expected = IntervalIndex.from_breaks(breaks)
+
+        result = interval_range(start=start, end=end, periods=4, freq=freq)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "start, mid, end",
+        [
+            (
+                Timestamp("2018-03-10", tz="US/Eastern"),
+                Timestamp("2018-03-10 23:30:00", tz="US/Eastern"),
+                Timestamp("2018-03-12", tz="US/Eastern"),
+            ),
+            (
+                Timestamp("2018-11-03", tz="US/Eastern"),
+                Timestamp("2018-11-04 00:30:00", tz="US/Eastern"),
+                Timestamp("2018-11-05", tz="US/Eastern"),
+            ),
+        ],
+    )
+    def test_linspace_dst_transition(self, start, mid, end):
+        # GH 20976: linspace behavior defined from start/end/periods
+        # accounts for the hour gained/lost during DST transition
+        start = start.as_unit("ns")
+        mid = mid.as_unit("ns")
+        end = end.as_unit("ns")
+        result = interval_range(start=start, end=end, periods=2)
+        expected = IntervalIndex.from_breaks([start, mid, end])
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("freq", [2, 2.0])
+    @pytest.mark.parametrize("end", [10, 10.0])
+    @pytest.mark.parametrize("start", [0, 0.0])
+    def test_float_subtype(self, start, end, freq):
+        # Has float subtype if any of start/end/freq are float, even if all
+        # resulting endpoints can safely be upcast to integers
+
+        # defined from start/end/freq
+        index = interval_range(start=start, end=end, freq=freq)
+        result = index.dtype.subtype
+        expected = "int64" if is_integer(start + end + freq) else "float64"
+        assert result == expected
+
+        # defined from start/periods/freq
+        index = interval_range(start=start, periods=5, freq=freq)
+        result = index.dtype.subtype
+        expected = "int64" if is_integer(start + freq) else "float64"
+        assert result == expected
+
+        # defined from end/periods/freq
+        index = interval_range(end=end, periods=5, freq=freq)
+        result = index.dtype.subtype
+        expected = "int64" if is_integer(end + freq) else "float64"
+        assert result == expected
+
+        # GH 20976: linspace behavior defined from start/end/periods
+        index = interval_range(start=start, end=end, periods=5)
+        result = index.dtype.subtype
+        expected = "int64" if is_integer(start + end) else "float64"
+        assert result == expected
+
+    def test_interval_range_fractional_period(self):
+        # float value for periods
+        expected = interval_range(start=0, periods=10)
+        msg = "Non-integer 'periods' in pd.date_range, .* pd.interval_range"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            result = interval_range(start=0, periods=10.5)
+        tm.assert_index_equal(result, expected)
+
+    def test_constructor_coverage(self):
+        # equivalent timestamp-like start/end
+        start, end = Timestamp("2017-01-01"), Timestamp("2017-01-15")
+        expected = interval_range(start=start, end=end)
+
+        result = interval_range(start=start.to_pydatetime(), end=end.to_pydatetime())
+        tm.assert_index_equal(result, expected)
+
+        result = interval_range(start=start.asm8, end=end.asm8)
+        tm.assert_index_equal(result, expected)
+
+        # equivalent freq with timestamp
+        equiv_freq = [
+            "D",
+            Day(),
+            Timedelta(days=1),
+            timedelta(days=1),
+            DateOffset(days=1),
+        ]
+        for freq in equiv_freq:
+            result = interval_range(start=start, end=end, freq=freq)
+            tm.assert_index_equal(result, expected)
+
+        # equivalent timedelta-like start/end
+        start, end = Timedelta(days=1), Timedelta(days=10)
+        expected = interval_range(start=start, end=end)
+
+        result = interval_range(start=start.to_pytimedelta(), end=end.to_pytimedelta())
+        tm.assert_index_equal(result, expected)
+
+        result = interval_range(start=start.asm8, end=end.asm8)
+        tm.assert_index_equal(result, expected)
+
+        # equivalent freq with timedelta
+        equiv_freq = ["D", Day(), Timedelta(days=1), timedelta(days=1)]
+        for freq in equiv_freq:
+            result = interval_range(start=start, end=end, 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):
+            interval_range(start=0)
+
+        with pytest.raises(ValueError, match=msg):
+            interval_range(end=5)
+
+        with pytest.raises(ValueError, match=msg):
+            interval_range(periods=2)
+
+        with pytest.raises(ValueError, match=msg):
+            interval_range()
+
+        # too many params
+        with pytest.raises(ValueError, match=msg):
+            interval_range(start=0, end=5, periods=6, freq=1.5)
+
+        # mixed units
+        msg = "start, end, freq need to be type compatible"
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=0, end=Timestamp("20130101"), freq=2)
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=0, end=Timedelta("1 day"), freq=2)
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=0, end=10, freq="D")
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=Timestamp("20130101"), end=10, freq="D")
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(
+                start=Timestamp("20130101"), end=Timedelta("1 day"), freq="D"
+            )
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(
+                start=Timestamp("20130101"), end=Timestamp("20130110"), freq=2
+            )
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=Timedelta("1 day"), end=10, freq="D")
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(
+                start=Timedelta("1 day"), end=Timestamp("20130110"), freq="D"
+            )
+
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=Timedelta("1 day"), end=Timedelta("10 days"), freq=2)
+
+        # invalid periods
+        msg = "periods must be a number, got foo"
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=0, periods="foo")
+
+        # invalid start
+        msg = "start must be numeric or datetime-like, got foo"
+        with pytest.raises(ValueError, match=msg):
+            interval_range(start="foo", periods=10)
+
+        # invalid end
+        msg = r"end must be numeric or datetime-like, got \(0, 1\]"
+        with pytest.raises(ValueError, match=msg):
+            interval_range(end=Interval(0, 1), periods=10)
+
+        # invalid freq for datetime-like
+        msg = "freq must be numeric or convertible to DateOffset, got foo"
+        with pytest.raises(ValueError, match=msg):
+            interval_range(start=0, end=10, freq="foo")
+
+        with pytest.raises(ValueError, match=msg):
+            interval_range(start=Timestamp("20130101"), periods=10, freq="foo")
+
+        with pytest.raises(ValueError, match=msg):
+            interval_range(end=Timedelta("1 day"), periods=10, freq="foo")
+
+        # mixed tz
+        start = Timestamp("2017-01-01", tz="US/Eastern")
+        end = Timestamp("2017-01-07", tz="US/Pacific")
+        msg = "Start and end cannot both be tz-aware with different timezones"
+        with pytest.raises(TypeError, match=msg):
+            interval_range(start=start, end=end)
+
+    def test_float_freq(self):
+        # GH 54477
+        result = interval_range(0, 1, freq=0.1)
+        expected = IntervalIndex.from_breaks([0 + 0.1 * n for n in range(11)])
+        tm.assert_index_equal(result, expected)
+
+        result = interval_range(0, 1, freq=0.6)
+        expected = IntervalIndex.from_breaks([0, 0.6])
+        tm.assert_index_equal(result, expected)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_interval_tree.py

@@ -0,0 +1,208 @@
+from itertools import permutations
+
+import numpy as np
+import pytest
+
+from pandas._libs.interval import IntervalTree
+from pandas.compat import IS64
+
+import pandas._testing as tm
+
+
+def skipif_32bit(param):
+    """
+    Skip parameters in a parametrize on 32bit systems. Specifically used
+    here to skip leaf_size parameters related to GH 23440.
+    """
+    marks = pytest.mark.skipif(not IS64, reason="GH 23440: int type mismatch on 32bit")
+    return pytest.param(param, marks=marks)
+
+
+@pytest.fixture(params=["int64", "float64", "uint64"])
+def dtype(request):
+    return request.param
+
+
+@pytest.fixture(params=[skipif_32bit(1), skipif_32bit(2), 10])
+def leaf_size(request):
+    """
+    Fixture to specify IntervalTree leaf_size parameter; to be used with the
+    tree fixture.
+    """
+    return request.param
+
+
+@pytest.fixture(
+    params=[
+        np.arange(5, dtype="int64"),
+        np.arange(5, dtype="uint64"),
+        np.arange(5, dtype="float64"),
+        np.array([0, 1, 2, 3, 4, np.nan], dtype="float64"),
+    ]
+)
+def tree(request, leaf_size):
+    left = request.param
+    return IntervalTree(left, left + 2, leaf_size=leaf_size)
+
+
+class TestIntervalTree:
+    def test_get_indexer(self, tree):
+        result = tree.get_indexer(np.array([1.0, 5.5, 6.5]))
+        expected = np.array([0, 4, -1], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+        with pytest.raises(
+            KeyError, match="'indexer does not intersect a unique set of intervals'"
+        ):
+            tree.get_indexer(np.array([3.0]))
+
+    @pytest.mark.parametrize(
+        "dtype, target_value, target_dtype",
+        [("int64", 2**63 + 1, "uint64"), ("uint64", -1, "int64")],
+    )
+    def test_get_indexer_overflow(self, dtype, target_value, target_dtype):
+        left, right = np.array([0, 1], dtype=dtype), np.array([1, 2], dtype=dtype)
+        tree = IntervalTree(left, right)
+
+        result = tree.get_indexer(np.array([target_value], dtype=target_dtype))
+        expected = np.array([-1], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_get_indexer_non_unique(self, tree):
+        indexer, missing = tree.get_indexer_non_unique(np.array([1.0, 2.0, 6.5]))
+
+        result = indexer[:1]
+        expected = np.array([0], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.sort(indexer[1:3])
+        expected = np.array([0, 1], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.sort(indexer[3:])
+        expected = np.array([-1], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = missing
+        expected = np.array([2], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "dtype, target_value, target_dtype",
+        [("int64", 2**63 + 1, "uint64"), ("uint64", -1, "int64")],
+    )
+    def test_get_indexer_non_unique_overflow(self, dtype, target_value, target_dtype):
+        left, right = np.array([0, 2], dtype=dtype), np.array([1, 3], dtype=dtype)
+        tree = IntervalTree(left, right)
+        target = np.array([target_value], dtype=target_dtype)
+
+        result_indexer, result_missing = tree.get_indexer_non_unique(target)
+        expected_indexer = np.array([-1], dtype="intp")
+        tm.assert_numpy_array_equal(result_indexer, expected_indexer)
+
+        expected_missing = np.array([0], dtype="intp")
+        tm.assert_numpy_array_equal(result_missing, expected_missing)
+
+    def test_duplicates(self, dtype):
+        left = np.array([0, 0, 0], dtype=dtype)
+        tree = IntervalTree(left, left + 1)
+
+        with pytest.raises(
+            KeyError, match="'indexer does not intersect a unique set of intervals'"
+        ):
+            tree.get_indexer(np.array([0.5]))
+
+        indexer, missing = tree.get_indexer_non_unique(np.array([0.5]))
+        result = np.sort(indexer)
+        expected = np.array([0, 1, 2], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = missing
+        expected = np.array([], dtype="intp")
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "leaf_size", [skipif_32bit(1), skipif_32bit(10), skipif_32bit(100), 10000]
+    )
+    def test_get_indexer_closed(self, closed, leaf_size):
+        x = np.arange(1000, dtype="float64")
+        found = x.astype("intp")
+        not_found = (-1 * np.ones(1000)).astype("intp")
+
+        tree = IntervalTree(x, x + 0.5, closed=closed, leaf_size=leaf_size)
+        tm.assert_numpy_array_equal(found, tree.get_indexer(x + 0.25))
+
+        expected = found if tree.closed_left else not_found
+        tm.assert_numpy_array_equal(expected, tree.get_indexer(x + 0.0))
+
+        expected = found if tree.closed_right else not_found
+        tm.assert_numpy_array_equal(expected, tree.get_indexer(x + 0.5))
+
+    @pytest.mark.parametrize(
+        "left, right, expected",
+        [
+            (np.array([0, 1, 4], dtype="int64"), np.array([2, 3, 5]), True),
+            (np.array([0, 1, 2], dtype="int64"), np.array([5, 4, 3]), True),
+            (np.array([0, 1, np.nan]), np.array([5, 4, np.nan]), True),
+            (np.array([0, 2, 4], dtype="int64"), np.array([1, 3, 5]), False),
+            (np.array([0, 2, np.nan]), np.array([1, 3, np.nan]), False),
+        ],
+    )
+    @pytest.mark.parametrize("order", (list(x) for x in permutations(range(3))))
+    def test_is_overlapping(self, closed, order, left, right, expected):
+        # GH 23309
+        tree = IntervalTree(left[order], right[order], closed=closed)
+        result = tree.is_overlapping
+        assert result is expected
+
+    @pytest.mark.parametrize("order", (list(x) for x in permutations(range(3))))
+    def test_is_overlapping_endpoints(self, closed, order):
+        """shared endpoints are marked as overlapping"""
+        # GH 23309
+        left, right = np.arange(3, dtype="int64"), np.arange(1, 4)
+        tree = IntervalTree(left[order], right[order], closed=closed)
+        result = tree.is_overlapping
+        expected = closed == "both"
+        assert result is expected
+
+    @pytest.mark.parametrize(
+        "left, right",
+        [
+            (np.array([], dtype="int64"), np.array([], dtype="int64")),
+            (np.array([0], dtype="int64"), np.array([1], dtype="int64")),
+            (np.array([np.nan]), np.array([np.nan])),
+            (np.array([np.nan] * 3), np.array([np.nan] * 3)),
+        ],
+    )
+    def test_is_overlapping_trivial(self, closed, left, right):
+        # GH 23309
+        tree = IntervalTree(left, right, closed=closed)
+        assert tree.is_overlapping is False
+
+    @pytest.mark.skipif(not IS64, reason="GH 23440")
+    def test_construction_overflow(self):
+        # GH 25485
+        left, right = np.arange(101, dtype="int64"), [np.iinfo(np.int64).max] * 101
+        tree = IntervalTree(left, right)
+
+        # pivot should be average of left/right medians
+        result = tree.root.pivot
+        expected = (50 + np.iinfo(np.int64).max) / 2
+        assert result == expected
+
+    @pytest.mark.parametrize(
+        "left, right, expected",
+        [
+            ([-np.inf, 1.0], [1.0, 2.0], 0.0),
+            ([-np.inf, -2.0], [-2.0, -1.0], -2.0),
+            ([-2.0, -1.0], [-1.0, np.inf], 0.0),
+            ([1.0, 2.0], [2.0, np.inf], 2.0),
+        ],
+    )
+    def test_inf_bound_infinite_recursion(self, left, right, expected):
+        # GH 46658
+
+        tree = IntervalTree(left * 101, right * 101)
+
+        result = tree.root.pivot
+        assert result == expected

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_join.py

@@ -0,0 +1,44 @@
+import pytest
+
+from pandas import (
+    IntervalIndex,
+    MultiIndex,
+    RangeIndex,
+)
+import pandas._testing as tm
+
+
+@pytest.fixture
+def range_index():
+    return RangeIndex(3, name="range_index")
+
+
+@pytest.fixture
+def interval_index():
+    return IntervalIndex.from_tuples(
+        [(0.0, 1.0), (1.0, 2.0), (1.5, 2.5)], name="interval_index"
+    )
+
+
+def test_join_overlapping_in_mi_to_same_intervalindex(range_index, interval_index):
+    #  GH-45661
+    multi_index = MultiIndex.from_product([interval_index, range_index])
+    result = multi_index.join(interval_index)
+
+    tm.assert_index_equal(result, multi_index)
+
+
+def test_join_overlapping_to_multiindex_with_same_interval(range_index, interval_index):
+    #  GH-45661
+    multi_index = MultiIndex.from_product([interval_index, range_index])
+    result = interval_index.join(multi_index)
+
+    tm.assert_index_equal(result, multi_index)
+
+
+def test_join_overlapping_interval_to_another_intervalindex(interval_index):
+    #  GH-45661
+    flipped_interval_index = interval_index[::-1]
+    result = interval_index.join(flipped_interval_index)
+
+    tm.assert_index_equal(result, interval_index)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_pickle.py

@@ -0,0 +1,13 @@
+import pytest
+
+from pandas import IntervalIndex
+import pandas._testing as tm
+
+
+class TestPickle:
+    @pytest.mark.parametrize("closed", ["left", "right", "both"])
+    def test_pickle_round_trip_closed(self, closed):
+        # https://github.com/pandas-dev/pandas/issues/35658
+        idx = IntervalIndex.from_tuples([(1, 2), (2, 3)], closed=closed)
+        result = tm.round_trip_pickle(idx)
+        tm.assert_index_equal(result, idx)

py311/lib/python3.11/site-packages/pandas/tests/indexes/interval/test_setops.py

@@ -0,0 +1,208 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    Index,
+    IntervalIndex,
+    Timestamp,
+    interval_range,
+)
+import pandas._testing as tm
+
+
+def monotonic_index(start, end, dtype="int64", closed="right"):
+    return IntervalIndex.from_breaks(np.arange(start, end, dtype=dtype), closed=closed)
+
+
+def empty_index(dtype="int64", closed="right"):
+    return IntervalIndex(np.array([], dtype=dtype), closed=closed)
+
+
+class TestIntervalIndex:
+    def test_union(self, closed, sort):
+        index = monotonic_index(0, 11, closed=closed)
+        other = monotonic_index(5, 13, closed=closed)
+
+        expected = monotonic_index(0, 13, closed=closed)
+        result = index[::-1].union(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].union(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.union(index, sort=sort), index)
+        tm.assert_index_equal(index.union(index[:1], sort=sort), index)
+
+    def test_union_empty_result(self, closed, sort):
+        # GH 19101: empty result, same dtype
+        index = empty_index(dtype="int64", closed=closed)
+        result = index.union(index, sort=sort)
+        tm.assert_index_equal(result, index)
+
+        # GH 19101: empty result, different numeric dtypes -> 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)

py311/lib/python3.11/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

py311/lib/python3.11/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)

py311/lib/python3.11/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")

py311/lib/python3.11/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 pd.StringDtype(na_value=np.nan)
+    expected = Series(
+        ["int64", exp],
+        index=MultiIndex.from_tuples([("a", "b"), ("c", "d")]),
+        dtype=object,
+    )
+    tm.assert_series_equal(result, expected)

py311/lib/python3.11/site-packages/pandas/tests/indexes/multi/test_conversion.py

@@ -0,0 +1,201 @@
+import numpy as np
+import pytest
+
+from pandas.compat.numpy import np_version_gt2
+
+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_array_interface(idx):
+    # https://github.com/pandas-dev/pandas/pull/60046
+    result = np.asarray(idx)
+    expected = np.empty((6,), dtype=object)
+    expected[:] = [
+        ("foo", "one"),
+        ("foo", "two"),
+        ("bar", "one"),
+        ("baz", "two"),
+        ("qux", "one"),
+        ("qux", "two"),
+    ]
+    tm.assert_numpy_array_equal(result, expected)
+
+    # it always gives a copy by default, but the values are cached, so results
+    # are still sharing memory
+    result_copy1 = np.asarray(idx)
+    result_copy2 = np.asarray(idx)
+    assert np.may_share_memory(result_copy1, result_copy2)
+
+    # with explicit copy=True, then it is an actual copy
+    result_copy1 = np.array(idx, copy=True)
+    result_copy2 = np.array(idx, copy=True)
+    assert not np.may_share_memory(result_copy1, result_copy2)
+
+    if not np_version_gt2:
+        # copy=False semantics are only supported in NumPy>=2.
+        return
+
+    # for MultiIndex, copy=False is never allowed
+    msg = "Starting with NumPy 2.0, the behavior of the 'copy' keyword has changed"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        np.array(idx, copy=False)
+
+
+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)

py311/lib/python3.11/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

py311/lib/python3.11/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)

py311/lib/python3.11/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)

py311/lib/python3.11/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

py311/lib/python3.11/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

py311/lib/python3.11/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)

py311/lib/python3.11/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

py311/lib/python3.11/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

py311/lib/python3.11/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)

py311/lib/python3.11/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))

py311/lib/python3.11/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="str"), Series([None], dtype="str")]
+        ),
+    )
+    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)

py311/lib/python3.11/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)

py311/lib/python3.11/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]))

py311/lib/python3.11/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)

py311/lib/python3.11/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