Add files using upload-large-folder tool

lib/python3.12/site-packages/pandas/tests/api/test_api.py

@@ -0,0 +1,383 @@
+from __future__ import annotations
+
+import pytest
+
+import pandas as pd
+from pandas import api
+import pandas._testing as tm
+from pandas.api import (
+    extensions as api_extensions,
+    indexers as api_indexers,
+    interchange as api_interchange,
+    types as api_types,
+    typing as api_typing,
+)
+
+
+class Base:
+    def check(self, namespace, expected, ignored=None):
+        # see which names are in the namespace, minus optional
+        # ignored ones
+        # compare vs the expected
+
+        result = sorted(
+            f for f in dir(namespace) if not f.startswith("__") and f != "annotations"
+        )
+        if ignored is not None:
+            result = sorted(set(result) - set(ignored))
+
+        expected = sorted(expected)
+        tm.assert_almost_equal(result, expected)
+
+
+class TestPDApi(Base):
+    # these are optionally imported based on testing
+    # & need to be ignored
+    ignored = ["tests", "locale", "conftest", "_version_meson"]
+
+    # top-level sub-packages
+    public_lib = [
+        "api",
+        "arrays",
+        "options",
+        "test",
+        "testing",
+        "errors",
+        "plotting",
+        "io",
+        "tseries",
+    ]
+    private_lib = ["compat", "core", "pandas", "util", "_built_with_meson"]
+
+    # misc
+    misc = ["IndexSlice", "NaT", "NA"]
+
+    # top-level classes
+    classes = [
+        "ArrowDtype",
+        "Categorical",
+        "CategoricalIndex",
+        "DataFrame",
+        "DateOffset",
+        "DatetimeIndex",
+        "ExcelFile",
+        "ExcelWriter",
+        "Flags",
+        "Grouper",
+        "HDFStore",
+        "Index",
+        "MultiIndex",
+        "Period",
+        "PeriodIndex",
+        "RangeIndex",
+        "Series",
+        "SparseDtype",
+        "StringDtype",
+        "Timedelta",
+        "TimedeltaIndex",
+        "Timestamp",
+        "Interval",
+        "IntervalIndex",
+        "CategoricalDtype",
+        "PeriodDtype",
+        "IntervalDtype",
+        "DatetimeTZDtype",
+        "BooleanDtype",
+        "Int8Dtype",
+        "Int16Dtype",
+        "Int32Dtype",
+        "Int64Dtype",
+        "UInt8Dtype",
+        "UInt16Dtype",
+        "UInt32Dtype",
+        "UInt64Dtype",
+        "Float32Dtype",
+        "Float64Dtype",
+        "NamedAgg",
+    ]
+
+    # these are already deprecated; awaiting removal
+    deprecated_classes: list[str] = []
+
+    # external modules exposed in pandas namespace
+    modules: list[str] = []
+
+    # top-level functions
+    funcs = [
+        "array",
+        "bdate_range",
+        "concat",
+        "crosstab",
+        "cut",
+        "date_range",
+        "interval_range",
+        "eval",
+        "factorize",
+        "get_dummies",
+        "from_dummies",
+        "infer_freq",
+        "isna",
+        "isnull",
+        "lreshape",
+        "melt",
+        "notna",
+        "notnull",
+        "offsets",
+        "merge",
+        "merge_ordered",
+        "merge_asof",
+        "period_range",
+        "pivot",
+        "pivot_table",
+        "qcut",
+        "show_versions",
+        "timedelta_range",
+        "unique",
+        "value_counts",
+        "wide_to_long",
+    ]
+
+    # top-level option funcs
+    funcs_option = [
+        "reset_option",
+        "describe_option",
+        "get_option",
+        "option_context",
+        "set_option",
+        "set_eng_float_format",
+    ]
+
+    # top-level read_* funcs
+    funcs_read = [
+        "read_clipboard",
+        "read_csv",
+        "read_excel",
+        "read_fwf",
+        "read_gbq",
+        "read_hdf",
+        "read_html",
+        "read_xml",
+        "read_json",
+        "read_pickle",
+        "read_sas",
+        "read_sql",
+        "read_sql_query",
+        "read_sql_table",
+        "read_stata",
+        "read_table",
+        "read_feather",
+        "read_parquet",
+        "read_orc",
+        "read_spss",
+    ]
+
+    # top-level json funcs
+    funcs_json = ["json_normalize"]
+
+    # top-level to_* funcs
+    funcs_to = ["to_datetime", "to_numeric", "to_pickle", "to_timedelta"]
+
+    # top-level to deprecate in the future
+    deprecated_funcs_in_future: list[str] = []
+
+    # these are already deprecated; awaiting removal
+    deprecated_funcs: list[str] = []
+
+    # private modules in pandas namespace
+    private_modules = [
+        "_config",
+        "_libs",
+        "_is_numpy_dev",
+        "_pandas_datetime_CAPI",
+        "_pandas_parser_CAPI",
+        "_testing",
+        "_typing",
+    ]
+    if not pd._built_with_meson:
+        private_modules.append("_version")
+
+    def test_api(self):
+        checkthese = (
+            self.public_lib
+            + self.private_lib
+            + self.misc
+            + self.modules
+            + self.classes
+            + self.funcs
+            + self.funcs_option
+            + self.funcs_read
+            + self.funcs_json
+            + self.funcs_to
+            + self.private_modules
+        )
+        self.check(namespace=pd, expected=checkthese, ignored=self.ignored)
+
+    def test_api_all(self):
+        expected = set(
+            self.public_lib
+            + self.misc
+            + self.modules
+            + self.classes
+            + self.funcs
+            + self.funcs_option
+            + self.funcs_read
+            + self.funcs_json
+            + self.funcs_to
+        ) - set(self.deprecated_classes)
+        actual = set(pd.__all__)
+
+        extraneous = actual - expected
+        assert not extraneous
+
+        missing = expected - actual
+        assert not missing
+
+    def test_depr(self):
+        deprecated_list = (
+            self.deprecated_classes
+            + self.deprecated_funcs
+            + self.deprecated_funcs_in_future
+        )
+        for depr in deprecated_list:
+            with tm.assert_produces_warning(FutureWarning):
+                _ = getattr(pd, depr)
+
+
+class TestApi(Base):
+    allowed_api_dirs = [
+        "types",
+        "extensions",
+        "indexers",
+        "interchange",
+        "typing",
+    ]
+    allowed_typing = [
+        "DataFrameGroupBy",
+        "DatetimeIndexResamplerGroupby",
+        "Expanding",
+        "ExpandingGroupby",
+        "ExponentialMovingWindow",
+        "ExponentialMovingWindowGroupby",
+        "JsonReader",
+        "NaTType",
+        "NAType",
+        "PeriodIndexResamplerGroupby",
+        "Resampler",
+        "Rolling",
+        "RollingGroupby",
+        "SeriesGroupBy",
+        "StataReader",
+        "TimedeltaIndexResamplerGroupby",
+        "TimeGrouper",
+        "Window",
+    ]
+    allowed_api_types = [
+        "is_any_real_numeric_dtype",
+        "is_array_like",
+        "is_bool",
+        "is_bool_dtype",
+        "is_categorical_dtype",
+        "is_complex",
+        "is_complex_dtype",
+        "is_datetime64_any_dtype",
+        "is_datetime64_dtype",
+        "is_datetime64_ns_dtype",
+        "is_datetime64tz_dtype",
+        "is_dict_like",
+        "is_dtype_equal",
+        "is_extension_array_dtype",
+        "is_file_like",
+        "is_float",
+        "is_float_dtype",
+        "is_hashable",
+        "is_int64_dtype",
+        "is_integer",
+        "is_integer_dtype",
+        "is_interval",
+        "is_interval_dtype",
+        "is_iterator",
+        "is_list_like",
+        "is_named_tuple",
+        "is_number",
+        "is_numeric_dtype",
+        "is_object_dtype",
+        "is_period_dtype",
+        "is_re",
+        "is_re_compilable",
+        "is_scalar",
+        "is_signed_integer_dtype",
+        "is_sparse",
+        "is_string_dtype",
+        "is_timedelta64_dtype",
+        "is_timedelta64_ns_dtype",
+        "is_unsigned_integer_dtype",
+        "pandas_dtype",
+        "infer_dtype",
+        "union_categoricals",
+        "CategoricalDtype",
+        "DatetimeTZDtype",
+        "IntervalDtype",
+        "PeriodDtype",
+    ]
+    allowed_api_interchange = ["from_dataframe", "DataFrame"]
+    allowed_api_indexers = [
+        "check_array_indexer",
+        "BaseIndexer",
+        "FixedForwardWindowIndexer",
+        "VariableOffsetWindowIndexer",
+    ]
+    allowed_api_extensions = [
+        "no_default",
+        "ExtensionDtype",
+        "register_extension_dtype",
+        "register_dataframe_accessor",
+        "register_index_accessor",
+        "register_series_accessor",
+        "take",
+        "ExtensionArray",
+        "ExtensionScalarOpsMixin",
+    ]
+
+    def test_api(self):
+        self.check(api, self.allowed_api_dirs)
+
+    def test_api_typing(self):
+        self.check(api_typing, self.allowed_typing)
+
+    def test_api_types(self):
+        self.check(api_types, self.allowed_api_types)
+
+    def test_api_interchange(self):
+        self.check(api_interchange, self.allowed_api_interchange)
+
+    def test_api_indexers(self):
+        self.check(api_indexers, self.allowed_api_indexers)
+
+    def test_api_extensions(self):
+        self.check(api_extensions, self.allowed_api_extensions)
+
+
+class TestTesting(Base):
+    funcs = [
+        "assert_frame_equal",
+        "assert_series_equal",
+        "assert_index_equal",
+        "assert_extension_array_equal",
+    ]
+
+    def test_testing(self):
+        from pandas import testing
+
+        self.check(testing, self.funcs)
+
+    def test_util_in_top_level(self):
+        with pytest.raises(AttributeError, match="foo"):
+            pd.util.foo
+
+
+def test_pandas_array_alias():
+    msg = "PandasArray has been renamed NumpyExtensionArray"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        res = pd.arrays.PandasArray
+
+    assert res is pd.arrays.NumpyExtensionArray

lib/python3.12/site-packages/pandas/tests/api/test_types.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+import pandas._testing as tm
+from pandas.api import types
+from pandas.tests.api.test_api import Base
+
+
+class TestTypes(Base):
+    allowed = [
+        "is_any_real_numeric_dtype",
+        "is_bool",
+        "is_bool_dtype",
+        "is_categorical_dtype",
+        "is_complex",
+        "is_complex_dtype",
+        "is_datetime64_any_dtype",
+        "is_datetime64_dtype",
+        "is_datetime64_ns_dtype",
+        "is_datetime64tz_dtype",
+        "is_dtype_equal",
+        "is_float",
+        "is_float_dtype",
+        "is_int64_dtype",
+        "is_integer",
+        "is_integer_dtype",
+        "is_number",
+        "is_numeric_dtype",
+        "is_object_dtype",
+        "is_scalar",
+        "is_sparse",
+        "is_string_dtype",
+        "is_signed_integer_dtype",
+        "is_timedelta64_dtype",
+        "is_timedelta64_ns_dtype",
+        "is_unsigned_integer_dtype",
+        "is_period_dtype",
+        "is_interval",
+        "is_interval_dtype",
+        "is_re",
+        "is_re_compilable",
+        "is_dict_like",
+        "is_iterator",
+        "is_file_like",
+        "is_list_like",
+        "is_hashable",
+        "is_array_like",
+        "is_named_tuple",
+        "pandas_dtype",
+        "union_categoricals",
+        "infer_dtype",
+        "is_extension_array_dtype",
+    ]
+    deprecated: list[str] = []
+    dtypes = ["CategoricalDtype", "DatetimeTZDtype", "PeriodDtype", "IntervalDtype"]
+
+    def test_types(self):
+        self.check(types, self.allowed + self.dtypes + self.deprecated)
+
+    def test_deprecated_from_api_types(self):
+        for t in self.deprecated:
+            with tm.assert_produces_warning(FutureWarning):
+                getattr(types, t)(1)

lib/python3.12/site-packages/pandas/tests/construction/test_extract_array.py

@@ -0,0 +1,18 @@
+from pandas import Index
+import pandas._testing as tm
+from pandas.core.construction import extract_array
+
+
+def test_extract_array_rangeindex():
+    ri = Index(range(5))
+
+    expected = ri._values
+    res = extract_array(ri, extract_numpy=True, extract_range=True)
+    tm.assert_numpy_array_equal(res, expected)
+    res = extract_array(ri, extract_numpy=False, extract_range=True)
+    tm.assert_numpy_array_equal(res, expected)
+
+    res = extract_array(ri, extract_numpy=True, extract_range=False)
+    tm.assert_index_equal(res, ri)
+    res = extract_array(ri, extract_numpy=False, extract_range=False)
+    tm.assert_index_equal(res, ri)

lib/python3.12/site-packages/pandas/tests/extension/array_with_attr/__init__.py

@@ -0,0 +1,6 @@
+from pandas.tests.extension.array_with_attr.array import (
+    FloatAttrArray,
+    FloatAttrDtype,
+)
+
+__all__ = ["FloatAttrArray", "FloatAttrDtype"]

lib/python3.12/site-packages/pandas/tests/extension/array_with_attr/array.py

@@ -0,0 +1,89 @@
+"""
+Test extension array that has custom attribute information (not stored on the dtype).
+
+"""
+from __future__ import annotations
+
+import numbers
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas.core.dtypes.base import ExtensionDtype
+
+import pandas as pd
+from pandas.core.arrays import ExtensionArray
+
+if TYPE_CHECKING:
+    from pandas._typing import type_t
+
+
+class FloatAttrDtype(ExtensionDtype):
+    type = float
+    name = "float_attr"
+    na_value = np.nan
+
+    @classmethod
+    def construct_array_type(cls) -> type_t[FloatAttrArray]:
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        return FloatAttrArray
+
+
+class FloatAttrArray(ExtensionArray):
+    dtype = FloatAttrDtype()
+    __array_priority__ = 1000
+
+    def __init__(self, values, attr=None) -> None:
+        if not isinstance(values, np.ndarray):
+            raise TypeError("Need to pass a numpy array of float64 dtype as values")
+        if not values.dtype == "float64":
+            raise TypeError("Need to pass a numpy array of float64 dtype as values")
+        self.data = values
+        self.attr = attr
+
+    @classmethod
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+        if not copy:
+            data = np.asarray(scalars, dtype="float64")
+        else:
+            data = np.array(scalars, dtype="float64", copy=copy)
+        return cls(data)
+
+    def __getitem__(self, item):
+        if isinstance(item, numbers.Integral):
+            return self.data[item]
+        else:
+            # slice, list-like, mask
+            item = pd.api.indexers.check_array_indexer(self, item)
+            return type(self)(self.data[item], self.attr)
+
+    def __len__(self) -> int:
+        return len(self.data)
+
+    def isna(self):
+        return np.isnan(self.data)
+
+    def take(self, indexer, allow_fill=False, fill_value=None):
+        from pandas.api.extensions import take
+
+        data = self.data
+        if allow_fill and fill_value is None:
+            fill_value = self.dtype.na_value
+
+        result = take(data, indexer, fill_value=fill_value, allow_fill=allow_fill)
+        return type(self)(result, self.attr)
+
+    def copy(self):
+        return type(self)(self.data.copy(), self.attr)
+
+    @classmethod
+    def _concat_same_type(cls, to_concat):
+        data = np.concatenate([x.data for x in to_concat])
+        attr = to_concat[0].attr if len(to_concat) else None
+        return cls(data, attr)

lib/python3.12/site-packages/pandas/tests/extension/array_with_attr/test_array_with_attr.py

@@ -0,0 +1,33 @@
+import numpy as np
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.tests.extension.array_with_attr import FloatAttrArray
+
+
+def test_concat_with_all_na():
+    # https://github.com/pandas-dev/pandas/pull/47762
+    # ensure that attribute of the column array is preserved (when it gets
+    # preserved in reindexing the array) during merge/concat
+    arr = FloatAttrArray(np.array([np.nan, np.nan], dtype="float64"), attr="test")
+
+    df1 = pd.DataFrame({"col": arr, "key": [0, 1]})
+    df2 = pd.DataFrame({"key": [0, 1], "col2": [1, 2]})
+    result = pd.merge(df1, df2, on="key")
+    expected = pd.DataFrame({"col": arr, "key": [0, 1], "col2": [1, 2]})
+    tm.assert_frame_equal(result, expected)
+    assert result["col"].array.attr == "test"
+
+    df1 = pd.DataFrame({"col": arr, "key": [0, 1]})
+    df2 = pd.DataFrame({"key": [0, 2], "col2": [1, 2]})
+    result = pd.merge(df1, df2, on="key")
+    expected = pd.DataFrame({"col": arr.take([0]), "key": [0], "col2": [1]})
+    tm.assert_frame_equal(result, expected)
+    assert result["col"].array.attr == "test"
+
+    result = pd.concat([df1.set_index("key"), df2.set_index("key")], axis=1)
+    expected = pd.DataFrame(
+        {"col": arr.take([0, 1, -1]), "col2": [1, np.nan, 2], "key": [0, 1, 2]}
+    ).set_index("key")
+    tm.assert_frame_equal(result, expected)
+    assert result["col"].array.attr == "test"

lib/python3.12/site-packages/pandas/tests/extension/base/__init__.py

@@ -0,0 +1,131 @@
+"""
+Base test suite for extension arrays.
+
+These tests are intended for third-party libraries to subclass to validate
+that their extension arrays and dtypes satisfy the interface. Moving or
+renaming the tests should not be done lightly.
+
+Libraries are expected to implement a few pytest fixtures to provide data
+for the tests. The fixtures may be located in either
+
+* The same module as your test class.
+* A ``conftest.py`` in the same directory as your test class.
+
+The full list of fixtures may be found in the ``conftest.py`` next to this
+file.
+
+.. code-block:: python
+
+   import pytest
+   from pandas.tests.extension.base import BaseDtypeTests
+
+
+   @pytest.fixture
+   def dtype():
+       return MyDtype()
+
+
+   class TestMyDtype(BaseDtypeTests):
+       pass
+
+
+Your class ``TestDtype`` will inherit all the tests defined on
+``BaseDtypeTests``. pytest's fixture discover will supply your ``dtype``
+wherever the test requires it. You're free to implement additional tests.
+
+"""
+from pandas.tests.extension.base.accumulate import BaseAccumulateTests
+from pandas.tests.extension.base.casting import BaseCastingTests
+from pandas.tests.extension.base.constructors import BaseConstructorsTests
+from pandas.tests.extension.base.dim2 import (  # noqa: F401
+    Dim2CompatTests,
+    NDArrayBacked2DTests,
+)
+from pandas.tests.extension.base.dtype import BaseDtypeTests
+from pandas.tests.extension.base.getitem import BaseGetitemTests
+from pandas.tests.extension.base.groupby import BaseGroupbyTests
+from pandas.tests.extension.base.index import BaseIndexTests
+from pandas.tests.extension.base.interface import BaseInterfaceTests
+from pandas.tests.extension.base.io import BaseParsingTests
+from pandas.tests.extension.base.methods import BaseMethodsTests
+from pandas.tests.extension.base.missing import BaseMissingTests
+from pandas.tests.extension.base.ops import (  # noqa: F401
+    BaseArithmeticOpsTests,
+    BaseComparisonOpsTests,
+    BaseOpsUtil,
+    BaseUnaryOpsTests,
+)
+from pandas.tests.extension.base.printing import BasePrintingTests
+from pandas.tests.extension.base.reduce import BaseReduceTests
+from pandas.tests.extension.base.reshaping import BaseReshapingTests
+from pandas.tests.extension.base.setitem import BaseSetitemTests
+
+
+# One test class that you can inherit as an alternative to inheriting all the
+# test classes above.
+# Note 1) this excludes Dim2CompatTests and NDArrayBacked2DTests.
+# Note 2) this uses BaseReduceTests and and _not_ BaseBooleanReduceTests,
+#  BaseNoReduceTests, or BaseNumericReduceTests
+class ExtensionTests(
+    BaseAccumulateTests,
+    BaseCastingTests,
+    BaseConstructorsTests,
+    BaseDtypeTests,
+    BaseGetitemTests,
+    BaseGroupbyTests,
+    BaseIndexTests,
+    BaseInterfaceTests,
+    BaseParsingTests,
+    BaseMethodsTests,
+    BaseMissingTests,
+    BaseArithmeticOpsTests,
+    BaseComparisonOpsTests,
+    BaseUnaryOpsTests,
+    BasePrintingTests,
+    BaseReduceTests,
+    BaseReshapingTests,
+    BaseSetitemTests,
+    Dim2CompatTests,
+):
+    pass
+
+
+def __getattr__(name: str):
+    import warnings
+
+    if name == "BaseNoReduceTests":
+        warnings.warn(
+            "BaseNoReduceTests is deprecated and will be removed in a "
+            "future version. Use BaseReduceTests and override "
+            "`_supports_reduction` instead.",
+            FutureWarning,
+        )
+        from pandas.tests.extension.base.reduce import BaseNoReduceTests
+
+        return BaseNoReduceTests
+
+    elif name == "BaseNumericReduceTests":
+        warnings.warn(
+            "BaseNumericReduceTests is deprecated and will be removed in a "
+            "future version. Use BaseReduceTests and override "
+            "`_supports_reduction` instead.",
+            FutureWarning,
+        )
+        from pandas.tests.extension.base.reduce import BaseNumericReduceTests
+
+        return BaseNumericReduceTests
+
+    elif name == "BaseBooleanReduceTests":
+        warnings.warn(
+            "BaseBooleanReduceTests is deprecated and will be removed in a "
+            "future version. Use BaseReduceTests and override "
+            "`_supports_reduction` instead.",
+            FutureWarning,
+        )
+        from pandas.tests.extension.base.reduce import BaseBooleanReduceTests
+
+        return BaseBooleanReduceTests
+
+    raise AttributeError(
+        f"module 'pandas.tests.extension.base' has no attribute '{name}'"
+    )

lib/python3.12/site-packages/pandas/tests/extension/base/accumulate.py

@@ -0,0 +1,39 @@
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+class BaseAccumulateTests:
+    """
+    Accumulation specific tests. Generally these only
+    make sense for numeric/boolean operations.
+    """
+
+    def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
+        # Do we expect this accumulation to be supported for this dtype?
+        # We default to assuming "no"; subclass authors should override here.
+        return False
+
+    def check_accumulate(self, ser: pd.Series, op_name: str, skipna: bool):
+        try:
+            alt = ser.astype("float64")
+        except TypeError:
+            # e.g. Period can't be cast to float64
+            alt = ser.astype(object)
+
+        result = getattr(ser, op_name)(skipna=skipna)
+        expected = getattr(alt, op_name)(skipna=skipna)
+        tm.assert_series_equal(result, expected, check_dtype=False)
+
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_accumulate_series(self, data, all_numeric_accumulations, skipna):
+        op_name = all_numeric_accumulations
+        ser = pd.Series(data)
+
+        if self._supports_accumulation(ser, op_name):
+            self.check_accumulate(ser, op_name, skipna)
+        else:
+            with pytest.raises((NotImplementedError, TypeError)):
+                # TODO: require TypeError for things that will _never_ work?
+                getattr(ser, op_name)(skipna=skipna)

lib/python3.12/site-packages/pandas/tests/extension/base/base.py

@@ -0,0 +1,2 @@
+class BaseExtensionTests:
+    pass