Updated script that can be controled by Nodejs web app

lib/python3.13/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/python3.13/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/python3.13/site-packages/pandas/tests/apply/common.py

@@ -0,0 +1,7 @@
+from pandas.core.groupby.base import transformation_kernels
+
+# There is no Series.cumcount or DataFrame.cumcount
+series_transform_kernels = [
+    x for x in sorted(transformation_kernels) if x != "cumcount"
+]
+frame_transform_kernels = [x for x in sorted(transformation_kernels) if x != "cumcount"]

lib/python3.13/site-packages/pandas/tests/apply/test_frame_apply_relabeling.py

@@ -0,0 +1,113 @@
+import numpy as np
+import pytest
+
+from pandas.compat.numpy import np_version_gte1p25
+
+import pandas as pd
+import pandas._testing as tm
+
+
+def test_agg_relabel():
+    # GH 26513
+    df = pd.DataFrame({"A": [1, 2, 1, 2], "B": [1, 2, 3, 4], "C": [3, 4, 5, 6]})
+
+    # simplest case with one column, one func
+    result = df.agg(foo=("B", "sum"))
+    expected = pd.DataFrame({"B": [10]}, index=pd.Index(["foo"]))
+    tm.assert_frame_equal(result, expected)
+
+    # test on same column with different methods
+    result = df.agg(foo=("B", "sum"), bar=("B", "min"))
+    expected = pd.DataFrame({"B": [10, 1]}, index=pd.Index(["foo", "bar"]))
+
+    tm.assert_frame_equal(result, expected)
+
+
+def test_agg_relabel_multi_columns_multi_methods():
+    # GH 26513, test on multiple columns with multiple methods
+    df = pd.DataFrame({"A": [1, 2, 1, 2], "B": [1, 2, 3, 4], "C": [3, 4, 5, 6]})
+    result = df.agg(
+        foo=("A", "sum"),
+        bar=("B", "mean"),
+        cat=("A", "min"),
+        dat=("B", "max"),
+        f=("A", "max"),
+        g=("C", "min"),
+    )
+    expected = pd.DataFrame(
+        {
+            "A": [6.0, np.nan, 1.0, np.nan, 2.0, np.nan],
+            "B": [np.nan, 2.5, np.nan, 4.0, np.nan, np.nan],
+            "C": [np.nan, np.nan, np.nan, np.nan, np.nan, 3.0],
+        },
+        index=pd.Index(["foo", "bar", "cat", "dat", "f", "g"]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.xfail(np_version_gte1p25, reason="name of min now equals name of np.min")
+def test_agg_relabel_partial_functions():
+    # GH 26513, test on partial, functools or more complex cases
+    df = pd.DataFrame({"A": [1, 2, 1, 2], "B": [1, 2, 3, 4], "C": [3, 4, 5, 6]})
+    msg = "using Series.[mean|min]"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = df.agg(foo=("A", np.mean), bar=("A", "mean"), cat=("A", min))
+    expected = pd.DataFrame(
+        {"A": [1.5, 1.5, 1.0]}, index=pd.Index(["foo", "bar", "cat"])
+    )
+    tm.assert_frame_equal(result, expected)
+
+    msg = "using Series.[mean|min|max|sum]"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = df.agg(
+            foo=("A", min),
+            bar=("A", np.min),
+            cat=("B", max),
+            dat=("C", "min"),
+            f=("B", np.sum),
+            kk=("B", lambda x: min(x)),
+        )
+    expected = pd.DataFrame(
+        {
+            "A": [1.0, 1.0, np.nan, np.nan, np.nan, np.nan],
+            "B": [np.nan, np.nan, 4.0, np.nan, 10.0, 1.0],
+            "C": [np.nan, np.nan, np.nan, 3.0, np.nan, np.nan],
+        },
+        index=pd.Index(["foo", "bar", "cat", "dat", "f", "kk"]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+def test_agg_namedtuple():
+    # GH 26513
+    df = pd.DataFrame({"A": [0, 1], "B": [1, 2]})
+    result = df.agg(
+        foo=pd.NamedAgg("B", "sum"),
+        bar=pd.NamedAgg("B", "min"),
+        cat=pd.NamedAgg(column="B", aggfunc="count"),
+        fft=pd.NamedAgg("B", aggfunc="max"),
+    )
+
+    expected = pd.DataFrame(
+        {"B": [3, 1, 2, 2]}, index=pd.Index(["foo", "bar", "cat", "fft"])
+    )
+    tm.assert_frame_equal(result, expected)
+
+    result = df.agg(
+        foo=pd.NamedAgg("A", "min"),
+        bar=pd.NamedAgg(column="B", aggfunc="max"),
+        cat=pd.NamedAgg(column="A", aggfunc="max"),
+    )
+    expected = pd.DataFrame(
+        {"A": [0.0, np.nan, 1.0], "B": [np.nan, 2.0, np.nan]},
+        index=pd.Index(["foo", "bar", "cat"]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+def test_reconstruct_func():
+    # GH 28472, test to ensure reconstruct_func isn't moved;
+    # This method is used by other libraries (e.g. dask)
+    result = pd.core.apply.reconstruct_func("min")
+    expected = (False, "min", None, None)
+    tm.assert_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/apply/test_frame_transform.py

@@ -0,0 +1,264 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    DataFrame,
+    MultiIndex,
+    Series,
+)
+import pandas._testing as tm
+from pandas.tests.apply.common import frame_transform_kernels
+from pandas.tests.frame.common import zip_frames
+
+
+def unpack_obj(obj, klass, axis):
+    """
+    Helper to ensure we have the right type of object for a test parametrized
+    over frame_or_series.
+    """
+    if klass is not DataFrame:
+        obj = obj["A"]
+        if axis != 0:
+            pytest.skip(f"Test is only for DataFrame with axis={axis}")
+    return obj
+
+
+def test_transform_ufunc(axis, float_frame, frame_or_series):
+    # GH 35964
+    obj = unpack_obj(float_frame, frame_or_series, axis)
+
+    with np.errstate(all="ignore"):
+        f_sqrt = np.sqrt(obj)
+
+    # ufunc
+    result = obj.transform(np.sqrt, axis=axis)
+    expected = f_sqrt
+    tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops, names",
+    [
+        ([np.sqrt], ["sqrt"]),
+        ([np.abs, np.sqrt], ["absolute", "sqrt"]),
+        (np.array([np.sqrt]), ["sqrt"]),
+        (np.array([np.abs, np.sqrt]), ["absolute", "sqrt"]),
+    ],
+)
+def test_transform_listlike(axis, float_frame, ops, names):
+    # GH 35964
+    other_axis = 1 if axis in {0, "index"} else 0
+    with np.errstate(all="ignore"):
+        expected = zip_frames([op(float_frame) for op in ops], axis=other_axis)
+    if axis in {0, "index"}:
+        expected.columns = MultiIndex.from_product([float_frame.columns, names])
+    else:
+        expected.index = MultiIndex.from_product([float_frame.index, names])
+    result = float_frame.transform(ops, axis=axis)
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("ops", [[], np.array([])])
+def test_transform_empty_listlike(float_frame, ops, frame_or_series):
+    obj = unpack_obj(float_frame, frame_or_series, 0)
+
+    with pytest.raises(ValueError, match="No transform functions were provided"):
+        obj.transform(ops)
+
+
+def test_transform_listlike_func_with_args():
+    # GH 50624
+    df = DataFrame({"x": [1, 2, 3]})
+
+    def foo1(x, a=1, c=0):
+        return x + a + c
+
+    def foo2(x, b=2, c=0):
+        return x + b + c
+
+    msg = r"foo1\(\) got an unexpected keyword argument 'b'"
+    with pytest.raises(TypeError, match=msg):
+        df.transform([foo1, foo2], 0, 3, b=3, c=4)
+
+    result = df.transform([foo1, foo2], 0, 3, c=4)
+    expected = DataFrame(
+        [[8, 8], [9, 9], [10, 10]],
+        columns=MultiIndex.from_tuples([("x", "foo1"), ("x", "foo2")]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [dict, Series])
+def test_transform_dictlike(axis, float_frame, box):
+    # GH 35964
+    if axis in (0, "index"):
+        e = float_frame.columns[0]
+        expected = float_frame[[e]].transform(np.abs)
+    else:
+        e = float_frame.index[0]
+        expected = float_frame.iloc[[0]].transform(np.abs)
+    result = float_frame.transform(box({e: np.abs}), axis=axis)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_transform_dictlike_mixed():
+    # GH 40018 - mix of lists and non-lists in values of a dictionary
+    df = DataFrame({"a": [1, 2], "b": [1, 4], "c": [1, 4]})
+    result = df.transform({"b": ["sqrt", "abs"], "c": "sqrt"})
+    expected = DataFrame(
+        [[1.0, 1, 1.0], [2.0, 4, 2.0]],
+        columns=MultiIndex([("b", "c"), ("sqrt", "abs")], [(0, 0, 1), (0, 1, 0)]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops",
+    [
+        {},
+        {"A": []},
+        {"A": [], "B": "cumsum"},
+        {"A": "cumsum", "B": []},
+        {"A": [], "B": ["cumsum"]},
+        {"A": ["cumsum"], "B": []},
+    ],
+)
+def test_transform_empty_dictlike(float_frame, ops, frame_or_series):
+    obj = unpack_obj(float_frame, frame_or_series, 0)
+
+    with pytest.raises(ValueError, match="No transform functions were provided"):
+        obj.transform(ops)
+
+
+@pytest.mark.parametrize("use_apply", [True, False])
+def test_transform_udf(axis, float_frame, use_apply, frame_or_series):
+    # GH 35964
+    obj = unpack_obj(float_frame, frame_or_series, axis)
+
+    # transform uses UDF either via apply or passing the entire DataFrame
+    def func(x):
+        # transform is using apply iff x is not a DataFrame
+        if use_apply == isinstance(x, frame_or_series):
+            # Force transform to fallback
+            raise ValueError
+        return x + 1
+
+    result = obj.transform(func, axis=axis)
+    expected = obj + 1
+    tm.assert_equal(result, expected)
+
+
+wont_fail = ["ffill", "bfill", "fillna", "pad", "backfill", "shift"]
+frame_kernels_raise = [x for x in frame_transform_kernels if x not in wont_fail]
+
+
+@pytest.mark.parametrize("op", [*frame_kernels_raise, lambda x: x + 1])
+def test_transform_bad_dtype(op, frame_or_series, request):
+    # GH 35964
+    if op == "ngroup":
+        request.applymarker(
+            pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
+        )
+
+    obj = DataFrame({"A": 3 * [object]})  # DataFrame that will fail on most transforms
+    obj = tm.get_obj(obj, frame_or_series)
+    error = TypeError
+    msg = "|".join(
+        [
+            "not supported between instances of 'type' and 'type'",
+            "unsupported operand type",
+        ]
+    )
+
+    with pytest.raises(error, match=msg):
+        obj.transform(op)
+    with pytest.raises(error, match=msg):
+        obj.transform([op])
+    with pytest.raises(error, match=msg):
+        obj.transform({"A": op})
+    with pytest.raises(error, match=msg):
+        obj.transform({"A": [op]})
+
+
+@pytest.mark.parametrize("op", frame_kernels_raise)
+def test_transform_failure_typeerror(request, op):
+    # GH 35964
+
+    if op == "ngroup":
+        request.applymarker(
+            pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
+        )
+
+    # Using object makes most transform kernels fail
+    df = DataFrame({"A": 3 * [object], "B": [1, 2, 3]})
+    error = TypeError
+    msg = "|".join(
+        [
+            "not supported between instances of 'type' and 'type'",
+            "unsupported operand type",
+        ]
+    )
+
+    with pytest.raises(error, match=msg):
+        df.transform([op])
+
+    with pytest.raises(error, match=msg):
+        df.transform({"A": op, "B": op})
+
+    with pytest.raises(error, match=msg):
+        df.transform({"A": [op], "B": [op]})
+
+    with pytest.raises(error, match=msg):
+        df.transform({"A": [op, "shift"], "B": [op]})
+
+
+def test_transform_failure_valueerror():
+    # GH 40211
+    def op(x):
+        if np.sum(np.sum(x)) < 10:
+            raise ValueError
+        return x
+
+    df = DataFrame({"A": [1, 2, 3], "B": [400, 500, 600]})
+    msg = "Transform function failed"
+
+    with pytest.raises(ValueError, match=msg):
+        df.transform([op])
+
+    with pytest.raises(ValueError, match=msg):
+        df.transform({"A": op, "B": op})
+
+    with pytest.raises(ValueError, match=msg):
+        df.transform({"A": [op], "B": [op]})
+
+    with pytest.raises(ValueError, match=msg):
+        df.transform({"A": [op, "shift"], "B": [op]})
+
+
+@pytest.mark.parametrize("use_apply", [True, False])
+def test_transform_passes_args(use_apply, frame_or_series):
+    # GH 35964
+    # transform uses UDF either via apply or passing the entire DataFrame
+    expected_args = [1, 2]
+    expected_kwargs = {"c": 3}
+
+    def f(x, a, b, c):
+        # transform is using apply iff x is not a DataFrame
+        if use_apply == isinstance(x, frame_or_series):
+            # Force transform to fallback
+            raise ValueError
+        assert [a, b] == expected_args
+        assert c == expected_kwargs["c"]
+        return x
+
+    frame_or_series([1]).transform(f, 0, *expected_args, **expected_kwargs)
+
+
+def test_transform_empty_dataframe():
+    # https://github.com/pandas-dev/pandas/issues/39636
+    df = DataFrame([], columns=["col1", "col2"])
+    result = df.transform(lambda x: x + 10)
+    tm.assert_frame_equal(result, df)
+
+    result = df["col1"].transform(lambda x: x + 10)
+    tm.assert_series_equal(result, df["col1"])

lib/python3.13/site-packages/pandas/tests/apply/test_invalid_arg.py

@@ -0,0 +1,361 @@
+# Tests specifically aimed at detecting bad arguments.
+# This file is organized by reason for exception.
+#     1. always invalid argument values
+#     2. missing column(s)
+#     3. incompatible ops/dtype/args/kwargs
+#     4. invalid result shape/type
+# If your test does not fit into one of these categories, add to this list.
+
+from itertools import chain
+import re
+
+import numpy as np
+import pytest
+
+from pandas.errors import SpecificationError
+
+from pandas import (
+    DataFrame,
+    Series,
+    date_range,
+)
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize("result_type", ["foo", 1])
+def test_result_type_error(result_type):
+    # allowed result_type
+    df = DataFrame(
+        np.tile(np.arange(3, dtype="int64"), 6).reshape(6, -1) + 1,
+        columns=["A", "B", "C"],
+    )
+
+    msg = (
+        "invalid value for result_type, must be one of "
+        "{None, 'reduce', 'broadcast', 'expand'}"
+    )
+    with pytest.raises(ValueError, match=msg):
+        df.apply(lambda x: [1, 2, 3], axis=1, result_type=result_type)
+
+
+def test_apply_invalid_axis_value():
+    df = DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]], index=["a", "a", "c"])
+    msg = "No axis named 2 for object type DataFrame"
+    with pytest.raises(ValueError, match=msg):
+        df.apply(lambda x: x, 2)
+
+
+def test_agg_raises():
+    # GH 26513
+    df = DataFrame({"A": [0, 1], "B": [1, 2]})
+    msg = "Must provide"
+
+    with pytest.raises(TypeError, match=msg):
+        df.agg()
+
+
+def test_map_with_invalid_na_action_raises():
+    # https://github.com/pandas-dev/pandas/issues/32815
+    s = Series([1, 2, 3])
+    msg = "na_action must either be 'ignore' or None"
+    with pytest.raises(ValueError, match=msg):
+        s.map(lambda x: x, na_action="____")
+
+
+@pytest.mark.parametrize("input_na_action", ["____", True])
+def test_map_arg_is_dict_with_invalid_na_action_raises(input_na_action):
+    # https://github.com/pandas-dev/pandas/issues/46588
+    s = Series([1, 2, 3])
+    msg = f"na_action must either be 'ignore' or None, {input_na_action} was passed"
+    with pytest.raises(ValueError, match=msg):
+        s.map({1: 2}, na_action=input_na_action)
+
+
+@pytest.mark.parametrize("method", ["apply", "agg", "transform"])
+@pytest.mark.parametrize("func", [{"A": {"B": "sum"}}, {"A": {"B": ["sum"]}}])
+def test_nested_renamer(frame_or_series, method, func):
+    # GH 35964
+    obj = frame_or_series({"A": [1]})
+    match = "nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=match):
+        getattr(obj, method)(func)
+
+
+@pytest.mark.parametrize(
+    "renamer",
+    [{"foo": ["min", "max"]}, {"foo": ["min", "max"], "bar": ["sum", "mean"]}],
+)
+def test_series_nested_renamer(renamer):
+    s = Series(range(6), dtype="int64", name="series")
+    msg = "nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        s.agg(renamer)
+
+
+def test_apply_dict_depr():
+    tsdf = DataFrame(
+        np.random.default_rng(2).standard_normal((10, 3)),
+        columns=["A", "B", "C"],
+        index=date_range("1/1/2000", periods=10),
+    )
+    msg = "nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        tsdf.A.agg({"foo": ["sum", "mean"]})
+
+
+@pytest.mark.parametrize("method", ["agg", "transform"])
+def test_dict_nested_renaming_depr(method):
+    df = DataFrame({"A": range(5), "B": 5})
+
+    # nested renaming
+    msg = r"nested renamer is not supported"
+    with pytest.raises(SpecificationError, match=msg):
+        getattr(df, method)({"A": {"foo": "min"}, "B": {"bar": "max"}})
+
+
+@pytest.mark.parametrize("method", ["apply", "agg", "transform"])
+@pytest.mark.parametrize("func", [{"B": "sum"}, {"B": ["sum"]}])
+def test_missing_column(method, func):
+    # GH 40004
+    obj = DataFrame({"A": [1]})
+    match = re.escape("Column(s) ['B'] do not exist")
+    with pytest.raises(KeyError, match=match):
+        getattr(obj, method)(func)
+
+
+def test_transform_mixed_column_name_dtypes():
+    # GH39025
+    df = DataFrame({"a": ["1"]})
+    msg = r"Column\(s\) \[1, 'b'\] do not exist"
+    with pytest.raises(KeyError, match=msg):
+        df.transform({"a": int, 1: str, "b": int})
+
+
+@pytest.mark.parametrize(
+    "how, args", [("pct_change", ()), ("nsmallest", (1, ["a", "b"])), ("tail", 1)]
+)
+def test_apply_str_axis_1_raises(how, args):
+    # GH 39211 - some ops don't support axis=1
+    df = DataFrame({"a": [1, 2], "b": [3, 4]})
+    msg = f"Operation {how} does not support axis=1"
+    with pytest.raises(ValueError, match=msg):
+        df.apply(how, axis=1, args=args)
+
+
+def test_transform_axis_1_raises():
+    # GH 35964
+    msg = "No axis named 1 for object type Series"
+    with pytest.raises(ValueError, match=msg):
+        Series([1]).transform("sum", axis=1)
+
+
+def test_apply_modify_traceback():
+    data = DataFrame(
+        {
+            "A": [
+                "foo",
+                "foo",
+                "foo",
+                "foo",
+                "bar",
+                "bar",
+                "bar",
+                "bar",
+                "foo",
+                "foo",
+                "foo",
+            ],
+            "B": [
+                "one",
+                "one",
+                "one",
+                "two",
+                "one",
+                "one",
+                "one",
+                "two",
+                "two",
+                "two",
+                "one",
+            ],
+            "C": [
+                "dull",
+                "dull",
+                "shiny",
+                "dull",
+                "dull",
+                "shiny",
+                "shiny",
+                "dull",
+                "shiny",
+                "shiny",
+                "shiny",
+            ],
+            "D": np.random.default_rng(2).standard_normal(11),
+            "E": np.random.default_rng(2).standard_normal(11),
+            "F": np.random.default_rng(2).standard_normal(11),
+        }
+    )
+
+    data.loc[4, "C"] = np.nan
+
+    def transform(row):
+        if row["C"].startswith("shin") and row["A"] == "foo":
+            row["D"] = 7
+        return row
+
+    msg = "'float' object has no attribute 'startswith'"
+    with pytest.raises(AttributeError, match=msg):
+        data.apply(transform, axis=1)
+
+
+@pytest.mark.parametrize(
+    "df, func, expected",
+    tm.get_cython_table_params(
+        DataFrame([["a", "b"], ["b", "a"]]), [["cumprod", TypeError]]
+    ),
+)
+def test_agg_cython_table_raises_frame(df, func, expected, axis, using_infer_string):
+    # GH 21224
+    if using_infer_string:
+        import pyarrow as pa
+
+        expected = (expected, pa.lib.ArrowNotImplementedError)
+
+    msg = "can't multiply sequence by non-int of type 'str'|has no kernel"
+    warn = None if isinstance(func, str) else FutureWarning
+    with pytest.raises(expected, match=msg):
+        with tm.assert_produces_warning(warn, match="using DataFrame.cumprod"):
+            df.agg(func, axis=axis)
+
+
+@pytest.mark.parametrize(
+    "series, func, expected",
+    chain(
+        tm.get_cython_table_params(
+            Series("a b c".split()),
+            [
+                ("mean", TypeError),  # mean raises TypeError
+                ("prod", TypeError),
+                ("std", TypeError),
+                ("var", TypeError),
+                ("median", TypeError),
+                ("cumprod", TypeError),
+            ],
+        )
+    ),
+)
+def test_agg_cython_table_raises_series(series, func, expected, using_infer_string):
+    # GH21224
+    msg = r"[Cc]ould not convert|can't multiply sequence by non-int of type"
+    if func == "median" or func is np.nanmedian or func is np.median:
+        msg = r"Cannot convert \['a' 'b' 'c'\] to numeric"
+
+    if using_infer_string:
+        import pyarrow as pa
+
+        expected = (expected, pa.lib.ArrowNotImplementedError)
+
+    msg = msg + "|does not support|has no kernel"
+    warn = None if isinstance(func, str) else FutureWarning
+
+    with pytest.raises(expected, match=msg):
+        # e.g. Series('a b'.split()).cumprod() will raise
+        with tm.assert_produces_warning(warn, match="is currently using Series.*"):
+            series.agg(func)
+
+
+def test_agg_none_to_type():
+    # GH 40543
+    df = DataFrame({"a": [None]})
+    msg = re.escape("int() argument must be a string")
+    with pytest.raises(TypeError, match=msg):
+        df.agg({"a": lambda x: int(x.iloc[0])})
+
+
+def test_transform_none_to_type():
+    # GH#34377
+    df = DataFrame({"a": [None]})
+    msg = "argument must be a"
+    with pytest.raises(TypeError, match=msg):
+        df.transform({"a": lambda x: int(x.iloc[0])})
+
+
+@pytest.mark.parametrize(
+    "func",
+    [
+        lambda x: np.array([1, 2]).reshape(-1, 2),
+        lambda x: [1, 2],
+        lambda x: Series([1, 2]),
+    ],
+)
+def test_apply_broadcast_error(func):
+    df = DataFrame(
+        np.tile(np.arange(3, dtype="int64"), 6).reshape(6, -1) + 1,
+        columns=["A", "B", "C"],
+    )
+
+    # > 1 ndim
+    msg = "too many dims to broadcast|cannot broadcast result"
+    with pytest.raises(ValueError, match=msg):
+        df.apply(func, axis=1, result_type="broadcast")
+
+
+def test_transform_and_agg_err_agg(axis, float_frame):
+    # cannot both transform and agg
+    msg = "cannot combine transform and aggregation operations"
+    with pytest.raises(ValueError, match=msg):
+        with np.errstate(all="ignore"):
+            float_frame.agg(["max", "sqrt"], axis=axis)
+
+
+@pytest.mark.filterwarnings("ignore::FutureWarning")  # GH53325
+@pytest.mark.parametrize(
+    "func, msg",
+    [
+        (["sqrt", "max"], "cannot combine transform and aggregation"),
+        (
+            {"foo": np.sqrt, "bar": "sum"},
+            "cannot perform both aggregation and transformation",
+        ),
+    ],
+)
+def test_transform_and_agg_err_series(string_series, func, msg):
+    # we are trying to transform with an aggregator
+    with pytest.raises(ValueError, match=msg):
+        with np.errstate(all="ignore"):
+            string_series.agg(func)
+
+
+@pytest.mark.parametrize("func", [["max", "min"], ["max", "sqrt"]])
+def test_transform_wont_agg_frame(axis, float_frame, func):
+    # GH 35964
+    # cannot both transform and agg
+    msg = "Function did not transform"
+    with pytest.raises(ValueError, match=msg):
+        float_frame.transform(func, axis=axis)
+
+
+@pytest.mark.parametrize("func", [["min", "max"], ["sqrt", "max"]])
+def test_transform_wont_agg_series(string_series, func):
+    # GH 35964
+    # we are trying to transform with an aggregator
+    msg = "Function did not transform"
+
+    with pytest.raises(ValueError, match=msg):
+        string_series.transform(func)
+
+
+@pytest.mark.parametrize(
+    "op_wrapper", [lambda x: x, lambda x: [x], lambda x: {"A": x}, lambda x: {"A": [x]}]
+)
+def test_transform_reducer_raises(all_reductions, frame_or_series, op_wrapper):
+    # GH 35964
+    op = op_wrapper(all_reductions)
+
+    obj = DataFrame({"A": [1, 2, 3]})
+    obj = tm.get_obj(obj, frame_or_series)
+
+    msg = "Function did not transform"
+    with pytest.raises(ValueError, match=msg):
+        obj.transform(op)

lib/python3.13/site-packages/pandas/tests/apply/test_numba.py

@@ -0,0 +1,118 @@
+import numpy as np
+import pytest
+
+import pandas.util._test_decorators as td
+
+from pandas import (
+    DataFrame,
+    Index,
+)
+import pandas._testing as tm
+
+pytestmark = [td.skip_if_no("numba"), pytest.mark.single_cpu]
+
+
+@pytest.fixture(params=[0, 1])
+def apply_axis(request):
+    return request.param
+
+
+def test_numba_vs_python_noop(float_frame, apply_axis):
+    func = lambda x: x
+    result = float_frame.apply(func, engine="numba", axis=apply_axis)
+    expected = float_frame.apply(func, engine="python", axis=apply_axis)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_numba_vs_python_string_index():
+    # GH#56189
+    pytest.importorskip("pyarrow")
+    df = DataFrame(
+        1,
+        index=Index(["a", "b"], dtype="string[pyarrow_numpy]"),
+        columns=Index(["x", "y"], dtype="string[pyarrow_numpy]"),
+    )
+    func = lambda x: x
+    result = df.apply(func, engine="numba", axis=0)
+    expected = df.apply(func, engine="python", axis=0)
+    tm.assert_frame_equal(
+        result, expected, check_column_type=False, check_index_type=False
+    )
+
+
+def test_numba_vs_python_indexing():
+    frame = DataFrame(
+        {"a": [1, 2, 3], "b": [4, 5, 6], "c": [7.0, 8.0, 9.0]},
+        index=Index(["A", "B", "C"]),
+    )
+    row_func = lambda x: x["c"]
+    result = frame.apply(row_func, engine="numba", axis=1)
+    expected = frame.apply(row_func, engine="python", axis=1)
+    tm.assert_series_equal(result, expected)
+
+    col_func = lambda x: x["A"]
+    result = frame.apply(col_func, engine="numba", axis=0)
+    expected = frame.apply(col_func, engine="python", axis=0)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "reduction",
+    [lambda x: x.mean(), lambda x: x.min(), lambda x: x.max(), lambda x: x.sum()],
+)
+def test_numba_vs_python_reductions(reduction, apply_axis):
+    df = DataFrame(np.ones((4, 4), dtype=np.float64))
+    result = df.apply(reduction, engine="numba", axis=apply_axis)
+    expected = df.apply(reduction, engine="python", axis=apply_axis)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("colnames", [[1, 2, 3], [1.0, 2.0, 3.0]])
+def test_numba_numeric_colnames(colnames):
+    # Check that numeric column names lower properly and can be indxed on
+    df = DataFrame(
+        np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype=np.int64), columns=colnames
+    )
+    first_col = colnames[0]
+    f = lambda x: x[first_col]  # Get the first column
+    result = df.apply(f, engine="numba", axis=1)
+    expected = df.apply(f, engine="python", axis=1)
+    tm.assert_series_equal(result, expected)
+
+
+def test_numba_parallel_unsupported(float_frame):
+    f = lambda x: x
+    with pytest.raises(
+        NotImplementedError,
+        match="Parallel apply is not supported when raw=False and engine='numba'",
+    ):
+        float_frame.apply(f, engine="numba", engine_kwargs={"parallel": True})
+
+
+def test_numba_nonunique_unsupported(apply_axis):
+    f = lambda x: x
+    df = DataFrame({"a": [1, 2]}, index=Index(["a", "a"]))
+    with pytest.raises(
+        NotImplementedError,
+        match="The index/columns must be unique when raw=False and engine='numba'",
+    ):
+        df.apply(f, engine="numba", axis=apply_axis)
+
+
+def test_numba_unsupported_dtypes(apply_axis):
+    f = lambda x: x
+    df = DataFrame({"a": [1, 2], "b": ["a", "b"], "c": [4, 5]})
+    df["c"] = df["c"].astype("double[pyarrow]")
+
+    with pytest.raises(
+        ValueError,
+        match="Column b must have a numeric dtype. Found 'object|string' instead",
+    ):
+        df.apply(f, engine="numba", axis=apply_axis)
+
+    with pytest.raises(
+        ValueError,
+        match="Column c is backed by an extension array, "
+        "which is not supported by the numba engine.",
+    ):
+        df["c"].to_frame().apply(f, engine="numba", axis=apply_axis)

lib/python3.13/site-packages/pandas/tests/apply/test_series_apply.py

@@ -0,0 +1,701 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Index,
+    MultiIndex,
+    Series,
+    concat,
+    date_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+from pandas.tests.apply.common import series_transform_kernels
+
+
+@pytest.fixture(params=[False, "compat"])
+def by_row(request):
+    return request.param
+
+
+def test_series_map_box_timedelta(by_row):
+    # GH#11349
+    ser = Series(timedelta_range("1 day 1 s", periods=3, freq="h"))
+
+    def f(x):
+        return x.total_seconds() if by_row else x.dt.total_seconds()
+
+    result = ser.apply(f, by_row=by_row)
+
+    expected = ser.map(lambda x: x.total_seconds())
+    tm.assert_series_equal(result, expected)
+
+    expected = Series([86401.0, 90001.0, 93601.0])
+    tm.assert_series_equal(result, expected)
+
+
+def test_apply(datetime_series, by_row):
+    result = datetime_series.apply(np.sqrt, by_row=by_row)
+    with np.errstate(all="ignore"):
+        expected = np.sqrt(datetime_series)
+    tm.assert_series_equal(result, expected)
+
+    # element-wise apply (ufunc)
+    result = datetime_series.apply(np.exp, by_row=by_row)
+    expected = np.exp(datetime_series)
+    tm.assert_series_equal(result, expected)
+
+    # empty series
+    s = Series(dtype=object, name="foo", index=Index([], name="bar"))
+    rs = s.apply(lambda x: x, by_row=by_row)
+    tm.assert_series_equal(s, rs)
+
+    # check all metadata (GH 9322)
+    assert s is not rs
+    assert s.index is rs.index
+    assert s.dtype == rs.dtype
+    assert s.name == rs.name
+
+    # index but no data
+    s = Series(index=[1, 2, 3], dtype=np.float64)
+    rs = s.apply(lambda x: x, by_row=by_row)
+    tm.assert_series_equal(s, rs)
+
+
+def test_apply_map_same_length_inference_bug():
+    s = Series([1, 2])
+
+    def f(x):
+        return (x, x + 1)
+
+    result = s.apply(f, by_row="compat")
+    expected = s.map(f)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("convert_dtype", [True, False])
+def test_apply_convert_dtype_deprecated(convert_dtype):
+    ser = Series(np.random.default_rng(2).standard_normal(10))
+
+    def func(x):
+        return x if x > 0 else np.nan
+
+    with tm.assert_produces_warning(FutureWarning):
+        ser.apply(func, convert_dtype=convert_dtype, by_row="compat")
+
+
+def test_apply_args():
+    s = Series(["foo,bar"])
+
+    result = s.apply(str.split, args=(",",))
+    assert result[0] == ["foo", "bar"]
+    assert isinstance(result[0], list)
+
+
+@pytest.mark.parametrize(
+    "args, kwargs, increment",
+    [((), {}, 0), ((), {"a": 1}, 1), ((2, 3), {}, 32), ((1,), {"c": 2}, 201)],
+)
+def test_agg_args(args, kwargs, increment):
+    # GH 43357
+    def f(x, a=0, b=0, c=0):
+        return x + a + 10 * b + 100 * c
+
+    s = Series([1, 2])
+    msg = (
+        "in Series.agg cannot aggregate and has been deprecated. "
+        "Use Series.transform to keep behavior unchanged."
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = s.agg(f, 0, *args, **kwargs)
+    expected = s + increment
+    tm.assert_series_equal(result, expected)
+
+
+def test_agg_mapping_func_deprecated():
+    # GH 53325
+    s = Series([1, 2, 3])
+
+    def foo1(x, a=1, c=0):
+        return x + a + c
+
+    def foo2(x, b=2, c=0):
+        return x + b + c
+
+    msg = "using .+ in Series.agg cannot aggregate and"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        s.agg(foo1, 0, 3, c=4)
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        s.agg([foo1, foo2], 0, 3, c=4)
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        s.agg({"a": foo1, "b": foo2}, 0, 3, c=4)
+
+
+def test_series_apply_map_box_timestamps(by_row):
+    # GH#2689, GH#2627
+    ser = Series(date_range("1/1/2000", periods=10))
+
+    def func(x):
+        return (x.hour, x.day, x.month)
+
+    if not by_row:
+        msg = "Series' object has no attribute 'hour'"
+        with pytest.raises(AttributeError, match=msg):
+            ser.apply(func, by_row=by_row)
+        return
+
+    result = ser.apply(func, by_row=by_row)
+    expected = ser.map(func)
+    tm.assert_series_equal(result, expected)
+
+
+def test_apply_box_dt64():
+    # ufunc will not be boxed. Same test cases as the test_map_box
+    vals = [pd.Timestamp("2011-01-01"), pd.Timestamp("2011-01-02")]
+    ser = Series(vals, dtype="M8[ns]")
+    assert ser.dtype == "datetime64[ns]"
+    # boxed value must be Timestamp instance
+    res = ser.apply(lambda x: f"{type(x).__name__}_{x.day}_{x.tz}", by_row="compat")
+    exp = Series(["Timestamp_1_None", "Timestamp_2_None"])
+    tm.assert_series_equal(res, exp)
+
+
+def test_apply_box_dt64tz():
+    vals = [
+        pd.Timestamp("2011-01-01", tz="US/Eastern"),
+        pd.Timestamp("2011-01-02", tz="US/Eastern"),
+    ]
+    ser = Series(vals, dtype="M8[ns, US/Eastern]")
+    assert ser.dtype == "datetime64[ns, US/Eastern]"
+    res = ser.apply(lambda x: f"{type(x).__name__}_{x.day}_{x.tz}", by_row="compat")
+    exp = Series(["Timestamp_1_US/Eastern", "Timestamp_2_US/Eastern"])
+    tm.assert_series_equal(res, exp)
+
+
+def test_apply_box_td64():
+    # timedelta
+    vals = [pd.Timedelta("1 days"), pd.Timedelta("2 days")]
+    ser = Series(vals)
+    assert ser.dtype == "timedelta64[ns]"
+    res = ser.apply(lambda x: f"{type(x).__name__}_{x.days}", by_row="compat")
+    exp = Series(["Timedelta_1", "Timedelta_2"])
+    tm.assert_series_equal(res, exp)
+
+
+def test_apply_box_period():
+    # period
+    vals = [pd.Period("2011-01-01", freq="M"), pd.Period("2011-01-02", freq="M")]
+    ser = Series(vals)
+    assert ser.dtype == "Period[M]"
+    res = ser.apply(lambda x: f"{type(x).__name__}_{x.freqstr}", by_row="compat")
+    exp = Series(["Period_M", "Period_M"])
+    tm.assert_series_equal(res, exp)
+
+
+def test_apply_datetimetz(by_row):
+    values = date_range("2011-01-01", "2011-01-02", freq="h").tz_localize("Asia/Tokyo")
+    s = Series(values, name="XX")
+
+    result = s.apply(lambda x: x + pd.offsets.Day(), by_row=by_row)
+    exp_values = date_range("2011-01-02", "2011-01-03", freq="h").tz_localize(
+        "Asia/Tokyo"
+    )
+    exp = Series(exp_values, name="XX")
+    tm.assert_series_equal(result, exp)
+
+    result = s.apply(lambda x: x.hour if by_row else x.dt.hour, by_row=by_row)
+    exp = Series(list(range(24)) + [0], name="XX", dtype="int64" if by_row else "int32")
+    tm.assert_series_equal(result, exp)
+
+    # not vectorized
+    def f(x):
+        return str(x.tz) if by_row else str(x.dt.tz)
+
+    result = s.apply(f, by_row=by_row)
+    if by_row:
+        exp = Series(["Asia/Tokyo"] * 25, name="XX")
+        tm.assert_series_equal(result, exp)
+    else:
+        assert result == "Asia/Tokyo"
+
+
+def test_apply_categorical(by_row, using_infer_string):
+    values = pd.Categorical(list("ABBABCD"), categories=list("DCBA"), ordered=True)
+    ser = Series(values, name="XX", index=list("abcdefg"))
+
+    if not by_row:
+        msg = "Series' object has no attribute 'lower"
+        with pytest.raises(AttributeError, match=msg):
+            ser.apply(lambda x: x.lower(), by_row=by_row)
+        assert ser.apply(lambda x: "A", by_row=by_row) == "A"
+        return
+
+    result = ser.apply(lambda x: x.lower(), by_row=by_row)
+
+    # should be categorical dtype when the number of categories are
+    # the same
+    values = pd.Categorical(list("abbabcd"), categories=list("dcba"), ordered=True)
+    exp = Series(values, name="XX", index=list("abcdefg"))
+    tm.assert_series_equal(result, exp)
+    tm.assert_categorical_equal(result.values, exp.values)
+
+    result = ser.apply(lambda x: "A")
+    exp = Series(["A"] * 7, name="XX", index=list("abcdefg"))
+    tm.assert_series_equal(result, exp)
+    assert result.dtype == object if not using_infer_string else "string[pyarrow_numpy]"
+
+
+@pytest.mark.parametrize("series", [["1-1", "1-1", np.nan], ["1-1", "1-2", np.nan]])
+def test_apply_categorical_with_nan_values(series, by_row):
+    # GH 20714 bug fixed in: GH 24275
+    s = Series(series, dtype="category")
+    if not by_row:
+        msg = "'Series' object has no attribute 'split'"
+        with pytest.raises(AttributeError, match=msg):
+            s.apply(lambda x: x.split("-")[0], by_row=by_row)
+        return
+
+    result = s.apply(lambda x: x.split("-")[0], by_row=by_row)
+    result = result.astype(object)
+    expected = Series(["1", "1", np.nan], dtype="category")
+    expected = expected.astype(object)
+    tm.assert_series_equal(result, expected)
+
+
+def test_apply_empty_integer_series_with_datetime_index(by_row):
+    # GH 21245
+    s = Series([], index=date_range(start="2018-01-01", periods=0), dtype=int)
+    result = s.apply(lambda x: x, by_row=by_row)
+    tm.assert_series_equal(result, s)
+
+
+def test_apply_dataframe_iloc():
+    uintDF = DataFrame(np.uint64([1, 2, 3, 4, 5]), columns=["Numbers"])
+    indexDF = DataFrame([2, 3, 2, 1, 2], columns=["Indices"])
+
+    def retrieve(targetRow, targetDF):
+        val = targetDF["Numbers"].iloc[targetRow]
+        return val
+
+    result = indexDF["Indices"].apply(retrieve, args=(uintDF,))
+    expected = Series([3, 4, 3, 2, 3], name="Indices", dtype="uint64")
+    tm.assert_series_equal(result, expected)
+
+
+def test_transform(string_series, by_row):
+    # transforming functions
+
+    with np.errstate(all="ignore"):
+        f_sqrt = np.sqrt(string_series)
+        f_abs = np.abs(string_series)
+
+        # ufunc
+        result = string_series.apply(np.sqrt, by_row=by_row)
+        expected = f_sqrt.copy()
+        tm.assert_series_equal(result, expected)
+
+        # list-like
+        result = string_series.apply([np.sqrt], by_row=by_row)
+        expected = f_sqrt.to_frame().copy()
+        expected.columns = ["sqrt"]
+        tm.assert_frame_equal(result, expected)
+
+        result = string_series.apply(["sqrt"], by_row=by_row)
+        tm.assert_frame_equal(result, expected)
+
+        # multiple items in list
+        # these are in the order as if we are applying both functions per
+        # series and then concatting
+        expected = concat([f_sqrt, f_abs], axis=1)
+        expected.columns = ["sqrt", "absolute"]
+        result = string_series.apply([np.sqrt, np.abs], by_row=by_row)
+        tm.assert_frame_equal(result, expected)
+
+        # dict, provide renaming
+        expected = concat([f_sqrt, f_abs], axis=1)
+        expected.columns = ["foo", "bar"]
+        expected = expected.unstack().rename("series")
+
+        result = string_series.apply({"foo": np.sqrt, "bar": np.abs}, by_row=by_row)
+        tm.assert_series_equal(result.reindex_like(expected), expected)
+
+
+@pytest.mark.parametrize("op", series_transform_kernels)
+def test_transform_partial_failure(op, request):
+    # GH 35964
+    if op in ("ffill", "bfill", "pad", "backfill", "shift"):
+        request.applymarker(
+            pytest.mark.xfail(reason=f"{op} is successful on any dtype")
+        )
+
+    # Using object makes most transform kernels fail
+    ser = Series(3 * [object])
+
+    if op in ("fillna", "ngroup"):
+        error = ValueError
+        msg = "Transform function failed"
+    else:
+        error = TypeError
+        msg = "|".join(
+            [
+                "not supported between instances of 'type' and 'type'",
+                "unsupported operand type",
+            ]
+        )
+
+    with pytest.raises(error, match=msg):
+        ser.transform([op, "shift"])
+
+    with pytest.raises(error, match=msg):
+        ser.transform({"A": op, "B": "shift"})
+
+    with pytest.raises(error, match=msg):
+        ser.transform({"A": [op], "B": ["shift"]})
+
+    with pytest.raises(error, match=msg):
+        ser.transform({"A": [op, "shift"], "B": [op]})
+
+
+def test_transform_partial_failure_valueerror():
+    # GH 40211
+    def noop(x):
+        return x
+
+    def raising_op(_):
+        raise ValueError
+
+    ser = Series(3 * [object])
+    msg = "Transform function failed"
+
+    with pytest.raises(ValueError, match=msg):
+        ser.transform([noop, raising_op])
+
+    with pytest.raises(ValueError, match=msg):
+        ser.transform({"A": raising_op, "B": noop})
+
+    with pytest.raises(ValueError, match=msg):
+        ser.transform({"A": [raising_op], "B": [noop]})
+
+    with pytest.raises(ValueError, match=msg):
+        ser.transform({"A": [noop, raising_op], "B": [noop]})
+
+
+def test_demo():
+    # demonstration tests
+    s = Series(range(6), dtype="int64", name="series")
+
+    result = s.agg(["min", "max"])
+    expected = Series([0, 5], index=["min", "max"], name="series")
+    tm.assert_series_equal(result, expected)
+
+    result = s.agg({"foo": "min"})
+    expected = Series([0], index=["foo"], name="series")
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("func", [str, lambda x: str(x)])
+def test_apply_map_evaluate_lambdas_the_same(string_series, func, by_row):
+    # test that we are evaluating row-by-row first if by_row="compat"
+    # else vectorized evaluation
+    result = string_series.apply(func, by_row=by_row)
+
+    if by_row:
+        expected = string_series.map(func)
+        tm.assert_series_equal(result, expected)
+    else:
+        assert result == str(string_series)
+
+
+def test_agg_evaluate_lambdas(string_series):
+    # GH53325
+    # in the future, the result will be a Series class.
+
+    with tm.assert_produces_warning(FutureWarning):
+        result = string_series.agg(lambda x: type(x))
+    assert isinstance(result, Series) and len(result) == len(string_series)
+
+    with tm.assert_produces_warning(FutureWarning):
+        result = string_series.agg(type)
+    assert isinstance(result, Series) and len(result) == len(string_series)
+
+
+@pytest.mark.parametrize("op_name", ["agg", "apply"])
+def test_with_nested_series(datetime_series, op_name):
+    # GH 2316
+    # .agg with a reducer and a transform, what to do
+    msg = "cannot aggregate"
+    warning = FutureWarning if op_name == "agg" else None
+    with tm.assert_produces_warning(warning, match=msg):
+        # GH52123
+        result = getattr(datetime_series, op_name)(
+            lambda x: Series([x, x**2], index=["x", "x^2"])
+        )
+    expected = DataFrame({"x": datetime_series, "x^2": datetime_series**2})
+    tm.assert_frame_equal(result, expected)
+
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = datetime_series.agg(lambda x: Series([x, x**2], index=["x", "x^2"]))
+    tm.assert_frame_equal(result, expected)
+
+
+def test_replicate_describe(string_series):
+    # this also tests a result set that is all scalars
+    expected = string_series.describe()
+    result = string_series.apply(
+        {
+            "count": "count",
+            "mean": "mean",
+            "std": "std",
+            "min": "min",
+            "25%": lambda x: x.quantile(0.25),
+            "50%": "median",
+            "75%": lambda x: x.quantile(0.75),
+            "max": "max",
+        },
+    )
+    tm.assert_series_equal(result, expected)
+
+
+def test_reduce(string_series):
+    # reductions with named functions
+    result = string_series.agg(["sum", "mean"])
+    expected = Series(
+        [string_series.sum(), string_series.mean()],
+        ["sum", "mean"],
+        name=string_series.name,
+    )
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "how, kwds",
+    [("agg", {}), ("apply", {"by_row": "compat"}), ("apply", {"by_row": False})],
+)
+def test_non_callable_aggregates(how, kwds):
+    # test agg using non-callable series attributes
+    # GH 39116 - expand to apply
+    s = Series([1, 2, None])
+
+    # Calling agg w/ just a string arg same as calling s.arg
+    result = getattr(s, how)("size", **kwds)
+    expected = s.size
+    assert result == expected
+
+    # test when mixed w/ callable reducers
+    result = getattr(s, how)(["size", "count", "mean"], **kwds)
+    expected = Series({"size": 3.0, "count": 2.0, "mean": 1.5})
+    tm.assert_series_equal(result, expected)
+
+    result = getattr(s, how)({"size": "size", "count": "count", "mean": "mean"}, **kwds)
+    tm.assert_series_equal(result, expected)
+
+
+def test_series_apply_no_suffix_index(by_row):
+    # GH36189
+    s = Series([4] * 3)
+    result = s.apply(["sum", lambda x: x.sum(), lambda x: x.sum()], by_row=by_row)
+    expected = Series([12, 12, 12], index=["sum", "<lambda>", "<lambda>"])
+
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "dti,exp",
+    [
+        (
+            Series([1, 2], index=pd.DatetimeIndex([0, 31536000000])),
+            DataFrame(np.repeat([[1, 2]], 2, axis=0), dtype="int64"),
+        ),
+        (
+            Series(
+                np.arange(10, dtype=np.float64),
+                index=date_range("2020-01-01", periods=10),
+                name="ts",
+            ),
+            DataFrame(np.repeat([[1, 2]], 10, axis=0), dtype="int64"),
+        ),
+    ],
+)
+@pytest.mark.parametrize("aware", [True, False])
+def test_apply_series_on_date_time_index_aware_series(dti, exp, aware):
+    # GH 25959
+    # Calling apply on a localized time series should not cause an error
+    if aware:
+        index = dti.tz_localize("UTC").index
+    else:
+        index = dti.index
+    result = Series(index).apply(lambda x: Series([1, 2]))
+    tm.assert_frame_equal(result, exp)
+
+
+@pytest.mark.parametrize(
+    "by_row, expected", [("compat", Series(np.ones(10), dtype="int64")), (False, 1)]
+)
+def test_apply_scalar_on_date_time_index_aware_series(by_row, expected):
+    # GH 25959
+    # Calling apply on a localized time series should not cause an error
+    series = Series(
+        np.arange(10, dtype=np.float64),
+        index=date_range("2020-01-01", periods=10, tz="UTC"),
+    )
+    result = Series(series.index).apply(lambda x: 1, by_row=by_row)
+    tm.assert_equal(result, expected)
+
+
+def test_apply_to_timedelta(by_row):
+    list_of_valid_strings = ["00:00:01", "00:00:02"]
+    a = pd.to_timedelta(list_of_valid_strings)
+    b = Series(list_of_valid_strings).apply(pd.to_timedelta, by_row=by_row)
+    tm.assert_series_equal(Series(a), b)
+
+    list_of_strings = ["00:00:01", np.nan, pd.NaT, pd.NaT]
+
+    a = pd.to_timedelta(list_of_strings)
+    ser = Series(list_of_strings)
+    b = ser.apply(pd.to_timedelta, by_row=by_row)
+    tm.assert_series_equal(Series(a), b)
+
+
+@pytest.mark.parametrize(
+    "ops, names",
+    [
+        ([np.sum], ["sum"]),
+        ([np.sum, np.mean], ["sum", "mean"]),
+        (np.array([np.sum]), ["sum"]),
+        (np.array([np.sum, np.mean]), ["sum", "mean"]),
+    ],
+)
+@pytest.mark.parametrize(
+    "how, kwargs",
+    [["agg", {}], ["apply", {"by_row": "compat"}], ["apply", {"by_row": False}]],
+)
+def test_apply_listlike_reducer(string_series, ops, names, how, kwargs):
+    # GH 39140
+    expected = Series({name: op(string_series) for name, op in zip(names, ops)})
+    expected.name = "series"
+    warn = FutureWarning if how == "agg" else None
+    msg = f"using Series.[{'|'.join(names)}]"
+    with tm.assert_produces_warning(warn, match=msg):
+        result = getattr(string_series, how)(ops, **kwargs)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops",
+    [
+        {"A": np.sum},
+        {"A": np.sum, "B": np.mean},
+        Series({"A": np.sum}),
+        Series({"A": np.sum, "B": np.mean}),
+    ],
+)
+@pytest.mark.parametrize(
+    "how, kwargs",
+    [["agg", {}], ["apply", {"by_row": "compat"}], ["apply", {"by_row": False}]],
+)
+def test_apply_dictlike_reducer(string_series, ops, how, kwargs, by_row):
+    # GH 39140
+    expected = Series({name: op(string_series) for name, op in ops.items()})
+    expected.name = string_series.name
+    warn = FutureWarning if how == "agg" else None
+    msg = "using Series.[sum|mean]"
+    with tm.assert_produces_warning(warn, match=msg):
+        result = getattr(string_series, how)(ops, **kwargs)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops, names",
+    [
+        ([np.sqrt], ["sqrt"]),
+        ([np.abs, np.sqrt], ["absolute", "sqrt"]),
+        (np.array([np.sqrt]), ["sqrt"]),
+        (np.array([np.abs, np.sqrt]), ["absolute", "sqrt"]),
+    ],
+)
+def test_apply_listlike_transformer(string_series, ops, names, by_row):
+    # GH 39140
+    with np.errstate(all="ignore"):
+        expected = concat([op(string_series) for op in ops], axis=1)
+        expected.columns = names
+        result = string_series.apply(ops, by_row=by_row)
+        tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops, expected",
+    [
+        ([lambda x: x], DataFrame({"<lambda>": [1, 2, 3]})),
+        ([lambda x: x.sum()], Series([6], index=["<lambda>"])),
+    ],
+)
+def test_apply_listlike_lambda(ops, expected, by_row):
+    # GH53400
+    ser = Series([1, 2, 3])
+    result = ser.apply(ops, by_row=by_row)
+    tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops",
+    [
+        {"A": np.sqrt},
+        {"A": np.sqrt, "B": np.exp},
+        Series({"A": np.sqrt}),
+        Series({"A": np.sqrt, "B": np.exp}),
+    ],
+)
+def test_apply_dictlike_transformer(string_series, ops, by_row):
+    # GH 39140
+    with np.errstate(all="ignore"):
+        expected = concat({name: op(string_series) for name, op in ops.items()})
+        expected.name = string_series.name
+        result = string_series.apply(ops, by_row=by_row)
+        tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops, expected",
+    [
+        (
+            {"a": lambda x: x},
+            Series([1, 2, 3], index=MultiIndex.from_arrays([["a"] * 3, range(3)])),
+        ),
+        ({"a": lambda x: x.sum()}, Series([6], index=["a"])),
+    ],
+)
+def test_apply_dictlike_lambda(ops, by_row, expected):
+    # GH53400
+    ser = Series([1, 2, 3])
+    result = ser.apply(ops, by_row=by_row)
+    tm.assert_equal(result, expected)
+
+
+def test_apply_retains_column_name(by_row):
+    # GH 16380
+    df = DataFrame({"x": range(3)}, Index(range(3), name="x"))
+    result = df.x.apply(lambda x: Series(range(x + 1), Index(range(x + 1), name="y")))
+    expected = DataFrame(
+        [[0.0, np.nan, np.nan], [0.0, 1.0, np.nan], [0.0, 1.0, 2.0]],
+        columns=Index(range(3), name="y"),
+        index=Index(range(3), name="x"),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+def test_apply_type():
+    # GH 46719
+    s = Series([3, "string", float], index=["a", "b", "c"])
+    result = s.apply(type)
+    expected = Series([int, str, type], index=["a", "b", "c"])
+    tm.assert_series_equal(result, expected)
+
+
+def test_series_apply_unpack_nested_data():
+    # GH#55189
+    ser = Series([[1, 2, 3], [4, 5, 6, 7]])
+    result = ser.apply(lambda x: Series(x))
+    expected = DataFrame({0: [1.0, 4.0], 1: [2.0, 5.0], 2: [3.0, 6.0], 3: [np.nan, 7]})
+    tm.assert_frame_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/apply/test_series_apply_relabeling.py

@@ -0,0 +1,39 @@
+import pandas as pd
+import pandas._testing as tm
+
+
+def test_relabel_no_duplicated_method():
+    # this is to test there is no duplicated method used in agg
+    df = pd.DataFrame({"A": [1, 2, 1, 2], "B": [1, 2, 3, 4]})
+
+    result = df["A"].agg(foo="sum")
+    expected = df["A"].agg({"foo": "sum"})
+    tm.assert_series_equal(result, expected)
+
+    result = df["B"].agg(foo="min", bar="max")
+    expected = df["B"].agg({"foo": "min", "bar": "max"})
+    tm.assert_series_equal(result, expected)
+
+    msg = "using Series.[sum|min|max]"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = df["B"].agg(foo=sum, bar=min, cat="max")
+    msg = "using Series.[sum|min|max]"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        expected = df["B"].agg({"foo": sum, "bar": min, "cat": "max"})
+    tm.assert_series_equal(result, expected)
+
+
+def test_relabel_duplicated_method():
+    # this is to test with nested renaming, duplicated method can be used
+    # if they are assigned with different new names
+    df = pd.DataFrame({"A": [1, 2, 1, 2], "B": [1, 2, 3, 4]})
+
+    result = df["A"].agg(foo="sum", bar="sum")
+    expected = pd.Series([6, 6], index=["foo", "bar"], name="A")
+    tm.assert_series_equal(result, expected)
+
+    msg = "using Series.min"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = df["B"].agg(foo=min, bar="min")
+    expected = pd.Series([1, 1], index=["foo", "bar"], name="B")
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/apply/test_series_transform.py

@@ -0,0 +1,84 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    DataFrame,
+    MultiIndex,
+    Series,
+    concat,
+)
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "args, kwargs, increment",
+    [((), {}, 0), ((), {"a": 1}, 1), ((2, 3), {}, 32), ((1,), {"c": 2}, 201)],
+)
+def test_agg_args(args, kwargs, increment):
+    # GH 43357
+    def f(x, a=0, b=0, c=0):
+        return x + a + 10 * b + 100 * c
+
+    s = Series([1, 2])
+    result = s.transform(f, 0, *args, **kwargs)
+    expected = s + increment
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "ops, names",
+    [
+        ([np.sqrt], ["sqrt"]),
+        ([np.abs, np.sqrt], ["absolute", "sqrt"]),
+        (np.array([np.sqrt]), ["sqrt"]),
+        (np.array([np.abs, np.sqrt]), ["absolute", "sqrt"]),
+    ],
+)
+def test_transform_listlike(string_series, ops, names):
+    # GH 35964
+    with np.errstate(all="ignore"):
+        expected = concat([op(string_series) for op in ops], axis=1)
+        expected.columns = names
+        result = string_series.transform(ops)
+        tm.assert_frame_equal(result, expected)
+
+
+def test_transform_listlike_func_with_args():
+    # GH 50624
+
+    s = Series([1, 2, 3])
+
+    def foo1(x, a=1, c=0):
+        return x + a + c
+
+    def foo2(x, b=2, c=0):
+        return x + b + c
+
+    msg = r"foo1\(\) got an unexpected keyword argument 'b'"
+    with pytest.raises(TypeError, match=msg):
+        s.transform([foo1, foo2], 0, 3, b=3, c=4)
+
+    result = s.transform([foo1, foo2], 0, 3, c=4)
+    expected = DataFrame({"foo1": [8, 9, 10], "foo2": [8, 9, 10]})
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [dict, Series])
+def test_transform_dictlike(string_series, box):
+    # GH 35964
+    with np.errstate(all="ignore"):
+        expected = concat([np.sqrt(string_series), np.abs(string_series)], axis=1)
+    expected.columns = ["foo", "bar"]
+    result = string_series.transform(box({"foo": np.sqrt, "bar": np.abs}))
+    tm.assert_frame_equal(result, expected)
+
+
+def test_transform_dictlike_mixed():
+    # GH 40018 - mix of lists and non-lists in values of a dictionary
+    df = Series([1, 4])
+    result = df.transform({"b": ["sqrt", "abs"], "c": "sqrt"})
+    expected = DataFrame(
+        [[1.0, 1, 1.0], [2.0, 4, 2.0]],
+        columns=MultiIndex([("b", "c"), ("sqrt", "abs")], [(0, 0, 1), (0, 1, 0)]),
+    )
+    tm.assert_frame_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/apply/test_str.py

@@ -0,0 +1,326 @@
+from itertools import chain
+import operator
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.common import is_number
+
+from pandas import (
+    DataFrame,
+    Series,
+)
+import pandas._testing as tm
+from pandas.tests.apply.common import (
+    frame_transform_kernels,
+    series_transform_kernels,
+)
+
+
+@pytest.mark.parametrize("func", ["sum", "mean", "min", "max", "std"])
+@pytest.mark.parametrize(
+    "args,kwds",
+    [
+        pytest.param([], {}, id="no_args_or_kwds"),
+        pytest.param([1], {}, id="axis_from_args"),
+        pytest.param([], {"axis": 1}, id="axis_from_kwds"),
+        pytest.param([], {"numeric_only": True}, id="optional_kwds"),
+        pytest.param([1, True], {"numeric_only": True}, id="args_and_kwds"),
+    ],
+)
+@pytest.mark.parametrize("how", ["agg", "apply"])
+def test_apply_with_string_funcs(request, float_frame, func, args, kwds, how):
+    if len(args) > 1 and how == "agg":
+        request.applymarker(
+            pytest.mark.xfail(
+                raises=TypeError,
+                reason="agg/apply signature mismatch - agg passes 2nd "
+                "argument to func",
+            )
+        )
+    result = getattr(float_frame, how)(func, *args, **kwds)
+    expected = getattr(float_frame, func)(*args, **kwds)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("arg", ["sum", "mean", "min", "max", "std"])
+def test_with_string_args(datetime_series, arg):
+    result = datetime_series.apply(arg)
+    expected = getattr(datetime_series, arg)()
+    assert result == expected
+
+
+@pytest.mark.parametrize("op", ["mean", "median", "std", "var"])
+@pytest.mark.parametrize("how", ["agg", "apply"])
+def test_apply_np_reducer(op, how):
+    # GH 39116
+    float_frame = DataFrame({"a": [1, 2], "b": [3, 4]})
+    result = getattr(float_frame, how)(op)
+    # pandas ddof defaults to 1, numpy to 0
+    kwargs = {"ddof": 1} if op in ("std", "var") else {}
+    expected = Series(
+        getattr(np, op)(float_frame, axis=0, **kwargs), index=float_frame.columns
+    )
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "op", ["abs", "ceil", "cos", "cumsum", "exp", "log", "sqrt", "square"]
+)
+@pytest.mark.parametrize("how", ["transform", "apply"])
+def test_apply_np_transformer(float_frame, op, how):
+    # GH 39116
+
+    # float_frame will _usually_ have negative values, which will
+    #  trigger the warning here, but let's put one in just to be sure
+    float_frame.iloc[0, 0] = -1.0
+    warn = None
+    if op in ["log", "sqrt"]:
+        warn = RuntimeWarning
+
+    with tm.assert_produces_warning(warn, check_stacklevel=False):
+        # float_frame fixture is defined in conftest.py, so we don't check the
+        # stacklevel as otherwise the test would fail.
+        result = getattr(float_frame, how)(op)
+        expected = getattr(np, op)(float_frame)
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "series, func, expected",
+    chain(
+        tm.get_cython_table_params(
+            Series(dtype=np.float64),
+            [
+                ("sum", 0),
+                ("max", np.nan),
+                ("min", np.nan),
+                ("all", True),
+                ("any", False),
+                ("mean", np.nan),
+                ("prod", 1),
+                ("std", np.nan),
+                ("var", np.nan),
+                ("median", np.nan),
+            ],
+        ),
+        tm.get_cython_table_params(
+            Series([np.nan, 1, 2, 3]),
+            [
+                ("sum", 6),
+                ("max", 3),
+                ("min", 1),
+                ("all", True),
+                ("any", True),
+                ("mean", 2),
+                ("prod", 6),
+                ("std", 1),
+                ("var", 1),
+                ("median", 2),
+            ],
+        ),
+        tm.get_cython_table_params(
+            Series("a b c".split()),
+            [
+                ("sum", "abc"),
+                ("max", "c"),
+                ("min", "a"),
+                ("all", True),
+                ("any", True),
+            ],
+        ),
+    ),
+)
+def test_agg_cython_table_series(series, func, expected):
+    # GH21224
+    # test reducing functions in
+    # pandas.core.base.SelectionMixin._cython_table
+    warn = None if isinstance(func, str) else FutureWarning
+    with tm.assert_produces_warning(warn, match="is currently using Series.*"):
+        result = series.agg(func)
+    if is_number(expected):
+        assert np.isclose(result, expected, equal_nan=True)
+    else:
+        assert result == expected
+
+
+@pytest.mark.parametrize(
+    "series, func, expected",
+    chain(
+        tm.get_cython_table_params(
+            Series(dtype=np.float64),
+            [
+                ("cumprod", Series([], dtype=np.float64)),
+                ("cumsum", Series([], dtype=np.float64)),
+            ],
+        ),
+        tm.get_cython_table_params(
+            Series([np.nan, 1, 2, 3]),
+            [
+                ("cumprod", Series([np.nan, 1, 2, 6])),
+                ("cumsum", Series([np.nan, 1, 3, 6])),
+            ],
+        ),
+        tm.get_cython_table_params(
+            Series("a b c".split()), [("cumsum", Series(["a", "ab", "abc"]))]
+        ),
+    ),
+)
+def test_agg_cython_table_transform_series(series, func, expected):
+    # GH21224
+    # test transforming functions in
+    # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
+    warn = None if isinstance(func, str) else FutureWarning
+    with tm.assert_produces_warning(warn, match="is currently using Series.*"):
+        result = series.agg(func)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "df, func, expected",
+    chain(
+        tm.get_cython_table_params(
+            DataFrame(),
+            [
+                ("sum", Series(dtype="float64")),
+                ("max", Series(dtype="float64")),
+                ("min", Series(dtype="float64")),
+                ("all", Series(dtype=bool)),
+                ("any", Series(dtype=bool)),
+                ("mean", Series(dtype="float64")),
+                ("prod", Series(dtype="float64")),
+                ("std", Series(dtype="float64")),
+                ("var", Series(dtype="float64")),
+                ("median", Series(dtype="float64")),
+            ],
+        ),
+        tm.get_cython_table_params(
+            DataFrame([[np.nan, 1], [1, 2]]),
+            [
+                ("sum", Series([1.0, 3])),
+                ("max", Series([1.0, 2])),
+                ("min", Series([1.0, 1])),
+                ("all", Series([True, True])),
+                ("any", Series([True, True])),
+                ("mean", Series([1, 1.5])),
+                ("prod", Series([1.0, 2])),
+                ("std", Series([np.nan, 0.707107])),
+                ("var", Series([np.nan, 0.5])),
+                ("median", Series([1, 1.5])),
+            ],
+        ),
+    ),
+)
+def test_agg_cython_table_frame(df, func, expected, axis):
+    # GH 21224
+    # test reducing functions in
+    # pandas.core.base.SelectionMixin._cython_table
+    warn = None if isinstance(func, str) else FutureWarning
+    with tm.assert_produces_warning(warn, match="is currently using DataFrame.*"):
+        # GH#53425
+        result = df.agg(func, axis=axis)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "df, func, expected",
+    chain(
+        tm.get_cython_table_params(
+            DataFrame(), [("cumprod", DataFrame()), ("cumsum", DataFrame())]
+        ),
+        tm.get_cython_table_params(
+            DataFrame([[np.nan, 1], [1, 2]]),
+            [
+                ("cumprod", DataFrame([[np.nan, 1], [1, 2]])),
+                ("cumsum", DataFrame([[np.nan, 1], [1, 3]])),
+            ],
+        ),
+    ),
+)
+def test_agg_cython_table_transform_frame(df, func, expected, axis):
+    # GH 21224
+    # test transforming functions in
+    # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
+    if axis in ("columns", 1):
+        # operating blockwise doesn't let us preserve dtypes
+        expected = expected.astype("float64")
+
+    warn = None if isinstance(func, str) else FutureWarning
+    with tm.assert_produces_warning(warn, match="is currently using DataFrame.*"):
+        # GH#53425
+        result = df.agg(func, axis=axis)
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("op", series_transform_kernels)
+def test_transform_groupby_kernel_series(request, string_series, op):
+    # GH 35964
+    if op == "ngroup":
+        request.applymarker(
+            pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
+        )
+    args = [0.0] if op == "fillna" else []
+    ones = np.ones(string_series.shape[0])
+
+    warn = FutureWarning if op == "fillna" else None
+    msg = "SeriesGroupBy.fillna is deprecated"
+    with tm.assert_produces_warning(warn, match=msg):
+        expected = string_series.groupby(ones).transform(op, *args)
+    result = string_series.transform(op, 0, *args)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("op", frame_transform_kernels)
+def test_transform_groupby_kernel_frame(request, axis, float_frame, op):
+    if op == "ngroup":
+        request.applymarker(
+            pytest.mark.xfail(raises=ValueError, reason="ngroup not valid for NDFrame")
+        )
+
+    # GH 35964
+
+    args = [0.0] if op == "fillna" else []
+    if axis in (0, "index"):
+        ones = np.ones(float_frame.shape[0])
+        msg = "The 'axis' keyword in DataFrame.groupby is deprecated"
+    else:
+        ones = np.ones(float_frame.shape[1])
+        msg = "DataFrame.groupby with axis=1 is deprecated"
+
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        gb = float_frame.groupby(ones, axis=axis)
+
+    warn = FutureWarning if op == "fillna" else None
+    op_msg = "DataFrameGroupBy.fillna is deprecated"
+    with tm.assert_produces_warning(warn, match=op_msg):
+        expected = gb.transform(op, *args)
+
+    result = float_frame.transform(op, axis, *args)
+    tm.assert_frame_equal(result, expected)
+
+    # same thing, but ensuring we have multiple blocks
+    assert "E" not in float_frame.columns
+    float_frame["E"] = float_frame["A"].copy()
+    assert len(float_frame._mgr.arrays) > 1
+
+    if axis in (0, "index"):
+        ones = np.ones(float_frame.shape[0])
+    else:
+        ones = np.ones(float_frame.shape[1])
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        gb2 = float_frame.groupby(ones, axis=axis)
+    warn = FutureWarning if op == "fillna" else None
+    op_msg = "DataFrameGroupBy.fillna is deprecated"
+    with tm.assert_produces_warning(warn, match=op_msg):
+        expected2 = gb2.transform(op, *args)
+    result2 = float_frame.transform(op, axis, *args)
+    tm.assert_frame_equal(result2, expected2)
+
+
+@pytest.mark.parametrize("method", ["abs", "shift", "pct_change", "cumsum", "rank"])
+def test_transform_method_name(method):
+    # GH 19760
+    df = DataFrame({"A": [-1, 2]})
+    result = df.transform(method)
+    expected = operator.methodcaller(method)(df)
+    tm.assert_frame_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arithmetic/common.py

@@ -0,0 +1,155 @@
+"""
+Assertion helpers for arithmetic tests.
+"""
+import numpy as np
+import pytest
+
+from pandas import (
+    DataFrame,
+    Index,
+    Series,
+    array,
+)
+import pandas._testing as tm
+from pandas.core.arrays import (
+    BooleanArray,
+    NumpyExtensionArray,
+)
+
+
+def assert_cannot_add(left, right, msg="cannot add"):
+    """
+    Helper to assert that left and right cannot be added.
+
+    Parameters
+    ----------
+    left : object
+    right : object
+    msg : str, default "cannot add"
+    """
+    with pytest.raises(TypeError, match=msg):
+        left + right
+    with pytest.raises(TypeError, match=msg):
+        right + left
+
+
+def assert_invalid_addsub_type(left, right, msg=None):
+    """
+    Helper to assert that left and right can be neither added nor subtracted.
+
+    Parameters
+    ----------
+    left : object
+    right : object
+    msg : str or None, default None
+    """
+    with pytest.raises(TypeError, match=msg):
+        left + right
+    with pytest.raises(TypeError, match=msg):
+        right + left
+    with pytest.raises(TypeError, match=msg):
+        left - right
+    with pytest.raises(TypeError, match=msg):
+        right - left
+
+
+def get_upcast_box(left, right, is_cmp: bool = False):
+    """
+    Get the box to use for 'expected' in an arithmetic or comparison operation.
+
+    Parameters
+    left : Any
+    right : Any
+    is_cmp : bool, default False
+        Whether the operation is a comparison method.
+    """
+
+    if isinstance(left, DataFrame) or isinstance(right, DataFrame):
+        return DataFrame
+    if isinstance(left, Series) or isinstance(right, Series):
+        if is_cmp and isinstance(left, Index):
+            # Index does not defer for comparisons
+            return np.array
+        return Series
+    if isinstance(left, Index) or isinstance(right, Index):
+        if is_cmp:
+            return np.array
+        return Index
+    return tm.to_array
+
+
+def assert_invalid_comparison(left, right, box):
+    """
+    Assert that comparison operations with mismatched types behave correctly.
+
+    Parameters
+    ----------
+    left : np.ndarray, ExtensionArray, Index, or Series
+    right : object
+    box : {pd.DataFrame, pd.Series, pd.Index, pd.array, tm.to_array}
+    """
+    # Not for tznaive-tzaware comparison
+
+    # Note: not quite the same as how we do this for tm.box_expected
+    xbox = box if box not in [Index, array] else np.array
+
+    def xbox2(x):
+        # Eventually we'd like this to be tighter, but for now we'll
+        #  just exclude NumpyExtensionArray[bool]
+        if isinstance(x, NumpyExtensionArray):
+            return x._ndarray
+        if isinstance(x, BooleanArray):
+            # NB: we are assuming no pd.NAs for now
+            return x.astype(bool)
+        return x
+
+    # rev_box: box to use for reversed comparisons
+    rev_box = xbox
+    if isinstance(right, Index) and isinstance(left, Series):
+        rev_box = np.array
+
+    result = xbox2(left == right)
+    expected = xbox(np.zeros(result.shape, dtype=np.bool_))
+
+    tm.assert_equal(result, expected)
+
+    result = xbox2(right == left)
+    tm.assert_equal(result, rev_box(expected))
+
+    result = xbox2(left != right)
+    tm.assert_equal(result, ~expected)
+
+    result = xbox2(right != left)
+    tm.assert_equal(result, rev_box(~expected))
+
+    msg = "|".join(
+        [
+            "Invalid comparison between",
+            "Cannot compare type",
+            "not supported between",
+            "invalid type promotion",
+            (
+                # GH#36706 npdev 1.20.0 2020-09-28
+                r"The DTypes <class 'numpy.dtype\[datetime64\]'> and "
+                r"<class 'numpy.dtype\[int64\]'> do not have a common DType. "
+                "For example they cannot be stored in a single array unless the "
+                "dtype is `object`."
+            ),
+        ]
+    )
+    with pytest.raises(TypeError, match=msg):
+        left < right
+    with pytest.raises(TypeError, match=msg):
+        left <= right
+    with pytest.raises(TypeError, match=msg):
+        left > right
+    with pytest.raises(TypeError, match=msg):
+        left >= right
+    with pytest.raises(TypeError, match=msg):
+        right < left
+    with pytest.raises(TypeError, match=msg):
+        right <= left
+    with pytest.raises(TypeError, match=msg):
+        right > left
+    with pytest.raises(TypeError, match=msg):
+        right >= left

lib/python3.13/site-packages/pandas/tests/arithmetic/conftest.py

@@ -0,0 +1,139 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import Index
+
+
+@pytest.fixture(params=[1, np.array(1, dtype=np.int64)])
+def one(request):
+    """
+    Several variants of integer value 1. The zero-dim integer array
+    behaves like an integer.
+
+    This fixture can be used to check that datetimelike indexes handle
+    addition and subtraction of integers and zero-dimensional arrays
+    of integers.
+
+    Examples
+    --------
+    dti = pd.date_range('2016-01-01', periods=2, freq='h')
+    dti
+    DatetimeIndex(['2016-01-01 00:00:00', '2016-01-01 01:00:00'],
+    dtype='datetime64[ns]', freq='h')
+    dti + one
+    DatetimeIndex(['2016-01-01 01:00:00', '2016-01-01 02:00:00'],
+    dtype='datetime64[ns]', freq='h')
+    """
+    return request.param
+
+
+zeros = [
+    box_cls([0] * 5, dtype=dtype)
+    for box_cls in [Index, np.array, pd.array]
+    for dtype in [np.int64, np.uint64, np.float64]
+]
+zeros.extend([box_cls([-0.0] * 5, dtype=np.float64) for box_cls in [Index, np.array]])
+zeros.extend([np.array(0, dtype=dtype) for dtype in [np.int64, np.uint64, np.float64]])
+zeros.extend([np.array(-0.0, dtype=np.float64)])
+zeros.extend([0, 0.0, -0.0])
+
+
+@pytest.fixture(params=zeros)
+def zero(request):
+    """
+    Several types of scalar zeros and length 5 vectors of zeros.
+
+    This fixture can be used to check that numeric-dtype indexes handle
+    division by any zero numeric-dtype.
+
+    Uses vector of length 5 for broadcasting with `numeric_idx` fixture,
+    which creates numeric-dtype vectors also of length 5.
+
+    Examples
+    --------
+    arr = RangeIndex(5)
+    arr / zeros
+    Index([nan, inf, inf, inf, inf], dtype='float64')
+    """
+    return request.param
+
+
+# ------------------------------------------------------------------
+# Scalar Fixtures
+
+
+@pytest.fixture(
+    params=[
+        pd.Timedelta("10m7s").to_pytimedelta(),
+        pd.Timedelta("10m7s"),
+        pd.Timedelta("10m7s").to_timedelta64(),
+    ],
+    ids=lambda x: type(x).__name__,
+)
+def scalar_td(request):
+    """
+    Several variants of Timedelta scalars representing 10 minutes and 7 seconds.
+    """
+    return request.param
+
+
+@pytest.fixture(
+    params=[
+        pd.offsets.Day(3),
+        pd.offsets.Hour(72),
+        pd.Timedelta(days=3).to_pytimedelta(),
+        pd.Timedelta("72:00:00"),
+        np.timedelta64(3, "D"),
+        np.timedelta64(72, "h"),
+    ],
+    ids=lambda x: type(x).__name__,
+)
+def three_days(request):
+    """
+    Several timedelta-like and DateOffset objects that each represent
+    a 3-day timedelta
+    """
+    return request.param
+
+
+@pytest.fixture(
+    params=[
+        pd.offsets.Hour(2),
+        pd.offsets.Minute(120),
+        pd.Timedelta(hours=2).to_pytimedelta(),
+        pd.Timedelta(seconds=2 * 3600),
+        np.timedelta64(2, "h"),
+        np.timedelta64(120, "m"),
+    ],
+    ids=lambda x: type(x).__name__,
+)
+def two_hours(request):
+    """
+    Several timedelta-like and DateOffset objects that each represent
+    a 2-hour timedelta
+    """
+    return request.param
+
+
+_common_mismatch = [
+    pd.offsets.YearBegin(2),
+    pd.offsets.MonthBegin(1),
+    pd.offsets.Minute(),
+]
+
+
+@pytest.fixture(
+    params=[
+        np.timedelta64(4, "h"),
+        pd.Timedelta(hours=23).to_pytimedelta(),
+        pd.Timedelta("23:00:00"),
+    ]
+    + _common_mismatch
+)
+def not_daily(request):
+    """
+    Several timedelta-like and DateOffset instances that are _not_
+    compatible with Daily frequencies.
+    """
+    return request.param

lib/python3.13/site-packages/pandas/tests/arithmetic/test_array_ops.py

@@ -0,0 +1,39 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas._testing as tm
+from pandas.core.ops.array_ops import (
+    comparison_op,
+    na_logical_op,
+)
+
+
+def test_na_logical_op_2d():
+    left = np.arange(8).reshape(4, 2)
+    right = left.astype(object)
+    right[0, 0] = np.nan
+
+    # Check that we fall back to the vec_binop branch
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        operator.or_(left, right)
+
+    result = na_logical_op(left, right, operator.or_)
+    expected = right
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_object_comparison_2d():
+    left = np.arange(9).reshape(3, 3).astype(object)
+    right = left.T
+
+    result = comparison_op(left, right, operator.eq)
+    expected = np.eye(3).astype(bool)
+    tm.assert_numpy_array_equal(result, expected)
+
+    # Ensure that cython doesn't raise on non-writeable arg, which
+    #  we can get from np.broadcast_to
+    right.flags.writeable = False
+    result = comparison_op(left, right, operator.ne)
+    tm.assert_numpy_array_equal(result, ~expected)

lib/python3.13/site-packages/pandas/tests/arithmetic/test_categorical.py

@@ -0,0 +1,25 @@
+import numpy as np
+
+from pandas import (
+    Categorical,
+    Series,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalComparisons:
+    def test_categorical_nan_equality(self):
+        cat = Series(Categorical(["a", "b", "c", np.nan]))
+        expected = Series([True, True, True, False])
+        result = cat == cat
+        tm.assert_series_equal(result, expected)
+
+    def test_categorical_tuple_equality(self):
+        # GH 18050
+        ser = Series([(0, 0), (0, 1), (0, 0), (1, 0), (1, 1)])
+        expected = Series([True, False, True, False, False])
+        result = ser == (0, 0)
+        tm.assert_series_equal(result, expected)
+
+        result = ser.astype("category") == (0, 0)
+        tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arithmetic/test_interval.py

@@ -0,0 +1,306 @@
+import operator
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.common import is_list_like
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    Index,
+    Interval,
+    IntervalIndex,
+    Period,
+    Series,
+    Timedelta,
+    Timestamp,
+    date_range,
+    period_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+from pandas.core.arrays import (
+    BooleanArray,
+    IntervalArray,
+)
+from pandas.tests.arithmetic.common import get_upcast_box
+
+
+@pytest.fixture(
+    params=[
+        (Index([0, 2, 4, 4]), Index([1, 3, 5, 8])),
+        (Index([0.0, 1.0, 2.0, np.nan]), Index([1.0, 2.0, 3.0, np.nan])),
+        (
+            timedelta_range("0 days", periods=3).insert(3, pd.NaT),
+            timedelta_range("1 day", periods=3).insert(3, pd.NaT),
+        ),
+        (
+            date_range("20170101", periods=3).insert(3, pd.NaT),
+            date_range("20170102", periods=3).insert(3, pd.NaT),
+        ),
+        (
+            date_range("20170101", periods=3, tz="US/Eastern").insert(3, pd.NaT),
+            date_range("20170102", periods=3, tz="US/Eastern").insert(3, pd.NaT),
+        ),
+    ],
+    ids=lambda x: str(x[0].dtype),
+)
+def left_right_dtypes(request):
+    """
+    Fixture for building an IntervalArray from various dtypes
+    """
+    return request.param
+
+
+@pytest.fixture
+def interval_array(left_right_dtypes):
+    """
+    Fixture to generate an IntervalArray of various dtypes containing NA if possible
+    """
+    left, right = left_right_dtypes
+    return IntervalArray.from_arrays(left, right)
+
+
+def create_categorical_intervals(left, right, closed="right"):
+    return Categorical(IntervalIndex.from_arrays(left, right, closed))
+
+
+def create_series_intervals(left, right, closed="right"):
+    return Series(IntervalArray.from_arrays(left, right, closed))
+
+
+def create_series_categorical_intervals(left, right, closed="right"):
+    return Series(Categorical(IntervalIndex.from_arrays(left, right, closed)))
+
+
+class TestComparison:
+    @pytest.fixture(params=[operator.eq, operator.ne])
+    def op(self, request):
+        return request.param
+
+    @pytest.fixture(
+        params=[
+            IntervalArray.from_arrays,
+            IntervalIndex.from_arrays,
+            create_categorical_intervals,
+            create_series_intervals,
+            create_series_categorical_intervals,
+        ],
+        ids=[
+            "IntervalArray",
+            "IntervalIndex",
+            "Categorical[Interval]",
+            "Series[Interval]",
+            "Series[Categorical[Interval]]",
+        ],
+    )
+    def interval_constructor(self, request):
+        """
+        Fixture for all pandas native interval constructors.
+        To be used as the LHS of IntervalArray comparisons.
+        """
+        return request.param
+
+    def elementwise_comparison(self, op, interval_array, other):
+        """
+        Helper that performs elementwise comparisons between `array` and `other`
+        """
+        other = other if is_list_like(other) else [other] * len(interval_array)
+        expected = np.array([op(x, y) for x, y in zip(interval_array, other)])
+        if isinstance(other, Series):
+            return Series(expected, index=other.index)
+        return expected
+
+    def test_compare_scalar_interval(self, op, interval_array):
+        # matches first interval
+        other = interval_array[0]
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # matches on a single endpoint but not both
+        other = Interval(interval_array.left[0], interval_array.right[1])
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_compare_scalar_interval_mixed_closed(self, op, closed, other_closed):
+        interval_array = IntervalArray.from_arrays(range(2), range(1, 3), closed=closed)
+        other = Interval(0, 1, closed=other_closed)
+
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_compare_scalar_na(self, op, interval_array, nulls_fixture, box_with_array):
+        box = box_with_array
+        obj = tm.box_expected(interval_array, box)
+        result = op(obj, nulls_fixture)
+
+        if nulls_fixture is pd.NA:
+            # GH#31882
+            exp = np.ones(interval_array.shape, dtype=bool)
+            expected = BooleanArray(exp, exp)
+        else:
+            expected = self.elementwise_comparison(op, interval_array, nulls_fixture)
+
+        if not (box is Index and nulls_fixture is pd.NA):
+            # don't cast expected from BooleanArray to ndarray[object]
+            xbox = get_upcast_box(obj, nulls_fixture, True)
+            expected = tm.box_expected(expected, xbox)
+
+        tm.assert_equal(result, expected)
+
+        rev = op(nulls_fixture, obj)
+        tm.assert_equal(rev, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            0,
+            1.0,
+            True,
+            "foo",
+            Timestamp("2017-01-01"),
+            Timestamp("2017-01-01", tz="US/Eastern"),
+            Timedelta("0 days"),
+            Period("2017-01-01", "D"),
+        ],
+    )
+    def test_compare_scalar_other(self, op, interval_array, other):
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_compare_list_like_interval(self, op, interval_array, interval_constructor):
+        # same endpoints
+        other = interval_constructor(interval_array.left, interval_array.right)
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_equal(result, expected)
+
+        # different endpoints
+        other = interval_constructor(
+            interval_array.left[::-1], interval_array.right[::-1]
+        )
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_equal(result, expected)
+
+        # all nan endpoints
+        other = interval_constructor([np.nan] * 4, [np.nan] * 4)
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_equal(result, expected)
+
+    def test_compare_list_like_interval_mixed_closed(
+        self, op, interval_constructor, closed, other_closed
+    ):
+        interval_array = IntervalArray.from_arrays(range(2), range(1, 3), closed=closed)
+        other = interval_constructor(range(2), range(1, 3), closed=other_closed)
+
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            (
+                Interval(0, 1),
+                Interval(Timedelta("1 day"), Timedelta("2 days")),
+                Interval(4, 5, "both"),
+                Interval(10, 20, "neither"),
+            ),
+            (0, 1.5, Timestamp("20170103"), np.nan),
+            (
+                Timestamp("20170102", tz="US/Eastern"),
+                Timedelta("2 days"),
+                "baz",
+                pd.NaT,
+            ),
+        ],
+    )
+    def test_compare_list_like_object(self, op, interval_array, other):
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_compare_list_like_nan(self, op, interval_array, nulls_fixture):
+        other = [nulls_fixture] * 4
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+
+        tm.assert_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            np.arange(4, dtype="int64"),
+            np.arange(4, dtype="float64"),
+            date_range("2017-01-01", periods=4),
+            date_range("2017-01-01", periods=4, tz="US/Eastern"),
+            timedelta_range("0 days", periods=4),
+            period_range("2017-01-01", periods=4, freq="D"),
+            Categorical(list("abab")),
+            Categorical(date_range("2017-01-01", periods=4)),
+            pd.array(list("abcd")),
+            pd.array(["foo", 3.14, None, object()], dtype=object),
+        ],
+        ids=lambda x: str(x.dtype),
+    )
+    def test_compare_list_like_other(self, op, interval_array, other):
+        result = op(interval_array, other)
+        expected = self.elementwise_comparison(op, interval_array, other)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("length", [1, 3, 5])
+    @pytest.mark.parametrize("other_constructor", [IntervalArray, list])
+    def test_compare_length_mismatch_errors(self, op, other_constructor, length):
+        interval_array = IntervalArray.from_arrays(range(4), range(1, 5))
+        other = other_constructor([Interval(0, 1)] * length)
+        with pytest.raises(ValueError, match="Lengths must match to compare"):
+            op(interval_array, other)
+
+    @pytest.mark.parametrize(
+        "constructor, expected_type, assert_func",
+        [
+            (IntervalIndex, np.array, tm.assert_numpy_array_equal),
+            (Series, Series, tm.assert_series_equal),
+        ],
+    )
+    def test_index_series_compat(self, op, constructor, expected_type, assert_func):
+        # IntervalIndex/Series that rely on IntervalArray for comparisons
+        breaks = range(4)
+        index = constructor(IntervalIndex.from_breaks(breaks))
+
+        # scalar comparisons
+        other = index[0]
+        result = op(index, other)
+        expected = expected_type(self.elementwise_comparison(op, index, other))
+        assert_func(result, expected)
+
+        other = breaks[0]
+        result = op(index, other)
+        expected = expected_type(self.elementwise_comparison(op, index, other))
+        assert_func(result, expected)
+
+        # list-like comparisons
+        other = IntervalArray.from_breaks(breaks)
+        result = op(index, other)
+        expected = expected_type(self.elementwise_comparison(op, index, other))
+        assert_func(result, expected)
+
+        other = [index[0], breaks[0], "foo"]
+        result = op(index, other)
+        expected = expected_type(self.elementwise_comparison(op, index, other))
+        assert_func(result, expected)
+
+    @pytest.mark.parametrize("scalars", ["a", False, 1, 1.0, None])
+    def test_comparison_operations(self, scalars):
+        # GH #28981
+        expected = Series([False, False])
+        s = Series([Interval(0, 1), Interval(1, 2)], dtype="interval")
+        result = s == scalars
+        tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arithmetic/test_object.py

@@ -0,0 +1,420 @@
+# Arithmetic tests for DataFrame/Series/Index/Array classes that should
+# behave identically.
+# Specifically for object dtype
+import datetime
+from decimal import Decimal
+import operator
+
+import numpy as np
+import pytest
+
+from pandas._config import using_pyarrow_string_dtype
+
+import pandas.util._test_decorators as td
+
+import pandas as pd
+from pandas import (
+    Series,
+    Timestamp,
+    option_context,
+)
+import pandas._testing as tm
+from pandas.core import ops
+
+# ------------------------------------------------------------------
+# Comparisons
+
+
+class TestObjectComparisons:
+    def test_comparison_object_numeric_nas(self, comparison_op):
+        ser = Series(np.random.default_rng(2).standard_normal(10), dtype=object)
+        shifted = ser.shift(2)
+
+        func = comparison_op
+
+        result = func(ser, shifted)
+        expected = func(ser.astype(float), shifted.astype(float))
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "infer_string", [False, pytest.param(True, marks=td.skip_if_no("pyarrow"))]
+    )
+    def test_object_comparisons(self, infer_string):
+        with option_context("future.infer_string", infer_string):
+            ser = Series(["a", "b", np.nan, "c", "a"])
+
+            result = ser == "a"
+            expected = Series([True, False, False, False, True])
+            tm.assert_series_equal(result, expected)
+
+            result = ser < "a"
+            expected = Series([False, False, False, False, False])
+            tm.assert_series_equal(result, expected)
+
+            result = ser != "a"
+            expected = -(ser == "a")
+            tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype", [None, object])
+    def test_more_na_comparisons(self, dtype):
+        left = Series(["a", np.nan, "c"], dtype=dtype)
+        right = Series(["a", np.nan, "d"], dtype=dtype)
+
+        result = left == right
+        expected = Series([True, False, False])
+        tm.assert_series_equal(result, expected)
+
+        result = left != right
+        expected = Series([False, True, True])
+        tm.assert_series_equal(result, expected)
+
+        result = left == np.nan
+        expected = Series([False, False, False])
+        tm.assert_series_equal(result, expected)
+
+        result = left != np.nan
+        expected = Series([True, True, True])
+        tm.assert_series_equal(result, expected)
+
+
+# ------------------------------------------------------------------
+# Arithmetic
+
+
+class TestArithmetic:
+    def test_add_period_to_array_of_offset(self):
+        # GH#50162
+        per = pd.Period("2012-1-1", freq="D")
+        pi = pd.period_range("2012-1-1", periods=10, freq="D")
+        idx = per - pi
+
+        expected = pd.Index([x + per for x in idx], dtype=object)
+        result = idx + per
+        tm.assert_index_equal(result, expected)
+
+        result = per + idx
+        tm.assert_index_equal(result, expected)
+
+    # TODO: parametrize
+    def test_pow_ops_object(self):
+        # GH#22922
+        # pow is weird with masking & 1, so testing here
+        a = Series([1, np.nan, 1, np.nan], dtype=object)
+        b = Series([1, np.nan, np.nan, 1], dtype=object)
+        result = a**b
+        expected = Series(a.values**b.values, dtype=object)
+        tm.assert_series_equal(result, expected)
+
+        result = b**a
+        expected = Series(b.values**a.values, dtype=object)
+
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize("op", [operator.add, ops.radd])
+    @pytest.mark.parametrize("other", ["category", "Int64"])
+    def test_add_extension_scalar(self, other, box_with_array, op):
+        # GH#22378
+        # Check that scalars satisfying is_extension_array_dtype(obj)
+        # do not incorrectly try to dispatch to an ExtensionArray operation
+
+        arr = Series(["a", "b", "c"])
+        expected = Series([op(x, other) for x in arr])
+
+        arr = tm.box_expected(arr, box_with_array)
+        expected = tm.box_expected(expected, box_with_array)
+
+        result = op(arr, other)
+        tm.assert_equal(result, expected)
+
+    def test_objarr_add_str(self, box_with_array):
+        ser = Series(["x", np.nan, "x"])
+        expected = Series(["xa", np.nan, "xa"])
+
+        ser = tm.box_expected(ser, box_with_array)
+        expected = tm.box_expected(expected, box_with_array)
+
+        result = ser + "a"
+        tm.assert_equal(result, expected)
+
+    def test_objarr_radd_str(self, box_with_array):
+        ser = Series(["x", np.nan, "x"])
+        expected = Series(["ax", np.nan, "ax"])
+
+        ser = tm.box_expected(ser, box_with_array)
+        expected = tm.box_expected(expected, box_with_array)
+
+        result = "a" + ser
+        tm.assert_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "data",
+        [
+            [1, 2, 3],
+            [1.1, 2.2, 3.3],
+            [Timestamp("2011-01-01"), Timestamp("2011-01-02"), pd.NaT],
+            ["x", "y", 1],
+        ],
+    )
+    @pytest.mark.parametrize("dtype", [None, object])
+    def test_objarr_radd_str_invalid(self, dtype, data, box_with_array):
+        ser = Series(data, dtype=dtype)
+
+        ser = tm.box_expected(ser, box_with_array)
+        msg = "|".join(
+            [
+                "can only concatenate str",
+                "did not contain a loop with signature matching types",
+                "unsupported operand type",
+                "must be str",
+            ]
+        )
+        with pytest.raises(TypeError, match=msg):
+            "foo_" + ser
+
+    @pytest.mark.parametrize("op", [operator.add, ops.radd, operator.sub, ops.rsub])
+    def test_objarr_add_invalid(self, op, box_with_array):
+        # invalid ops
+        box = box_with_array
+
+        obj_ser = Series(list("abc"), dtype=object, name="objects")
+
+        obj_ser = tm.box_expected(obj_ser, box)
+        msg = "|".join(
+            [
+                "can only concatenate str",
+                "unsupported operand type",
+                "must be str",
+                "has no kernel",
+            ]
+        )
+        with pytest.raises(Exception, match=msg):
+            op(obj_ser, 1)
+        with pytest.raises(Exception, match=msg):
+            op(obj_ser, np.array(1, dtype=np.int64))
+
+    # TODO: Moved from tests.series.test_operators; needs cleanup
+    def test_operators_na_handling(self):
+        ser = Series(["foo", "bar", "baz", np.nan])
+        result = "prefix_" + ser
+        expected = Series(["prefix_foo", "prefix_bar", "prefix_baz", np.nan])
+        tm.assert_series_equal(result, expected)
+
+        result = ser + "_suffix"
+        expected = Series(["foo_suffix", "bar_suffix", "baz_suffix", np.nan])
+        tm.assert_series_equal(result, expected)
+
+    # TODO: parametrize over box
+    @pytest.mark.parametrize("dtype", [None, object])
+    def test_series_with_dtype_radd_timedelta(self, dtype):
+        # note this test is _not_ aimed at timedelta64-dtyped Series
+        # as of 2.0 we retain object dtype when ser.dtype == object
+        ser = Series(
+            [pd.Timedelta("1 days"), pd.Timedelta("2 days"), pd.Timedelta("3 days")],
+            dtype=dtype,
+        )
+        expected = Series(
+            [pd.Timedelta("4 days"), pd.Timedelta("5 days"), pd.Timedelta("6 days")],
+            dtype=dtype,
+        )
+
+        result = pd.Timedelta("3 days") + ser
+        tm.assert_series_equal(result, expected)
+
+        result = ser + pd.Timedelta("3 days")
+        tm.assert_series_equal(result, expected)
+
+    # TODO: cleanup & parametrize over box
+    def test_mixed_timezone_series_ops_object(self):
+        # GH#13043
+        ser = Series(
+            [
+                Timestamp("2015-01-01", tz="US/Eastern"),
+                Timestamp("2015-01-01", tz="Asia/Tokyo"),
+            ],
+            name="xxx",
+        )
+        assert ser.dtype == object
+
+        exp = Series(
+            [
+                Timestamp("2015-01-02", tz="US/Eastern"),
+                Timestamp("2015-01-02", tz="Asia/Tokyo"),
+            ],
+            name="xxx",
+        )
+        tm.assert_series_equal(ser + pd.Timedelta("1 days"), exp)
+        tm.assert_series_equal(pd.Timedelta("1 days") + ser, exp)
+
+        # object series & object series
+        ser2 = Series(
+            [
+                Timestamp("2015-01-03", tz="US/Eastern"),
+                Timestamp("2015-01-05", tz="Asia/Tokyo"),
+            ],
+            name="xxx",
+        )
+        assert ser2.dtype == object
+        exp = Series(
+            [pd.Timedelta("2 days"), pd.Timedelta("4 days")], name="xxx", dtype=object
+        )
+        tm.assert_series_equal(ser2 - ser, exp)
+        tm.assert_series_equal(ser - ser2, -exp)
+
+        ser = Series(
+            [pd.Timedelta("01:00:00"), pd.Timedelta("02:00:00")],
+            name="xxx",
+            dtype=object,
+        )
+        assert ser.dtype == object
+
+        exp = Series(
+            [pd.Timedelta("01:30:00"), pd.Timedelta("02:30:00")],
+            name="xxx",
+            dtype=object,
+        )
+        tm.assert_series_equal(ser + pd.Timedelta("00:30:00"), exp)
+        tm.assert_series_equal(pd.Timedelta("00:30:00") + ser, exp)
+
+    # TODO: cleanup & parametrize over box
+    def test_iadd_preserves_name(self):
+        # GH#17067, GH#19723 __iadd__ and __isub__ should preserve index name
+        ser = Series([1, 2, 3])
+        ser.index.name = "foo"
+
+        ser.index += 1
+        assert ser.index.name == "foo"
+
+        ser.index -= 1
+        assert ser.index.name == "foo"
+
+    def test_add_string(self):
+        # from bug report
+        index = pd.Index(["a", "b", "c"])
+        index2 = index + "foo"
+
+        assert "a" not in index2
+        assert "afoo" in index2
+
+    def test_iadd_string(self):
+        index = pd.Index(["a", "b", "c"])
+        # doesn't fail test unless there is a check before `+=`
+        assert "a" in index
+
+        index += "_x"
+        assert "a_x" in index
+
+    @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="add doesn't work")
+    def test_add(self):
+        index = pd.Index([str(i) for i in range(10)])
+        expected = pd.Index(index.values * 2)
+        tm.assert_index_equal(index + index, expected)
+        tm.assert_index_equal(index + index.tolist(), expected)
+        tm.assert_index_equal(index.tolist() + index, expected)
+
+        # test add and radd
+        index = pd.Index(list("abc"))
+        expected = pd.Index(["a1", "b1", "c1"])
+        tm.assert_index_equal(index + "1", expected)
+        expected = pd.Index(["1a", "1b", "1c"])
+        tm.assert_index_equal("1" + index, expected)
+
+    def test_sub_fail(self, using_infer_string):
+        index = pd.Index([str(i) for i in range(10)])
+
+        if using_infer_string:
+            import pyarrow as pa
+
+            err = pa.lib.ArrowNotImplementedError
+            msg = "has no kernel"
+        else:
+            err = TypeError
+            msg = "unsupported operand type|Cannot broadcast"
+        with pytest.raises(err, match=msg):
+            index - "a"
+        with pytest.raises(err, match=msg):
+            index - index
+        with pytest.raises(err, match=msg):
+            index - index.tolist()
+        with pytest.raises(err, match=msg):
+            index.tolist() - index
+
+    def test_sub_object(self):
+        # GH#19369
+        index = pd.Index([Decimal(1), Decimal(2)])
+        expected = pd.Index([Decimal(0), Decimal(1)])
+
+        result = index - Decimal(1)
+        tm.assert_index_equal(result, expected)
+
+        result = index - pd.Index([Decimal(1), Decimal(1)])
+        tm.assert_index_equal(result, expected)
+
+        msg = "unsupported operand type"
+        with pytest.raises(TypeError, match=msg):
+            index - "foo"
+
+        with pytest.raises(TypeError, match=msg):
+            index - np.array([2, "foo"], dtype=object)
+
+    def test_rsub_object(self, fixed_now_ts):
+        # GH#19369
+        index = pd.Index([Decimal(1), Decimal(2)])
+        expected = pd.Index([Decimal(1), Decimal(0)])
+
+        result = Decimal(2) - index
+        tm.assert_index_equal(result, expected)
+
+        result = np.array([Decimal(2), Decimal(2)]) - index
+        tm.assert_index_equal(result, expected)
+
+        msg = "unsupported operand type"
+        with pytest.raises(TypeError, match=msg):
+            "foo" - index
+
+        with pytest.raises(TypeError, match=msg):
+            np.array([True, fixed_now_ts]) - index
+
+
+class MyIndex(pd.Index):
+    # Simple index subclass that tracks ops calls.
+
+    _calls: int
+
+    @classmethod
+    def _simple_new(cls, values, name=None, dtype=None):
+        result = object.__new__(cls)
+        result._data = values
+        result._name = name
+        result._calls = 0
+        result._reset_identity()
+
+        return result
+
+    def __add__(self, other):
+        self._calls += 1
+        return self._simple_new(self._data)
+
+    def __radd__(self, other):
+        return self.__add__(other)
+
+
+@pytest.mark.parametrize(
+    "other",
+    [
+        [datetime.timedelta(1), datetime.timedelta(2)],
+        [datetime.datetime(2000, 1, 1), datetime.datetime(2000, 1, 2)],
+        [pd.Period("2000"), pd.Period("2001")],
+        ["a", "b"],
+    ],
+    ids=["timedelta", "datetime", "period", "object"],
+)
+def test_index_ops_defer_to_unknown_subclasses(other):
+    # https://github.com/pandas-dev/pandas/issues/31109
+    values = np.array(
+        [datetime.date(2000, 1, 1), datetime.date(2000, 1, 2)], dtype=object
+    )
+    a = MyIndex._simple_new(values)
+    other = pd.Index(other)
+    result = other + a
+    assert isinstance(result, MyIndex)
+    assert a._calls == 1

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_arithmetic.py

@@ -0,0 +1,139 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.fixture
+def data():
+    """Fixture returning boolean array with valid and missing values."""
+    return pd.array(
+        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        dtype="boolean",
+    )
+
+
+@pytest.fixture
+def left_array():
+    """Fixture returning boolean array with valid and missing values."""
+    return pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+
+
+@pytest.fixture
+def right_array():
+    """Fixture returning boolean array with valid and missing values."""
+    return pd.array([True, False, None] * 3, dtype="boolean")
+
+
+# Basic test for the arithmetic array ops
+# -----------------------------------------------------------------------------
+
+
+@pytest.mark.parametrize(
+    "opname, exp",
+    [
+        ("add", [True, True, None, True, False, None, None, None, None]),
+        ("mul", [True, False, None, False, False, None, None, None, None]),
+    ],
+    ids=["add", "mul"],
+)
+def test_add_mul(left_array, right_array, opname, exp):
+    op = getattr(operator, opname)
+    result = op(left_array, right_array)
+    expected = pd.array(exp, dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_sub(left_array, right_array):
+    msg = (
+        r"numpy boolean subtract, the `-` operator, is (?:deprecated|not supported), "
+        r"use the bitwise_xor, the `\^` operator, or the logical_xor function instead\."
+    )
+    with pytest.raises(TypeError, match=msg):
+        left_array - right_array
+
+
+def test_div(left_array, right_array):
+    msg = "operator '.*' not implemented for bool dtypes"
+    with pytest.raises(NotImplementedError, match=msg):
+        # check that we are matching the non-masked Series behavior
+        pd.Series(left_array._data) / pd.Series(right_array._data)
+
+    with pytest.raises(NotImplementedError, match=msg):
+        left_array / right_array
+
+
+@pytest.mark.parametrize(
+    "opname",
+    [
+        "floordiv",
+        "mod",
+        "pow",
+    ],
+)
+def test_op_int8(left_array, right_array, opname):
+    op = getattr(operator, opname)
+    if opname != "mod":
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            result = op(left_array, right_array)
+        return
+    result = op(left_array, right_array)
+    expected = op(left_array.astype("Int8"), right_array.astype("Int8"))
+    tm.assert_extension_array_equal(result, expected)
+
+
+# Test generic characteristics / errors
+# -----------------------------------------------------------------------------
+
+
+def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
+    # invalid ops
+
+    if using_infer_string:
+        import pyarrow as pa
+
+        err = (TypeError, pa.lib.ArrowNotImplementedError, NotImplementedError)
+    else:
+        err = TypeError
+
+    op = all_arithmetic_operators
+    s = pd.Series(data)
+    ops = getattr(s, op)
+
+    # invalid scalars
+    msg = (
+        "did not contain a loop with signature matching types|"
+        "BooleanArray cannot perform the operation|"
+        "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):
+        ops("foo")
+    msg = "|".join(
+        [
+            r"unsupported operand type\(s\) for",
+            "Concatenation operation is not implemented for NumPy arrays",
+            "has no kernel",
+        ]
+    )
+    with pytest.raises(err, match=msg):
+        ops(pd.Timestamp("20180101"))
+
+    # invalid array-likes
+    if op not in ("__mul__", "__rmul__"):
+        # TODO(extension) numpy's mul with object array sees booleans as numbers
+        msg = "|".join(
+            [
+                r"unsupported operand type\(s\) for",
+                "can only concatenate str",
+                "not all arguments converted during string formatting",
+                "has no kernel",
+                "not implemented",
+            ]
+        )
+        with pytest.raises(err, match=msg):
+            ops(pd.Series("foo", index=s.index))

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_astype.py

@@ -0,0 +1,53 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+def test_astype():
+    # with missing values
+    arr = pd.array([True, False, None], dtype="boolean")
+
+    with pytest.raises(ValueError, match="cannot convert NA to integer"):
+        arr.astype("int64")
+
+    with pytest.raises(ValueError, match="cannot convert float NaN to"):
+        arr.astype("bool")
+
+    result = arr.astype("float64")
+    expected = np.array([1, 0, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.astype("str")
+    expected = np.array(["True", "False", "<NA>"], dtype=f"{tm.ENDIAN}U5")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # no missing values
+    arr = pd.array([True, False, True], dtype="boolean")
+    result = arr.astype("int64")
+    expected = np.array([1, 0, 1], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.astype("bool")
+    expected = np.array([True, False, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_astype_to_boolean_array():
+    # astype to BooleanArray
+    arr = pd.array([True, False, None], dtype="boolean")
+
+    result = arr.astype("boolean")
+    tm.assert_extension_array_equal(result, arr)
+    result = arr.astype(pd.BooleanDtype())
+    tm.assert_extension_array_equal(result, arr)
+
+
+def test_astype_to_integer_array():
+    # astype to IntegerArray
+    arr = pd.array([True, False, None], dtype="boolean")
+
+    result = arr.astype("Int64")
+    expected = pd.array([1, 0, None], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_comparison.py

@@ -0,0 +1,60 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.arrays import BooleanArray
+from pandas.tests.arrays.masked_shared import ComparisonOps
+
+
+@pytest.fixture
+def data():
+    """Fixture returning boolean array with valid and missing data"""
+    return pd.array(
+        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        dtype="boolean",
+    )
+
+
+@pytest.fixture
+def dtype():
+    """Fixture returning BooleanDtype"""
+    return pd.BooleanDtype()
+
+
+class TestComparisonOps(ComparisonOps):
+    def test_compare_scalar(self, data, comparison_op):
+        self._compare_other(data, comparison_op, True)
+
+    def test_compare_array(self, data, comparison_op):
+        other = pd.array([True] * len(data), dtype="boolean")
+        self._compare_other(data, comparison_op, other)
+        other = np.array([True] * len(data))
+        self._compare_other(data, comparison_op, other)
+        other = pd.Series([True] * len(data))
+        self._compare_other(data, comparison_op, other)
+
+    @pytest.mark.parametrize("other", [True, False, pd.NA])
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
+
+    def test_array(self, comparison_op):
+        op = comparison_op
+        a = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        b = pd.array([True, False, None] * 3, dtype="boolean")
+
+        result = op(a, b)
+
+        values = op(a._data, b._data)
+        mask = a._mask | b._mask
+        expected = BooleanArray(values, mask)
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        result[0] = None
+        tm.assert_extension_array_equal(
+            a, pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        )
+        tm.assert_extension_array_equal(
+            b, pd.array([True, False, None] * 3, dtype="boolean")
+        )

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_construction.py

@@ -0,0 +1,325 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.arrays import BooleanArray
+from pandas.core.arrays.boolean import coerce_to_array
+
+
+def test_boolean_array_constructor():
+    values = np.array([True, False, True, False], dtype="bool")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = BooleanArray(values, mask)
+    expected = pd.array([True, False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    with pytest.raises(TypeError, match="values should be boolean numpy array"):
+        BooleanArray(values.tolist(), mask)
+
+    with pytest.raises(TypeError, match="mask should be boolean numpy array"):
+        BooleanArray(values, mask.tolist())
+
+    with pytest.raises(TypeError, match="values should be boolean numpy array"):
+        BooleanArray(values.astype(int), mask)
+
+    with pytest.raises(TypeError, match="mask should be boolean numpy array"):
+        BooleanArray(values, None)
+
+    with pytest.raises(ValueError, match="values.shape must match mask.shape"):
+        BooleanArray(values.reshape(1, -1), mask)
+
+    with pytest.raises(ValueError, match="values.shape must match mask.shape"):
+        BooleanArray(values, mask.reshape(1, -1))
+
+
+def test_boolean_array_constructor_copy():
+    values = np.array([True, False, True, False], dtype="bool")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = BooleanArray(values, mask)
+    assert result._data is values
+    assert result._mask is mask
+
+    result = BooleanArray(values, mask, copy=True)
+    assert result._data is not values
+    assert result._mask is not mask
+
+
+def test_to_boolean_array():
+    expected = BooleanArray(
+        np.array([True, False, True]), np.array([False, False, False])
+    )
+
+    result = pd.array([True, False, True], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, True]), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, True], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    expected = BooleanArray(
+        np.array([True, False, True]), np.array([False, False, True])
+    )
+
+    result = pd.array([True, False, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, None], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_boolean_array_all_none():
+    expected = BooleanArray(np.array([True, True, True]), np.array([True, True, True]))
+
+    result = pd.array([None, None, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([None, None, None], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "a, b",
+    [
+        ([True, False, None, np.nan, pd.NA], [True, False, None, None, None]),
+        ([True, np.nan], [True, None]),
+        ([True, pd.NA], [True, None]),
+        ([np.nan, np.nan], [None, None]),
+        (np.array([np.nan, np.nan], dtype=float), [None, None]),
+    ],
+)
+def test_to_boolean_array_missing_indicators(a, b):
+    result = pd.array(a, dtype="boolean")
+    expected = pd.array(b, dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values",
+    [
+        ["foo", "bar"],
+        ["1", "2"],
+        # "foo",
+        [1, 2],
+        [1.0, 2.0],
+        pd.date_range("20130101", periods=2),
+        np.array(["foo"]),
+        np.array([1, 2]),
+        np.array([1.0, 2.0]),
+        [np.nan, {"a": 1}],
+    ],
+)
+def test_to_boolean_array_error(values):
+    # error in converting existing arrays to BooleanArray
+    msg = "Need to pass bool-like value"
+    with pytest.raises(TypeError, match=msg):
+        pd.array(values, dtype="boolean")
+
+
+def test_to_boolean_array_from_integer_array():
+    result = pd.array(np.array([1, 0, 1, 0]), dtype="boolean")
+    expected = pd.array([True, False, True, False], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    result = pd.array(np.array([1, 0, 1, None]), dtype="boolean")
+    expected = pd.array([True, False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_boolean_array_from_float_array():
+    result = pd.array(np.array([1.0, 0.0, 1.0, 0.0]), dtype="boolean")
+    expected = pd.array([True, False, True, False], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    result = pd.array(np.array([1.0, 0.0, 1.0, np.nan]), dtype="boolean")
+    expected = pd.array([True, False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_boolean_array_integer_like():
+    # integers of 0's and 1's
+    result = pd.array([1, 0, 1, 0], dtype="boolean")
+    expected = pd.array([True, False, True, False], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    result = pd.array([1, 0, 1, None], dtype="boolean")
+    expected = pd.array([True, False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_coerce_to_array():
+    # TODO this is currently not public API
+    values = np.array([True, False, True, False], dtype="bool")
+    mask = np.array([False, False, False, True], dtype="bool")
+    result = BooleanArray(*coerce_to_array(values, mask=mask))
+    expected = BooleanArray(values, mask)
+    tm.assert_extension_array_equal(result, expected)
+    assert result._data is values
+    assert result._mask is mask
+    result = BooleanArray(*coerce_to_array(values, mask=mask, copy=True))
+    expected = BooleanArray(values, mask)
+    tm.assert_extension_array_equal(result, expected)
+    assert result._data is not values
+    assert result._mask is not mask
+
+    # mixed missing from values and mask
+    values = [True, False, None, False]
+    mask = np.array([False, False, False, True], dtype="bool")
+    result = BooleanArray(*coerce_to_array(values, mask=mask))
+    expected = BooleanArray(
+        np.array([True, False, True, True]), np.array([False, False, True, True])
+    )
+    tm.assert_extension_array_equal(result, expected)
+    result = BooleanArray(*coerce_to_array(np.array(values, dtype=object), mask=mask))
+    tm.assert_extension_array_equal(result, expected)
+    result = BooleanArray(*coerce_to_array(values, mask=mask.tolist()))
+    tm.assert_extension_array_equal(result, expected)
+
+    # raise errors for wrong dimension
+    values = np.array([True, False, True, False], dtype="bool")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    # passing 2D values is OK as long as no mask
+    coerce_to_array(values.reshape(1, -1))
+
+    with pytest.raises(ValueError, match="values.shape and mask.shape must match"):
+        coerce_to_array(values.reshape(1, -1), mask=mask)
+
+    with pytest.raises(ValueError, match="values.shape and mask.shape must match"):
+        coerce_to_array(values, mask=mask.reshape(1, -1))
+
+
+def test_coerce_to_array_from_boolean_array():
+    # passing BooleanArray to coerce_to_array
+    values = np.array([True, False, True, False], dtype="bool")
+    mask = np.array([False, False, False, True], dtype="bool")
+    arr = BooleanArray(values, mask)
+    result = BooleanArray(*coerce_to_array(arr))
+    tm.assert_extension_array_equal(result, arr)
+    # no copy
+    assert result._data is arr._data
+    assert result._mask is arr._mask
+
+    result = BooleanArray(*coerce_to_array(arr), copy=True)
+    tm.assert_extension_array_equal(result, arr)
+    assert result._data is not arr._data
+    assert result._mask is not arr._mask
+
+    with pytest.raises(ValueError, match="cannot pass mask for BooleanArray input"):
+        coerce_to_array(arr, mask=mask)
+
+
+def test_coerce_to_numpy_array():
+    # with missing values -> object dtype
+    arr = pd.array([True, False, None], dtype="boolean")
+    result = np.array(arr)
+    expected = np.array([True, False, pd.NA], dtype="object")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # also with no missing values -> object dtype
+    arr = pd.array([True, False, True], dtype="boolean")
+    result = np.array(arr)
+    expected = np.array([True, False, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # force bool dtype
+    result = np.array(arr, dtype="bool")
+    expected = np.array([True, False, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+    # with missing values will raise error
+    arr = pd.array([True, False, None], dtype="boolean")
+    msg = (
+        "cannot convert to 'bool'-dtype NumPy array with missing values. "
+        "Specify an appropriate 'na_value' for this dtype."
+    )
+    with pytest.raises(ValueError, match=msg):
+        np.array(arr, dtype="bool")
+
+
+def test_to_boolean_array_from_strings():
+    result = BooleanArray._from_sequence_of_strings(
+        np.array(["True", "False", "1", "1.0", "0", "0.0", np.nan], dtype=object),
+        dtype="boolean",
+    )
+    expected = BooleanArray(
+        np.array([True, False, True, True, False, False, False]),
+        np.array([False, False, False, False, False, False, True]),
+    )
+
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_boolean_array_from_strings_invalid_string():
+    with pytest.raises(ValueError, match="cannot be cast"):
+        BooleanArray._from_sequence_of_strings(["donkey"], dtype="boolean")
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy(box):
+    con = pd.Series if box else pd.array
+    # default (with or without missing values) -> object dtype
+    arr = con([True, False, True], dtype="boolean")
+    result = arr.to_numpy()
+    expected = np.array([True, False, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([True, False, None], dtype="boolean")
+    result = arr.to_numpy()
+    expected = np.array([True, False, pd.NA], dtype="object")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([True, False, None], dtype="boolean")
+    result = arr.to_numpy(dtype="str")
+    expected = np.array([True, False, pd.NA], dtype=f"{tm.ENDIAN}U5")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # no missing values -> can convert to bool, otherwise raises
+    arr = con([True, False, True], dtype="boolean")
+    result = arr.to_numpy(dtype="bool")
+    expected = np.array([True, False, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([True, False, None], dtype="boolean")
+    with pytest.raises(ValueError, match="cannot convert to 'bool'-dtype"):
+        result = arr.to_numpy(dtype="bool")
+
+    # specify dtype and na_value
+    arr = con([True, False, None], dtype="boolean")
+    result = arr.to_numpy(dtype=object, na_value=None)
+    expected = np.array([True, False, None], dtype="object")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype=bool, na_value=False)
+    expected = np.array([True, False, False], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype="int64", na_value=-99)
+    expected = np.array([1, 0, -99], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype="float64", na_value=np.nan)
+    expected = np.array([1, 0, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # converting to int or float without specifying na_value raises
+    with pytest.raises(ValueError, match="cannot convert to 'int64'-dtype"):
+        arr.to_numpy(dtype="int64")
+
+
+def test_to_numpy_copy():
+    # to_numpy can be zero-copy if no missing values
+    arr = pd.array([True, False, True], dtype="boolean")
+    result = arr.to_numpy(dtype=bool)
+    result[0] = False
+    tm.assert_extension_array_equal(
+        arr, pd.array([False, False, True], dtype="boolean")
+    )
+
+    arr = pd.array([True, False, True], dtype="boolean")
+    result = arr.to_numpy(dtype=bool, copy=True)
+    result[0] = False
+    tm.assert_extension_array_equal(arr, pd.array([True, False, True], dtype="boolean"))

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_function.py

@@ -0,0 +1,126 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "ufunc", [np.add, np.logical_or, np.logical_and, np.logical_xor]
+)
+def test_ufuncs_binary(ufunc):
+    # two BooleanArrays
+    a = pd.array([True, False, None], dtype="boolean")
+    result = ufunc(a, a)
+    expected = pd.array(ufunc(a._data, a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    s = pd.Series(a)
+    result = ufunc(s, a)
+    expected = pd.Series(ufunc(a._data, a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_series_equal(result, expected)
+
+    # Boolean with numpy array
+    arr = np.array([True, True, False])
+    result = ufunc(a, arr)
+    expected = pd.array(ufunc(a._data, arr), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(arr, a)
+    expected = pd.array(ufunc(arr, a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    # BooleanArray with scalar
+    result = ufunc(a, True)
+    expected = pd.array(ufunc(a._data, True), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(True, a)
+    expected = pd.array(ufunc(True, a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    # not handled types
+    msg = r"operand type\(s\) all returned NotImplemented from __array_ufunc__"
+    with pytest.raises(TypeError, match=msg):
+        ufunc(a, "test")
+
+
+@pytest.mark.parametrize("ufunc", [np.logical_not])
+def test_ufuncs_unary(ufunc):
+    a = pd.array([True, False, None], dtype="boolean")
+    result = ufunc(a)
+    expected = pd.array(ufunc(a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_extension_array_equal(result, expected)
+
+    ser = pd.Series(a)
+    result = ufunc(ser)
+    expected = pd.Series(ufunc(a._data), dtype="boolean")
+    expected[a._mask] = np.nan
+    tm.assert_series_equal(result, expected)
+
+
+def test_ufunc_numeric():
+    # np.sqrt on np.bool_ returns float16, which we upcast to Float32
+    #  bc we do not have Float16
+    arr = pd.array([True, False, None], dtype="boolean")
+
+    res = np.sqrt(arr)
+
+    expected = pd.array([1, 0, None], dtype="Float32")
+    tm.assert_extension_array_equal(res, expected)
+
+
+@pytest.mark.parametrize("values", [[True, False], [True, None]])
+def test_ufunc_reduce_raises(values):
+    arr = pd.array(values, dtype="boolean")
+
+    res = np.add.reduce(arr)
+    if arr[-1] is pd.NA:
+        expected = pd.NA
+    else:
+        expected = arr._data.sum()
+    tm.assert_almost_equal(res, expected)
+
+
+def test_value_counts_na():
+    arr = pd.array([True, False, pd.NA], dtype="boolean")
+    result = arr.value_counts(dropna=False)
+    expected = pd.Series([1, 1, 1], index=arr, dtype="Int64", name="count")
+    assert expected.index.dtype == arr.dtype
+    tm.assert_series_equal(result, expected)
+
+    result = arr.value_counts(dropna=True)
+    expected = pd.Series([1, 1], index=arr[:-1], dtype="Int64", name="count")
+    assert expected.index.dtype == arr.dtype
+    tm.assert_series_equal(result, expected)
+
+
+def test_value_counts_with_normalize():
+    ser = pd.Series([True, False, pd.NA], dtype="boolean")
+    result = ser.value_counts(normalize=True)
+    expected = pd.Series([1, 1], index=ser[:-1], dtype="Float64", name="proportion") / 2
+    assert expected.index.dtype == "boolean"
+    tm.assert_series_equal(result, expected)
+
+
+def test_diff():
+    a = pd.array(
+        [True, True, False, False, True, None, True, None, False], dtype="boolean"
+    )
+    result = pd.core.algorithms.diff(a, 1)
+    expected = pd.array(
+        [None, False, True, False, True, None, None, None, None], dtype="boolean"
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    ser = pd.Series(a)
+    result = ser.diff()
+    expected = pd.Series(expected)
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_indexing.py

@@ -0,0 +1,13 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize("na", [None, np.nan, pd.NA])
+def test_setitem_missing_values(na):
+    arr = pd.array([True, False, None], dtype="boolean")
+    expected = pd.array([True, None, None], dtype="boolean")
+    arr[1] = na
+    tm.assert_extension_array_equal(arr, expected)

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_logical.py

@@ -0,0 +1,254 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.arrays import BooleanArray
+from pandas.core.ops.mask_ops import (
+    kleene_and,
+    kleene_or,
+    kleene_xor,
+)
+from pandas.tests.extension.base import BaseOpsUtil
+
+
+class TestLogicalOps(BaseOpsUtil):
+    def test_numpy_scalars_ok(self, all_logical_operators):
+        a = pd.array([True, False, None], dtype="boolean")
+        op = getattr(a, all_logical_operators)
+
+        tm.assert_extension_array_equal(op(True), op(np.bool_(True)))
+        tm.assert_extension_array_equal(op(False), op(np.bool_(False)))
+
+    def get_op_from_name(self, op_name):
+        short_opname = op_name.strip("_")
+        short_opname = short_opname if "xor" in short_opname else short_opname + "_"
+        try:
+            op = getattr(operator, short_opname)
+        except AttributeError:
+            # Assume it is the reverse operator
+            rop = getattr(operator, short_opname[1:])
+            op = lambda x, y: rop(y, x)
+
+        return op
+
+    def test_empty_ok(self, all_logical_operators):
+        a = pd.array([], dtype="boolean")
+        op_name = all_logical_operators
+        result = getattr(a, op_name)(True)
+        tm.assert_extension_array_equal(a, result)
+
+        result = getattr(a, op_name)(False)
+        tm.assert_extension_array_equal(a, result)
+
+        result = getattr(a, op_name)(pd.NA)
+        tm.assert_extension_array_equal(a, result)
+
+    @pytest.mark.parametrize(
+        "other", ["a", pd.Timestamp(2017, 1, 1, 12), np.timedelta64(4)]
+    )
+    def test_eq_mismatched_type(self, other):
+        # GH-44499
+        arr = pd.array([True, False])
+        result = arr == other
+        expected = pd.array([False, False])
+        tm.assert_extension_array_equal(result, expected)
+
+        result = arr != other
+        expected = pd.array([True, True])
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_logical_length_mismatch_raises(self, all_logical_operators):
+        op_name = all_logical_operators
+        a = pd.array([True, False, None], dtype="boolean")
+        msg = "Lengths must match"
+
+        with pytest.raises(ValueError, match=msg):
+            getattr(a, op_name)([True, False])
+
+        with pytest.raises(ValueError, match=msg):
+            getattr(a, op_name)(np.array([True, False]))
+
+        with pytest.raises(ValueError, match=msg):
+            getattr(a, op_name)(pd.array([True, False], dtype="boolean"))
+
+    def test_logical_nan_raises(self, all_logical_operators):
+        op_name = all_logical_operators
+        a = pd.array([True, False, None], dtype="boolean")
+        msg = "Got float instead"
+
+        with pytest.raises(TypeError, match=msg):
+            getattr(a, op_name)(np.nan)
+
+    @pytest.mark.parametrize("other", ["a", 1])
+    def test_non_bool_or_na_other_raises(self, other, all_logical_operators):
+        a = pd.array([True, False], dtype="boolean")
+        with pytest.raises(TypeError, match=str(type(other).__name__)):
+            getattr(a, all_logical_operators)(other)
+
+    def test_kleene_or(self):
+        # A clear test of behavior.
+        a = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        b = pd.array([True, False, None] * 3, dtype="boolean")
+        result = a | b
+        expected = pd.array(
+            [True, True, True, True, False, None, True, None, None], dtype="boolean"
+        )
+        tm.assert_extension_array_equal(result, expected)
+
+        result = b | a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        )
+        tm.assert_extension_array_equal(
+            b, pd.array([True, False, None] * 3, dtype="boolean")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (pd.NA, [True, None, None]),
+            (True, [True, True, True]),
+            (np.bool_(True), [True, True, True]),
+            (False, [True, False, None]),
+            (np.bool_(False), [True, False, None]),
+        ],
+    )
+    def test_kleene_or_scalar(self, other, expected):
+        # TODO: test True & False
+        a = pd.array([True, False, None], dtype="boolean")
+        result = a | other
+        expected = pd.array(expected, dtype="boolean")
+        tm.assert_extension_array_equal(result, expected)
+
+        result = other | a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True, False, None], dtype="boolean")
+        )
+
+    def test_kleene_and(self):
+        # A clear test of behavior.
+        a = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        b = pd.array([True, False, None] * 3, dtype="boolean")
+        result = a & b
+        expected = pd.array(
+            [True, False, None, False, False, False, None, False, None], dtype="boolean"
+        )
+        tm.assert_extension_array_equal(result, expected)
+
+        result = b & a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        )
+        tm.assert_extension_array_equal(
+            b, pd.array([True, False, None] * 3, dtype="boolean")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (pd.NA, [None, False, None]),
+            (True, [True, False, None]),
+            (False, [False, False, False]),
+            (np.bool_(True), [True, False, None]),
+            (np.bool_(False), [False, False, False]),
+        ],
+    )
+    def test_kleene_and_scalar(self, other, expected):
+        a = pd.array([True, False, None], dtype="boolean")
+        result = a & other
+        expected = pd.array(expected, dtype="boolean")
+        tm.assert_extension_array_equal(result, expected)
+
+        result = other & a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True, False, None], dtype="boolean")
+        )
+
+    def test_kleene_xor(self):
+        a = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        b = pd.array([True, False, None] * 3, dtype="boolean")
+        result = a ^ b
+        expected = pd.array(
+            [False, True, None, True, False, None, None, None, None], dtype="boolean"
+        )
+        tm.assert_extension_array_equal(result, expected)
+
+        result = b ^ a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        )
+        tm.assert_extension_array_equal(
+            b, pd.array([True, False, None] * 3, dtype="boolean")
+        )
+
+    @pytest.mark.parametrize(
+        "other, expected",
+        [
+            (pd.NA, [None, None, None]),
+            (True, [False, True, None]),
+            (np.bool_(True), [False, True, None]),
+            (np.bool_(False), [True, False, None]),
+        ],
+    )
+    def test_kleene_xor_scalar(self, other, expected):
+        a = pd.array([True, False, None], dtype="boolean")
+        result = a ^ other
+        expected = pd.array(expected, dtype="boolean")
+        tm.assert_extension_array_equal(result, expected)
+
+        result = other ^ a
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        tm.assert_extension_array_equal(
+            a, pd.array([True, False, None], dtype="boolean")
+        )
+
+    @pytest.mark.parametrize("other", [True, False, pd.NA, [True, False, None] * 3])
+    def test_no_masked_assumptions(self, other, all_logical_operators):
+        # The logical operations should not assume that masked values are False!
+        a = pd.arrays.BooleanArray(
+            np.array([True, True, True, False, False, False, True, False, True]),
+            np.array([False] * 6 + [True, True, True]),
+        )
+        b = pd.array([True] * 3 + [False] * 3 + [None] * 3, dtype="boolean")
+        if isinstance(other, list):
+            other = pd.array(other, dtype="boolean")
+
+        result = getattr(a, all_logical_operators)(other)
+        expected = getattr(b, all_logical_operators)(other)
+        tm.assert_extension_array_equal(result, expected)
+
+        if isinstance(other, BooleanArray):
+            other._data[other._mask] = True
+            a._data[a._mask] = False
+
+            result = getattr(a, all_logical_operators)(other)
+            expected = getattr(b, all_logical_operators)(other)
+            tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("operation", [kleene_or, kleene_xor, kleene_and])
+def test_error_both_scalar(operation):
+    msg = r"Either `left` or `right` need to be a np\.ndarray."
+    with pytest.raises(TypeError, match=msg):
+        # masks need to be non-None, otherwise it ends up in an infinite recursion
+        operation(True, True, np.zeros(1), np.zeros(1))

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_ops.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import pandas._testing as tm
+
+
+class TestUnaryOps:
+    def test_invert(self):
+        a = pd.array([True, False, None], dtype="boolean")
+        expected = pd.array([False, True, None], dtype="boolean")
+        tm.assert_extension_array_equal(~a, expected)
+
+        expected = pd.Series(expected, index=["a", "b", "c"], name="name")
+        result = ~pd.Series(a, index=["a", "b", "c"], name="name")
+        tm.assert_series_equal(result, expected)
+
+        df = pd.DataFrame({"A": a, "B": [True, False, False]}, index=["a", "b", "c"])
+        result = ~df
+        expected = pd.DataFrame(
+            {"A": expected, "B": [False, True, True]}, index=["a", "b", "c"]
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_abs(self):
+        # matching numpy behavior, abs is the identity function
+        arr = pd.array([True, False, None], dtype="boolean")
+        result = abs(arr)
+
+        tm.assert_extension_array_equal(result, arr)

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_reduction.py

@@ -0,0 +1,62 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+
+
+@pytest.fixture
+def data():
+    """Fixture returning boolean array, with valid and missing values."""
+    return pd.array(
+        [True, False] * 4 + [np.nan] + [True, False] * 44 + [np.nan] + [True, False],
+        dtype="boolean",
+    )
+
+
+@pytest.mark.parametrize(
+    "values, exp_any, exp_all, exp_any_noskip, exp_all_noskip",
+    [
+        ([True, pd.NA], True, True, True, pd.NA),
+        ([False, pd.NA], False, False, pd.NA, False),
+        ([pd.NA], False, True, pd.NA, pd.NA),
+        ([], False, True, False, True),
+        # GH-33253: all True / all False values buggy with skipna=False
+        ([True, True], True, True, True, True),
+        ([False, False], False, False, False, False),
+    ],
+)
+def test_any_all(values, exp_any, exp_all, exp_any_noskip, exp_all_noskip):
+    # the methods return numpy scalars
+    exp_any = pd.NA if exp_any is pd.NA else np.bool_(exp_any)
+    exp_all = pd.NA if exp_all is pd.NA else np.bool_(exp_all)
+    exp_any_noskip = pd.NA if exp_any_noskip is pd.NA else np.bool_(exp_any_noskip)
+    exp_all_noskip = pd.NA if exp_all_noskip is pd.NA else np.bool_(exp_all_noskip)
+
+    for con in [pd.array, pd.Series]:
+        a = con(values, dtype="boolean")
+        assert a.any() is exp_any
+        assert a.all() is exp_all
+        assert a.any(skipna=False) is exp_any_noskip
+        assert a.all(skipna=False) is exp_all_noskip
+
+        assert np.any(a.any()) is exp_any
+        assert np.all(a.all()) is exp_all
+
+
+@pytest.mark.parametrize("dropna", [True, False])
+def test_reductions_return_types(dropna, data, all_numeric_reductions):
+    op = all_numeric_reductions
+    s = pd.Series(data)
+    if dropna:
+        s = s.dropna()
+
+    if op in ("sum", "prod"):
+        assert isinstance(getattr(s, op)(), np.int_)
+    elif op == "count":
+        # Oddly on the 32 bit build (but not Windows), this is intc (!= intp)
+        assert isinstance(getattr(s, op)(), np.integer)
+    elif op in ("min", "max"):
+        assert isinstance(getattr(s, op)(), np.bool_)
+    else:
+        # "mean", "std", "var", "median", "kurt", "skew"
+        assert isinstance(getattr(s, op)(), np.float64)

lib/python3.13/site-packages/pandas/tests/arrays/boolean/test_repr.py

@@ -0,0 +1,13 @@
+import pandas as pd
+
+
+def test_repr():
+    df = pd.DataFrame({"A": pd.array([True, False, None], dtype="boolean")})
+    expected = "       A\n0   True\n1  False\n2   <NA>"
+    assert repr(df) == expected
+
+    expected = "0     True\n1    False\n2     <NA>\nName: A, dtype: boolean"
+    assert repr(df.A) == expected
+
+    expected = "<BooleanArray>\n[True, False, <NA>]\nLength: 3, dtype: boolean"
+    assert repr(df.A.array) == expected

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_algos.py

@@ -0,0 +1,89 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize("ordered", [True, False])
+@pytest.mark.parametrize("categories", [["b", "a", "c"], ["a", "b", "c", "d"]])
+def test_factorize(categories, ordered):
+    cat = pd.Categorical(
+        ["b", "b", "a", "c", None], categories=categories, ordered=ordered
+    )
+    codes, uniques = pd.factorize(cat)
+    expected_codes = np.array([0, 0, 1, 2, -1], dtype=np.intp)
+    expected_uniques = pd.Categorical(
+        ["b", "a", "c"], categories=categories, ordered=ordered
+    )
+
+    tm.assert_numpy_array_equal(codes, expected_codes)
+    tm.assert_categorical_equal(uniques, expected_uniques)
+
+
+def test_factorized_sort():
+    cat = pd.Categorical(["b", "b", None, "a"])
+    codes, uniques = pd.factorize(cat, sort=True)
+    expected_codes = np.array([1, 1, -1, 0], dtype=np.intp)
+    expected_uniques = pd.Categorical(["a", "b"])
+
+    tm.assert_numpy_array_equal(codes, expected_codes)
+    tm.assert_categorical_equal(uniques, expected_uniques)
+
+
+def test_factorized_sort_ordered():
+    cat = pd.Categorical(
+        ["b", "b", None, "a"], categories=["c", "b", "a"], ordered=True
+    )
+
+    codes, uniques = pd.factorize(cat, sort=True)
+    expected_codes = np.array([0, 0, -1, 1], dtype=np.intp)
+    expected_uniques = pd.Categorical(
+        ["b", "a"], categories=["c", "b", "a"], ordered=True
+    )
+
+    tm.assert_numpy_array_equal(codes, expected_codes)
+    tm.assert_categorical_equal(uniques, expected_uniques)
+
+
+def test_isin_cats():
+    # GH2003
+    cat = pd.Categorical(["a", "b", np.nan])
+
+    result = cat.isin(["a", np.nan])
+    expected = np.array([True, False, True], dtype=bool)
+    tm.assert_numpy_array_equal(expected, result)
+
+    result = cat.isin(["a", "c"])
+    expected = np.array([True, False, False], dtype=bool)
+    tm.assert_numpy_array_equal(expected, result)
+
+
+@pytest.mark.parametrize("value", [[""], [None, ""], [pd.NaT, ""]])
+def test_isin_cats_corner_cases(value):
+    # GH36550
+    cat = pd.Categorical([""])
+    result = cat.isin(value)
+    expected = np.array([True], dtype=bool)
+    tm.assert_numpy_array_equal(expected, result)
+
+
+@pytest.mark.parametrize("empty", [[], pd.Series(dtype=object), np.array([])])
+def test_isin_empty(empty):
+    s = pd.Categorical(["a", "b"])
+    expected = np.array([False, False], dtype=bool)
+
+    result = s.isin(empty)
+    tm.assert_numpy_array_equal(expected, result)
+
+
+def test_diff():
+    ser = pd.Series([1, 2, 3], dtype="category")
+
+    msg = "Convert to a suitable dtype"
+    with pytest.raises(TypeError, match=msg):
+        ser.diff()
+
+    df = ser.to_frame(name="A")
+    with pytest.raises(TypeError, match=msg):
+        df.diff()

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_analytics.py

@@ -0,0 +1,349 @@
+import re
+import sys
+
+import numpy as np
+import pytest
+
+from pandas.compat import PYPY
+
+from pandas import (
+    Categorical,
+    CategoricalDtype,
+    DataFrame,
+    Index,
+    NaT,
+    Series,
+    date_range,
+)
+import pandas._testing as tm
+from pandas.api.types import is_scalar
+
+
+class TestCategoricalAnalytics:
+    @pytest.mark.parametrize("aggregation", ["min", "max"])
+    def test_min_max_not_ordered_raises(self, aggregation):
+        # unordered cats have no min/max
+        cat = Categorical(["a", "b", "c", "d"], ordered=False)
+        msg = f"Categorical is not ordered for operation {aggregation}"
+        agg_func = getattr(cat, aggregation)
+
+        with pytest.raises(TypeError, match=msg):
+            agg_func()
+
+        ufunc = np.minimum if aggregation == "min" else np.maximum
+        with pytest.raises(TypeError, match=msg):
+            ufunc.reduce(cat)
+
+    def test_min_max_ordered(self, index_or_series_or_array):
+        cat = Categorical(["a", "b", "c", "d"], ordered=True)
+        obj = index_or_series_or_array(cat)
+        _min = obj.min()
+        _max = obj.max()
+        assert _min == "a"
+        assert _max == "d"
+
+        assert np.minimum.reduce(obj) == "a"
+        assert np.maximum.reduce(obj) == "d"
+        # TODO: raises if we pass axis=0  (on Index and Categorical, not Series)
+
+        cat = Categorical(
+            ["a", "b", "c", "d"], categories=["d", "c", "b", "a"], ordered=True
+        )
+        obj = index_or_series_or_array(cat)
+        _min = obj.min()
+        _max = obj.max()
+        assert _min == "d"
+        assert _max == "a"
+        assert np.minimum.reduce(obj) == "d"
+        assert np.maximum.reduce(obj) == "a"
+
+    def test_min_max_reduce(self):
+        # GH52788
+        cat = Categorical(["a", "b", "c", "d"], ordered=True)
+        df = DataFrame(cat)
+
+        result_max = df.agg("max")
+        expected_max = Series(Categorical(["d"], dtype=cat.dtype))
+        tm.assert_series_equal(result_max, expected_max)
+
+        result_min = df.agg("min")
+        expected_min = Series(Categorical(["a"], dtype=cat.dtype))
+        tm.assert_series_equal(result_min, expected_min)
+
+    @pytest.mark.parametrize(
+        "categories,expected",
+        [
+            (list("ABC"), np.nan),
+            ([1, 2, 3], np.nan),
+            pytest.param(
+                Series(date_range("2020-01-01", periods=3), dtype="category"),
+                NaT,
+                marks=pytest.mark.xfail(
+                    reason="https://github.com/pandas-dev/pandas/issues/29962"
+                ),
+            ),
+        ],
+    )
+    @pytest.mark.parametrize("aggregation", ["min", "max"])
+    def test_min_max_ordered_empty(self, categories, expected, aggregation):
+        # GH 30227
+        cat = Categorical([], categories=categories, ordered=True)
+
+        agg_func = getattr(cat, aggregation)
+        result = agg_func()
+        assert result is expected
+
+    @pytest.mark.parametrize(
+        "values, categories",
+        [(["a", "b", "c", np.nan], list("cba")), ([1, 2, 3, np.nan], [3, 2, 1])],
+    )
+    @pytest.mark.parametrize("skipna", [True, False])
+    @pytest.mark.parametrize("function", ["min", "max"])
+    def test_min_max_with_nan(self, values, categories, function, skipna):
+        # GH 25303
+        cat = Categorical(values, categories=categories, ordered=True)
+        result = getattr(cat, function)(skipna=skipna)
+
+        if skipna is False:
+            assert result is np.nan
+        else:
+            expected = categories[0] if function == "min" else categories[2]
+            assert result == expected
+
+    @pytest.mark.parametrize("function", ["min", "max"])
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_min_max_only_nan(self, function, skipna):
+        # https://github.com/pandas-dev/pandas/issues/33450
+        cat = Categorical([np.nan], categories=[1, 2], ordered=True)
+        result = getattr(cat, function)(skipna=skipna)
+        assert result is np.nan
+
+    @pytest.mark.parametrize("method", ["min", "max"])
+    def test_numeric_only_min_max_raises(self, method):
+        # GH 25303
+        cat = Categorical(
+            [np.nan, 1, 2, np.nan], categories=[5, 4, 3, 2, 1], ordered=True
+        )
+        with pytest.raises(TypeError, match=".* got an unexpected keyword"):
+            getattr(cat, method)(numeric_only=True)
+
+    @pytest.mark.parametrize("method", ["min", "max"])
+    def test_numpy_min_max_raises(self, method):
+        cat = Categorical(["a", "b", "c", "b"], ordered=False)
+        msg = (
+            f"Categorical is not ordered for operation {method}\n"
+            "you can use .as_ordered() to change the Categorical to an ordered one"
+        )
+        method = getattr(np, method)
+        with pytest.raises(TypeError, match=re.escape(msg)):
+            method(cat)
+
+    @pytest.mark.parametrize("kwarg", ["axis", "out", "keepdims"])
+    @pytest.mark.parametrize("method", ["min", "max"])
+    def test_numpy_min_max_unsupported_kwargs_raises(self, method, kwarg):
+        cat = Categorical(["a", "b", "c", "b"], ordered=True)
+        msg = (
+            f"the '{kwarg}' parameter is not supported in the pandas implementation "
+            f"of {method}"
+        )
+        if kwarg == "axis":
+            msg = r"`axis` must be fewer than the number of dimensions \(1\)"
+        kwargs = {kwarg: 42}
+        method = getattr(np, method)
+        with pytest.raises(ValueError, match=msg):
+            method(cat, **kwargs)
+
+    @pytest.mark.parametrize("method, expected", [("min", "a"), ("max", "c")])
+    def test_numpy_min_max_axis_equals_none(self, method, expected):
+        cat = Categorical(["a", "b", "c", "b"], ordered=True)
+        method = getattr(np, method)
+        result = method(cat, axis=None)
+        assert result == expected
+
+    @pytest.mark.parametrize(
+        "values,categories,exp_mode",
+        [
+            ([1, 1, 2, 4, 5, 5, 5], [5, 4, 3, 2, 1], [5]),
+            ([1, 1, 1, 4, 5, 5, 5], [5, 4, 3, 2, 1], [5, 1]),
+            ([1, 2, 3, 4, 5], [5, 4, 3, 2, 1], [5, 4, 3, 2, 1]),
+            ([np.nan, np.nan, np.nan, 4, 5], [5, 4, 3, 2, 1], [5, 4]),
+            ([np.nan, np.nan, np.nan, 4, 5, 4], [5, 4, 3, 2, 1], [4]),
+            ([np.nan, np.nan, 4, 5, 4], [5, 4, 3, 2, 1], [4]),
+        ],
+    )
+    def test_mode(self, values, categories, exp_mode):
+        cat = Categorical(values, categories=categories, ordered=True)
+        res = Series(cat).mode()._values
+        exp = Categorical(exp_mode, categories=categories, ordered=True)
+        tm.assert_categorical_equal(res, exp)
+
+    def test_searchsorted(self, ordered):
+        # https://github.com/pandas-dev/pandas/issues/8420
+        # https://github.com/pandas-dev/pandas/issues/14522
+
+        cat = Categorical(
+            ["cheese", "milk", "apple", "bread", "bread"],
+            categories=["cheese", "milk", "apple", "bread"],
+            ordered=ordered,
+        )
+        ser = Series(cat)
+
+        # Searching for single item argument, side='left' (default)
+        res_cat = cat.searchsorted("apple")
+        assert res_cat == 2
+        assert is_scalar(res_cat)
+
+        res_ser = ser.searchsorted("apple")
+        assert res_ser == 2
+        assert is_scalar(res_ser)
+
+        # Searching for single item array, side='left' (default)
+        res_cat = cat.searchsorted(["bread"])
+        res_ser = ser.searchsorted(["bread"])
+        exp = np.array([3], dtype=np.intp)
+        tm.assert_numpy_array_equal(res_cat, exp)
+        tm.assert_numpy_array_equal(res_ser, exp)
+
+        # Searching for several items array, side='right'
+        res_cat = cat.searchsorted(["apple", "bread"], side="right")
+        res_ser = ser.searchsorted(["apple", "bread"], side="right")
+        exp = np.array([3, 5], dtype=np.intp)
+        tm.assert_numpy_array_equal(res_cat, exp)
+        tm.assert_numpy_array_equal(res_ser, exp)
+
+        # Searching for a single value that is not from the Categorical
+        with pytest.raises(TypeError, match="cucumber"):
+            cat.searchsorted("cucumber")
+        with pytest.raises(TypeError, match="cucumber"):
+            ser.searchsorted("cucumber")
+
+        # Searching for multiple values one of each is not from the Categorical
+        msg = (
+            "Cannot setitem on a Categorical with a new category, "
+            "set the categories first"
+        )
+        with pytest.raises(TypeError, match=msg):
+            cat.searchsorted(["bread", "cucumber"])
+        with pytest.raises(TypeError, match=msg):
+            ser.searchsorted(["bread", "cucumber"])
+
+    def test_unique(self, ordered):
+        # GH38140
+        dtype = CategoricalDtype(["a", "b", "c"], ordered=ordered)
+
+        # categories are reordered based on value when ordered=False
+        cat = Categorical(["a", "b", "c"], dtype=dtype)
+        res = cat.unique()
+        tm.assert_categorical_equal(res, cat)
+
+        cat = Categorical(["a", "b", "a", "a"], dtype=dtype)
+        res = cat.unique()
+        tm.assert_categorical_equal(res, Categorical(["a", "b"], dtype=dtype))
+
+        cat = Categorical(["c", "a", "b", "a", "a"], dtype=dtype)
+        res = cat.unique()
+        exp_cat = Categorical(["c", "a", "b"], dtype=dtype)
+        tm.assert_categorical_equal(res, exp_cat)
+
+        # nan must be removed
+        cat = Categorical(["b", np.nan, "b", np.nan, "a"], dtype=dtype)
+        res = cat.unique()
+        exp_cat = Categorical(["b", np.nan, "a"], dtype=dtype)
+        tm.assert_categorical_equal(res, exp_cat)
+
+    def test_unique_index_series(self, ordered):
+        # GH38140
+        dtype = CategoricalDtype([3, 2, 1], ordered=ordered)
+
+        c = Categorical([3, 1, 2, 2, 1], dtype=dtype)
+        # Categorical.unique sorts categories by appearance order
+        # if ordered=False
+        exp = Categorical([3, 1, 2], dtype=dtype)
+        tm.assert_categorical_equal(c.unique(), exp)
+
+        tm.assert_index_equal(Index(c).unique(), Index(exp))
+        tm.assert_categorical_equal(Series(c).unique(), exp)
+
+        c = Categorical([1, 1, 2, 2], dtype=dtype)
+        exp = Categorical([1, 2], dtype=dtype)
+        tm.assert_categorical_equal(c.unique(), exp)
+        tm.assert_index_equal(Index(c).unique(), Index(exp))
+        tm.assert_categorical_equal(Series(c).unique(), exp)
+
+    def test_shift(self):
+        # GH 9416
+        cat = Categorical(["a", "b", "c", "d", "a"])
+
+        # shift forward
+        sp1 = cat.shift(1)
+        xp1 = Categorical([np.nan, "a", "b", "c", "d"])
+        tm.assert_categorical_equal(sp1, xp1)
+        tm.assert_categorical_equal(cat[:-1], sp1[1:])
+
+        # shift back
+        sn2 = cat.shift(-2)
+        xp2 = Categorical(
+            ["c", "d", "a", np.nan, np.nan], categories=["a", "b", "c", "d"]
+        )
+        tm.assert_categorical_equal(sn2, xp2)
+        tm.assert_categorical_equal(cat[2:], sn2[:-2])
+
+        # shift by zero
+        tm.assert_categorical_equal(cat, cat.shift(0))
+
+    def test_nbytes(self):
+        cat = Categorical([1, 2, 3])
+        exp = 3 + 3 * 8  # 3 int8s for values + 3 int64s for categories
+        assert cat.nbytes == exp
+
+    def test_memory_usage(self):
+        cat = Categorical([1, 2, 3])
+
+        # .categories is an index, so we include the hashtable
+        assert 0 < cat.nbytes <= cat.memory_usage()
+        assert 0 < cat.nbytes <= cat.memory_usage(deep=True)
+
+        cat = Categorical(["foo", "foo", "bar"])
+        assert cat.memory_usage(deep=True) > cat.nbytes
+
+        if not PYPY:
+            # sys.getsizeof will call the .memory_usage with
+            # deep=True, and add on some GC overhead
+            diff = cat.memory_usage(deep=True) - sys.getsizeof(cat)
+            assert abs(diff) < 100
+
+    def test_map(self):
+        c = Categorical(list("ABABC"), categories=list("CBA"), ordered=True)
+        result = c.map(lambda x: x.lower(), na_action=None)
+        exp = Categorical(list("ababc"), categories=list("cba"), ordered=True)
+        tm.assert_categorical_equal(result, exp)
+
+        c = Categorical(list("ABABC"), categories=list("ABC"), ordered=False)
+        result = c.map(lambda x: x.lower(), na_action=None)
+        exp = Categorical(list("ababc"), categories=list("abc"), ordered=False)
+        tm.assert_categorical_equal(result, exp)
+
+        result = c.map(lambda x: 1, na_action=None)
+        # GH 12766: Return an index not an array
+        tm.assert_index_equal(result, Index(np.array([1] * 5, dtype=np.int64)))
+
+    @pytest.mark.parametrize("value", [1, "True", [1, 2, 3], 5.0])
+    def test_validate_inplace_raises(self, value):
+        cat = Categorical(["A", "B", "B", "C", "A"])
+        msg = (
+            'For argument "inplace" expected type bool, '
+            f"received type {type(value).__name__}"
+        )
+
+        with pytest.raises(ValueError, match=msg):
+            cat.sort_values(inplace=value)
+
+    def test_quantile_empty(self):
+        # make sure we have correct itemsize on resulting codes
+        cat = Categorical(["A", "B"])
+        idx = Index([0.0, 0.5])
+        result = cat[:0]._quantile(idx, interpolation="linear")
+        assert result._codes.dtype == np.int8
+
+        expected = cat.take([-1, -1], allow_fill=True)
+        tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_api.py

@@ -0,0 +1,501 @@
+import re
+
+import numpy as np
+import pytest
+
+from pandas.compat import PY311
+
+from pandas import (
+    Categorical,
+    CategoricalIndex,
+    DataFrame,
+    Index,
+    Series,
+    StringDtype,
+)
+import pandas._testing as tm
+from pandas.core.arrays.categorical import recode_for_categories
+
+
+class TestCategoricalAPI:
+    def test_to_list_deprecated(self):
+        # GH#51254
+        cat1 = Categorical(list("acb"), ordered=False)
+        msg = "Categorical.to_list is deprecated and will be removed"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            cat1.to_list()
+
+    def test_ordered_api(self):
+        # GH 9347
+        cat1 = Categorical(list("acb"), ordered=False)
+        tm.assert_index_equal(cat1.categories, Index(["a", "b", "c"]))
+        assert not cat1.ordered
+
+        cat2 = Categorical(list("acb"), categories=list("bca"), ordered=False)
+        tm.assert_index_equal(cat2.categories, Index(["b", "c", "a"]))
+        assert not cat2.ordered
+
+        cat3 = Categorical(list("acb"), ordered=True)
+        tm.assert_index_equal(cat3.categories, Index(["a", "b", "c"]))
+        assert cat3.ordered
+
+        cat4 = Categorical(list("acb"), categories=list("bca"), ordered=True)
+        tm.assert_index_equal(cat4.categories, Index(["b", "c", "a"]))
+        assert cat4.ordered
+
+    def test_set_ordered(self):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        cat2 = cat.as_unordered()
+        assert not cat2.ordered
+        cat2 = cat.as_ordered()
+        assert cat2.ordered
+
+        assert cat2.set_ordered(True).ordered
+        assert not cat2.set_ordered(False).ordered
+
+        # removed in 0.19.0
+        msg = (
+            "property 'ordered' of 'Categorical' object has no setter"
+            if PY311
+            else "can't set attribute"
+        )
+        with pytest.raises(AttributeError, match=msg):
+            cat.ordered = True
+        with pytest.raises(AttributeError, match=msg):
+            cat.ordered = False
+
+    def test_rename_categories(self):
+        cat = Categorical(["a", "b", "c", "a"])
+
+        # inplace=False: the old one must not be changed
+        res = cat.rename_categories([1, 2, 3])
+        tm.assert_numpy_array_equal(
+            res.__array__(), np.array([1, 2, 3, 1], dtype=np.int64)
+        )
+        tm.assert_index_equal(res.categories, Index([1, 2, 3]))
+
+        exp_cat = np.array(["a", "b", "c", "a"], dtype=np.object_)
+        tm.assert_numpy_array_equal(cat.__array__(), exp_cat)
+
+        exp_cat = Index(["a", "b", "c"])
+        tm.assert_index_equal(cat.categories, exp_cat)
+
+        # GH18862 (let rename_categories take callables)
+        result = cat.rename_categories(lambda x: x.upper())
+        expected = Categorical(["A", "B", "C", "A"])
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("new_categories", [[1, 2, 3, 4], [1, 2]])
+    def test_rename_categories_wrong_length_raises(self, new_categories):
+        cat = Categorical(["a", "b", "c", "a"])
+        msg = (
+            "new categories need to have the same number of items as the "
+            "old categories!"
+        )
+        with pytest.raises(ValueError, match=msg):
+            cat.rename_categories(new_categories)
+
+    def test_rename_categories_series(self):
+        # https://github.com/pandas-dev/pandas/issues/17981
+        c = Categorical(["a", "b"])
+        result = c.rename_categories(Series([0, 1], index=["a", "b"]))
+        expected = Categorical([0, 1])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_rename_categories_dict(self):
+        # GH 17336
+        cat = Categorical(["a", "b", "c", "d"])
+        res = cat.rename_categories({"a": 4, "b": 3, "c": 2, "d": 1})
+        expected = Index([4, 3, 2, 1])
+        tm.assert_index_equal(res.categories, expected)
+
+        # Test for dicts of smaller length
+        cat = Categorical(["a", "b", "c", "d"])
+        res = cat.rename_categories({"a": 1, "c": 3})
+
+        expected = Index([1, "b", 3, "d"])
+        tm.assert_index_equal(res.categories, expected)
+
+        # Test for dicts with bigger length
+        cat = Categorical(["a", "b", "c", "d"])
+        res = cat.rename_categories({"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6})
+        expected = Index([1, 2, 3, 4])
+        tm.assert_index_equal(res.categories, expected)
+
+        # Test for dicts with no items from old categories
+        cat = Categorical(["a", "b", "c", "d"])
+        res = cat.rename_categories({"f": 1, "g": 3})
+
+        expected = Index(["a", "b", "c", "d"])
+        tm.assert_index_equal(res.categories, expected)
+
+    def test_reorder_categories(self):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        old = cat.copy()
+        new = Categorical(
+            ["a", "b", "c", "a"], categories=["c", "b", "a"], ordered=True
+        )
+
+        res = cat.reorder_categories(["c", "b", "a"])
+        # cat must be the same as before
+        tm.assert_categorical_equal(cat, old)
+        # only res is changed
+        tm.assert_categorical_equal(res, new)
+
+    @pytest.mark.parametrize(
+        "new_categories",
+        [
+            ["a"],  # not all "old" included in "new"
+            ["a", "b", "d"],  # still not all "old" in "new"
+            ["a", "b", "c", "d"],  # all "old" included in "new", but too long
+        ],
+    )
+    def test_reorder_categories_raises(self, new_categories):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        msg = "items in new_categories are not the same as in old categories"
+        with pytest.raises(ValueError, match=msg):
+            cat.reorder_categories(new_categories)
+
+    def test_add_categories(self):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        old = cat.copy()
+        new = Categorical(
+            ["a", "b", "c", "a"], categories=["a", "b", "c", "d"], ordered=True
+        )
+
+        res = cat.add_categories("d")
+        tm.assert_categorical_equal(cat, old)
+        tm.assert_categorical_equal(res, new)
+
+        res = cat.add_categories(["d"])
+        tm.assert_categorical_equal(cat, old)
+        tm.assert_categorical_equal(res, new)
+
+        # GH 9927
+        cat = Categorical(list("abc"), ordered=True)
+        expected = Categorical(list("abc"), categories=list("abcde"), ordered=True)
+        # test with Series, np.array, index, list
+        res = cat.add_categories(Series(["d", "e"]))
+        tm.assert_categorical_equal(res, expected)
+        res = cat.add_categories(np.array(["d", "e"]))
+        tm.assert_categorical_equal(res, expected)
+        res = cat.add_categories(Index(["d", "e"]))
+        tm.assert_categorical_equal(res, expected)
+        res = cat.add_categories(["d", "e"])
+        tm.assert_categorical_equal(res, expected)
+
+    def test_add_categories_existing_raises(self):
+        # new is in old categories
+        cat = Categorical(["a", "b", "c", "d"], ordered=True)
+        msg = re.escape("new categories must not include old categories: {'d'}")
+        with pytest.raises(ValueError, match=msg):
+            cat.add_categories(["d"])
+
+    def test_add_categories_losing_dtype_information(self):
+        # GH#48812
+        cat = Categorical(Series([1, 2], dtype="Int64"))
+        ser = Series([4], dtype="Int64")
+        result = cat.add_categories(ser)
+        expected = Categorical(
+            Series([1, 2], dtype="Int64"), categories=Series([1, 2, 4], dtype="Int64")
+        )
+        tm.assert_categorical_equal(result, expected)
+
+        cat = Categorical(Series(["a", "b", "a"], dtype=StringDtype()))
+        ser = Series(["d"], dtype=StringDtype())
+        result = cat.add_categories(ser)
+        expected = Categorical(
+            Series(["a", "b", "a"], dtype=StringDtype()),
+            categories=Series(["a", "b", "d"], dtype=StringDtype()),
+        )
+        tm.assert_categorical_equal(result, expected)
+
+    def test_set_categories(self):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        exp_categories = Index(["c", "b", "a"])
+        exp_values = np.array(["a", "b", "c", "a"], dtype=np.object_)
+
+        cat = cat.set_categories(["c", "b", "a"])
+        res = cat.set_categories(["a", "b", "c"])
+        # cat must be the same as before
+        tm.assert_index_equal(cat.categories, exp_categories)
+        tm.assert_numpy_array_equal(cat.__array__(), exp_values)
+        # only res is changed
+        exp_categories_back = Index(["a", "b", "c"])
+        tm.assert_index_equal(res.categories, exp_categories_back)
+        tm.assert_numpy_array_equal(res.__array__(), exp_values)
+
+        # not all "old" included in "new" -> all not included ones are now
+        # np.nan
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        res = cat.set_categories(["a"])
+        tm.assert_numpy_array_equal(res.codes, np.array([0, -1, -1, 0], dtype=np.int8))
+
+        # still not all "old" in "new"
+        res = cat.set_categories(["a", "b", "d"])
+        tm.assert_numpy_array_equal(res.codes, np.array([0, 1, -1, 0], dtype=np.int8))
+        tm.assert_index_equal(res.categories, Index(["a", "b", "d"]))
+
+        # all "old" included in "new"
+        cat = cat.set_categories(["a", "b", "c", "d"])
+        exp_categories = Index(["a", "b", "c", "d"])
+        tm.assert_index_equal(cat.categories, exp_categories)
+
+        # internals...
+        c = Categorical([1, 2, 3, 4, 1], categories=[1, 2, 3, 4], ordered=True)
+        tm.assert_numpy_array_equal(c._codes, np.array([0, 1, 2, 3, 0], dtype=np.int8))
+        tm.assert_index_equal(c.categories, Index([1, 2, 3, 4]))
+
+        exp = np.array([1, 2, 3, 4, 1], dtype=np.int64)
+        tm.assert_numpy_array_equal(np.asarray(c), exp)
+
+        # all "pointers" to '4' must be changed from 3 to 0,...
+        c = c.set_categories([4, 3, 2, 1])
+
+        # positions are changed
+        tm.assert_numpy_array_equal(c._codes, np.array([3, 2, 1, 0, 3], dtype=np.int8))
+
+        # categories are now in new order
+        tm.assert_index_equal(c.categories, Index([4, 3, 2, 1]))
+
+        # output is the same
+        exp = np.array([1, 2, 3, 4, 1], dtype=np.int64)
+        tm.assert_numpy_array_equal(np.asarray(c), exp)
+        assert c.min() == 4
+        assert c.max() == 1
+
+        # set_categories should set the ordering if specified
+        c2 = c.set_categories([4, 3, 2, 1], ordered=False)
+        assert not c2.ordered
+
+        tm.assert_numpy_array_equal(np.asarray(c), np.asarray(c2))
+
+        # set_categories should pass thru the ordering
+        c2 = c.set_ordered(False).set_categories([4, 3, 2, 1])
+        assert not c2.ordered
+
+        tm.assert_numpy_array_equal(np.asarray(c), np.asarray(c2))
+
+    @pytest.mark.parametrize(
+        "values, categories, new_categories",
+        [
+            # No NaNs, same cats, same order
+            (["a", "b", "a"], ["a", "b"], ["a", "b"]),
+            # No NaNs, same cats, different order
+            (["a", "b", "a"], ["a", "b"], ["b", "a"]),
+            # Same, unsorted
+            (["b", "a", "a"], ["a", "b"], ["a", "b"]),
+            # No NaNs, same cats, different order
+            (["b", "a", "a"], ["a", "b"], ["b", "a"]),
+            # NaNs
+            (["a", "b", "c"], ["a", "b"], ["a", "b"]),
+            (["a", "b", "c"], ["a", "b"], ["b", "a"]),
+            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            # Introduce NaNs
+            (["a", "b", "c"], ["a", "b"], ["a"]),
+            (["a", "b", "c"], ["a", "b"], ["b"]),
+            (["b", "a", "c"], ["a", "b"], ["a"]),
+            (["b", "a", "c"], ["a", "b"], ["a"]),
+            # No overlap
+            (["a", "b", "c"], ["a", "b"], ["d", "e"]),
+        ],
+    )
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_set_categories_many(self, values, categories, new_categories, ordered):
+        c = Categorical(values, categories)
+        expected = Categorical(values, new_categories, ordered)
+        result = c.set_categories(new_categories, ordered=ordered)
+        tm.assert_categorical_equal(result, expected)
+
+    def test_set_categories_rename_less(self):
+        # GH 24675
+        cat = Categorical(["A", "B"])
+        result = cat.set_categories(["A"], rename=True)
+        expected = Categorical(["A", np.nan])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_set_categories_private(self):
+        cat = Categorical(["a", "b", "c"], categories=["a", "b", "c", "d"])
+        cat._set_categories(["a", "c", "d", "e"])
+        expected = Categorical(["a", "c", "d"], categories=list("acde"))
+        tm.assert_categorical_equal(cat, expected)
+
+        # fastpath
+        cat = Categorical(["a", "b", "c"], categories=["a", "b", "c", "d"])
+        cat._set_categories(["a", "c", "d", "e"], fastpath=True)
+        expected = Categorical(["a", "c", "d"], categories=list("acde"))
+        tm.assert_categorical_equal(cat, expected)
+
+    def test_remove_categories(self):
+        cat = Categorical(["a", "b", "c", "a"], ordered=True)
+        old = cat.copy()
+        new = Categorical(["a", "b", np.nan, "a"], categories=["a", "b"], ordered=True)
+
+        res = cat.remove_categories("c")
+        tm.assert_categorical_equal(cat, old)
+        tm.assert_categorical_equal(res, new)
+
+        res = cat.remove_categories(["c"])
+        tm.assert_categorical_equal(cat, old)
+        tm.assert_categorical_equal(res, new)
+
+    @pytest.mark.parametrize("removals", [["c"], ["c", np.nan], "c", ["c", "c"]])
+    def test_remove_categories_raises(self, removals):
+        cat = Categorical(["a", "b", "a"])
+        message = re.escape("removals must all be in old categories: {'c'}")
+
+        with pytest.raises(ValueError, match=message):
+            cat.remove_categories(removals)
+
+    def test_remove_unused_categories(self):
+        c = Categorical(["a", "b", "c", "d", "a"], categories=["a", "b", "c", "d", "e"])
+        exp_categories_all = Index(["a", "b", "c", "d", "e"])
+        exp_categories_dropped = Index(["a", "b", "c", "d"])
+
+        tm.assert_index_equal(c.categories, exp_categories_all)
+
+        res = c.remove_unused_categories()
+        tm.assert_index_equal(res.categories, exp_categories_dropped)
+        tm.assert_index_equal(c.categories, exp_categories_all)
+
+        # with NaN values (GH11599)
+        c = Categorical(["a", "b", "c", np.nan], categories=["a", "b", "c", "d", "e"])
+        res = c.remove_unused_categories()
+        tm.assert_index_equal(res.categories, Index(np.array(["a", "b", "c"])))
+        exp_codes = np.array([0, 1, 2, -1], dtype=np.int8)
+        tm.assert_numpy_array_equal(res.codes, exp_codes)
+        tm.assert_index_equal(c.categories, exp_categories_all)
+
+        val = ["F", np.nan, "D", "B", "D", "F", np.nan]
+        cat = Categorical(values=val, categories=list("ABCDEFG"))
+        out = cat.remove_unused_categories()
+        tm.assert_index_equal(out.categories, Index(["B", "D", "F"]))
+        exp_codes = np.array([2, -1, 1, 0, 1, 2, -1], dtype=np.int8)
+        tm.assert_numpy_array_equal(out.codes, exp_codes)
+        assert out.tolist() == val
+
+        alpha = list("abcdefghijklmnopqrstuvwxyz")
+        val = np.random.default_rng(2).choice(alpha[::2], 10000).astype("object")
+        val[np.random.default_rng(2).choice(len(val), 100)] = np.nan
+
+        cat = Categorical(values=val, categories=alpha)
+        out = cat.remove_unused_categories()
+        assert out.tolist() == val.tolist()
+
+
+class TestCategoricalAPIWithFactor:
+    def test_describe(self):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        # string type
+        desc = factor.describe()
+        assert factor.ordered
+        exp_index = CategoricalIndex(
+            ["a", "b", "c"], name="categories", ordered=factor.ordered
+        )
+        expected = DataFrame(
+            {"counts": [3, 2, 3], "freqs": [3 / 8.0, 2 / 8.0, 3 / 8.0]}, index=exp_index
+        )
+        tm.assert_frame_equal(desc, expected)
+
+        # check unused categories
+        cat = factor.copy()
+        cat = cat.set_categories(["a", "b", "c", "d"])
+        desc = cat.describe()
+
+        exp_index = CategoricalIndex(
+            list("abcd"), ordered=factor.ordered, name="categories"
+        )
+        expected = DataFrame(
+            {"counts": [3, 2, 3, 0], "freqs": [3 / 8.0, 2 / 8.0, 3 / 8.0, 0]},
+            index=exp_index,
+        )
+        tm.assert_frame_equal(desc, expected)
+
+        # check an integer one
+        cat = Categorical([1, 2, 3, 1, 2, 3, 3, 2, 1, 1, 1])
+        desc = cat.describe()
+        exp_index = CategoricalIndex([1, 2, 3], ordered=cat.ordered, name="categories")
+        expected = DataFrame(
+            {"counts": [5, 3, 3], "freqs": [5 / 11.0, 3 / 11.0, 3 / 11.0]},
+            index=exp_index,
+        )
+        tm.assert_frame_equal(desc, expected)
+
+        # https://github.com/pandas-dev/pandas/issues/3678
+        # describe should work with NaN
+        cat = Categorical([np.nan, 1, 2, 2])
+        desc = cat.describe()
+        expected = DataFrame(
+            {"counts": [1, 2, 1], "freqs": [1 / 4.0, 2 / 4.0, 1 / 4.0]},
+            index=CategoricalIndex(
+                [1, 2, np.nan], categories=[1, 2], name="categories"
+            ),
+        )
+        tm.assert_frame_equal(desc, expected)
+
+
+class TestPrivateCategoricalAPI:
+    def test_codes_immutable(self):
+        # Codes should be read only
+        c = Categorical(["a", "b", "c", "a", np.nan])
+        exp = np.array([0, 1, 2, 0, -1], dtype="int8")
+        tm.assert_numpy_array_equal(c.codes, exp)
+
+        # Assignments to codes should raise
+        msg = (
+            "property 'codes' of 'Categorical' object has no setter"
+            if PY311
+            else "can't set attribute"
+        )
+        with pytest.raises(AttributeError, match=msg):
+            c.codes = np.array([0, 1, 2, 0, 1], dtype="int8")
+
+        # changes in the codes array should raise
+        codes = c.codes
+
+        with pytest.raises(ValueError, match="assignment destination is read-only"):
+            codes[4] = 1
+
+        # But even after getting the codes, the original array should still be
+        # writeable!
+        c[4] = "a"
+        exp = np.array([0, 1, 2, 0, 0], dtype="int8")
+        tm.assert_numpy_array_equal(c.codes, exp)
+        c._codes[4] = 2
+        exp = np.array([0, 1, 2, 0, 2], dtype="int8")
+        tm.assert_numpy_array_equal(c.codes, exp)
+
+    @pytest.mark.parametrize(
+        "codes, old, new, expected",
+        [
+            ([0, 1], ["a", "b"], ["a", "b"], [0, 1]),
+            ([0, 1], ["b", "a"], ["b", "a"], [0, 1]),
+            ([0, 1], ["a", "b"], ["b", "a"], [1, 0]),
+            ([0, 1], ["b", "a"], ["a", "b"], [1, 0]),
+            ([0, 1, 0, 1], ["a", "b"], ["a", "b", "c"], [0, 1, 0, 1]),
+            ([0, 1, 2, 2], ["a", "b", "c"], ["a", "b"], [0, 1, -1, -1]),
+            ([0, 1, -1], ["a", "b", "c"], ["a", "b", "c"], [0, 1, -1]),
+            ([0, 1, -1], ["a", "b", "c"], ["b"], [-1, 0, -1]),
+            ([0, 1, -1], ["a", "b", "c"], ["d"], [-1, -1, -1]),
+            ([0, 1, -1], ["a", "b", "c"], [], [-1, -1, -1]),
+            ([-1, -1], [], ["a", "b"], [-1, -1]),
+            ([1, 0], ["b", "a"], ["a", "b"], [0, 1]),
+        ],
+    )
+    def test_recode_to_categories(self, codes, old, new, expected):
+        codes = np.asanyarray(codes, dtype=np.int8)
+        expected = np.asanyarray(expected, dtype=np.int8)
+        old = Index(old)
+        new = Index(new)
+        result = recode_for_categories(codes, old, new)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_recode_to_categories_large(self):
+        N = 1000
+        codes = np.arange(N)
+        old = Index(codes)
+        expected = np.arange(N - 1, -1, -1, dtype=np.int16)
+        new = Index(expected)
+        result = recode_for_categories(codes, old, new)
+        tm.assert_numpy_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_astype.py

@@ -0,0 +1,155 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    Categorical,
+    CategoricalDtype,
+    CategoricalIndex,
+    DatetimeIndex,
+    Interval,
+    NaT,
+    Period,
+    Timestamp,
+    array,
+    to_datetime,
+)
+import pandas._testing as tm
+
+
+class TestAstype:
+    @pytest.mark.parametrize("cls", [Categorical, CategoricalIndex])
+    @pytest.mark.parametrize("values", [[1, np.nan], [Timestamp("2000"), NaT]])
+    def test_astype_nan_to_int(self, cls, values):
+        # GH#28406
+        obj = cls(values)
+
+        msg = "Cannot (cast|convert)"
+        with pytest.raises((ValueError, TypeError), match=msg):
+            obj.astype(int)
+
+    @pytest.mark.parametrize(
+        "expected",
+        [
+            array(["2019", "2020"], dtype="datetime64[ns, UTC]"),
+            array([0, 0], dtype="timedelta64[ns]"),
+            array([Period("2019"), Period("2020")], dtype="period[Y-DEC]"),
+            array([Interval(0, 1), Interval(1, 2)], dtype="interval"),
+            array([1, np.nan], dtype="Int64"),
+        ],
+    )
+    def test_astype_category_to_extension_dtype(self, expected):
+        # GH#28668
+        result = expected.astype("category").astype(expected.dtype)
+
+        tm.assert_extension_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "dtype, expected",
+        [
+            (
+                "datetime64[ns]",
+                np.array(["2015-01-01T00:00:00.000000000"], dtype="datetime64[ns]"),
+            ),
+            (
+                "datetime64[ns, MET]",
+                DatetimeIndex([Timestamp("2015-01-01 00:00:00+0100", tz="MET")]).array,
+            ),
+        ],
+    )
+    def test_astype_to_datetime64(self, dtype, expected):
+        # GH#28448
+        result = Categorical(["2015-01-01"]).astype(dtype)
+        assert result == expected
+
+    def test_astype_str_int_categories_to_nullable_int(self):
+        # GH#39616
+        dtype = CategoricalDtype([str(i) for i in range(5)])
+        codes = np.random.default_rng(2).integers(5, size=20)
+        arr = Categorical.from_codes(codes, dtype=dtype)
+
+        res = arr.astype("Int64")
+        expected = array(codes, dtype="Int64")
+        tm.assert_extension_array_equal(res, expected)
+
+    def test_astype_str_int_categories_to_nullable_float(self):
+        # GH#39616
+        dtype = CategoricalDtype([str(i / 2) for i in range(5)])
+        codes = np.random.default_rng(2).integers(5, size=20)
+        arr = Categorical.from_codes(codes, dtype=dtype)
+
+        res = arr.astype("Float64")
+        expected = array(codes, dtype="Float64") / 2
+        tm.assert_extension_array_equal(res, expected)
+
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_astype(self, ordered):
+        # string
+        cat = Categorical(list("abbaaccc"), ordered=ordered)
+        result = cat.astype(object)
+        expected = np.array(cat)
+        tm.assert_numpy_array_equal(result, expected)
+
+        msg = r"Cannot cast object|string dtype to float64"
+        with pytest.raises(ValueError, match=msg):
+            cat.astype(float)
+
+        # numeric
+        cat = Categorical([0, 1, 2, 2, 1, 0, 1, 0, 2], ordered=ordered)
+        result = cat.astype(object)
+        expected = np.array(cat, dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = cat.astype(int)
+        expected = np.array(cat, dtype="int")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = cat.astype(float)
+        expected = np.array(cat, dtype=float)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype_ordered", [True, False])
+    @pytest.mark.parametrize("cat_ordered", [True, False])
+    def test_astype_category(self, dtype_ordered, cat_ordered):
+        # GH#10696/GH#18593
+        data = list("abcaacbab")
+        cat = Categorical(data, categories=list("bac"), ordered=cat_ordered)
+
+        # standard categories
+        dtype = CategoricalDtype(ordered=dtype_ordered)
+        result = cat.astype(dtype)
+        expected = Categorical(data, categories=cat.categories, ordered=dtype_ordered)
+        tm.assert_categorical_equal(result, expected)
+
+        # non-standard categories
+        dtype = CategoricalDtype(list("adc"), dtype_ordered)
+        result = cat.astype(dtype)
+        expected = Categorical(data, dtype=dtype)
+        tm.assert_categorical_equal(result, expected)
+
+        if dtype_ordered is False:
+            # dtype='category' can't specify ordered, so only test once
+            result = cat.astype("category")
+            expected = cat
+            tm.assert_categorical_equal(result, expected)
+
+    def test_astype_object_datetime_categories(self):
+        # GH#40754
+        cat = Categorical(to_datetime(["2021-03-27", NaT]))
+        result = cat.astype(object)
+        expected = np.array([Timestamp("2021-03-27 00:00:00"), NaT], dtype="object")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_astype_object_timestamp_categories(self):
+        # GH#18024
+        cat = Categorical([Timestamp("2014-01-01")])
+        result = cat.astype(object)
+        expected = np.array([Timestamp("2014-01-01 00:00:00")], dtype="object")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_astype_category_readonly_mask_values(self):
+        # GH#53658
+        arr = array([0, 1, 2], dtype="Int64")
+        arr._mask.flags["WRITEABLE"] = False
+        result = arr.astype("category")
+        expected = array([0, 1, 2], dtype="Int64").astype("category")
+        tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_constructors.py

@@ -0,0 +1,783 @@
+from datetime import (
+    date,
+    datetime,
+)
+
+import numpy as np
+import pytest
+
+from pandas._config import using_pyarrow_string_dtype
+
+from pandas.core.dtypes.common import (
+    is_float_dtype,
+    is_integer_dtype,
+)
+from pandas.core.dtypes.dtypes import CategoricalDtype
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    CategoricalIndex,
+    DatetimeIndex,
+    Index,
+    Interval,
+    IntervalIndex,
+    MultiIndex,
+    NaT,
+    Series,
+    Timestamp,
+    date_range,
+    period_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalConstructors:
+    def test_fastpath_deprecated(self):
+        codes = np.array([1, 2, 3])
+        dtype = CategoricalDtype(categories=["a", "b", "c", "d"], ordered=False)
+        msg = "The 'fastpath' keyword in Categorical is deprecated"
+        with tm.assert_produces_warning(DeprecationWarning, match=msg):
+            Categorical(codes, dtype=dtype, fastpath=True)
+
+    def test_categorical_from_cat_and_dtype_str_preserve_ordered(self):
+        # GH#49309 we should preserve orderedness in `res`
+        cat = Categorical([3, 1], categories=[3, 2, 1], ordered=True)
+
+        res = Categorical(cat, dtype="category")
+        assert res.dtype.ordered
+
+    def test_categorical_disallows_scalar(self):
+        # GH#38433
+        with pytest.raises(TypeError, match="Categorical input must be list-like"):
+            Categorical("A", categories=["A", "B"])
+
+    def test_categorical_1d_only(self):
+        # ndim > 1
+        msg = "> 1 ndim Categorical are not supported at this time"
+        with pytest.raises(NotImplementedError, match=msg):
+            Categorical(np.array([list("abcd")]))
+
+    def test_validate_ordered(self):
+        # see gh-14058
+        exp_msg = "'ordered' must either be 'True' or 'False'"
+        exp_err = TypeError
+
+        # This should be a boolean.
+        ordered = np.array([0, 1, 2])
+
+        with pytest.raises(exp_err, match=exp_msg):
+            Categorical([1, 2, 3], ordered=ordered)
+
+        with pytest.raises(exp_err, match=exp_msg):
+            Categorical.from_codes(
+                [0, 0, 1], categories=["a", "b", "c"], ordered=ordered
+            )
+
+    def test_constructor_empty(self):
+        # GH 17248
+        c = Categorical([])
+        expected = Index([])
+        tm.assert_index_equal(c.categories, expected)
+
+        c = Categorical([], categories=[1, 2, 3])
+        expected = Index([1, 2, 3], dtype=np.int64)
+        tm.assert_index_equal(c.categories, expected)
+
+    def test_constructor_empty_boolean(self):
+        # see gh-22702
+        cat = Categorical([], categories=[True, False])
+        categories = sorted(cat.categories.tolist())
+        assert categories == [False, True]
+
+    def test_constructor_tuples(self):
+        values = np.array([(1,), (1, 2), (1,), (1, 2)], dtype=object)
+        result = Categorical(values)
+        expected = Index([(1,), (1, 2)], tupleize_cols=False)
+        tm.assert_index_equal(result.categories, expected)
+        assert result.ordered is False
+
+    def test_constructor_tuples_datetimes(self):
+        # numpy will auto reshape when all of the tuples are the
+        # same len, so add an extra one with 2 items and slice it off
+        values = np.array(
+            [
+                (Timestamp("2010-01-01"),),
+                (Timestamp("2010-01-02"),),
+                (Timestamp("2010-01-01"),),
+                (Timestamp("2010-01-02"),),
+                ("a", "b"),
+            ],
+            dtype=object,
+        )[:-1]
+        result = Categorical(values)
+        expected = Index(
+            [(Timestamp("2010-01-01"),), (Timestamp("2010-01-02"),)],
+            tupleize_cols=False,
+        )
+        tm.assert_index_equal(result.categories, expected)
+
+    def test_constructor_unsortable(self):
+        # it works!
+        arr = np.array([1, 2, 3, datetime.now()], dtype="O")
+        factor = Categorical(arr, ordered=False)
+        assert not factor.ordered
+
+        # this however will raise as cannot be sorted
+        msg = (
+            "'values' is not ordered, please explicitly specify the "
+            "categories order by passing in a categories argument."
+        )
+        with pytest.raises(TypeError, match=msg):
+            Categorical(arr, ordered=True)
+
+    def test_constructor_interval(self):
+        result = Categorical(
+            [Interval(1, 2), Interval(2, 3), Interval(3, 6)], ordered=True
+        )
+        ii = IntervalIndex([Interval(1, 2), Interval(2, 3), Interval(3, 6)])
+        exp = Categorical(ii, ordered=True)
+        tm.assert_categorical_equal(result, exp)
+        tm.assert_index_equal(result.categories, ii)
+
+    def test_constructor(self):
+        exp_arr = np.array(["a", "b", "c", "a", "b", "c"], dtype=np.object_)
+        c1 = Categorical(exp_arr)
+        tm.assert_numpy_array_equal(c1.__array__(), exp_arr)
+        c2 = Categorical(exp_arr, categories=["a", "b", "c"])
+        tm.assert_numpy_array_equal(c2.__array__(), exp_arr)
+        c2 = Categorical(exp_arr, categories=["c", "b", "a"])
+        tm.assert_numpy_array_equal(c2.__array__(), exp_arr)
+
+        # categories must be unique
+        msg = "Categorical categories must be unique"
+        with pytest.raises(ValueError, match=msg):
+            Categorical([1, 2], [1, 2, 2])
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical(["a", "b"], ["a", "b", "b"])
+
+        # The default should be unordered
+        c1 = Categorical(["a", "b", "c", "a"])
+        assert not c1.ordered
+
+        # Categorical as input
+        c1 = Categorical(["a", "b", "c", "a"])
+        c2 = Categorical(c1)
+        tm.assert_categorical_equal(c1, c2)
+
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
+        c2 = Categorical(c1)
+        tm.assert_categorical_equal(c1, c2)
+
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
+        c2 = Categorical(c1)
+        tm.assert_categorical_equal(c1, c2)
+
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
+        c2 = Categorical(c1, categories=["a", "b", "c"])
+        tm.assert_numpy_array_equal(c1.__array__(), c2.__array__())
+        tm.assert_index_equal(c2.categories, Index(["a", "b", "c"]))
+
+        # Series of dtype category
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
+        c2 = Categorical(Series(c1))
+        tm.assert_categorical_equal(c1, c2)
+
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "c", "b"])
+        c2 = Categorical(Series(c1))
+        tm.assert_categorical_equal(c1, c2)
+
+        # Series
+        c1 = Categorical(["a", "b", "c", "a"])
+        c2 = Categorical(Series(["a", "b", "c", "a"]))
+        tm.assert_categorical_equal(c1, c2)
+
+        c1 = Categorical(["a", "b", "c", "a"], categories=["a", "b", "c", "d"])
+        c2 = Categorical(Series(["a", "b", "c", "a"]), categories=["a", "b", "c", "d"])
+        tm.assert_categorical_equal(c1, c2)
+
+        # This should result in integer categories, not float!
+        cat = Categorical([1, 2, 3, np.nan], categories=[1, 2, 3])
+        assert is_integer_dtype(cat.categories)
+
+        # https://github.com/pandas-dev/pandas/issues/3678
+        cat = Categorical([np.nan, 1, 2, 3])
+        assert is_integer_dtype(cat.categories)
+
+        # this should result in floats
+        cat = Categorical([np.nan, 1, 2.0, 3])
+        assert is_float_dtype(cat.categories)
+
+        cat = Categorical([np.nan, 1.0, 2.0, 3.0])
+        assert is_float_dtype(cat.categories)
+
+        # This doesn't work -> this would probably need some kind of "remember
+        # the original type" feature to try to cast the array interface result
+        # to...
+
+        # vals = np.asarray(cat[cat.notna()])
+        # assert is_integer_dtype(vals)
+
+        # corner cases
+        cat = Categorical([1])
+        assert len(cat.categories) == 1
+        assert cat.categories[0] == 1
+        assert len(cat.codes) == 1
+        assert cat.codes[0] == 0
+
+        cat = Categorical(["a"])
+        assert len(cat.categories) == 1
+        assert cat.categories[0] == "a"
+        assert len(cat.codes) == 1
+        assert cat.codes[0] == 0
+
+        # two arrays
+        #  - when the first is an integer dtype and the second is not
+        #  - when the resulting codes are all -1/NaN
+        with tm.assert_produces_warning(None):
+            Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])
+
+        with tm.assert_produces_warning(None):
+            Categorical([0, 1, 2, 0, 1, 2], categories=[3, 4, 5])
+
+        # the next one are from the old docs
+        with tm.assert_produces_warning(None):
+            Categorical([0, 1, 2, 0, 1, 2], [1, 2, 3])
+            cat = Categorical([1, 2], categories=[1, 2, 3])
+
+        # this is a legitimate constructor
+        with tm.assert_produces_warning(None):
+            Categorical(np.array([], dtype="int64"), categories=[3, 2, 1], ordered=True)
+
+    def test_constructor_with_existing_categories(self):
+        # GH25318: constructing with pd.Series used to bogusly skip recoding
+        # categories
+        c0 = Categorical(["a", "b", "c", "a"])
+        c1 = Categorical(["a", "b", "c", "a"], categories=["b", "c"])
+
+        c2 = Categorical(c0, categories=c1.categories)
+        tm.assert_categorical_equal(c1, c2)
+
+        c3 = Categorical(Series(c0), categories=c1.categories)
+        tm.assert_categorical_equal(c1, c3)
+
+    def test_constructor_not_sequence(self):
+        # https://github.com/pandas-dev/pandas/issues/16022
+        msg = r"^Parameter 'categories' must be list-like, was"
+        with pytest.raises(TypeError, match=msg):
+            Categorical(["a", "b"], categories="a")
+
+    def test_constructor_with_null(self):
+        # Cannot have NaN in categories
+        msg = "Categorical categories cannot be null"
+        with pytest.raises(ValueError, match=msg):
+            Categorical([np.nan, "a", "b", "c"], categories=[np.nan, "a", "b", "c"])
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical([None, "a", "b", "c"], categories=[None, "a", "b", "c"])
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical(
+                DatetimeIndex(["nat", "20160101"]),
+                categories=[NaT, Timestamp("20160101")],
+            )
+
+    def test_constructor_with_index(self):
+        ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
+        tm.assert_categorical_equal(ci.values, Categorical(ci))
+
+        ci = CategoricalIndex(list("aabbca"), categories=list("cab"))
+        tm.assert_categorical_equal(
+            ci.values, Categorical(ci.astype(object), categories=ci.categories)
+        )
+
+    def test_constructor_with_generator(self):
+        # This was raising an Error in isna(single_val).any() because isna
+        # returned a scalar for a generator
+
+        exp = Categorical([0, 1, 2])
+        cat = Categorical(x for x in [0, 1, 2])
+        tm.assert_categorical_equal(cat, exp)
+        cat = Categorical(range(3))
+        tm.assert_categorical_equal(cat, exp)
+
+        MultiIndex.from_product([range(5), ["a", "b", "c"]])
+
+        # check that categories accept generators and sequences
+        cat = Categorical([0, 1, 2], categories=(x for x in [0, 1, 2]))
+        tm.assert_categorical_equal(cat, exp)
+        cat = Categorical([0, 1, 2], categories=range(3))
+        tm.assert_categorical_equal(cat, exp)
+
+    def test_constructor_with_rangeindex(self):
+        # RangeIndex is preserved in Categories
+        rng = Index(range(3))
+
+        cat = Categorical(rng)
+        tm.assert_index_equal(cat.categories, rng, exact=True)
+
+        cat = Categorical([1, 2, 0], categories=rng)
+        tm.assert_index_equal(cat.categories, rng, exact=True)
+
+    @pytest.mark.parametrize(
+        "dtl",
+        [
+            date_range("1995-01-01 00:00:00", periods=5, freq="s"),
+            date_range("1995-01-01 00:00:00", periods=5, freq="s", tz="US/Eastern"),
+            timedelta_range("1 day", periods=5, freq="s"),
+        ],
+    )
+    def test_constructor_with_datetimelike(self, dtl):
+        # see gh-12077
+        # constructor with a datetimelike and NaT
+
+        s = Series(dtl)
+        c = Categorical(s)
+
+        expected = type(dtl)(s)
+        expected._data.freq = None
+
+        tm.assert_index_equal(c.categories, expected)
+        tm.assert_numpy_array_equal(c.codes, np.arange(5, dtype="int8"))
+
+        # with NaT
+        s2 = s.copy()
+        s2.iloc[-1] = NaT
+        c = Categorical(s2)
+
+        expected = type(dtl)(s2.dropna())
+        expected._data.freq = None
+
+        tm.assert_index_equal(c.categories, expected)
+
+        exp = np.array([0, 1, 2, 3, -1], dtype=np.int8)
+        tm.assert_numpy_array_equal(c.codes, exp)
+
+        result = repr(c)
+        assert "NaT" in result
+
+    def test_constructor_from_index_series_datetimetz(self):
+        idx = date_range("2015-01-01 10:00", freq="D", periods=3, tz="US/Eastern")
+        idx = idx._with_freq(None)  # freq not preserved in result.categories
+        result = Categorical(idx)
+        tm.assert_index_equal(result.categories, idx)
+
+        result = Categorical(Series(idx))
+        tm.assert_index_equal(result.categories, idx)
+
+    def test_constructor_date_objects(self):
+        # we dont cast date objects to timestamps, matching Index constructor
+        v = date.today()
+
+        cat = Categorical([v, v])
+        assert cat.categories.dtype == object
+        assert type(cat.categories[0]) is date
+
+    def test_constructor_from_index_series_timedelta(self):
+        idx = timedelta_range("1 days", freq="D", periods=3)
+        idx = idx._with_freq(None)  # freq not preserved in result.categories
+        result = Categorical(idx)
+        tm.assert_index_equal(result.categories, idx)
+
+        result = Categorical(Series(idx))
+        tm.assert_index_equal(result.categories, idx)
+
+    def test_constructor_from_index_series_period(self):
+        idx = period_range("2015-01-01", freq="D", periods=3)
+        result = Categorical(idx)
+        tm.assert_index_equal(result.categories, idx)
+
+        result = Categorical(Series(idx))
+        tm.assert_index_equal(result.categories, idx)
+
+    @pytest.mark.parametrize(
+        "values",
+        [
+            np.array([1.0, 1.2, 1.8, np.nan]),
+            np.array([1, 2, 3], dtype="int64"),
+            ["a", "b", "c", np.nan],
+            [pd.Period("2014-01"), pd.Period("2014-02"), NaT],
+            [Timestamp("2014-01-01"), Timestamp("2014-01-02"), NaT],
+            [
+                Timestamp("2014-01-01", tz="US/Eastern"),
+                Timestamp("2014-01-02", tz="US/Eastern"),
+                NaT,
+            ],
+        ],
+    )
+    def test_constructor_invariant(self, values):
+        # GH 14190
+        c = Categorical(values)
+        c2 = Categorical(c)
+        tm.assert_categorical_equal(c, c2)
+
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_constructor_with_dtype(self, ordered):
+        categories = ["b", "a", "c"]
+        dtype = CategoricalDtype(categories, ordered=ordered)
+        result = Categorical(["a", "b", "a", "c"], dtype=dtype)
+        expected = Categorical(
+            ["a", "b", "a", "c"], categories=categories, ordered=ordered
+        )
+        tm.assert_categorical_equal(result, expected)
+        assert result.ordered is ordered
+
+    def test_constructor_dtype_and_others_raises(self):
+        dtype = CategoricalDtype(["a", "b"], ordered=True)
+        msg = "Cannot specify `categories` or `ordered` together with `dtype`."
+        with pytest.raises(ValueError, match=msg):
+            Categorical(["a", "b"], categories=["a", "b"], dtype=dtype)
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical(["a", "b"], ordered=True, dtype=dtype)
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical(["a", "b"], ordered=False, dtype=dtype)
+
+    @pytest.mark.parametrize("categories", [None, ["a", "b"], ["a", "c"]])
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_constructor_str_category(self, categories, ordered):
+        result = Categorical(
+            ["a", "b"], categories=categories, ordered=ordered, dtype="category"
+        )
+        expected = Categorical(["a", "b"], categories=categories, ordered=ordered)
+        tm.assert_categorical_equal(result, expected)
+
+    def test_constructor_str_unknown(self):
+        with pytest.raises(ValueError, match="Unknown dtype"):
+            Categorical([1, 2], dtype="foo")
+
+    @pytest.mark.xfail(using_pyarrow_string_dtype(), reason="Can't be NumPy strings")
+    def test_constructor_np_strs(self):
+        # GH#31499 Hashtable.map_locations needs to work on np.str_ objects
+        cat = Categorical(["1", "0", "1"], [np.str_("0"), np.str_("1")])
+        assert all(isinstance(x, np.str_) for x in cat.categories)
+
+    def test_constructor_from_categorical_with_dtype(self):
+        dtype = CategoricalDtype(["a", "b", "c"], ordered=True)
+        values = Categorical(["a", "b", "d"])
+        result = Categorical(values, dtype=dtype)
+        # We use dtype.categories, not values.categories
+        expected = Categorical(
+            ["a", "b", "d"], categories=["a", "b", "c"], ordered=True
+        )
+        tm.assert_categorical_equal(result, expected)
+
+    def test_constructor_from_categorical_with_unknown_dtype(self):
+        dtype = CategoricalDtype(None, ordered=True)
+        values = Categorical(["a", "b", "d"])
+        result = Categorical(values, dtype=dtype)
+        # We use values.categories, not dtype.categories
+        expected = Categorical(
+            ["a", "b", "d"], categories=["a", "b", "d"], ordered=True
+        )
+        tm.assert_categorical_equal(result, expected)
+
+    def test_constructor_from_categorical_string(self):
+        values = Categorical(["a", "b", "d"])
+        # use categories, ordered
+        result = Categorical(
+            values, categories=["a", "b", "c"], ordered=True, dtype="category"
+        )
+        expected = Categorical(
+            ["a", "b", "d"], categories=["a", "b", "c"], ordered=True
+        )
+        tm.assert_categorical_equal(result, expected)
+
+        # No string
+        result = Categorical(values, categories=["a", "b", "c"], ordered=True)
+        tm.assert_categorical_equal(result, expected)
+
+    def test_constructor_with_categorical_categories(self):
+        # GH17884
+        expected = Categorical(["a", "b"], categories=["a", "b", "c"])
+
+        result = Categorical(["a", "b"], categories=Categorical(["a", "b", "c"]))
+        tm.assert_categorical_equal(result, expected)
+
+        result = Categorical(["a", "b"], categories=CategoricalIndex(["a", "b", "c"]))
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("klass", [lambda x: np.array(x, dtype=object), list])
+    def test_construction_with_null(self, klass, nulls_fixture):
+        # https://github.com/pandas-dev/pandas/issues/31927
+        values = klass(["a", nulls_fixture, "b"])
+        result = Categorical(values)
+
+        dtype = CategoricalDtype(["a", "b"])
+        codes = [0, -1, 1]
+        expected = Categorical.from_codes(codes=codes, dtype=dtype)
+
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("validate", [True, False])
+    def test_from_codes_nullable_int_categories(self, any_numeric_ea_dtype, validate):
+        # GH#39649
+        cats = pd.array(range(5), dtype=any_numeric_ea_dtype)
+        codes = np.random.default_rng(2).integers(5, size=3)
+        dtype = CategoricalDtype(cats)
+        arr = Categorical.from_codes(codes, dtype=dtype, validate=validate)
+        assert arr.categories.dtype == cats.dtype
+        tm.assert_index_equal(arr.categories, Index(cats))
+
+    def test_from_codes_empty(self):
+        cat = ["a", "b", "c"]
+        result = Categorical.from_codes([], categories=cat)
+        expected = Categorical([], categories=cat)
+
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("validate", [True, False])
+    def test_from_codes_validate(self, validate):
+        # GH53122
+        dtype = CategoricalDtype(["a", "b"])
+        if validate:
+            with pytest.raises(ValueError, match="codes need to be between "):
+                Categorical.from_codes([4, 5], dtype=dtype, validate=validate)
+        else:
+            # passes, though has incorrect codes, but that's the user responsibility
+            Categorical.from_codes([4, 5], dtype=dtype, validate=validate)
+
+    def test_from_codes_too_few_categories(self):
+        dtype = CategoricalDtype(categories=[1, 2])
+        msg = "codes need to be between "
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes([1, 2], categories=dtype.categories)
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes([1, 2], dtype=dtype)
+
+    def test_from_codes_non_int_codes(self):
+        dtype = CategoricalDtype(categories=[1, 2])
+        msg = "codes need to be array-like integers"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(["a"], categories=dtype.categories)
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(["a"], dtype=dtype)
+
+    def test_from_codes_non_unique_categories(self):
+        with pytest.raises(ValueError, match="Categorical categories must be unique"):
+            Categorical.from_codes([0, 1, 2], categories=["a", "a", "b"])
+
+    def test_from_codes_nan_cat_included(self):
+        with pytest.raises(ValueError, match="Categorical categories cannot be null"):
+            Categorical.from_codes([0, 1, 2], categories=["a", "b", np.nan])
+
+    def test_from_codes_too_negative(self):
+        dtype = CategoricalDtype(categories=["a", "b", "c"])
+        msg = r"codes need to be between -1 and len\(categories\)-1"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes([-2, 1, 2], categories=dtype.categories)
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes([-2, 1, 2], dtype=dtype)
+
+    def test_from_codes(self):
+        dtype = CategoricalDtype(categories=["a", "b", "c"])
+        exp = Categorical(["a", "b", "c"], ordered=False)
+        res = Categorical.from_codes([0, 1, 2], categories=dtype.categories)
+        tm.assert_categorical_equal(exp, res)
+
+        res = Categorical.from_codes([0, 1, 2], dtype=dtype)
+        tm.assert_categorical_equal(exp, res)
+
+    @pytest.mark.parametrize("klass", [Categorical, CategoricalIndex])
+    def test_from_codes_with_categorical_categories(self, klass):
+        # GH17884
+        expected = Categorical(["a", "b"], categories=["a", "b", "c"])
+
+        result = Categorical.from_codes([0, 1], categories=klass(["a", "b", "c"]))
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("klass", [Categorical, CategoricalIndex])
+    def test_from_codes_with_non_unique_categorical_categories(self, klass):
+        with pytest.raises(ValueError, match="Categorical categories must be unique"):
+            Categorical.from_codes([0, 1], klass(["a", "b", "a"]))
+
+    def test_from_codes_with_nan_code(self):
+        # GH21767
+        codes = [1, 2, np.nan]
+        dtype = CategoricalDtype(categories=["a", "b", "c"])
+        with pytest.raises(ValueError, match="codes need to be array-like integers"):
+            Categorical.from_codes(codes, categories=dtype.categories)
+        with pytest.raises(ValueError, match="codes need to be array-like integers"):
+            Categorical.from_codes(codes, dtype=dtype)
+
+    @pytest.mark.parametrize("codes", [[1.0, 2.0, 0], [1.1, 2.0, 0]])
+    def test_from_codes_with_float(self, codes):
+        # GH21767
+        # float codes should raise even if values are equal to integers
+        dtype = CategoricalDtype(categories=["a", "b", "c"])
+
+        msg = "codes need to be array-like integers"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(codes, dtype.categories)
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(codes, dtype=dtype)
+
+    def test_from_codes_with_dtype_raises(self):
+        msg = "Cannot specify"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(
+                [0, 1], categories=["a", "b"], dtype=CategoricalDtype(["a", "b"])
+            )
+
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(
+                [0, 1], ordered=True, dtype=CategoricalDtype(["a", "b"])
+            )
+
+    def test_from_codes_neither(self):
+        msg = "Both were None"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes([0, 1])
+
+    def test_from_codes_with_nullable_int(self):
+        codes = pd.array([0, 1], dtype="Int64")
+        categories = ["a", "b"]
+
+        result = Categorical.from_codes(codes, categories=categories)
+        expected = Categorical.from_codes(codes.to_numpy(int), categories=categories)
+
+        tm.assert_categorical_equal(result, expected)
+
+    def test_from_codes_with_nullable_int_na_raises(self):
+        codes = pd.array([0, None], dtype="Int64")
+        categories = ["a", "b"]
+
+        msg = "codes cannot contain NA values"
+        with pytest.raises(ValueError, match=msg):
+            Categorical.from_codes(codes, categories=categories)
+
+    @pytest.mark.parametrize("dtype", [None, "category"])
+    def test_from_inferred_categories(self, dtype):
+        cats = ["a", "b"]
+        codes = np.array([0, 0, 1, 1], dtype="i8")
+        result = Categorical._from_inferred_categories(cats, codes, dtype)
+        expected = Categorical.from_codes(codes, cats)
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype", [None, "category"])
+    def test_from_inferred_categories_sorts(self, dtype):
+        cats = ["b", "a"]
+        codes = np.array([0, 1, 1, 1], dtype="i8")
+        result = Categorical._from_inferred_categories(cats, codes, dtype)
+        expected = Categorical.from_codes([1, 0, 0, 0], ["a", "b"])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_from_inferred_categories_dtype(self):
+        cats = ["a", "b", "d"]
+        codes = np.array([0, 1, 0, 2], dtype="i8")
+        dtype = CategoricalDtype(["c", "b", "a"], ordered=True)
+        result = Categorical._from_inferred_categories(cats, codes, dtype)
+        expected = Categorical(
+            ["a", "b", "a", "d"], categories=["c", "b", "a"], ordered=True
+        )
+        tm.assert_categorical_equal(result, expected)
+
+    def test_from_inferred_categories_coerces(self):
+        cats = ["1", "2", "bad"]
+        codes = np.array([0, 0, 1, 2], dtype="i8")
+        dtype = CategoricalDtype([1, 2])
+        result = Categorical._from_inferred_categories(cats, codes, dtype)
+        expected = Categorical([1, 1, 2, np.nan])
+        tm.assert_categorical_equal(result, expected)
+
+    @pytest.mark.parametrize("ordered", [None, True, False])
+    def test_construction_with_ordered(self, ordered):
+        # GH 9347, 9190
+        cat = Categorical([0, 1, 2], ordered=ordered)
+        assert cat.ordered == bool(ordered)
+
+    def test_constructor_imaginary(self):
+        values = [1, 2, 3 + 1j]
+        c1 = Categorical(values)
+        tm.assert_index_equal(c1.categories, Index(values))
+        tm.assert_numpy_array_equal(np.array(c1), np.array(values))
+
+    def test_constructor_string_and_tuples(self):
+        # GH 21416
+        c = Categorical(np.array(["c", ("a", "b"), ("b", "a"), "c"], dtype=object))
+        expected_index = Index([("a", "b"), ("b", "a"), "c"])
+        assert c.categories.equals(expected_index)
+
+    def test_interval(self):
+        idx = pd.interval_range(0, 10, periods=10)
+        cat = Categorical(idx, categories=idx)
+        expected_codes = np.arange(10, dtype="int8")
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+        # infer categories
+        cat = Categorical(idx)
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+        # list values
+        cat = Categorical(list(idx))
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+        # list values, categories
+        cat = Categorical(list(idx), categories=list(idx))
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+        # shuffled
+        values = idx.take([1, 2, 0])
+        cat = Categorical(values, categories=idx)
+        tm.assert_numpy_array_equal(cat.codes, np.array([1, 2, 0], dtype="int8"))
+        tm.assert_index_equal(cat.categories, idx)
+
+        # extra
+        values = pd.interval_range(8, 11, periods=3)
+        cat = Categorical(values, categories=idx)
+        expected_codes = np.array([8, 9, -1], dtype="int8")
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+        # overlapping
+        idx = IntervalIndex([Interval(0, 2), Interval(0, 1)])
+        cat = Categorical(idx, categories=idx)
+        expected_codes = np.array([0, 1], dtype="int8")
+        tm.assert_numpy_array_equal(cat.codes, expected_codes)
+        tm.assert_index_equal(cat.categories, idx)
+
+    def test_categorical_extension_array_nullable(self, nulls_fixture):
+        # GH:
+        arr = pd.arrays.StringArray._from_sequence(
+            [nulls_fixture] * 2, dtype=pd.StringDtype()
+        )
+        result = Categorical(arr)
+        assert arr.dtype == result.categories.dtype
+        expected = Categorical(Series([pd.NA, pd.NA], dtype=arr.dtype))
+        tm.assert_categorical_equal(result, expected)
+
+    def test_from_sequence_copy(self):
+        cat = Categorical(np.arange(5).repeat(2))
+        result = Categorical._from_sequence(cat, dtype=cat.dtype, copy=False)
+
+        # more generally, we'd be OK with a view
+        assert result._codes is cat._codes
+
+        result = Categorical._from_sequence(cat, dtype=cat.dtype, copy=True)
+
+        assert not tm.shares_memory(result, cat)
+
+    def test_constructor_datetime64_non_nano(self):
+        categories = np.arange(10).view("M8[D]")
+        values = categories[::2].copy()
+
+        cat = Categorical(values, categories=categories)
+        assert (cat == values).all()
+
+    def test_constructor_preserves_freq(self):
+        # GH33830 freq retention in categorical
+        dti = date_range("2016-01-01", periods=5)
+
+        expected = dti.freq
+
+        cat = Categorical(dti)
+        result = cat.categories.freq
+
+        assert expected == result

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_dtypes.py

@@ -0,0 +1,139 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import CategoricalDtype
+
+from pandas import (
+    Categorical,
+    CategoricalIndex,
+    Index,
+    IntervalIndex,
+    Series,
+    Timestamp,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalDtypes:
+    def test_categories_match_up_to_permutation(self):
+        # test dtype comparisons between cats
+
+        c1 = Categorical(list("aabca"), categories=list("abc"), ordered=False)
+        c2 = Categorical(list("aabca"), categories=list("cab"), ordered=False)
+        c3 = Categorical(list("aabca"), categories=list("cab"), ordered=True)
+        assert c1._categories_match_up_to_permutation(c1)
+        assert c2._categories_match_up_to_permutation(c2)
+        assert c3._categories_match_up_to_permutation(c3)
+        assert c1._categories_match_up_to_permutation(c2)
+        assert not c1._categories_match_up_to_permutation(c3)
+        assert not c1._categories_match_up_to_permutation(Index(list("aabca")))
+        assert not c1._categories_match_up_to_permutation(c1.astype(object))
+        assert c1._categories_match_up_to_permutation(CategoricalIndex(c1))
+        assert c1._categories_match_up_to_permutation(
+            CategoricalIndex(c1, categories=list("cab"))
+        )
+        assert not c1._categories_match_up_to_permutation(
+            CategoricalIndex(c1, ordered=True)
+        )
+
+        # GH 16659
+        s1 = Series(c1)
+        s2 = Series(c2)
+        s3 = Series(c3)
+        assert c1._categories_match_up_to_permutation(s1)
+        assert c2._categories_match_up_to_permutation(s2)
+        assert c3._categories_match_up_to_permutation(s3)
+        assert c1._categories_match_up_to_permutation(s2)
+        assert not c1._categories_match_up_to_permutation(s3)
+        assert not c1._categories_match_up_to_permutation(s1.astype(object))
+
+    def test_set_dtype_same(self):
+        c = Categorical(["a", "b", "c"])
+        result = c._set_dtype(CategoricalDtype(["a", "b", "c"]))
+        tm.assert_categorical_equal(result, c)
+
+    def test_set_dtype_new_categories(self):
+        c = Categorical(["a", "b", "c"])
+        result = c._set_dtype(CategoricalDtype(list("abcd")))
+        tm.assert_numpy_array_equal(result.codes, c.codes)
+        tm.assert_index_equal(result.dtype.categories, Index(list("abcd")))
+
+    @pytest.mark.parametrize(
+        "values, categories, new_categories",
+        [
+            # No NaNs, same cats, same order
+            (["a", "b", "a"], ["a", "b"], ["a", "b"]),
+            # No NaNs, same cats, different order
+            (["a", "b", "a"], ["a", "b"], ["b", "a"]),
+            # Same, unsorted
+            (["b", "a", "a"], ["a", "b"], ["a", "b"]),
+            # No NaNs, same cats, different order
+            (["b", "a", "a"], ["a", "b"], ["b", "a"]),
+            # NaNs
+            (["a", "b", "c"], ["a", "b"], ["a", "b"]),
+            (["a", "b", "c"], ["a", "b"], ["b", "a"]),
+            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            (["b", "a", "c"], ["a", "b"], ["a", "b"]),
+            # Introduce NaNs
+            (["a", "b", "c"], ["a", "b"], ["a"]),
+            (["a", "b", "c"], ["a", "b"], ["b"]),
+            (["b", "a", "c"], ["a", "b"], ["a"]),
+            (["b", "a", "c"], ["a", "b"], ["a"]),
+            # No overlap
+            (["a", "b", "c"], ["a", "b"], ["d", "e"]),
+        ],
+    )
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_set_dtype_many(self, values, categories, new_categories, ordered):
+        c = Categorical(values, categories)
+        expected = Categorical(values, new_categories, ordered)
+        result = c._set_dtype(expected.dtype)
+        tm.assert_categorical_equal(result, expected)
+
+    def test_set_dtype_no_overlap(self):
+        c = Categorical(["a", "b", "c"], ["d", "e"])
+        result = c._set_dtype(CategoricalDtype(["a", "b"]))
+        expected = Categorical([None, None, None], categories=["a", "b"])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_codes_dtypes(self):
+        # GH 8453
+        result = Categorical(["foo", "bar", "baz"])
+        assert result.codes.dtype == "int8"
+
+        result = Categorical([f"foo{i:05d}" for i in range(400)])
+        assert result.codes.dtype == "int16"
+
+        result = Categorical([f"foo{i:05d}" for i in range(40000)])
+        assert result.codes.dtype == "int32"
+
+        # adding cats
+        result = Categorical(["foo", "bar", "baz"])
+        assert result.codes.dtype == "int8"
+        result = result.add_categories([f"foo{i:05d}" for i in range(400)])
+        assert result.codes.dtype == "int16"
+
+        # removing cats
+        result = result.remove_categories([f"foo{i:05d}" for i in range(300)])
+        assert result.codes.dtype == "int8"
+
+    def test_iter_python_types(self):
+        # GH-19909
+        cat = Categorical([1, 2])
+        assert isinstance(next(iter(cat)), int)
+        assert isinstance(cat.tolist()[0], int)
+
+    def test_iter_python_types_datetime(self):
+        cat = Categorical([Timestamp("2017-01-01"), Timestamp("2017-01-02")])
+        assert isinstance(next(iter(cat)), Timestamp)
+        assert isinstance(cat.tolist()[0], Timestamp)
+
+    def test_interval_index_category(self):
+        # GH 38316
+        index = IntervalIndex.from_breaks(np.arange(3, dtype="uint64"))
+
+        result = CategoricalIndex(index).dtype.categories
+        expected = IntervalIndex.from_arrays(
+            [0, 1], [1, 2], dtype="interval[uint64, right]"
+        )
+        tm.assert_index_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_indexing.py

@@ -0,0 +1,388 @@
+import math
+
+import numpy as np
+import pytest
+
+from pandas import (
+    NA,
+    Categorical,
+    CategoricalIndex,
+    Index,
+    Interval,
+    IntervalIndex,
+    NaT,
+    PeriodIndex,
+    Series,
+    Timedelta,
+    Timestamp,
+)
+import pandas._testing as tm
+import pandas.core.common as com
+
+
+class TestCategoricalIndexingWithFactor:
+    def test_getitem(self):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        assert factor[0] == "a"
+        assert factor[-1] == "c"
+
+        subf = factor[[0, 1, 2]]
+        tm.assert_numpy_array_equal(subf._codes, np.array([0, 1, 1], dtype=np.int8))
+
+        subf = factor[np.asarray(factor) == "c"]
+        tm.assert_numpy_array_equal(subf._codes, np.array([2, 2, 2], dtype=np.int8))
+
+    def test_setitem(self):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        # int/positional
+        c = factor.copy()
+        c[0] = "b"
+        assert c[0] == "b"
+        c[-1] = "a"
+        assert c[-1] == "a"
+
+        # boolean
+        c = factor.copy()
+        indexer = np.zeros(len(c), dtype="bool")
+        indexer[0] = True
+        indexer[-1] = True
+        c[indexer] = "c"
+        expected = Categorical(["c", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+
+        tm.assert_categorical_equal(c, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [Categorical(["b", "a"]), Categorical(["b", "a"], categories=["b", "a"])],
+    )
+    def test_setitem_same_but_unordered(self, other):
+        # GH-24142
+        target = Categorical(["a", "b"], categories=["a", "b"])
+        mask = np.array([True, False])
+        target[mask] = other[mask]
+        expected = Categorical(["b", "b"], categories=["a", "b"])
+        tm.assert_categorical_equal(target, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            Categorical(["b", "a"], categories=["b", "a", "c"]),
+            Categorical(["b", "a"], categories=["a", "b", "c"]),
+            Categorical(["a", "a"], categories=["a"]),
+            Categorical(["b", "b"], categories=["b"]),
+        ],
+    )
+    def test_setitem_different_unordered_raises(self, other):
+        # GH-24142
+        target = Categorical(["a", "b"], categories=["a", "b"])
+        mask = np.array([True, False])
+        msg = "Cannot set a Categorical with another, without identical categories"
+        with pytest.raises(TypeError, match=msg):
+            target[mask] = other[mask]
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            Categorical(["b", "a"]),
+            Categorical(["b", "a"], categories=["b", "a"], ordered=True),
+            Categorical(["b", "a"], categories=["a", "b", "c"], ordered=True),
+        ],
+    )
+    def test_setitem_same_ordered_raises(self, other):
+        # Gh-24142
+        target = Categorical(["a", "b"], categories=["a", "b"], ordered=True)
+        mask = np.array([True, False])
+        msg = "Cannot set a Categorical with another, without identical categories"
+        with pytest.raises(TypeError, match=msg):
+            target[mask] = other[mask]
+
+    def test_setitem_tuple(self):
+        # GH#20439
+        cat = Categorical([(0, 1), (0, 2), (0, 1)])
+
+        # This should not raise
+        cat[1] = cat[0]
+        assert cat[1] == (0, 1)
+
+    def test_setitem_listlike(self):
+        # GH#9469
+        # properly coerce the input indexers
+
+        cat = Categorical(
+            np.random.default_rng(2).integers(0, 5, size=150000).astype(np.int8)
+        ).add_categories([-1000])
+        indexer = np.array([100000]).astype(np.int64)
+        cat[indexer] = -1000
+
+        # we are asserting the code result here
+        # which maps to the -1000 category
+        result = cat.codes[np.array([100000]).astype(np.int64)]
+        tm.assert_numpy_array_equal(result, np.array([5], dtype="int8"))
+
+
+class TestCategoricalIndexing:
+    def test_getitem_slice(self):
+        cat = Categorical(["a", "b", "c", "d", "a", "b", "c"])
+        sliced = cat[3]
+        assert sliced == "d"
+
+        sliced = cat[3:5]
+        expected = Categorical(["d", "a"], categories=["a", "b", "c", "d"])
+        tm.assert_categorical_equal(sliced, expected)
+
+    def test_getitem_listlike(self):
+        # GH 9469
+        # properly coerce the input indexers
+
+        c = Categorical(
+            np.random.default_rng(2).integers(0, 5, size=150000).astype(np.int8)
+        )
+        result = c.codes[np.array([100000]).astype(np.int64)]
+        expected = c[np.array([100000]).astype(np.int64)].codes
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_periodindex(self):
+        idx1 = PeriodIndex(
+            ["2014-01", "2014-01", "2014-02", "2014-02", "2014-03", "2014-03"],
+            freq="M",
+        )
+
+        cat1 = Categorical(idx1)
+        str(cat1)
+        exp_arr = np.array([0, 0, 1, 1, 2, 2], dtype=np.int8)
+        exp_idx = PeriodIndex(["2014-01", "2014-02", "2014-03"], freq="M")
+        tm.assert_numpy_array_equal(cat1._codes, exp_arr)
+        tm.assert_index_equal(cat1.categories, exp_idx)
+
+        idx2 = PeriodIndex(
+            ["2014-03", "2014-03", "2014-02", "2014-01", "2014-03", "2014-01"],
+            freq="M",
+        )
+        cat2 = Categorical(idx2, ordered=True)
+        str(cat2)
+        exp_arr = np.array([2, 2, 1, 0, 2, 0], dtype=np.int8)
+        exp_idx2 = PeriodIndex(["2014-01", "2014-02", "2014-03"], freq="M")
+        tm.assert_numpy_array_equal(cat2._codes, exp_arr)
+        tm.assert_index_equal(cat2.categories, exp_idx2)
+
+        idx3 = PeriodIndex(
+            [
+                "2013-12",
+                "2013-11",
+                "2013-10",
+                "2013-09",
+                "2013-08",
+                "2013-07",
+                "2013-05",
+            ],
+            freq="M",
+        )
+        cat3 = Categorical(idx3, ordered=True)
+        exp_arr = np.array([6, 5, 4, 3, 2, 1, 0], dtype=np.int8)
+        exp_idx = PeriodIndex(
+            [
+                "2013-05",
+                "2013-07",
+                "2013-08",
+                "2013-09",
+                "2013-10",
+                "2013-11",
+                "2013-12",
+            ],
+            freq="M",
+        )
+        tm.assert_numpy_array_equal(cat3._codes, exp_arr)
+        tm.assert_index_equal(cat3.categories, exp_idx)
+
+    @pytest.mark.parametrize(
+        "null_val",
+        [None, np.nan, NaT, NA, math.nan, "NaT", "nat", "NAT", "nan", "NaN", "NAN"],
+    )
+    def test_periodindex_on_null_types(self, null_val):
+        # GH 46673
+        result = PeriodIndex(["2022-04-06", "2022-04-07", null_val], freq="D")
+        expected = PeriodIndex(["2022-04-06", "2022-04-07", "NaT"], dtype="period[D]")
+        assert result[2] is NaT
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("new_categories", [[1, 2, 3, 4], [1, 2]])
+    def test_categories_assignments_wrong_length_raises(self, new_categories):
+        cat = Categorical(["a", "b", "c", "a"])
+        msg = (
+            "new categories need to have the same number of items "
+            "as the old categories!"
+        )
+        with pytest.raises(ValueError, match=msg):
+            cat.rename_categories(new_categories)
+
+    # Combinations of sorted/unique:
+    @pytest.mark.parametrize(
+        "idx_values", [[1, 2, 3, 4], [1, 3, 2, 4], [1, 3, 3, 4], [1, 2, 2, 4]]
+    )
+    # Combinations of missing/unique
+    @pytest.mark.parametrize("key_values", [[1, 2], [1, 5], [1, 1], [5, 5]])
+    @pytest.mark.parametrize("key_class", [Categorical, CategoricalIndex])
+    @pytest.mark.parametrize("dtype", [None, "category", "key"])
+    def test_get_indexer_non_unique(self, idx_values, key_values, key_class, dtype):
+        # GH 21448
+        key = key_class(key_values, categories=range(1, 5))
+
+        if dtype == "key":
+            dtype = key.dtype
+
+        # Test for flat index and CategoricalIndex with same/different cats:
+        idx = Index(idx_values, dtype=dtype)
+        expected, exp_miss = idx.get_indexer_non_unique(key_values)
+        result, res_miss = idx.get_indexer_non_unique(key)
+
+        tm.assert_numpy_array_equal(expected, result)
+        tm.assert_numpy_array_equal(exp_miss, res_miss)
+
+        exp_unique = idx.unique().get_indexer(key_values)
+        res_unique = idx.unique().get_indexer(key)
+        tm.assert_numpy_array_equal(res_unique, exp_unique)
+
+    def test_where_unobserved_nan(self):
+        ser = Series(Categorical(["a", "b"]))
+        result = ser.where([True, False])
+        expected = Series(Categorical(["a", None], categories=["a", "b"]))
+        tm.assert_series_equal(result, expected)
+
+        # all NA
+        ser = Series(Categorical(["a", "b"]))
+        result = ser.where([False, False])
+        expected = Series(Categorical([None, None], categories=["a", "b"]))
+        tm.assert_series_equal(result, expected)
+
+    def test_where_unobserved_categories(self):
+        ser = Series(Categorical(["a", "b", "c"], categories=["d", "c", "b", "a"]))
+        result = ser.where([True, True, False], other="b")
+        expected = Series(Categorical(["a", "b", "b"], categories=ser.cat.categories))
+        tm.assert_series_equal(result, expected)
+
+    def test_where_other_categorical(self):
+        ser = Series(Categorical(["a", "b", "c"], categories=["d", "c", "b", "a"]))
+        other = Categorical(["b", "c", "a"], categories=["a", "c", "b", "d"])
+        result = ser.where([True, False, True], other)
+        expected = Series(Categorical(["a", "c", "c"], dtype=ser.dtype))
+        tm.assert_series_equal(result, expected)
+
+    def test_where_new_category_raises(self):
+        ser = Series(Categorical(["a", "b", "c"]))
+        msg = "Cannot setitem on a Categorical with a new category"
+        with pytest.raises(TypeError, match=msg):
+            ser.where([True, False, True], "d")
+
+    def test_where_ordered_differs_rasies(self):
+        ser = Series(
+            Categorical(["a", "b", "c"], categories=["d", "c", "b", "a"], ordered=True)
+        )
+        other = Categorical(
+            ["b", "c", "a"], categories=["a", "c", "b", "d"], ordered=True
+        )
+        with pytest.raises(TypeError, match="without identical categories"):
+            ser.where([True, False, True], other)
+
+
+class TestContains:
+    def test_contains(self):
+        # GH#21508
+        cat = Categorical(list("aabbca"), categories=list("cab"))
+
+        assert "b" in cat
+        assert "z" not in cat
+        assert np.nan not in cat
+        with pytest.raises(TypeError, match="unhashable type: 'list'"):
+            assert [1] in cat
+
+        # assert codes NOT in index
+        assert 0 not in cat
+        assert 1 not in cat
+
+        cat = Categorical(list("aabbca") + [np.nan], categories=list("cab"))
+        assert np.nan in cat
+
+    @pytest.mark.parametrize(
+        "item, expected",
+        [
+            (Interval(0, 1), True),
+            (1.5, True),
+            (Interval(0.5, 1.5), False),
+            ("a", False),
+            (Timestamp(1), False),
+            (Timedelta(1), False),
+        ],
+        ids=str,
+    )
+    def test_contains_interval(self, item, expected):
+        # GH#23705
+        cat = Categorical(IntervalIndex.from_breaks(range(3)))
+        result = item in cat
+        assert result is expected
+
+    def test_contains_list(self):
+        # GH#21729
+        cat = Categorical([1, 2, 3])
+
+        assert "a" not in cat
+
+        with pytest.raises(TypeError, match="unhashable type"):
+            ["a"] in cat
+
+        with pytest.raises(TypeError, match="unhashable type"):
+            ["a", "b"] in cat
+
+
+@pytest.mark.parametrize("index", [True, False])
+def test_mask_with_boolean(index):
+    ser = Series(range(3))
+    idx = Categorical([True, False, True])
+    if index:
+        idx = CategoricalIndex(idx)
+
+    assert com.is_bool_indexer(idx)
+    result = ser[idx]
+    expected = ser[idx.astype("object")]
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("index", [True, False])
+def test_mask_with_boolean_na_treated_as_false(index):
+    # https://github.com/pandas-dev/pandas/issues/31503
+    ser = Series(range(3))
+    idx = Categorical([True, False, None])
+    if index:
+        idx = CategoricalIndex(idx)
+
+    result = ser[idx]
+    expected = ser[idx.fillna(False)]
+
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.fixture
+def non_coercible_categorical(monkeypatch):
+    """
+    Monkeypatch Categorical.__array__ to ensure no implicit conversion.
+
+    Raises
+    ------
+    ValueError
+        When Categorical.__array__ is called.
+    """
+
+    # TODO(Categorical): identify other places where this may be
+    # useful and move to a conftest.py
+    def array(self, dtype=None):
+        raise ValueError("I cannot be converted.")
+
+    with monkeypatch.context() as m:
+        m.setattr(Categorical, "__array__", array)
+        yield
+
+
+def test_series_at():
+    arr = Categorical(["a", "b", "c"])
+    ser = Series(arr)
+    result = ser.at[0]
+    assert result == "a"

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_map.py

@@ -0,0 +1,154 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    Index,
+    Series,
+)
+import pandas._testing as tm
+
+
+@pytest.fixture(params=[None, "ignore"])
+def na_action(request):
+    return request.param
+
+
+@pytest.mark.parametrize(
+    "data, categories",
+    [
+        (list("abcbca"), list("cab")),
+        (pd.interval_range(0, 3).repeat(3), pd.interval_range(0, 3)),
+    ],
+    ids=["string", "interval"],
+)
+def test_map_str(data, categories, ordered, na_action):
+    # GH 31202 - override base class since we want to maintain categorical/ordered
+    cat = Categorical(data, categories=categories, ordered=ordered)
+    result = cat.map(str, na_action=na_action)
+    expected = Categorical(
+        map(str, data), categories=map(str, categories), ordered=ordered
+    )
+    tm.assert_categorical_equal(result, expected)
+
+
+def test_map(na_action):
+    cat = Categorical(list("ABABC"), categories=list("CBA"), ordered=True)
+    result = cat.map(lambda x: x.lower(), na_action=na_action)
+    exp = Categorical(list("ababc"), categories=list("cba"), ordered=True)
+    tm.assert_categorical_equal(result, exp)
+
+    cat = Categorical(list("ABABC"), categories=list("BAC"), ordered=False)
+    result = cat.map(lambda x: x.lower(), na_action=na_action)
+    exp = Categorical(list("ababc"), categories=list("bac"), ordered=False)
+    tm.assert_categorical_equal(result, exp)
+
+    # GH 12766: Return an index not an array
+    result = cat.map(lambda x: 1, na_action=na_action)
+    exp = Index(np.array([1] * 5, dtype=np.int64))
+    tm.assert_index_equal(result, exp)
+
+    # change categories dtype
+    cat = Categorical(list("ABABC"), categories=list("BAC"), ordered=False)
+
+    def f(x):
+        return {"A": 10, "B": 20, "C": 30}.get(x)
+
+    result = cat.map(f, na_action=na_action)
+    exp = Categorical([10, 20, 10, 20, 30], categories=[20, 10, 30], ordered=False)
+    tm.assert_categorical_equal(result, exp)
+
+    mapper = Series([10, 20, 30], index=["A", "B", "C"])
+    result = cat.map(mapper, na_action=na_action)
+    tm.assert_categorical_equal(result, exp)
+
+    result = cat.map({"A": 10, "B": 20, "C": 30}, na_action=na_action)
+    tm.assert_categorical_equal(result, exp)
+
+
+@pytest.mark.parametrize(
+    ("data", "f", "expected"),
+    (
+        ([1, 1, np.nan], pd.isna, Index([False, False, True])),
+        ([1, 2, np.nan], pd.isna, Index([False, False, True])),
+        ([1, 1, np.nan], {1: False}, Categorical([False, False, np.nan])),
+        ([1, 2, np.nan], {1: False, 2: False}, Index([False, False, np.nan])),
+        (
+            [1, 1, np.nan],
+            Series([False, False]),
+            Categorical([False, False, np.nan]),
+        ),
+        (
+            [1, 2, np.nan],
+            Series([False] * 3),
+            Index([False, False, np.nan]),
+        ),
+    ),
+)
+def test_map_with_nan_none(data, f, expected):  # GH 24241
+    values = Categorical(data)
+    result = values.map(f, na_action=None)
+    if isinstance(expected, Categorical):
+        tm.assert_categorical_equal(result, expected)
+    else:
+        tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    ("data", "f", "expected"),
+    (
+        ([1, 1, np.nan], pd.isna, Categorical([False, False, np.nan])),
+        ([1, 2, np.nan], pd.isna, Index([False, False, np.nan])),
+        ([1, 1, np.nan], {1: False}, Categorical([False, False, np.nan])),
+        ([1, 2, np.nan], {1: False, 2: False}, Index([False, False, np.nan])),
+        (
+            [1, 1, np.nan],
+            Series([False, False]),
+            Categorical([False, False, np.nan]),
+        ),
+        (
+            [1, 2, np.nan],
+            Series([False, False, False]),
+            Index([False, False, np.nan]),
+        ),
+    ),
+)
+def test_map_with_nan_ignore(data, f, expected):  # GH 24241
+    values = Categorical(data)
+    result = values.map(f, na_action="ignore")
+    if data[1] == 1:
+        tm.assert_categorical_equal(result, expected)
+    else:
+        tm.assert_index_equal(result, expected)
+
+
+def test_map_with_dict_or_series(na_action):
+    orig_values = ["a", "B", 1, "a"]
+    new_values = ["one", 2, 3.0, "one"]
+    cat = Categorical(orig_values)
+
+    mapper = Series(new_values[:-1], index=orig_values[:-1])
+    result = cat.map(mapper, na_action=na_action)
+
+    # Order of categories in result can be different
+    expected = Categorical(new_values, categories=[3.0, 2, "one"])
+    tm.assert_categorical_equal(result, expected)
+
+    mapper = dict(zip(orig_values[:-1], new_values[:-1]))
+    result = cat.map(mapper, na_action=na_action)
+    # Order of categories in result can be different
+    tm.assert_categorical_equal(result, expected)
+
+
+def test_map_na_action_no_default_deprecated():
+    # GH51645
+    cat = Categorical(["a", "b", "c"])
+    msg = (
+        "The default value of 'ignore' for the `na_action` parameter in "
+        "pandas.Categorical.map is deprecated and will be "
+        "changed to 'None' in a future version. Please set na_action to the "
+        "desired value to avoid seeing this warning"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        cat.map(lambda x: x)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_missing.py

@@ -0,0 +1,216 @@
+import collections
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import CategoricalDtype
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    DataFrame,
+    Index,
+    Series,
+    isna,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalMissing:
+    def test_isna(self):
+        exp = np.array([False, False, True])
+        cat = Categorical(["a", "b", np.nan])
+        res = cat.isna()
+
+        tm.assert_numpy_array_equal(res, exp)
+
+    def test_na_flags_int_categories(self):
+        # #1457
+
+        categories = list(range(10))
+        labels = np.random.default_rng(2).integers(0, 10, 20)
+        labels[::5] = -1
+
+        cat = Categorical(labels, categories)
+        repr(cat)
+
+        tm.assert_numpy_array_equal(isna(cat), labels == -1)
+
+    def test_nan_handling(self):
+        # Nans are represented as -1 in codes
+        c = Categorical(["a", "b", np.nan, "a"])
+        tm.assert_index_equal(c.categories, Index(["a", "b"]))
+        tm.assert_numpy_array_equal(c._codes, np.array([0, 1, -1, 0], dtype=np.int8))
+        c[1] = np.nan
+        tm.assert_index_equal(c.categories, Index(["a", "b"]))
+        tm.assert_numpy_array_equal(c._codes, np.array([0, -1, -1, 0], dtype=np.int8))
+
+        # Adding nan to categories should make assigned nan point to the
+        # category!
+        c = Categorical(["a", "b", np.nan, "a"])
+        tm.assert_index_equal(c.categories, Index(["a", "b"]))
+        tm.assert_numpy_array_equal(c._codes, np.array([0, 1, -1, 0], dtype=np.int8))
+
+    def test_set_dtype_nans(self):
+        c = Categorical(["a", "b", np.nan])
+        result = c._set_dtype(CategoricalDtype(["a", "c"]))
+        tm.assert_numpy_array_equal(result.codes, np.array([0, -1, -1], dtype="int8"))
+
+    def test_set_item_nan(self):
+        cat = Categorical([1, 2, 3])
+        cat[1] = np.nan
+
+        exp = Categorical([1, np.nan, 3], categories=[1, 2, 3])
+        tm.assert_categorical_equal(cat, exp)
+
+    @pytest.mark.parametrize(
+        "fillna_kwargs, msg",
+        [
+            (
+                {"value": 1, "method": "ffill"},
+                "Cannot specify both 'value' and 'method'.",
+            ),
+            ({}, "Must specify a fill 'value' or 'method'."),
+            ({"method": "bad"}, "Invalid fill method. Expecting .* bad"),
+            (
+                {"value": Series([1, 2, 3, 4, "a"])},
+                "Cannot setitem on a Categorical with a new category",
+            ),
+        ],
+    )
+    def test_fillna_raises(self, fillna_kwargs, msg):
+        # https://github.com/pandas-dev/pandas/issues/19682
+        # https://github.com/pandas-dev/pandas/issues/13628
+        cat = Categorical([1, 2, 3, None, None])
+
+        if len(fillna_kwargs) == 1 and "value" in fillna_kwargs:
+            err = TypeError
+        else:
+            err = ValueError
+
+        with pytest.raises(err, match=msg):
+            cat.fillna(**fillna_kwargs)
+
+    @pytest.mark.parametrize("named", [True, False])
+    def test_fillna_iterable_category(self, named):
+        # https://github.com/pandas-dev/pandas/issues/21097
+        if named:
+            Point = collections.namedtuple("Point", "x y")
+        else:
+            Point = lambda *args: args  # tuple
+        cat = Categorical(np.array([Point(0, 0), Point(0, 1), None], dtype=object))
+        result = cat.fillna(Point(0, 0))
+        expected = Categorical([Point(0, 0), Point(0, 1), Point(0, 0)])
+
+        tm.assert_categorical_equal(result, expected)
+
+        # Case where the Point is not among our categories; we want ValueError,
+        #  not NotImplementedError GH#41914
+        cat = Categorical(np.array([Point(1, 0), Point(0, 1), None], dtype=object))
+        msg = "Cannot setitem on a Categorical with a new category"
+        with pytest.raises(TypeError, match=msg):
+            cat.fillna(Point(0, 0))
+
+    def test_fillna_array(self):
+        # accept Categorical or ndarray value if it holds appropriate values
+        cat = Categorical(["A", "B", "C", None, None])
+
+        other = cat.fillna("C")
+        result = cat.fillna(other)
+        tm.assert_categorical_equal(result, other)
+        assert isna(cat[-1])  # didn't modify original inplace
+
+        other = np.array(["A", "B", "C", "B", "A"])
+        result = cat.fillna(other)
+        expected = Categorical(["A", "B", "C", "B", "A"], dtype=cat.dtype)
+        tm.assert_categorical_equal(result, expected)
+        assert isna(cat[-1])  # didn't modify original inplace
+
+    @pytest.mark.parametrize(
+        "values, expected",
+        [
+            ([1, 2, 3], np.array([False, False, False])),
+            ([1, 2, np.nan], np.array([False, False, True])),
+            ([1, 2, np.inf], np.array([False, False, True])),
+            ([1, 2, pd.NA], np.array([False, False, True])),
+        ],
+    )
+    def test_use_inf_as_na(self, values, expected):
+        # https://github.com/pandas-dev/pandas/issues/33594
+        msg = "use_inf_as_na option is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            with pd.option_context("mode.use_inf_as_na", True):
+                cat = Categorical(values)
+                result = cat.isna()
+                tm.assert_numpy_array_equal(result, expected)
+
+                result = Series(cat).isna()
+                expected = Series(expected)
+                tm.assert_series_equal(result, expected)
+
+                result = DataFrame(cat).isna()
+                expected = DataFrame(expected)
+                tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "values, expected",
+        [
+            ([1, 2, 3], np.array([False, False, False])),
+            ([1, 2, np.nan], np.array([False, False, True])),
+            ([1, 2, np.inf], np.array([False, False, True])),
+            ([1, 2, pd.NA], np.array([False, False, True])),
+        ],
+    )
+    def test_use_inf_as_na_outside_context(self, values, expected):
+        # https://github.com/pandas-dev/pandas/issues/33594
+        # Using isna directly for Categorical will fail in general here
+        cat = Categorical(values)
+
+        msg = "use_inf_as_na option is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            with pd.option_context("mode.use_inf_as_na", True):
+                result = isna(cat)
+                tm.assert_numpy_array_equal(result, expected)
+
+                result = isna(Series(cat))
+                expected = Series(expected)
+                tm.assert_series_equal(result, expected)
+
+                result = isna(DataFrame(cat))
+                expected = DataFrame(expected)
+                tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "a1, a2, categories",
+        [
+            (["a", "b", "c"], [np.nan, "a", "b"], ["a", "b", "c"]),
+            ([1, 2, 3], [np.nan, 1, 2], [1, 2, 3]),
+        ],
+    )
+    def test_compare_categorical_with_missing(self, a1, a2, categories):
+        # GH 28384
+        cat_type = CategoricalDtype(categories)
+
+        # !=
+        result = Series(a1, dtype=cat_type) != Series(a2, dtype=cat_type)
+        expected = Series(a1) != Series(a2)
+        tm.assert_series_equal(result, expected)
+
+        # ==
+        result = Series(a1, dtype=cat_type) == Series(a2, dtype=cat_type)
+        expected = Series(a1) == Series(a2)
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "na_value, dtype",
+        [
+            (pd.NaT, "datetime64[ns]"),
+            (None, "float64"),
+            (np.nan, "float64"),
+            (pd.NA, "float64"),
+        ],
+    )
+    def test_categorical_only_missing_values_no_cast(self, na_value, dtype):
+        # GH#44900
+        result = Categorical([na_value, na_value])
+        tm.assert_index_equal(result.categories, Index([], dtype=dtype))

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_operators.py

@@ -0,0 +1,414 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    DataFrame,
+    Series,
+    Timestamp,
+    date_range,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalOpsWithFactor:
+    def test_categories_none_comparisons(self):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        tm.assert_categorical_equal(factor, factor)
+
+    def test_comparisons(self):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        result = factor[factor == "a"]
+        expected = factor[np.asarray(factor) == "a"]
+        tm.assert_categorical_equal(result, expected)
+
+        result = factor[factor != "a"]
+        expected = factor[np.asarray(factor) != "a"]
+        tm.assert_categorical_equal(result, expected)
+
+        result = factor[factor < "c"]
+        expected = factor[np.asarray(factor) < "c"]
+        tm.assert_categorical_equal(result, expected)
+
+        result = factor[factor > "a"]
+        expected = factor[np.asarray(factor) > "a"]
+        tm.assert_categorical_equal(result, expected)
+
+        result = factor[factor >= "b"]
+        expected = factor[np.asarray(factor) >= "b"]
+        tm.assert_categorical_equal(result, expected)
+
+        result = factor[factor <= "b"]
+        expected = factor[np.asarray(factor) <= "b"]
+        tm.assert_categorical_equal(result, expected)
+
+        n = len(factor)
+
+        other = factor[np.random.default_rng(2).permutation(n)]
+        result = factor == other
+        expected = np.asarray(factor) == np.asarray(other)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = factor == "d"
+        expected = np.zeros(len(factor), dtype=bool)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # comparisons with categoricals
+        cat_rev = Categorical(["a", "b", "c"], categories=["c", "b", "a"], ordered=True)
+        cat_rev_base = Categorical(
+            ["b", "b", "b"], categories=["c", "b", "a"], ordered=True
+        )
+        cat = Categorical(["a", "b", "c"], ordered=True)
+        cat_base = Categorical(["b", "b", "b"], categories=cat.categories, ordered=True)
+
+        # comparisons need to take categories ordering into account
+        res_rev = cat_rev > cat_rev_base
+        exp_rev = np.array([True, False, False])
+        tm.assert_numpy_array_equal(res_rev, exp_rev)
+
+        res_rev = cat_rev < cat_rev_base
+        exp_rev = np.array([False, False, True])
+        tm.assert_numpy_array_equal(res_rev, exp_rev)
+
+        res = cat > cat_base
+        exp = np.array([False, False, True])
+        tm.assert_numpy_array_equal(res, exp)
+
+        # Only categories with same categories can be compared
+        msg = "Categoricals can only be compared if 'categories' are the same"
+        with pytest.raises(TypeError, match=msg):
+            cat > cat_rev
+
+        cat_rev_base2 = Categorical(["b", "b", "b"], categories=["c", "b", "a", "d"])
+
+        with pytest.raises(TypeError, match=msg):
+            cat_rev > cat_rev_base2
+
+        # Only categories with same ordering information can be compared
+        cat_unordered = cat.set_ordered(False)
+        assert not (cat > cat).any()
+
+        with pytest.raises(TypeError, match=msg):
+            cat > cat_unordered
+
+        # comparison (in both directions) with Series will raise
+        s = Series(["b", "b", "b"], dtype=object)
+        msg = (
+            "Cannot compare a Categorical for op __gt__ with type "
+            r"<class 'numpy\.ndarray'>"
+        )
+        with pytest.raises(TypeError, match=msg):
+            cat > s
+        with pytest.raises(TypeError, match=msg):
+            cat_rev > s
+        with pytest.raises(TypeError, match=msg):
+            s < cat
+        with pytest.raises(TypeError, match=msg):
+            s < cat_rev
+
+        # comparison with numpy.array will raise in both direction, but only on
+        # newer numpy versions
+        a = np.array(["b", "b", "b"], dtype=object)
+        with pytest.raises(TypeError, match=msg):
+            cat > a
+        with pytest.raises(TypeError, match=msg):
+            cat_rev > a
+
+        # Make sure that unequal comparison take the categories order in
+        # account
+        cat_rev = Categorical(list("abc"), categories=list("cba"), ordered=True)
+        exp = np.array([True, False, False])
+        res = cat_rev > "b"
+        tm.assert_numpy_array_equal(res, exp)
+
+        # check that zero-dim array gets unboxed
+        res = cat_rev > np.array("b")
+        tm.assert_numpy_array_equal(res, exp)
+
+
+class TestCategoricalOps:
+    @pytest.mark.parametrize(
+        "categories",
+        [["a", "b"], [0, 1], [Timestamp("2019"), Timestamp("2020")]],
+    )
+    def test_not_equal_with_na(self, categories):
+        # https://github.com/pandas-dev/pandas/issues/32276
+        c1 = Categorical.from_codes([-1, 0], categories=categories)
+        c2 = Categorical.from_codes([0, 1], categories=categories)
+
+        result = c1 != c2
+
+        assert result.all()
+
+    def test_compare_frame(self):
+        # GH#24282 check that Categorical.__cmp__(DataFrame) defers to frame
+        data = ["a", "b", 2, "a"]
+        cat = Categorical(data)
+
+        df = DataFrame(cat)
+
+        result = cat == df.T
+        expected = DataFrame([[True, True, True, True]])
+        tm.assert_frame_equal(result, expected)
+
+        result = cat[::-1] != df.T
+        expected = DataFrame([[False, True, True, False]])
+        tm.assert_frame_equal(result, expected)
+
+    def test_compare_frame_raises(self, comparison_op):
+        # alignment raises unless we transpose
+        op = comparison_op
+        cat = Categorical(["a", "b", 2, "a"])
+        df = DataFrame(cat)
+        msg = "Unable to coerce to Series, length must be 1: given 4"
+        with pytest.raises(ValueError, match=msg):
+            op(cat, df)
+
+    def test_datetime_categorical_comparison(self):
+        dt_cat = Categorical(date_range("2014-01-01", periods=3), ordered=True)
+        tm.assert_numpy_array_equal(dt_cat > dt_cat[0], np.array([False, True, True]))
+        tm.assert_numpy_array_equal(dt_cat[0] < dt_cat, np.array([False, True, True]))
+
+    def test_reflected_comparison_with_scalars(self):
+        # GH8658
+        cat = Categorical([1, 2, 3], ordered=True)
+        tm.assert_numpy_array_equal(cat > cat[0], np.array([False, True, True]))
+        tm.assert_numpy_array_equal(cat[0] < cat, np.array([False, True, True]))
+
+    def test_comparison_with_unknown_scalars(self):
+        # https://github.com/pandas-dev/pandas/issues/9836#issuecomment-92123057
+        # and following comparisons with scalars not in categories should raise
+        # for unequal comps, but not for equal/not equal
+        cat = Categorical([1, 2, 3], ordered=True)
+
+        msg = "Invalid comparison between dtype=category and int"
+        with pytest.raises(TypeError, match=msg):
+            cat < 4
+        with pytest.raises(TypeError, match=msg):
+            cat > 4
+        with pytest.raises(TypeError, match=msg):
+            4 < cat
+        with pytest.raises(TypeError, match=msg):
+            4 > cat
+
+        tm.assert_numpy_array_equal(cat == 4, np.array([False, False, False]))
+        tm.assert_numpy_array_equal(cat != 4, np.array([True, True, True]))
+
+    def test_comparison_with_tuple(self):
+        cat = Categorical(np.array(["foo", (0, 1), 3, (0, 1)], dtype=object))
+
+        result = cat == "foo"
+        expected = np.array([True, False, False, False], dtype=bool)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = cat == (0, 1)
+        expected = np.array([False, True, False, True], dtype=bool)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = cat != (0, 1)
+        tm.assert_numpy_array_equal(result, ~expected)
+
+    @pytest.mark.filterwarnings("ignore::RuntimeWarning")
+    def test_comparison_of_ordered_categorical_with_nan_to_scalar(
+        self, compare_operators_no_eq_ne
+    ):
+        # https://github.com/pandas-dev/pandas/issues/26504
+        # BUG: fix ordered categorical comparison with missing values (#26504 )
+        # and following comparisons with scalars in categories with missing
+        # values should be evaluated as False
+
+        cat = Categorical([1, 2, 3, None], categories=[1, 2, 3], ordered=True)
+        scalar = 2
+        expected = getattr(np.array(cat), compare_operators_no_eq_ne)(scalar)
+        actual = getattr(cat, compare_operators_no_eq_ne)(scalar)
+        tm.assert_numpy_array_equal(actual, expected)
+
+    @pytest.mark.filterwarnings("ignore::RuntimeWarning")
+    def test_comparison_of_ordered_categorical_with_nan_to_listlike(
+        self, compare_operators_no_eq_ne
+    ):
+        # https://github.com/pandas-dev/pandas/issues/26504
+        # and following comparisons of missing values in ordered Categorical
+        # with listlike should be evaluated as False
+
+        cat = Categorical([1, 2, 3, None], categories=[1, 2, 3], ordered=True)
+        other = Categorical([2, 2, 2, 2], categories=[1, 2, 3], ordered=True)
+        expected = getattr(np.array(cat), compare_operators_no_eq_ne)(2)
+        actual = getattr(cat, compare_operators_no_eq_ne)(other)
+        tm.assert_numpy_array_equal(actual, expected)
+
+    @pytest.mark.parametrize(
+        "data,reverse,base",
+        [(list("abc"), list("cba"), list("bbb")), ([1, 2, 3], [3, 2, 1], [2, 2, 2])],
+    )
+    def test_comparisons(self, data, reverse, base):
+        cat_rev = Series(Categorical(data, categories=reverse, ordered=True))
+        cat_rev_base = Series(Categorical(base, categories=reverse, ordered=True))
+        cat = Series(Categorical(data, ordered=True))
+        cat_base = Series(
+            Categorical(base, categories=cat.cat.categories, ordered=True)
+        )
+        s = Series(base, dtype=object if base == list("bbb") else None)
+        a = np.array(base)
+
+        # comparisons need to take categories ordering into account
+        res_rev = cat_rev > cat_rev_base
+        exp_rev = Series([True, False, False])
+        tm.assert_series_equal(res_rev, exp_rev)
+
+        res_rev = cat_rev < cat_rev_base
+        exp_rev = Series([False, False, True])
+        tm.assert_series_equal(res_rev, exp_rev)
+
+        res = cat > cat_base
+        exp = Series([False, False, True])
+        tm.assert_series_equal(res, exp)
+
+        scalar = base[1]
+        res = cat > scalar
+        exp = Series([False, False, True])
+        exp2 = cat.values > scalar
+        tm.assert_series_equal(res, exp)
+        tm.assert_numpy_array_equal(res.values, exp2)
+        res_rev = cat_rev > scalar
+        exp_rev = Series([True, False, False])
+        exp_rev2 = cat_rev.values > scalar
+        tm.assert_series_equal(res_rev, exp_rev)
+        tm.assert_numpy_array_equal(res_rev.values, exp_rev2)
+
+        # Only categories with same categories can be compared
+        msg = "Categoricals can only be compared if 'categories' are the same"
+        with pytest.raises(TypeError, match=msg):
+            cat > cat_rev
+
+        # categorical cannot be compared to Series or numpy array, and also
+        # not the other way around
+        msg = (
+            "Cannot compare a Categorical for op __gt__ with type "
+            r"<class 'numpy\.ndarray'>"
+        )
+        with pytest.raises(TypeError, match=msg):
+            cat > s
+        with pytest.raises(TypeError, match=msg):
+            cat_rev > s
+        with pytest.raises(TypeError, match=msg):
+            cat > a
+        with pytest.raises(TypeError, match=msg):
+            cat_rev > a
+
+        with pytest.raises(TypeError, match=msg):
+            s < cat
+        with pytest.raises(TypeError, match=msg):
+            s < cat_rev
+
+        with pytest.raises(TypeError, match=msg):
+            a < cat
+        with pytest.raises(TypeError, match=msg):
+            a < cat_rev
+
+    @pytest.mark.parametrize(
+        "ctor",
+        [
+            lambda *args, **kwargs: Categorical(*args, **kwargs),
+            lambda *args, **kwargs: Series(Categorical(*args, **kwargs)),
+        ],
+    )
+    def test_unordered_different_order_equal(self, ctor):
+        # https://github.com/pandas-dev/pandas/issues/16014
+        c1 = ctor(["a", "b"], categories=["a", "b"], ordered=False)
+        c2 = ctor(["a", "b"], categories=["b", "a"], ordered=False)
+        assert (c1 == c2).all()
+
+        c1 = ctor(["a", "b"], categories=["a", "b"], ordered=False)
+        c2 = ctor(["b", "a"], categories=["b", "a"], ordered=False)
+        assert (c1 != c2).all()
+
+        c1 = ctor(["a", "a"], categories=["a", "b"], ordered=False)
+        c2 = ctor(["b", "b"], categories=["b", "a"], ordered=False)
+        assert (c1 != c2).all()
+
+        c1 = ctor(["a", "a"], categories=["a", "b"], ordered=False)
+        c2 = ctor(["a", "b"], categories=["b", "a"], ordered=False)
+        result = c1 == c2
+        tm.assert_numpy_array_equal(np.array(result), np.array([True, False]))
+
+    def test_unordered_different_categories_raises(self):
+        c1 = Categorical(["a", "b"], categories=["a", "b"], ordered=False)
+        c2 = Categorical(["a", "c"], categories=["c", "a"], ordered=False)
+
+        with pytest.raises(TypeError, match=("Categoricals can only be compared")):
+            c1 == c2
+
+    def test_compare_different_lengths(self):
+        c1 = Categorical([], categories=["a", "b"])
+        c2 = Categorical([], categories=["a"])
+
+        msg = "Categoricals can only be compared if 'categories' are the same."
+        with pytest.raises(TypeError, match=msg):
+            c1 == c2
+
+    def test_compare_unordered_different_order(self):
+        # https://github.com/pandas-dev/pandas/issues/16603#issuecomment-
+        # 349290078
+        a = Categorical(["a"], categories=["a", "b"])
+        b = Categorical(["b"], categories=["b", "a"])
+        assert not a.equals(b)
+
+    def test_numeric_like_ops(self):
+        df = DataFrame({"value": np.random.default_rng(2).integers(0, 10000, 100)})
+        labels = [f"{i} - {i + 499}" for i in range(0, 10000, 500)]
+        cat_labels = Categorical(labels, labels)
+
+        df = df.sort_values(by=["value"], ascending=True)
+        df["value_group"] = pd.cut(
+            df.value, range(0, 10500, 500), right=False, labels=cat_labels
+        )
+
+        # numeric ops should not succeed
+        for op, str_rep in [
+            ("__add__", r"\+"),
+            ("__sub__", "-"),
+            ("__mul__", r"\*"),
+            ("__truediv__", "/"),
+        ]:
+            msg = f"Series cannot perform the operation {str_rep}|unsupported operand"
+            with pytest.raises(TypeError, match=msg):
+                getattr(df, op)(df)
+
+        # reduction ops should not succeed (unless specifically defined, e.g.
+        # min/max)
+        s = df["value_group"]
+        for op in ["kurt", "skew", "var", "std", "mean", "sum", "median"]:
+            msg = f"does not support reduction '{op}'"
+            with pytest.raises(TypeError, match=msg):
+                getattr(s, op)(numeric_only=False)
+
+    def test_numeric_like_ops_series(self):
+        # numpy ops
+        s = Series(Categorical([1, 2, 3, 4]))
+        with pytest.raises(TypeError, match="does not support reduction 'sum'"):
+            np.sum(s)
+
+    @pytest.mark.parametrize(
+        "op, str_rep",
+        [
+            ("__add__", r"\+"),
+            ("__sub__", "-"),
+            ("__mul__", r"\*"),
+            ("__truediv__", "/"),
+        ],
+    )
+    def test_numeric_like_ops_series_arith(self, op, str_rep):
+        # numeric ops on a Series
+        s = Series(Categorical([1, 2, 3, 4]))
+        msg = f"Series cannot perform the operation {str_rep}|unsupported operand"
+        with pytest.raises(TypeError, match=msg):
+            getattr(s, op)(2)
+
+    def test_numeric_like_ops_series_invalid(self):
+        # invalid ufunc
+        s = Series(Categorical([1, 2, 3, 4]))
+        msg = "Object with dtype category cannot perform the numpy op log"
+        with pytest.raises(TypeError, match=msg):
+            np.log(s)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_replace.py

@@ -0,0 +1,111 @@
+import pytest
+
+import pandas as pd
+from pandas import Categorical
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "to_replace,value,expected,flip_categories",
+    [
+        # one-to-one
+        (1, 2, [2, 2, 3], False),
+        (1, 4, [4, 2, 3], False),
+        (4, 1, [1, 2, 3], False),
+        (5, 6, [1, 2, 3], False),
+        # many-to-one
+        ([1], 2, [2, 2, 3], False),
+        ([1, 2], 3, [3, 3, 3], False),
+        ([1, 2], 4, [4, 4, 3], False),
+        ((1, 2, 4), 5, [5, 5, 3], False),
+        ((5, 6), 2, [1, 2, 3], False),
+        ([1], [2], [2, 2, 3], False),
+        ([1, 4], [5, 2], [5, 2, 3], False),
+        # GH49404: overlap between to_replace and value
+        ([1, 2, 3], [2, 3, 4], [2, 3, 4], False),
+        # GH50872, GH46884: replace with null
+        (1, None, [None, 2, 3], False),
+        (1, pd.NA, [None, 2, 3], False),
+        # check_categorical sorts categories, which crashes on mixed dtypes
+        (3, "4", [1, 2, "4"], False),
+        ([1, 2, "3"], "5", ["5", "5", 3], True),
+    ],
+)
+@pytest.mark.filterwarnings(
+    "ignore:.*with CategoricalDtype is deprecated:FutureWarning"
+)
+def test_replace_categorical_series(to_replace, value, expected, flip_categories):
+    # GH 31720
+
+    ser = pd.Series([1, 2, 3], dtype="category")
+    result = ser.replace(to_replace, value)
+    expected = pd.Series(expected, dtype="category")
+    ser.replace(to_replace, value, inplace=True)
+
+    if flip_categories:
+        expected = expected.cat.set_categories(expected.cat.categories[::-1])
+
+    tm.assert_series_equal(expected, result, check_category_order=False)
+    tm.assert_series_equal(expected, ser, check_category_order=False)
+
+
+@pytest.mark.parametrize(
+    "to_replace, value, result, expected_error_msg",
+    [
+        ("b", "c", ["a", "c"], "Categorical.categories are different"),
+        ("c", "d", ["a", "b"], None),
+        # https://github.com/pandas-dev/pandas/issues/33288
+        ("a", "a", ["a", "b"], None),
+        ("b", None, ["a", None], "Categorical.categories length are different"),
+    ],
+)
+def test_replace_categorical(to_replace, value, result, expected_error_msg):
+    # GH#26988
+    cat = Categorical(["a", "b"])
+    expected = Categorical(result)
+    msg = (
+        r"The behavior of Series\.replace \(and DataFrame.replace\) "
+        "with CategoricalDtype"
+    )
+    warn = FutureWarning if expected_error_msg is not None else None
+    with tm.assert_produces_warning(warn, match=msg):
+        result = pd.Series(cat, copy=False).replace(to_replace, value)._values
+
+    tm.assert_categorical_equal(result, expected)
+    if to_replace == "b":  # the "c" test is supposed to be unchanged
+        with pytest.raises(AssertionError, match=expected_error_msg):
+            # ensure non-inplace call does not affect original
+            tm.assert_categorical_equal(cat, expected)
+
+    ser = pd.Series(cat, copy=False)
+    with tm.assert_produces_warning(warn, match=msg):
+        ser.replace(to_replace, value, inplace=True)
+    tm.assert_categorical_equal(cat, expected)
+
+
+def test_replace_categorical_ea_dtype():
+    # GH49404
+    cat = Categorical(pd.array(["a", "b"], dtype="string"))
+    msg = (
+        r"The behavior of Series\.replace \(and DataFrame.replace\) "
+        "with CategoricalDtype"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = pd.Series(cat).replace(["a", "b"], ["c", pd.NA])._values
+    expected = Categorical(pd.array(["c", pd.NA], dtype="string"))
+    tm.assert_categorical_equal(result, expected)
+
+
+def test_replace_maintain_ordering():
+    # GH51016
+    dtype = pd.CategoricalDtype([0, 1, 2], ordered=True)
+    ser = pd.Series([0, 1, 2], dtype=dtype)
+    msg = (
+        r"The behavior of Series\.replace \(and DataFrame.replace\) "
+        "with CategoricalDtype"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = ser.replace(0, 2)
+    expected_dtype = pd.CategoricalDtype([1, 2], ordered=True)
+    expected = pd.Series([2, 1, 2], dtype=expected_dtype)
+    tm.assert_series_equal(expected, result, check_category_order=True)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_repr.py

@@ -0,0 +1,550 @@
+import numpy as np
+import pytest
+
+from pandas._config import using_pyarrow_string_dtype
+
+from pandas import (
+    Categorical,
+    CategoricalDtype,
+    CategoricalIndex,
+    Index,
+    Series,
+    date_range,
+    option_context,
+    period_range,
+    timedelta_range,
+)
+
+
+class TestCategoricalReprWithFactor:
+    def test_print(self, using_infer_string):
+        factor = Categorical(["a", "b", "b", "a", "a", "c", "c", "c"], ordered=True)
+        if using_infer_string:
+            expected = [
+                "['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c']",
+                "Categories (3, string): [a < b < c]",
+            ]
+        else:
+            expected = [
+                "['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c']",
+                "Categories (3, object): ['a' < 'b' < 'c']",
+            ]
+        expected = "\n".join(expected)
+        actual = repr(factor)
+        assert actual == expected
+
+
+class TestCategoricalRepr:
+    def test_big_print(self):
+        codes = np.array([0, 1, 2, 0, 1, 2] * 100)
+        dtype = CategoricalDtype(categories=Index(["a", "b", "c"], dtype=object))
+        factor = Categorical.from_codes(codes, dtype=dtype)
+        expected = [
+            "['a', 'b', 'c', 'a', 'b', ..., 'b', 'c', 'a', 'b', 'c']",
+            "Length: 600",
+            "Categories (3, object): ['a', 'b', 'c']",
+        ]
+        expected = "\n".join(expected)
+
+        actual = repr(factor)
+
+        assert actual == expected
+
+    def test_empty_print(self):
+        factor = Categorical([], Index(["a", "b", "c"], dtype=object))
+        expected = "[], Categories (3, object): ['a', 'b', 'c']"
+        actual = repr(factor)
+        assert actual == expected
+
+        assert expected == actual
+        factor = Categorical([], Index(["a", "b", "c"], dtype=object), ordered=True)
+        expected = "[], Categories (3, object): ['a' < 'b' < 'c']"
+        actual = repr(factor)
+        assert expected == actual
+
+        factor = Categorical([], [])
+        expected = "[], Categories (0, object): []"
+        assert expected == repr(factor)
+
+    def test_print_none_width(self):
+        # GH10087
+        a = Series(Categorical([1, 2, 3, 4]))
+        exp = (
+            "0    1\n1    2\n2    3\n3    4\n"
+            "dtype: category\nCategories (4, int64): [1, 2, 3, 4]"
+        )
+
+        with option_context("display.width", None):
+            assert exp == repr(a)
+
+    @pytest.mark.skipif(
+        using_pyarrow_string_dtype(),
+        reason="Change once infer_string is set to True by default",
+    )
+    def test_unicode_print(self):
+        c = Categorical(["aaaaa", "bb", "cccc"] * 20)
+        expected = """\
+['aaaaa', 'bb', 'cccc', 'aaaaa', 'bb', ..., 'bb', 'cccc', 'aaaaa', 'bb', 'cccc']
+Length: 60
+Categories (3, object): ['aaaaa', 'bb', 'cccc']"""
+
+        assert repr(c) == expected
+
+        c = Categorical(["ああああ", "いいいいい", "ううううううう"] * 20)
+        expected = """\
+['ああああ', 'いいいいい', 'ううううううう', 'ああああ', 'いいいいい', ..., 'いいいいい', 'ううううううう', 'ああああ', 'いいいいい', 'ううううううう']
+Length: 60
+Categories (3, object): ['ああああ', 'いいいいい', 'ううううううう']"""  # noqa: E501
+
+        assert repr(c) == expected
+
+        # unicode option should not affect to Categorical, as it doesn't care
+        # the repr width
+        with option_context("display.unicode.east_asian_width", True):
+            c = Categorical(["ああああ", "いいいいい", "ううううううう"] * 20)
+            expected = """['ああああ', 'いいいいい', 'ううううううう', 'ああああ', 'いいいいい', ..., 'いいいいい', 'ううううううう', 'ああああ', 'いいいいい', 'ううううううう']
+Length: 60
+Categories (3, object): ['ああああ', 'いいいいい', 'ううううううう']"""  # noqa: E501
+
+            assert repr(c) == expected
+
+    def test_categorical_repr(self):
+        c = Categorical([1, 2, 3])
+        exp = """[1, 2, 3]
+Categories (3, int64): [1, 2, 3]"""
+
+        assert repr(c) == exp
+
+        c = Categorical([1, 2, 3, 1, 2, 3], categories=[1, 2, 3])
+        exp = """[1, 2, 3, 1, 2, 3]
+Categories (3, int64): [1, 2, 3]"""
+
+        assert repr(c) == exp
+
+        c = Categorical([1, 2, 3, 4, 5] * 10)
+        exp = """[1, 2, 3, 4, 5, ..., 1, 2, 3, 4, 5]
+Length: 50
+Categories (5, int64): [1, 2, 3, 4, 5]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(np.arange(20, dtype=np.int64))
+        exp = """[0, 1, 2, 3, 4, ..., 15, 16, 17, 18, 19]
+Length: 20
+Categories (20, int64): [0, 1, 2, 3, ..., 16, 17, 18, 19]"""
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_ordered(self):
+        c = Categorical([1, 2, 3], ordered=True)
+        exp = """[1, 2, 3]
+Categories (3, int64): [1 < 2 < 3]"""
+
+        assert repr(c) == exp
+
+        c = Categorical([1, 2, 3, 1, 2, 3], categories=[1, 2, 3], ordered=True)
+        exp = """[1, 2, 3, 1, 2, 3]
+Categories (3, int64): [1 < 2 < 3]"""
+
+        assert repr(c) == exp
+
+        c = Categorical([1, 2, 3, 4, 5] * 10, ordered=True)
+        exp = """[1, 2, 3, 4, 5, ..., 1, 2, 3, 4, 5]
+Length: 50
+Categories (5, int64): [1 < 2 < 3 < 4 < 5]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(np.arange(20, dtype=np.int64), ordered=True)
+        exp = """[0, 1, 2, 3, 4, ..., 15, 16, 17, 18, 19]
+Length: 20
+Categories (20, int64): [0 < 1 < 2 < 3 ... 16 < 17 < 18 < 19]"""
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_datetime(self):
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5)
+        c = Categorical(idx)
+
+        exp = (
+            "[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, "
+            "2011-01-01 12:00:00, 2011-01-01 13:00:00]\n"
+            "Categories (5, datetime64[ns]): [2011-01-01 09:00:00, "
+            "2011-01-01 10:00:00, 2011-01-01 11:00:00,\n"
+            "                                 2011-01-01 12:00:00, "
+            "2011-01-01 13:00:00]"
+            ""
+        )
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = (
+            "[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, "
+            "2011-01-01 12:00:00, 2011-01-01 13:00:00, 2011-01-01 09:00:00, "
+            "2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, "
+            "2011-01-01 13:00:00]\n"
+            "Categories (5, datetime64[ns]): [2011-01-01 09:00:00, "
+            "2011-01-01 10:00:00, 2011-01-01 11:00:00,\n"
+            "                                 2011-01-01 12:00:00, "
+            "2011-01-01 13:00:00]"
+        )
+
+        assert repr(c) == exp
+
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5, tz="US/Eastern")
+        c = Categorical(idx)
+        exp = (
+            "[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, "
+            "2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, "
+            "2011-01-01 13:00:00-05:00]\n"
+            "Categories (5, datetime64[ns, US/Eastern]): "
+            "[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00,\n"
+            "                                             "
+            "2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00,\n"
+            "                                             "
+            "2011-01-01 13:00:00-05:00]"
+        )
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = (
+            "[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, "
+            "2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, "
+            "2011-01-01 13:00:00-05:00, 2011-01-01 09:00:00-05:00, "
+            "2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, "
+            "2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00]\n"
+            "Categories (5, datetime64[ns, US/Eastern]): "
+            "[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00,\n"
+            "                                             "
+            "2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00,\n"
+            "                                             "
+            "2011-01-01 13:00:00-05:00]"
+        )
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_datetime_ordered(self):
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5)
+        c = Categorical(idx, ordered=True)
+        exp = """[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, 2011-01-01 13:00:00]
+Categories (5, datetime64[ns]): [2011-01-01 09:00:00 < 2011-01-01 10:00:00 < 2011-01-01 11:00:00 <
+                                 2011-01-01 12:00:00 < 2011-01-01 13:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, 2011-01-01 13:00:00, 2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, 2011-01-01 13:00:00]
+Categories (5, datetime64[ns]): [2011-01-01 09:00:00 < 2011-01-01 10:00:00 < 2011-01-01 11:00:00 <
+                                 2011-01-01 12:00:00 < 2011-01-01 13:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5, tz="US/Eastern")
+        c = Categorical(idx, ordered=True)
+        exp = """[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00]
+Categories (5, datetime64[ns, US/Eastern]): [2011-01-01 09:00:00-05:00 < 2011-01-01 10:00:00-05:00 <
+                                             2011-01-01 11:00:00-05:00 < 2011-01-01 12:00:00-05:00 <
+                                             2011-01-01 13:00:00-05:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00, 2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00]
+Categories (5, datetime64[ns, US/Eastern]): [2011-01-01 09:00:00-05:00 < 2011-01-01 10:00:00-05:00 <
+                                             2011-01-01 11:00:00-05:00 < 2011-01-01 12:00:00-05:00 <
+                                             2011-01-01 13:00:00-05:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_int_with_nan(self):
+        c = Categorical([1, 2, np.nan])
+        c_exp = """[1, 2, NaN]\nCategories (2, int64): [1, 2]"""
+        assert repr(c) == c_exp
+
+        s = Series([1, 2, np.nan], dtype="object").astype("category")
+        s_exp = """0      1\n1      2\n2    NaN
+dtype: category
+Categories (2, int64): [1, 2]"""
+        assert repr(s) == s_exp
+
+    def test_categorical_repr_period(self):
+        idx = period_range("2011-01-01 09:00", freq="h", periods=5)
+        c = Categorical(idx)
+        exp = """[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00]
+Categories (5, period[h]): [2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00,
+                            2011-01-01 13:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = """[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00, 2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00]
+Categories (5, period[h]): [2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00,
+                            2011-01-01 13:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        idx = period_range("2011-01", freq="M", periods=5)
+        c = Categorical(idx)
+        exp = """[2011-01, 2011-02, 2011-03, 2011-04, 2011-05]
+Categories (5, period[M]): [2011-01, 2011-02, 2011-03, 2011-04, 2011-05]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = """[2011-01, 2011-02, 2011-03, 2011-04, 2011-05, 2011-01, 2011-02, 2011-03, 2011-04, 2011-05]
+Categories (5, period[M]): [2011-01, 2011-02, 2011-03, 2011-04, 2011-05]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_period_ordered(self):
+        idx = period_range("2011-01-01 09:00", freq="h", periods=5)
+        c = Categorical(idx, ordered=True)
+        exp = """[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00]
+Categories (5, period[h]): [2011-01-01 09:00 < 2011-01-01 10:00 < 2011-01-01 11:00 < 2011-01-01 12:00 <
+                            2011-01-01 13:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00, 2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00]
+Categories (5, period[h]): [2011-01-01 09:00 < 2011-01-01 10:00 < 2011-01-01 11:00 < 2011-01-01 12:00 <
+                            2011-01-01 13:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        idx = period_range("2011-01", freq="M", periods=5)
+        c = Categorical(idx, ordered=True)
+        exp = """[2011-01, 2011-02, 2011-03, 2011-04, 2011-05]
+Categories (5, period[M]): [2011-01 < 2011-02 < 2011-03 < 2011-04 < 2011-05]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[2011-01, 2011-02, 2011-03, 2011-04, 2011-05, 2011-01, 2011-02, 2011-03, 2011-04, 2011-05]
+Categories (5, period[M]): [2011-01 < 2011-02 < 2011-03 < 2011-04 < 2011-05]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_timedelta(self):
+        idx = timedelta_range("1 days", periods=5)
+        c = Categorical(idx)
+        exp = """[1 days, 2 days, 3 days, 4 days, 5 days]
+Categories (5, timedelta64[ns]): [1 days, 2 days, 3 days, 4 days, 5 days]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = """[1 days, 2 days, 3 days, 4 days, 5 days, 1 days, 2 days, 3 days, 4 days, 5 days]
+Categories (5, timedelta64[ns]): [1 days, 2 days, 3 days, 4 days, 5 days]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        idx = timedelta_range("1 hours", periods=20)
+        c = Categorical(idx)
+        exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
+Length: 20
+Categories (20, timedelta64[ns]): [0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00,
+                                   3 days 01:00:00, ..., 16 days 01:00:00, 17 days 01:00:00,
+                                   18 days 01:00:00, 19 days 01:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx)
+        exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
+Length: 40
+Categories (20, timedelta64[ns]): [0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00,
+                                   3 days 01:00:00, ..., 16 days 01:00:00, 17 days 01:00:00,
+                                   18 days 01:00:00, 19 days 01:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+    def test_categorical_repr_timedelta_ordered(self):
+        idx = timedelta_range("1 days", periods=5)
+        c = Categorical(idx, ordered=True)
+        exp = """[1 days, 2 days, 3 days, 4 days, 5 days]
+Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[1 days, 2 days, 3 days, 4 days, 5 days, 1 days, 2 days, 3 days, 4 days, 5 days]
+Categories (5, timedelta64[ns]): [1 days < 2 days < 3 days < 4 days < 5 days]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        idx = timedelta_range("1 hours", periods=20)
+        c = Categorical(idx, ordered=True)
+        exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
+Length: 20
+Categories (20, timedelta64[ns]): [0 days 01:00:00 < 1 days 01:00:00 < 2 days 01:00:00 <
+                                   3 days 01:00:00 ... 16 days 01:00:00 < 17 days 01:00:00 <
+                                   18 days 01:00:00 < 19 days 01:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+        c = Categorical(idx.append(idx), categories=idx, ordered=True)
+        exp = """[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, 4 days 01:00:00, ..., 15 days 01:00:00, 16 days 01:00:00, 17 days 01:00:00, 18 days 01:00:00, 19 days 01:00:00]
+Length: 40
+Categories (20, timedelta64[ns]): [0 days 01:00:00 < 1 days 01:00:00 < 2 days 01:00:00 <
+                                   3 days 01:00:00 ... 16 days 01:00:00 < 17 days 01:00:00 <
+                                   18 days 01:00:00 < 19 days 01:00:00]"""  # noqa: E501
+
+        assert repr(c) == exp
+
+    def test_categorical_index_repr(self):
+        idx = CategoricalIndex(Categorical([1, 2, 3]))
+        exp = """CategoricalIndex([1, 2, 3], categories=[1, 2, 3], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(idx) == exp
+
+        i = CategoricalIndex(Categorical(np.arange(10, dtype=np.int64)))
+        exp = """CategoricalIndex([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], categories=[0, 1, 2, 3, ..., 6, 7, 8, 9], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_ordered(self):
+        i = CategoricalIndex(Categorical([1, 2, 3], ordered=True))
+        exp = """CategoricalIndex([1, 2, 3], categories=[1, 2, 3], ordered=True, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        i = CategoricalIndex(Categorical(np.arange(10, dtype=np.int64), ordered=True))
+        exp = """CategoricalIndex([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], categories=[0, 1, 2, 3, ..., 6, 7, 8, 9], ordered=True, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_datetime(self):
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00:00', '2011-01-01 10:00:00',
+                  '2011-01-01 11:00:00', '2011-01-01 12:00:00',
+                  '2011-01-01 13:00:00'],
+                 categories=[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, 2011-01-01 13:00:00], ordered=False, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5, tz="US/Eastern")
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00:00-05:00', '2011-01-01 10:00:00-05:00',
+                  '2011-01-01 11:00:00-05:00', '2011-01-01 12:00:00-05:00',
+                  '2011-01-01 13:00:00-05:00'],
+                 categories=[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00], ordered=False, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_datetime_ordered(self):
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5)
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['2011-01-01 09:00:00', '2011-01-01 10:00:00',
+                  '2011-01-01 11:00:00', '2011-01-01 12:00:00',
+                  '2011-01-01 13:00:00'],
+                 categories=[2011-01-01 09:00:00, 2011-01-01 10:00:00, 2011-01-01 11:00:00, 2011-01-01 12:00:00, 2011-01-01 13:00:00], ordered=True, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        idx = date_range("2011-01-01 09:00", freq="h", periods=5, tz="US/Eastern")
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['2011-01-01 09:00:00-05:00', '2011-01-01 10:00:00-05:00',
+                  '2011-01-01 11:00:00-05:00', '2011-01-01 12:00:00-05:00',
+                  '2011-01-01 13:00:00-05:00'],
+                 categories=[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00], ordered=True, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        i = CategoricalIndex(Categorical(idx.append(idx), ordered=True))
+        exp = """CategoricalIndex(['2011-01-01 09:00:00-05:00', '2011-01-01 10:00:00-05:00',
+                  '2011-01-01 11:00:00-05:00', '2011-01-01 12:00:00-05:00',
+                  '2011-01-01 13:00:00-05:00', '2011-01-01 09:00:00-05:00',
+                  '2011-01-01 10:00:00-05:00', '2011-01-01 11:00:00-05:00',
+                  '2011-01-01 12:00:00-05:00', '2011-01-01 13:00:00-05:00'],
+                 categories=[2011-01-01 09:00:00-05:00, 2011-01-01 10:00:00-05:00, 2011-01-01 11:00:00-05:00, 2011-01-01 12:00:00-05:00, 2011-01-01 13:00:00-05:00], ordered=True, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_period(self):
+        # test all length
+        idx = period_range("2011-01-01 09:00", freq="h", periods=1)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00'], categories=[2011-01-01 09:00], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        idx = period_range("2011-01-01 09:00", freq="h", periods=2)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00', '2011-01-01 10:00'], categories=[2011-01-01 09:00, 2011-01-01 10:00], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        idx = period_range("2011-01-01 09:00", freq="h", periods=3)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00', '2011-01-01 10:00', '2011-01-01 11:00'], categories=[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        idx = period_range("2011-01-01 09:00", freq="h", periods=5)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01-01 09:00', '2011-01-01 10:00', '2011-01-01 11:00',
+                  '2011-01-01 12:00', '2011-01-01 13:00'],
+                 categories=[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00], ordered=False, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        i = CategoricalIndex(Categorical(idx.append(idx)))
+        exp = """CategoricalIndex(['2011-01-01 09:00', '2011-01-01 10:00', '2011-01-01 11:00',
+                  '2011-01-01 12:00', '2011-01-01 13:00', '2011-01-01 09:00',
+                  '2011-01-01 10:00', '2011-01-01 11:00', '2011-01-01 12:00',
+                  '2011-01-01 13:00'],
+                 categories=[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00], ordered=False, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        idx = period_range("2011-01", freq="M", periods=5)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['2011-01', '2011-02', '2011-03', '2011-04', '2011-05'], categories=[2011-01, 2011-02, 2011-03, 2011-04, 2011-05], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_period_ordered(self):
+        idx = period_range("2011-01-01 09:00", freq="h", periods=5)
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['2011-01-01 09:00', '2011-01-01 10:00', '2011-01-01 11:00',
+                  '2011-01-01 12:00', '2011-01-01 13:00'],
+                 categories=[2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00, 2011-01-01 13:00], ordered=True, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+        idx = period_range("2011-01", freq="M", periods=5)
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['2011-01', '2011-02', '2011-03', '2011-04', '2011-05'], categories=[2011-01, 2011-02, 2011-03, 2011-04, 2011-05], ordered=True, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_timedelta(self):
+        idx = timedelta_range("1 days", periods=5)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['1 days', '2 days', '3 days', '4 days', '5 days'], categories=[1 days, 2 days, 3 days, 4 days, 5 days], ordered=False, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        idx = timedelta_range("1 hours", periods=10)
+        i = CategoricalIndex(Categorical(idx))
+        exp = """CategoricalIndex(['0 days 01:00:00', '1 days 01:00:00', '2 days 01:00:00',
+                  '3 days 01:00:00', '4 days 01:00:00', '5 days 01:00:00',
+                  '6 days 01:00:00', '7 days 01:00:00', '8 days 01:00:00',
+                  '9 days 01:00:00'],
+                 categories=[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, ..., 6 days 01:00:00, 7 days 01:00:00, 8 days 01:00:00, 9 days 01:00:00], ordered=False, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+    def test_categorical_index_repr_timedelta_ordered(self):
+        idx = timedelta_range("1 days", periods=5)
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['1 days', '2 days', '3 days', '4 days', '5 days'], categories=[1 days, 2 days, 3 days, 4 days, 5 days], ordered=True, dtype='category')"""  # noqa: E501
+        assert repr(i) == exp
+
+        idx = timedelta_range("1 hours", periods=10)
+        i = CategoricalIndex(Categorical(idx, ordered=True))
+        exp = """CategoricalIndex(['0 days 01:00:00', '1 days 01:00:00', '2 days 01:00:00',
+                  '3 days 01:00:00', '4 days 01:00:00', '5 days 01:00:00',
+                  '6 days 01:00:00', '7 days 01:00:00', '8 days 01:00:00',
+                  '9 days 01:00:00'],
+                 categories=[0 days 01:00:00, 1 days 01:00:00, 2 days 01:00:00, 3 days 01:00:00, ..., 6 days 01:00:00, 7 days 01:00:00, 8 days 01:00:00, 9 days 01:00:00], ordered=True, dtype='category')"""  # noqa: E501
+
+        assert repr(i) == exp
+
+    def test_categorical_str_repr(self):
+        # GH 33676
+        result = repr(Categorical([1, "2", 3, 4]))
+        expected = "[1, '2', 3, 4]\nCategories (4, object): [1, 3, 4, '2']"
+        assert result == expected

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_sorting.py

@@ -0,0 +1,128 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    Categorical,
+    Index,
+)
+import pandas._testing as tm
+
+
+class TestCategoricalSort:
+    def test_argsort(self):
+        c = Categorical([5, 3, 1, 4, 2], ordered=True)
+
+        expected = np.array([2, 4, 1, 3, 0])
+        tm.assert_numpy_array_equal(
+            c.argsort(ascending=True), expected, check_dtype=False
+        )
+
+        expected = expected[::-1]
+        tm.assert_numpy_array_equal(
+            c.argsort(ascending=False), expected, check_dtype=False
+        )
+
+    def test_numpy_argsort(self):
+        c = Categorical([5, 3, 1, 4, 2], ordered=True)
+
+        expected = np.array([2, 4, 1, 3, 0])
+        tm.assert_numpy_array_equal(np.argsort(c), expected, check_dtype=False)
+
+        tm.assert_numpy_array_equal(
+            np.argsort(c, kind="mergesort"), expected, check_dtype=False
+        )
+
+        msg = "the 'axis' parameter is not supported"
+        with pytest.raises(ValueError, match=msg):
+            np.argsort(c, axis=0)
+
+        msg = "the 'order' parameter is not supported"
+        with pytest.raises(ValueError, match=msg):
+            np.argsort(c, order="C")
+
+    def test_sort_values(self):
+        # unordered cats are sortable
+        cat = Categorical(["a", "b", "b", "a"], ordered=False)
+        cat.sort_values()
+
+        cat = Categorical(["a", "c", "b", "d"], ordered=True)
+
+        # sort_values
+        res = cat.sort_values()
+        exp = np.array(["a", "b", "c", "d"], dtype=object)
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, cat.categories)
+
+        cat = Categorical(
+            ["a", "c", "b", "d"], categories=["a", "b", "c", "d"], ordered=True
+        )
+        res = cat.sort_values()
+        exp = np.array(["a", "b", "c", "d"], dtype=object)
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, cat.categories)
+
+        res = cat.sort_values(ascending=False)
+        exp = np.array(["d", "c", "b", "a"], dtype=object)
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, cat.categories)
+
+        # sort (inplace order)
+        cat1 = cat.copy()
+        orig_codes = cat1._codes
+        cat1.sort_values(inplace=True)
+        assert cat1._codes is orig_codes
+        exp = np.array(["a", "b", "c", "d"], dtype=object)
+        tm.assert_numpy_array_equal(cat1.__array__(), exp)
+        tm.assert_index_equal(res.categories, cat.categories)
+
+        # reverse
+        cat = Categorical(["a", "c", "c", "b", "d"], ordered=True)
+        res = cat.sort_values(ascending=False)
+        exp_val = np.array(["d", "c", "c", "b", "a"], dtype=object)
+        exp_categories = Index(["a", "b", "c", "d"])
+        tm.assert_numpy_array_equal(res.__array__(), exp_val)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+    def test_sort_values_na_position(self):
+        # see gh-12882
+        cat = Categorical([5, 2, np.nan, 2, np.nan], ordered=True)
+        exp_categories = Index([2, 5])
+
+        exp = np.array([2.0, 2.0, 5.0, np.nan, np.nan])
+        res = cat.sort_values()  # default arguments
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        exp = np.array([np.nan, np.nan, 2.0, 2.0, 5.0])
+        res = cat.sort_values(ascending=True, na_position="first")
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        exp = np.array([np.nan, np.nan, 5.0, 2.0, 2.0])
+        res = cat.sort_values(ascending=False, na_position="first")
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        exp = np.array([2.0, 2.0, 5.0, np.nan, np.nan])
+        res = cat.sort_values(ascending=True, na_position="last")
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        exp = np.array([5.0, 2.0, 2.0, np.nan, np.nan])
+        res = cat.sort_values(ascending=False, na_position="last")
+        tm.assert_numpy_array_equal(res.__array__(), exp)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        cat = Categorical(["a", "c", "b", "d", np.nan], ordered=True)
+        res = cat.sort_values(ascending=False, na_position="last")
+        exp_val = np.array(["d", "c", "b", "a", np.nan], dtype=object)
+        exp_categories = Index(["a", "b", "c", "d"])
+        tm.assert_numpy_array_equal(res.__array__(), exp_val)
+        tm.assert_index_equal(res.categories, exp_categories)
+
+        cat = Categorical(["a", "c", "b", "d", np.nan], ordered=True)
+        res = cat.sort_values(ascending=False, na_position="first")
+        exp_val = np.array([np.nan, "d", "c", "b", "a"], dtype=object)
+        exp_categories = Index(["a", "b", "c", "d"])
+        tm.assert_numpy_array_equal(res.__array__(), exp_val)
+        tm.assert_index_equal(res.categories, exp_categories)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_subclass.py

@@ -0,0 +1,26 @@
+from pandas import Categorical
+import pandas._testing as tm
+
+
+class SubclassedCategorical(Categorical):
+    pass
+
+
+class TestCategoricalSubclassing:
+    def test_constructor(self):
+        sc = SubclassedCategorical(["a", "b", "c"])
+        assert isinstance(sc, SubclassedCategorical)
+        tm.assert_categorical_equal(sc, Categorical(["a", "b", "c"]))
+
+    def test_from_codes(self):
+        sc = SubclassedCategorical.from_codes([1, 0, 2], ["a", "b", "c"])
+        assert isinstance(sc, SubclassedCategorical)
+        exp = Categorical.from_codes([1, 0, 2], ["a", "b", "c"])
+        tm.assert_categorical_equal(sc, exp)
+
+    def test_map(self):
+        sc = SubclassedCategorical(["a", "b", "c"])
+        res = sc.map(lambda x: x.upper(), na_action=None)
+        assert isinstance(res, SubclassedCategorical)
+        exp = Categorical(["A", "B", "C"])
+        tm.assert_categorical_equal(res, exp)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_take.py

@@ -0,0 +1,89 @@
+import numpy as np
+import pytest
+
+from pandas import Categorical
+import pandas._testing as tm
+
+
+@pytest.fixture(params=[True, False])
+def allow_fill(request):
+    """Boolean 'allow_fill' parameter for Categorical.take"""
+    return request.param
+
+
+class TestTake:
+    # https://github.com/pandas-dev/pandas/issues/20664
+
+    def test_take_default_allow_fill(self):
+        cat = Categorical(["a", "b"])
+        with tm.assert_produces_warning(None):
+            result = cat.take([0, -1])
+
+        assert result.equals(cat)
+
+    def test_take_positive_no_warning(self):
+        cat = Categorical(["a", "b"])
+        with tm.assert_produces_warning(None):
+            cat.take([0, 0])
+
+    def test_take_bounds(self, allow_fill):
+        # https://github.com/pandas-dev/pandas/issues/20664
+        cat = Categorical(["a", "b", "a"])
+        if allow_fill:
+            msg = "indices are out-of-bounds"
+        else:
+            msg = "index 4 is out of bounds for( axis 0 with)? size 3"
+        with pytest.raises(IndexError, match=msg):
+            cat.take([4, 5], allow_fill=allow_fill)
+
+    def test_take_empty(self, allow_fill):
+        # https://github.com/pandas-dev/pandas/issues/20664
+        cat = Categorical([], categories=["a", "b"])
+        if allow_fill:
+            msg = "indices are out-of-bounds"
+        else:
+            msg = "cannot do a non-empty take from an empty axes"
+        with pytest.raises(IndexError, match=msg):
+            cat.take([0], allow_fill=allow_fill)
+
+    def test_positional_take(self, ordered):
+        cat = Categorical(["a", "a", "b", "b"], categories=["b", "a"], ordered=ordered)
+        result = cat.take([0, 1, 2], allow_fill=False)
+        expected = Categorical(
+            ["a", "a", "b"], categories=cat.categories, ordered=ordered
+        )
+        tm.assert_categorical_equal(result, expected)
+
+    def test_positional_take_unobserved(self, ordered):
+        cat = Categorical(["a", "b"], categories=["a", "b", "c"], ordered=ordered)
+        result = cat.take([1, 0], allow_fill=False)
+        expected = Categorical(["b", "a"], categories=cat.categories, ordered=ordered)
+        tm.assert_categorical_equal(result, expected)
+
+    def test_take_allow_fill(self):
+        # https://github.com/pandas-dev/pandas/issues/23296
+        cat = Categorical(["a", "a", "b"])
+        result = cat.take([0, -1, -1], allow_fill=True)
+        expected = Categorical(["a", np.nan, np.nan], categories=["a", "b"])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_take_fill_with_negative_one(self):
+        # -1 was a category
+        cat = Categorical([-1, 0, 1])
+        result = cat.take([0, -1, 1], allow_fill=True, fill_value=-1)
+        expected = Categorical([-1, -1, 0], categories=[-1, 0, 1])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_take_fill_value(self):
+        # https://github.com/pandas-dev/pandas/issues/23296
+        cat = Categorical(["a", "b", "c"])
+        result = cat.take([0, 1, -1], fill_value="a", allow_fill=True)
+        expected = Categorical(["a", "b", "a"], categories=["a", "b", "c"])
+        tm.assert_categorical_equal(result, expected)
+
+    def test_take_fill_value_new_raises(self):
+        # https://github.com/pandas-dev/pandas/issues/23296
+        cat = Categorical(["a", "b", "c"])
+        xpr = r"Cannot setitem on a Categorical with a new category \(d\)"
+        with pytest.raises(TypeError, match=xpr):
+            cat.take([0, 1, -1], fill_value="d", allow_fill=True)

lib/python3.13/site-packages/pandas/tests/arrays/categorical/test_warnings.py

@@ -0,0 +1,19 @@
+import pytest
+
+import pandas._testing as tm
+
+
+class TestCategoricalWarnings:
+    def test_tab_complete_warning(self, ip):
+        # https://github.com/pandas-dev/pandas/issues/16409
+        pytest.importorskip("IPython", minversion="6.0.0")
+        from IPython.core.completer import provisionalcompleter
+
+        code = "import pandas as pd; c = pd.Categorical([])"
+        ip.run_cell(code)
+
+        # GH 31324 newer jedi version raises Deprecation warning;
+        #  appears resolved 2021-02-02
+        with tm.assert_produces_warning(None, raise_on_extra_warnings=False):
+            with provisionalcompleter("ignore"):
+                list(ip.Completer.completions("c.", 1))

lib/python3.13/site-packages/pandas/tests/arrays/datetimes/test_constructors.py

@@ -0,0 +1,284 @@
+import numpy as np
+import pytest
+
+from pandas._libs import iNaT
+
+from pandas.core.dtypes.dtypes import DatetimeTZDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import DatetimeArray
+
+
+class TestDatetimeArrayConstructor:
+    def test_from_sequence_invalid_type(self):
+        mi = pd.MultiIndex.from_product([np.arange(5), np.arange(5)])
+        with pytest.raises(TypeError, match="Cannot create a DatetimeArray"):
+            DatetimeArray._from_sequence(mi, dtype="M8[ns]")
+
+    def test_only_1dim_accepted(self):
+        arr = np.array([0, 1, 2, 3], dtype="M8[h]").astype("M8[ns]")
+
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Only 1-dimensional"):
+                # 3-dim, we allow 2D to sneak in for ops purposes GH#29853
+                DatetimeArray(arr.reshape(2, 2, 1))
+
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Only 1-dimensional"):
+                # 0-dim
+                DatetimeArray(arr[[0]].squeeze())
+
+    def test_freq_validation(self):
+        # GH#24623 check that invalid instances cannot be created with the
+        #  public constructor
+        arr = np.arange(5, dtype=np.int64) * 3600 * 10**9
+
+        msg = (
+            "Inferred frequency h from passed values does not "
+            "conform to passed frequency W-SUN"
+        )
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match=msg):
+                DatetimeArray(arr, freq="W")
+
+    @pytest.mark.parametrize(
+        "meth",
+        [
+            DatetimeArray._from_sequence,
+            pd.to_datetime,
+            pd.DatetimeIndex,
+        ],
+    )
+    def test_mixing_naive_tzaware_raises(self, meth):
+        # GH#24569
+        arr = np.array([pd.Timestamp("2000"), pd.Timestamp("2000", tz="CET")])
+
+        msg = (
+            "Cannot mix tz-aware with tz-naive values|"
+            "Tz-aware datetime.datetime cannot be converted "
+            "to datetime64 unless utc=True"
+        )
+
+        for obj in [arr, arr[::-1]]:
+            # check that we raise regardless of whether naive is found
+            #  before aware or vice-versa
+            with pytest.raises(ValueError, match=msg):
+                meth(obj)
+
+    def test_from_pandas_array(self):
+        arr = pd.array(np.arange(5, dtype=np.int64)) * 3600 * 10**9
+
+        result = DatetimeArray._from_sequence(arr, dtype="M8[ns]")._with_freq("infer")
+
+        expected = pd.date_range("1970-01-01", periods=5, freq="h")._data
+        tm.assert_datetime_array_equal(result, expected)
+
+    def test_mismatched_timezone_raises(self):
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            arr = DatetimeArray(
+                np.array(["2000-01-01T06:00:00"], dtype="M8[ns]"),
+                dtype=DatetimeTZDtype(tz="US/Central"),
+            )
+        dtype = DatetimeTZDtype(tz="US/Eastern")
+        msg = r"dtype=datetime64\[ns.*\] does not match data dtype datetime64\[ns.*\]"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(TypeError, match=msg):
+                DatetimeArray(arr, dtype=dtype)
+
+        # also with mismatched tzawareness
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(TypeError, match=msg):
+                DatetimeArray(arr, dtype=np.dtype("M8[ns]"))
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(TypeError, match=msg):
+                DatetimeArray(arr.tz_localize(None), dtype=arr.dtype)
+
+    def test_non_array_raises(self):
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="list"):
+                DatetimeArray([1, 2, 3])
+
+    def test_bool_dtype_raises(self):
+        arr = np.array([1, 2, 3], dtype="bool")
+
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        msg = "Unexpected value for 'dtype': 'bool'. Must be"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match=msg):
+                DatetimeArray(arr)
+
+        msg = r"dtype bool cannot be converted to datetime64\[ns\]"
+        with pytest.raises(TypeError, match=msg):
+            DatetimeArray._from_sequence(arr, dtype="M8[ns]")
+
+        with pytest.raises(TypeError, match=msg):
+            pd.DatetimeIndex(arr)
+
+        with pytest.raises(TypeError, match=msg):
+            pd.to_datetime(arr)
+
+    def test_incorrect_dtype_raises(self):
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Unexpected value for 'dtype'."):
+                DatetimeArray(np.array([1, 2, 3], dtype="i8"), dtype="category")
+
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Unexpected value for 'dtype'."):
+                DatetimeArray(np.array([1, 2, 3], dtype="i8"), dtype="m8[s]")
+
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Unexpected value for 'dtype'."):
+                DatetimeArray(np.array([1, 2, 3], dtype="i8"), dtype="M8[D]")
+
+    def test_mismatched_values_dtype_units(self):
+        arr = np.array([1, 2, 3], dtype="M8[s]")
+        dtype = np.dtype("M8[ns]")
+        msg = "Values resolution does not match dtype."
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match=msg):
+                DatetimeArray(arr, dtype=dtype)
+
+        dtype2 = DatetimeTZDtype(tz="UTC", unit="ns")
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match=msg):
+                DatetimeArray(arr, dtype=dtype2)
+
+    def test_freq_infer_raises(self):
+        depr_msg = "DatetimeArray.__init__ is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            with pytest.raises(ValueError, match="Frequency inference"):
+                DatetimeArray(np.array([1, 2, 3], dtype="i8"), freq="infer")
+
+    def test_copy(self):
+        data = np.array([1, 2, 3], dtype="M8[ns]")
+        arr = DatetimeArray._from_sequence(data, copy=False)
+        assert arr._ndarray is data
+
+        arr = DatetimeArray._from_sequence(data, copy=True)
+        assert arr._ndarray is not data
+
+    @pytest.mark.parametrize("unit", ["s", "ms", "us", "ns"])
+    def test_numpy_datetime_unit(self, unit):
+        data = np.array([1, 2, 3], dtype=f"M8[{unit}]")
+        arr = DatetimeArray._from_sequence(data)
+        assert arr.unit == unit
+        assert arr[0].unit == unit
+
+
+class TestSequenceToDT64NS:
+    def test_tz_dtype_mismatch_raises(self):
+        arr = DatetimeArray._from_sequence(
+            ["2000"], dtype=DatetimeTZDtype(tz="US/Central")
+        )
+        with pytest.raises(TypeError, match="data is already tz-aware"):
+            DatetimeArray._from_sequence(arr, dtype=DatetimeTZDtype(tz="UTC"))
+
+    def test_tz_dtype_matches(self):
+        dtype = DatetimeTZDtype(tz="US/Central")
+        arr = DatetimeArray._from_sequence(["2000"], dtype=dtype)
+        result = DatetimeArray._from_sequence(arr, dtype=dtype)
+        tm.assert_equal(arr, result)
+
+    @pytest.mark.parametrize("order", ["F", "C"])
+    def test_2d(self, order):
+        dti = pd.date_range("2016-01-01", periods=6, tz="US/Pacific")
+        arr = np.array(dti, dtype=object).reshape(3, 2)
+        if order == "F":
+            arr = arr.T
+
+        res = DatetimeArray._from_sequence(arr, dtype=dti.dtype)
+        expected = DatetimeArray._from_sequence(arr.ravel(), dtype=dti.dtype).reshape(
+            arr.shape
+        )
+        tm.assert_datetime_array_equal(res, expected)
+
+
+# ----------------------------------------------------------------------------
+# Arrow interaction
+
+
+EXTREME_VALUES = [0, 123456789, None, iNaT, 2**63 - 1, -(2**63) + 1]
+FINE_TO_COARSE_SAFE = [123_000_000_000, None, -123_000_000_000]
+COARSE_TO_FINE_SAFE = [123, None, -123]
+
+
+@pytest.mark.parametrize(
+    ("pa_unit", "pd_unit", "pa_tz", "pd_tz", "data"),
+    [
+        ("s", "s", "UTC", "UTC", EXTREME_VALUES),
+        ("ms", "ms", "UTC", "Europe/Berlin", EXTREME_VALUES),
+        ("us", "us", "US/Eastern", "UTC", EXTREME_VALUES),
+        ("ns", "ns", "US/Central", "Asia/Kolkata", EXTREME_VALUES),
+        ("ns", "s", "UTC", "UTC", FINE_TO_COARSE_SAFE),
+        ("us", "ms", "UTC", "Europe/Berlin", FINE_TO_COARSE_SAFE),
+        ("ms", "us", "US/Eastern", "UTC", COARSE_TO_FINE_SAFE),
+        ("s", "ns", "US/Central", "Asia/Kolkata", COARSE_TO_FINE_SAFE),
+    ],
+)
+def test_from_arrow_with_different_units_and_timezones_with(
+    pa_unit, pd_unit, pa_tz, pd_tz, data
+):
+    pa = pytest.importorskip("pyarrow")
+
+    pa_type = pa.timestamp(pa_unit, tz=pa_tz)
+    arr = pa.array(data, type=pa_type)
+    dtype = DatetimeTZDtype(unit=pd_unit, tz=pd_tz)
+
+    result = dtype.__from_arrow__(arr)
+    expected = DatetimeArray._from_sequence(data, dtype=f"M8[{pa_unit}, UTC]").astype(
+        dtype, copy=False
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    result = dtype.__from_arrow__(pa.chunked_array([arr]))
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    ("unit", "tz"),
+    [
+        ("s", "UTC"),
+        ("ms", "Europe/Berlin"),
+        ("us", "US/Eastern"),
+        ("ns", "Asia/Kolkata"),
+        ("ns", "UTC"),
+    ],
+)
+def test_from_arrow_from_empty(unit, tz):
+    pa = pytest.importorskip("pyarrow")
+
+    data = []
+    arr = pa.array(data)
+    dtype = DatetimeTZDtype(unit=unit, tz=tz)
+
+    result = dtype.__from_arrow__(arr)
+    expected = DatetimeArray._from_sequence(np.array(data, dtype=f"datetime64[{unit}]"))
+    expected = expected.tz_localize(tz=tz)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = dtype.__from_arrow__(pa.chunked_array([arr]))
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_from_arrow_from_integers():
+    pa = pytest.importorskip("pyarrow")
+
+    data = [0, 123456789, None, 2**63 - 1, iNaT, -123456789]
+    arr = pa.array(data)
+    dtype = DatetimeTZDtype(unit="ns", tz="UTC")
+
+    result = dtype.__from_arrow__(arr)
+    expected = DatetimeArray._from_sequence(np.array(data, dtype="datetime64[ns]"))
+    expected = expected.tz_localize("UTC")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = dtype.__from_arrow__(pa.chunked_array([arr]))
+    tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/datetimes/test_cumulative.py

@@ -0,0 +1,44 @@
+import pytest
+
+import pandas._testing as tm
+from pandas.core.arrays import DatetimeArray
+
+
+class TestAccumulator:
+    def test_accumulators_freq(self):
+        # GH#50297
+        arr = DatetimeArray._from_sequence(
+            [
+                "2000-01-01",
+                "2000-01-02",
+                "2000-01-03",
+            ],
+            dtype="M8[ns]",
+        )._with_freq("infer")
+        result = arr._accumulate("cummin")
+        expected = DatetimeArray._from_sequence(["2000-01-01"] * 3, dtype="M8[ns]")
+        tm.assert_datetime_array_equal(result, expected)
+
+        result = arr._accumulate("cummax")
+        expected = DatetimeArray._from_sequence(
+            [
+                "2000-01-01",
+                "2000-01-02",
+                "2000-01-03",
+            ],
+            dtype="M8[ns]",
+        )
+        tm.assert_datetime_array_equal(result, expected)
+
+    @pytest.mark.parametrize("func", ["cumsum", "cumprod"])
+    def test_accumulators_disallowed(self, func):
+        # GH#50297
+        arr = DatetimeArray._from_sequence(
+            [
+                "2000-01-01",
+                "2000-01-02",
+            ],
+            dtype="M8[ns]",
+        )._with_freq("infer")
+        with pytest.raises(TypeError, match=f"Accumulation {func}"):
+            arr._accumulate(func)

lib/python3.13/site-packages/pandas/tests/arrays/datetimes/test_reductions.py

@@ -0,0 +1,183 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import DatetimeTZDtype
+
+import pandas as pd
+from pandas import NaT
+import pandas._testing as tm
+from pandas.core.arrays import DatetimeArray
+
+
+class TestReductions:
+    @pytest.fixture(params=["s", "ms", "us", "ns"])
+    def unit(self, request):
+        return request.param
+
+    @pytest.fixture
+    def arr1d(self, tz_naive_fixture):
+        """Fixture returning DatetimeArray with parametrized timezones"""
+        tz = tz_naive_fixture
+        dtype = DatetimeTZDtype(tz=tz) if tz is not None else np.dtype("M8[ns]")
+        arr = DatetimeArray._from_sequence(
+            [
+                "2000-01-03",
+                "2000-01-03",
+                "NaT",
+                "2000-01-02",
+                "2000-01-05",
+                "2000-01-04",
+            ],
+            dtype=dtype,
+        )
+        return arr
+
+    def test_min_max(self, arr1d, unit):
+        arr = arr1d
+        arr = arr.as_unit(unit)
+        tz = arr.tz
+
+        result = arr.min()
+        expected = pd.Timestamp("2000-01-02", tz=tz).as_unit(unit)
+        assert result == expected
+        assert result.unit == expected.unit
+
+        result = arr.max()
+        expected = pd.Timestamp("2000-01-05", tz=tz).as_unit(unit)
+        assert result == expected
+        assert result.unit == expected.unit
+
+        result = arr.min(skipna=False)
+        assert result is NaT
+
+        result = arr.max(skipna=False)
+        assert result is NaT
+
+    @pytest.mark.parametrize("tz", [None, "US/Central"])
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_min_max_empty(self, skipna, tz):
+        dtype = DatetimeTZDtype(tz=tz) if tz is not None else np.dtype("M8[ns]")
+        arr = DatetimeArray._from_sequence([], dtype=dtype)
+        result = arr.min(skipna=skipna)
+        assert result is NaT
+
+        result = arr.max(skipna=skipna)
+        assert result is NaT
+
+    @pytest.mark.parametrize("tz", [None, "US/Central"])
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_median_empty(self, skipna, tz):
+        dtype = DatetimeTZDtype(tz=tz) if tz is not None else np.dtype("M8[ns]")
+        arr = DatetimeArray._from_sequence([], dtype=dtype)
+        result = arr.median(skipna=skipna)
+        assert result is NaT
+
+        arr = arr.reshape(0, 3)
+        result = arr.median(axis=0, skipna=skipna)
+        expected = type(arr)._from_sequence([NaT, NaT, NaT], dtype=arr.dtype)
+        tm.assert_equal(result, expected)
+
+        result = arr.median(axis=1, skipna=skipna)
+        expected = type(arr)._from_sequence([], dtype=arr.dtype)
+        tm.assert_equal(result, expected)
+
+    def test_median(self, arr1d):
+        arr = arr1d
+
+        result = arr.median()
+        assert result == arr[0]
+        result = arr.median(skipna=False)
+        assert result is NaT
+
+        result = arr.dropna().median(skipna=False)
+        assert result == arr[0]
+
+        result = arr.median(axis=0)
+        assert result == arr[0]
+
+    def test_median_axis(self, arr1d):
+        arr = arr1d
+        assert arr.median(axis=0) == arr.median()
+        assert arr.median(axis=0, skipna=False) is NaT
+
+        msg = r"abs\(axis\) must be less than ndim"
+        with pytest.raises(ValueError, match=msg):
+            arr.median(axis=1)
+
+    @pytest.mark.filterwarnings("ignore:All-NaN slice encountered:RuntimeWarning")
+    def test_median_2d(self, arr1d):
+        arr = arr1d.reshape(1, -1)
+
+        # axis = None
+        assert arr.median() == arr1d.median()
+        assert arr.median(skipna=False) is NaT
+
+        # axis = 0
+        result = arr.median(axis=0)
+        expected = arr1d
+        tm.assert_equal(result, expected)
+
+        # Since column 3 is all-NaT, we get NaT there with or without skipna
+        result = arr.median(axis=0, skipna=False)
+        expected = arr1d
+        tm.assert_equal(result, expected)
+
+        # axis = 1
+        result = arr.median(axis=1)
+        expected = type(arr)._from_sequence([arr1d.median()], dtype=arr.dtype)
+        tm.assert_equal(result, expected)
+
+        result = arr.median(axis=1, skipna=False)
+        expected = type(arr)._from_sequence([NaT], dtype=arr.dtype)
+        tm.assert_equal(result, expected)
+
+    def test_mean(self, arr1d):
+        arr = arr1d
+
+        # manually verified result
+        expected = arr[0] + 0.4 * pd.Timedelta(days=1)
+
+        result = arr.mean()
+        assert result == expected
+        result = arr.mean(skipna=False)
+        assert result is NaT
+
+        result = arr.dropna().mean(skipna=False)
+        assert result == expected
+
+        result = arr.mean(axis=0)
+        assert result == expected
+
+    def test_mean_2d(self):
+        dti = pd.date_range("2016-01-01", periods=6, tz="US/Pacific")
+        dta = dti._data.reshape(3, 2)
+
+        result = dta.mean(axis=0)
+        expected = dta[1]
+        tm.assert_datetime_array_equal(result, expected)
+
+        result = dta.mean(axis=1)
+        expected = dta[:, 0] + pd.Timedelta(hours=12)
+        tm.assert_datetime_array_equal(result, expected)
+
+        result = dta.mean(axis=None)
+        expected = dti.mean()
+        assert result == expected
+
+    @pytest.mark.parametrize("skipna", [True, False])
+    def test_mean_empty(self, arr1d, skipna):
+        arr = arr1d[:0]
+
+        assert arr.mean(skipna=skipna) is NaT
+
+        arr2d = arr.reshape(0, 3)
+        result = arr2d.mean(axis=0, skipna=skipna)
+        expected = DatetimeArray._from_sequence([NaT, NaT, NaT], dtype=arr.dtype)
+        tm.assert_datetime_array_equal(result, expected)
+
+        result = arr2d.mean(axis=1, skipna=skipna)
+        expected = arr  # i.e. 1D, empty
+        tm.assert_datetime_array_equal(result, expected)
+
+        result = arr2d.mean(axis=None, skipna=skipna)
+        assert result is NaT

lib/python3.13/site-packages/pandas/tests/arrays/floating/conftest.py

@@ -0,0 +1,48 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.arrays.floating import (
+    Float32Dtype,
+    Float64Dtype,
+)
+
+
+@pytest.fixture(params=[Float32Dtype, Float64Dtype])
+def dtype(request):
+    """Parametrized fixture returning a float 'dtype'"""
+    return request.param()
+
+
+@pytest.fixture
+def data(dtype):
+    """Fixture returning 'data' array according to parametrized float 'dtype'"""
+    return pd.array(
+        list(np.arange(0.1, 0.9, 0.1))
+        + [pd.NA]
+        + list(np.arange(1, 9.8, 0.1))
+        + [pd.NA]
+        + [9.9, 10.0],
+        dtype=dtype,
+    )
+
+
+@pytest.fixture
+def data_missing(dtype):
+    """
+    Fixture returning array with missing data according to parametrized float
+    'dtype'.
+    """
+    return pd.array([np.nan, 0.1], dtype=dtype)
+
+
+@pytest.fixture(params=["data", "data_missing"])
+def all_data(request, data, data_missing):
+    """Parametrized fixture returning 'data' or 'data_missing' float arrays.
+
+    Used to test dtype conversion with and without missing values.
+    """
+    if request.param == "data":
+        return data
+    elif request.param == "data_missing":
+        return data_missing

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_arithmetic.py

@@ -0,0 +1,244 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import FloatingArray
+
+# Basic test for the arithmetic array ops
+# -----------------------------------------------------------------------------
+
+
+@pytest.mark.parametrize(
+    "opname, exp",
+    [
+        ("add", [1.1, 2.2, None, None, 5.5]),
+        ("mul", [0.1, 0.4, None, None, 2.5]),
+        ("sub", [0.9, 1.8, None, None, 4.5]),
+        ("truediv", [10.0, 10.0, None, None, 10.0]),
+        ("floordiv", [9.0, 9.0, None, None, 10.0]),
+        ("mod", [0.1, 0.2, None, None, 0.0]),
+    ],
+    ids=["add", "mul", "sub", "div", "floordiv", "mod"],
+)
+def test_array_op(dtype, opname, exp):
+    a = pd.array([1.0, 2.0, None, 4.0, 5.0], dtype=dtype)
+    b = pd.array([0.1, 0.2, 0.3, None, 0.5], dtype=dtype)
+
+    op = getattr(operator, opname)
+
+    result = op(a, b)
+    expected = pd.array(exp, dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("zero, negative", [(0, False), (0.0, False), (-0.0, True)])
+def test_divide_by_zero(dtype, zero, negative):
+    # TODO pending NA/NaN discussion
+    # https://github.com/pandas-dev/pandas/issues/32265/
+    a = pd.array([0, 1, -1, None], dtype=dtype)
+    result = a / zero
+    expected = FloatingArray(
+        np.array([np.nan, np.inf, -np.inf, np.nan], dtype=dtype.numpy_dtype),
+        np.array([False, False, False, True]),
+    )
+    if negative:
+        expected *= -1
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_pow_scalar(dtype):
+    a = pd.array([-1, 0, 1, None, 2], dtype=dtype)
+    result = a**0
+    expected = pd.array([1, 1, 1, 1, 1], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**1
+    expected = pd.array([-1, 0, 1, None, 2], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**pd.NA
+    expected = pd.array([None, None, 1, None, None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**np.nan
+    # TODO np.nan should be converted to pd.NA / missing before operation?
+    expected = FloatingArray(
+        np.array([np.nan, np.nan, 1, np.nan, np.nan], dtype=dtype.numpy_dtype),
+        mask=a._mask,
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    # reversed
+    a = a[1:]  # Can't raise integers to negative powers.
+
+    result = 0**a
+    expected = pd.array([1, 0, None, 0], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = 1**a
+    expected = pd.array([1, 1, 1, 1], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = pd.NA**a
+    expected = pd.array([1, None, None, None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = np.nan**a
+    expected = FloatingArray(
+        np.array([1, np.nan, np.nan, np.nan], dtype=dtype.numpy_dtype), mask=a._mask
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_pow_array(dtype):
+    a = pd.array([0, 0, 0, 1, 1, 1, None, None, None], dtype=dtype)
+    b = pd.array([0, 1, None, 0, 1, None, 0, 1, None], dtype=dtype)
+    result = a**b
+    expected = pd.array([1, 0, None, 1, 1, 1, 1, None, None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_rpow_one_to_na():
+    # https://github.com/pandas-dev/pandas/issues/22022
+    # https://github.com/pandas-dev/pandas/issues/29997
+    arr = pd.array([np.nan, np.nan], dtype="Float64")
+    result = np.array([1.0, 2.0]) ** arr
+    expected = pd.array([1.0, np.nan], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("other", [0, 0.5])
+def test_arith_zero_dim_ndarray(other):
+    arr = pd.array([1, None, 2], dtype="Float64")
+    result = arr + np.array(other)
+    expected = arr + other
+    tm.assert_equal(result, expected)
+
+
+# Test generic characteristics / errors
+# -----------------------------------------------------------------------------
+
+
+def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
+    op = all_arithmetic_operators
+    s = pd.Series(data)
+    ops = getattr(s, op)
+
+    if using_infer_string:
+        import pyarrow as pa
+
+        errs = (TypeError, pa.lib.ArrowNotImplementedError, NotImplementedError)
+    else:
+        errs = TypeError
+
+    # invalid scalars
+    msg = "|".join(
+        [
+            r"can only perform ops with numeric values",
+            r"FloatingArray cannot perform the operation mod",
+            "unsupported operand type",
+            "not all arguments converted during string formatting",
+            "can't multiply sequence by non-int of type 'float'",
+            "ufunc 'subtract' cannot use operands with types dtype",
+            r"can only concatenate str \(not \"float\"\) to str",
+            "ufunc '.*' not supported for the input types, and the inputs could not",
+            "ufunc '.*' did not contain a loop with signature matching types",
+            "Concatenation operation is not implemented for NumPy arrays",
+            "has no kernel",
+            "not implemented",
+        ]
+    )
+    with pytest.raises(errs, match=msg):
+        ops("foo")
+    with pytest.raises(errs, match=msg):
+        ops(pd.Timestamp("20180101"))
+
+    # invalid array-likes
+    with pytest.raises(errs, match=msg):
+        ops(pd.Series("foo", index=s.index))
+
+    msg = "|".join(
+        [
+            "can only perform ops with numeric values",
+            "cannot perform .* with this index type: DatetimeArray",
+            "Addition/subtraction of integers and integer-arrays "
+            "with DatetimeArray is no longer supported. *",
+            "unsupported operand type",
+            "not all arguments converted during string formatting",
+            "can't multiply sequence by non-int of type 'float'",
+            "ufunc 'subtract' cannot use operands with types dtype",
+            (
+                "ufunc 'add' cannot use operands with types "
+                rf"dtype\('{tm.ENDIAN}M8\[ns\]'\)"
+            ),
+            r"ufunc 'add' cannot use operands with types dtype\('float\d{2}'\)",
+            "cannot subtract DatetimeArray from ndarray",
+            "has no kernel",
+            "not implemented",
+        ]
+    )
+    with pytest.raises(errs, match=msg):
+        ops(pd.Series(pd.date_range("20180101", periods=len(s))))
+
+
+# Various
+# -----------------------------------------------------------------------------
+
+
+def test_cross_type_arithmetic():
+    df = pd.DataFrame(
+        {
+            "A": pd.array([1, 2, np.nan], dtype="Float64"),
+            "B": pd.array([1, np.nan, 3], dtype="Float32"),
+            "C": np.array([1, 2, 3], dtype="float64"),
+        }
+    )
+
+    result = df.A + df.C
+    expected = pd.Series([2, 4, np.nan], dtype="Float64")
+    tm.assert_series_equal(result, expected)
+
+    result = (df.A + df.C) * 3 == 12
+    expected = pd.Series([False, True, None], dtype="boolean")
+    tm.assert_series_equal(result, expected)
+
+    result = df.A + df.B
+    expected = pd.Series([2, np.nan, np.nan], dtype="Float64")
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "source, neg_target, abs_target",
+    [
+        ([1.1, 2.2, 3.3], [-1.1, -2.2, -3.3], [1.1, 2.2, 3.3]),
+        ([1.1, 2.2, None], [-1.1, -2.2, None], [1.1, 2.2, None]),
+        ([-1.1, 0.0, 1.1], [1.1, 0.0, -1.1], [1.1, 0.0, 1.1]),
+    ],
+)
+def test_unary_float_operators(float_ea_dtype, source, neg_target, abs_target):
+    # GH38794
+    dtype = float_ea_dtype
+    arr = pd.array(source, dtype=dtype)
+    neg_result, pos_result, abs_result = -arr, +arr, abs(arr)
+    neg_target = pd.array(neg_target, dtype=dtype)
+    abs_target = pd.array(abs_target, dtype=dtype)
+
+    tm.assert_extension_array_equal(neg_result, neg_target)
+    tm.assert_extension_array_equal(pos_result, arr)
+    assert not tm.shares_memory(pos_result, arr)
+    tm.assert_extension_array_equal(abs_result, abs_target)
+
+
+def test_bitwise(dtype):
+    left = pd.array([1, None, 3, 4], dtype=dtype)
+    right = pd.array([None, 3, 5, 4], dtype=dtype)
+
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left | right
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left & right
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left ^ right

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_astype.py

@@ -0,0 +1,128 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+def test_astype():
+    # with missing values
+    arr = pd.array([0.1, 0.2, None], dtype="Float64")
+
+    with pytest.raises(ValueError, match="cannot convert NA to integer"):
+        arr.astype("int64")
+
+    with pytest.raises(ValueError, match="cannot convert float NaN to bool"):
+        arr.astype("bool")
+
+    result = arr.astype("float64")
+    expected = np.array([0.1, 0.2, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    # no missing values
+    arr = pd.array([0.0, 1.0, 0.5], dtype="Float64")
+    result = arr.astype("int64")
+    expected = np.array([0, 1, 0], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.astype("bool")
+    expected = np.array([False, True, True], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_astype_to_floating_array():
+    # astype to FloatingArray
+    arr = pd.array([0.0, 1.0, None], dtype="Float64")
+
+    result = arr.astype("Float64")
+    tm.assert_extension_array_equal(result, arr)
+    result = arr.astype(pd.Float64Dtype())
+    tm.assert_extension_array_equal(result, arr)
+    result = arr.astype("Float32")
+    expected = pd.array([0.0, 1.0, None], dtype="Float32")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_astype_to_boolean_array():
+    # astype to BooleanArray
+    arr = pd.array([0.0, 1.0, None], dtype="Float64")
+
+    result = arr.astype("boolean")
+    expected = pd.array([False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = arr.astype(pd.BooleanDtype())
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_astype_to_integer_array():
+    # astype to IntegerArray
+    arr = pd.array([0.0, 1.5, None], dtype="Float64")
+
+    result = arr.astype("Int64")
+    expected = pd.array([0, 1, None], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_astype_str():
+    a = pd.array([0.1, 0.2, None], dtype="Float64")
+    expected = np.array(["0.1", "0.2", "<NA>"], dtype="U32")
+
+    tm.assert_numpy_array_equal(a.astype(str), expected)
+    tm.assert_numpy_array_equal(a.astype("str"), expected)
+
+
+def test_astype_copy():
+    arr = pd.array([0.1, 0.2, None], dtype="Float64")
+    orig = pd.array([0.1, 0.2, None], dtype="Float64")
+
+    # copy=True -> ensure both data and mask are actual copies
+    result = arr.astype("Float64", copy=True)
+    assert result is not arr
+    assert not tm.shares_memory(result, arr)
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, orig)
+    result[0] = pd.NA
+    tm.assert_extension_array_equal(arr, orig)
+
+    # copy=False
+    result = arr.astype("Float64", copy=False)
+    assert result is arr
+    assert np.shares_memory(result._data, arr._data)
+    assert np.shares_memory(result._mask, arr._mask)
+    result[0] = 10
+    assert arr[0] == 10
+    result[0] = pd.NA
+    assert arr[0] is pd.NA
+
+    # astype to different dtype -> always needs a copy -> even with copy=False
+    # we need to ensure that also the mask is actually copied
+    arr = pd.array([0.1, 0.2, None], dtype="Float64")
+    orig = pd.array([0.1, 0.2, None], dtype="Float64")
+
+    result = arr.astype("Float32", copy=False)
+    assert not tm.shares_memory(result, arr)
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, orig)
+    result[0] = pd.NA
+    tm.assert_extension_array_equal(arr, orig)
+
+
+def test_astype_object(dtype):
+    arr = pd.array([1.0, pd.NA], dtype=dtype)
+
+    result = arr.astype(object)
+    expected = np.array([1.0, pd.NA], dtype=object)
+    tm.assert_numpy_array_equal(result, expected)
+    # check exact element types
+    assert isinstance(result[0], float)
+    assert result[1] is pd.NA
+
+
+def test_Float64_conversion():
+    # GH#40729
+    testseries = pd.Series(["1", "2", "3", "4"], dtype="object")
+    result = testseries.astype(pd.Float64Dtype())
+
+    expected = pd.Series([1.0, 2.0, 3.0, 4.0], dtype=pd.Float64Dtype())
+
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_comparison.py

@@ -0,0 +1,65 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import FloatingArray
+from pandas.tests.arrays.masked_shared import (
+    ComparisonOps,
+    NumericOps,
+)
+
+
+class TestComparisonOps(NumericOps, ComparisonOps):
+    @pytest.mark.parametrize("other", [True, False, pd.NA, -1.0, 0.0, 1])
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
+
+    def test_compare_with_integerarray(self, comparison_op):
+        op = comparison_op
+        a = pd.array([0, 1, None] * 3, dtype="Int64")
+        b = pd.array([0] * 3 + [1] * 3 + [None] * 3, dtype="Float64")
+        other = b.astype("Int64")
+        expected = op(a, other)
+        result = op(a, b)
+        tm.assert_extension_array_equal(result, expected)
+        expected = op(other, a)
+        result = op(b, a)
+        tm.assert_extension_array_equal(result, expected)
+
+
+def test_equals():
+    # GH-30652
+    # equals is generally tested in /tests/extension/base/methods, but this
+    # specifically tests that two arrays of the same class but different dtype
+    # do not evaluate equal
+    a1 = pd.array([1, 2, None], dtype="Float64")
+    a2 = pd.array([1, 2, None], dtype="Float32")
+    assert a1.equals(a2) is False
+
+
+def test_equals_nan_vs_na():
+    # GH#44382
+
+    mask = np.zeros(3, dtype=bool)
+    data = np.array([1.0, np.nan, 3.0], dtype=np.float64)
+
+    left = FloatingArray(data, mask)
+    assert left.equals(left)
+    tm.assert_extension_array_equal(left, left)
+
+    assert left.equals(left.copy())
+    assert left.equals(FloatingArray(data.copy(), mask.copy()))
+
+    mask2 = np.array([False, True, False], dtype=bool)
+    data2 = np.array([1.0, 2.0, 3.0], dtype=np.float64)
+    right = FloatingArray(data2, mask2)
+    assert right.equals(right)
+    tm.assert_extension_array_equal(right, right)
+
+    assert not left.equals(right)
+
+    # with mask[1] = True, the only difference is data[1], which should
+    #  not matter for equals
+    mask[1] = True
+    assert left.equals(right)

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_concat.py

@@ -0,0 +1,20 @@
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "to_concat_dtypes, result_dtype",
+    [
+        (["Float64", "Float64"], "Float64"),
+        (["Float32", "Float64"], "Float64"),
+        (["Float32", "Float32"], "Float32"),
+    ],
+)
+def test_concat_series(to_concat_dtypes, result_dtype):
+    result = pd.concat([pd.Series([1, 2, pd.NA], dtype=t) for t in to_concat_dtypes])
+    expected = pd.concat([pd.Series([1, 2, pd.NA], dtype=object)] * 2).astype(
+        result_dtype
+    )
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_construction.py

@@ -0,0 +1,204 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import FloatingArray
+from pandas.core.arrays.floating import (
+    Float32Dtype,
+    Float64Dtype,
+)
+
+
+def test_uses_pandas_na():
+    a = pd.array([1, None], dtype=Float64Dtype())
+    assert a[1] is pd.NA
+
+
+def test_floating_array_constructor():
+    values = np.array([1, 2, 3, 4], dtype="float64")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = FloatingArray(values, mask)
+    expected = pd.array([1, 2, 3, np.nan], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+    tm.assert_numpy_array_equal(result._data, values)
+    tm.assert_numpy_array_equal(result._mask, mask)
+
+    msg = r".* should be .* numpy array. Use the 'pd.array' function instead"
+    with pytest.raises(TypeError, match=msg):
+        FloatingArray(values.tolist(), mask)
+
+    with pytest.raises(TypeError, match=msg):
+        FloatingArray(values, mask.tolist())
+
+    with pytest.raises(TypeError, match=msg):
+        FloatingArray(values.astype(int), mask)
+
+    msg = r"__init__\(\) missing 1 required positional argument: 'mask'"
+    with pytest.raises(TypeError, match=msg):
+        FloatingArray(values)
+
+
+def test_floating_array_disallows_float16():
+    # GH#44715
+    arr = np.array([1, 2], dtype=np.float16)
+    mask = np.array([False, False])
+
+    msg = "FloatingArray does not support np.float16 dtype"
+    with pytest.raises(TypeError, match=msg):
+        FloatingArray(arr, mask)
+
+
+def test_floating_array_disallows_Float16_dtype(request):
+    # GH#44715
+    with pytest.raises(TypeError, match="data type 'Float16' not understood"):
+        pd.array([1.0, 2.0], dtype="Float16")
+
+
+def test_floating_array_constructor_copy():
+    values = np.array([1, 2, 3, 4], dtype="float64")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = FloatingArray(values, mask)
+    assert result._data is values
+    assert result._mask is mask
+
+    result = FloatingArray(values, mask, copy=True)
+    assert result._data is not values
+    assert result._mask is not mask
+
+
+def test_to_array():
+    result = pd.array([0.1, 0.2, 0.3, 0.4])
+    expected = pd.array([0.1, 0.2, 0.3, 0.4], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "a, b",
+    [
+        ([1, None], [1, pd.NA]),
+        ([None], [pd.NA]),
+        ([None, np.nan], [pd.NA, pd.NA]),
+        ([1, np.nan], [1, pd.NA]),
+        ([np.nan], [pd.NA]),
+    ],
+)
+def test_to_array_none_is_nan(a, b):
+    result = pd.array(a, dtype="Float64")
+    expected = pd.array(b, dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_array_mixed_integer_float():
+    result = pd.array([1, 2.0])
+    expected = pd.array([1.0, 2.0], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = pd.array([1, None, 2.0])
+    expected = pd.array([1.0, None, 2.0], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values",
+    [
+        ["foo", "bar"],
+        "foo",
+        1,
+        1.0,
+        pd.date_range("20130101", periods=2),
+        np.array(["foo"]),
+        [[1, 2], [3, 4]],
+        [np.nan, {"a": 1}],
+        # GH#44514 all-NA case used to get quietly swapped out before checking ndim
+        np.array([pd.NA] * 6, dtype=object).reshape(3, 2),
+    ],
+)
+def test_to_array_error(values):
+    # error in converting existing arrays to FloatingArray
+    msg = "|".join(
+        [
+            "cannot be converted to FloatingDtype",
+            "values must be a 1D list-like",
+            "Cannot pass scalar",
+            r"float\(\) argument must be a string or a (real )?number, not 'dict'",
+            "could not convert string to float: 'foo'",
+            r"could not convert string to float: np\.str_\('foo'\)",
+        ]
+    )
+    with pytest.raises((TypeError, ValueError), match=msg):
+        pd.array(values, dtype="Float64")
+
+
+@pytest.mark.parametrize("values", [["1", "2", None], ["1.5", "2", None]])
+def test_construct_from_float_strings(values):
+    # see also test_to_integer_array_str
+    expected = pd.array([float(values[0]), 2, None], dtype="Float64")
+
+    res = pd.array(values, dtype="Float64")
+    tm.assert_extension_array_equal(res, expected)
+
+    res = FloatingArray._from_sequence(values)
+    tm.assert_extension_array_equal(res, expected)
+
+
+def test_to_array_inferred_dtype():
+    # if values has dtype -> respect it
+    result = pd.array(np.array([1, 2], dtype="float32"))
+    assert result.dtype == Float32Dtype()
+
+    # if values have no dtype -> always float64
+    result = pd.array([1.0, 2.0])
+    assert result.dtype == Float64Dtype()
+
+
+def test_to_array_dtype_keyword():
+    result = pd.array([1, 2], dtype="Float32")
+    assert result.dtype == Float32Dtype()
+
+    # if values has dtype -> override it
+    result = pd.array(np.array([1, 2], dtype="float32"), dtype="Float64")
+    assert result.dtype == Float64Dtype()
+
+
+def test_to_array_integer():
+    result = pd.array([1, 2], dtype="Float64")
+    expected = pd.array([1.0, 2.0], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    # for integer dtypes, the itemsize is not preserved
+    # TODO can we specify "floating" in general?
+    result = pd.array(np.array([1, 2], dtype="int32"), dtype="Float64")
+    assert result.dtype == Float64Dtype()
+
+
+@pytest.mark.parametrize(
+    "bool_values, values, target_dtype, expected_dtype",
+    [
+        ([False, True], [0, 1], Float64Dtype(), Float64Dtype()),
+        ([False, True], [0, 1], "Float64", Float64Dtype()),
+        ([False, True, np.nan], [0, 1, np.nan], Float64Dtype(), Float64Dtype()),
+    ],
+)
+def test_to_array_bool(bool_values, values, target_dtype, expected_dtype):
+    result = pd.array(bool_values, dtype=target_dtype)
+    assert result.dtype == expected_dtype
+    expected = pd.array(values, dtype=target_dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_series_from_float(data):
+    # construct from our dtype & string dtype
+    dtype = data.dtype
+
+    # from float
+    expected = pd.Series(data)
+    result = pd.Series(data.to_numpy(na_value=np.nan, dtype="float"), dtype=str(dtype))
+    tm.assert_series_equal(result, expected)
+
+    # from list
+    expected = pd.Series(data)
+    result = pd.Series(np.array(data).tolist(), dtype=str(dtype))
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_contains.py

@@ -0,0 +1,12 @@
+import numpy as np
+
+import pandas as pd
+
+
+def test_contains_nan():
+    # GH#52840
+    arr = pd.array(range(5)) / 0
+
+    assert np.isnan(arr._data[0])
+    assert not arr.isna()[0]
+    assert np.nan in arr

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_function.py

@@ -0,0 +1,194 @@
+import numpy as np
+import pytest
+
+from pandas.compat import IS64
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize("ufunc", [np.abs, np.sign])
+# np.sign emits a warning with nans, <https://github.com/numpy/numpy/issues/15127>
+@pytest.mark.filterwarnings("ignore:invalid value encountered in sign:RuntimeWarning")
+def test_ufuncs_single(ufunc):
+    a = pd.array([1, 2, -3, np.nan], dtype="Float64")
+    result = ufunc(a)
+    expected = pd.array(ufunc(a.astype(float)), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    s = pd.Series(a)
+    result = ufunc(s)
+    expected = pd.Series(expected)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("ufunc", [np.log, np.exp, np.sin, np.cos, np.sqrt])
+def test_ufuncs_single_float(ufunc):
+    a = pd.array([1.0, 0.2, 3.0, np.nan], dtype="Float64")
+    with np.errstate(invalid="ignore"):
+        result = ufunc(a)
+        expected = pd.array(ufunc(a.astype(float)), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    s = pd.Series(a)
+    with np.errstate(invalid="ignore"):
+        result = ufunc(s)
+        expected = pd.Series(ufunc(s.astype(float)), dtype="Float64")
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("ufunc", [np.add, np.subtract])
+def test_ufuncs_binary_float(ufunc):
+    # two FloatingArrays
+    a = pd.array([1, 0.2, -3, np.nan], dtype="Float64")
+    result = ufunc(a, a)
+    expected = pd.array(ufunc(a.astype(float), a.astype(float)), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    # FloatingArray with numpy array
+    arr = np.array([1, 2, 3, 4])
+    result = ufunc(a, arr)
+    expected = pd.array(ufunc(a.astype(float), arr), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(arr, a)
+    expected = pd.array(ufunc(arr, a.astype(float)), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    # FloatingArray with scalar
+    result = ufunc(a, 1)
+    expected = pd.array(ufunc(a.astype(float), 1), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(1, a)
+    expected = pd.array(ufunc(1, a.astype(float)), dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("values", [[0, 1], [0, None]])
+def test_ufunc_reduce_raises(values):
+    arr = pd.array(values, dtype="Float64")
+
+    res = np.add.reduce(arr)
+    expected = arr.sum(skipna=False)
+    tm.assert_almost_equal(res, expected)
+
+
+@pytest.mark.skipif(not IS64, reason="GH 36579: fail on 32-bit system")
+@pytest.mark.parametrize(
+    "pandasmethname, kwargs",
+    [
+        ("var", {"ddof": 0}),
+        ("var", {"ddof": 1}),
+        ("std", {"ddof": 0}),
+        ("std", {"ddof": 1}),
+        ("kurtosis", {}),
+        ("skew", {}),
+        ("sem", {}),
+    ],
+)
+def test_stat_method(pandasmethname, kwargs):
+    s = pd.Series(data=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, np.nan, np.nan], dtype="Float64")
+    pandasmeth = getattr(s, pandasmethname)
+    result = pandasmeth(**kwargs)
+    s2 = pd.Series(data=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6], dtype="float64")
+    pandasmeth = getattr(s2, pandasmethname)
+    expected = pandasmeth(**kwargs)
+    assert expected == result
+
+
+def test_value_counts_na():
+    arr = pd.array([0.1, 0.2, 0.1, pd.NA], dtype="Float64")
+    result = arr.value_counts(dropna=False)
+    idx = pd.Index([0.1, 0.2, pd.NA], dtype=arr.dtype)
+    assert idx.dtype == arr.dtype
+    expected = pd.Series([2, 1, 1], index=idx, dtype="Int64", name="count")
+    tm.assert_series_equal(result, expected)
+
+    result = arr.value_counts(dropna=True)
+    expected = pd.Series([2, 1], index=idx[:-1], dtype="Int64", name="count")
+    tm.assert_series_equal(result, expected)
+
+
+def test_value_counts_empty():
+    ser = pd.Series([], dtype="Float64")
+    result = ser.value_counts()
+    idx = pd.Index([], dtype="Float64")
+    assert idx.dtype == "Float64"
+    expected = pd.Series([], index=idx, dtype="Int64", name="count")
+    tm.assert_series_equal(result, expected)
+
+
+def test_value_counts_with_normalize():
+    ser = pd.Series([0.1, 0.2, 0.1, pd.NA], dtype="Float64")
+    result = ser.value_counts(normalize=True)
+    expected = pd.Series([2, 1], index=ser[:2], dtype="Float64", name="proportion") / 3
+    assert expected.index.dtype == ser.dtype
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("min_count", [0, 4])
+def test_floating_array_sum(skipna, min_count, dtype):
+    arr = pd.array([1, 2, 3, None], dtype=dtype)
+    result = arr.sum(skipna=skipna, min_count=min_count)
+    if skipna and min_count == 0:
+        assert result == 6.0
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize(
+    "values, expected", [([1, 2, 3], 6.0), ([1, 2, 3, None], 6.0), ([None], 0.0)]
+)
+def test_floating_array_numpy_sum(values, expected):
+    arr = pd.array(values, dtype="Float64")
+    result = np.sum(arr)
+    assert result == expected
+
+
+@pytest.mark.parametrize("op", ["sum", "min", "max", "prod"])
+def test_preserve_dtypes(op):
+    df = pd.DataFrame(
+        {
+            "A": ["a", "b", "b"],
+            "B": [1, None, 3],
+            "C": pd.array([0.1, None, 3.0], dtype="Float64"),
+        }
+    )
+
+    # op
+    result = getattr(df.C, op)()
+    assert isinstance(result, np.float64)
+
+    # groupby
+    result = getattr(df.groupby("A"), op)()
+
+    expected = pd.DataFrame(
+        {"B": np.array([1.0, 3.0]), "C": pd.array([0.1, 3], dtype="Float64")},
+        index=pd.Index(["a", "b"], name="A"),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("method", ["min", "max"])
+def test_floating_array_min_max(skipna, method, dtype):
+    arr = pd.array([0.0, 1.0, None], dtype=dtype)
+    func = getattr(arr, method)
+    result = func(skipna=skipna)
+    if skipna:
+        assert result == (0 if method == "min" else 1)
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("min_count", [0, 9])
+def test_floating_array_prod(skipna, min_count, dtype):
+    arr = pd.array([1.0, 2.0, None], dtype=dtype)
+    result = arr.prod(skipna=skipna, min_count=min_count)
+    if skipna and min_count == 0:
+        assert result == 2
+    else:
+        assert result is pd.NA

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_repr.py

@@ -0,0 +1,47 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.arrays.floating import (
+    Float32Dtype,
+    Float64Dtype,
+)
+
+
+def test_dtypes(dtype):
+    # smoke tests on auto dtype construction
+
+    np.dtype(dtype.type).kind == "f"
+    assert dtype.name is not None
+
+
+@pytest.mark.parametrize(
+    "dtype, expected",
+    [(Float32Dtype(), "Float32Dtype()"), (Float64Dtype(), "Float64Dtype()")],
+)
+def test_repr_dtype(dtype, expected):
+    assert repr(dtype) == expected
+
+
+def test_repr_array():
+    result = repr(pd.array([1.0, None, 3.0]))
+    expected = "<FloatingArray>\n[1.0, <NA>, 3.0]\nLength: 3, dtype: Float64"
+    assert result == expected
+
+
+def test_repr_array_long():
+    data = pd.array([1.0, 2.0, None] * 1000)
+    expected = """<FloatingArray>
+[ 1.0,  2.0, <NA>,  1.0,  2.0, <NA>,  1.0,  2.0, <NA>,  1.0,
+ ...
+ <NA>,  1.0,  2.0, <NA>,  1.0,  2.0, <NA>,  1.0,  2.0, <NA>]
+Length: 3000, dtype: Float64"""
+    result = repr(data)
+    assert result == expected
+
+
+def test_frame_repr(data_missing):
+    df = pd.DataFrame({"A": data_missing})
+    result = repr(df)
+    expected = "      A\n0  <NA>\n1   0.1"
+    assert result == expected

lib/python3.13/site-packages/pandas/tests/arrays/floating/test_to_numpy.py

@@ -0,0 +1,132 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import FloatingArray
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy(box):
+    con = pd.Series if box else pd.array
+
+    # default (with or without missing values) -> object dtype
+    arr = con([0.1, 0.2, 0.3], dtype="Float64")
+    result = arr.to_numpy()
+    expected = np.array([0.1, 0.2, 0.3], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([0.1, 0.2, None], dtype="Float64")
+    result = arr.to_numpy()
+    expected = np.array([0.1, 0.2, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_float(box):
+    con = pd.Series if box else pd.array
+
+    # no missing values -> can convert to float, otherwise raises
+    arr = con([0.1, 0.2, 0.3], dtype="Float64")
+    result = arr.to_numpy(dtype="float64")
+    expected = np.array([0.1, 0.2, 0.3], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([0.1, 0.2, None], dtype="Float64")
+    result = arr.to_numpy(dtype="float64")
+    expected = np.array([0.1, 0.2, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype="float64", na_value=np.nan)
+    expected = np.array([0.1, 0.2, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_int(box):
+    con = pd.Series if box else pd.array
+
+    # no missing values -> can convert to int, otherwise raises
+    arr = con([1.0, 2.0, 3.0], dtype="Float64")
+    result = arr.to_numpy(dtype="int64")
+    expected = np.array([1, 2, 3], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    arr = con([1.0, 2.0, None], dtype="Float64")
+    with pytest.raises(ValueError, match="cannot convert to 'int64'-dtype"):
+        result = arr.to_numpy(dtype="int64")
+
+    # automatic casting (floors the values)
+    arr = con([0.1, 0.9, 1.1], dtype="Float64")
+    result = arr.to_numpy(dtype="int64")
+    expected = np.array([0, 0, 1], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_na_value(box):
+    con = pd.Series if box else pd.array
+
+    arr = con([0.0, 1.0, None], dtype="Float64")
+    result = arr.to_numpy(dtype=object, na_value=None)
+    expected = np.array([0.0, 1.0, None], dtype="object")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype=bool, na_value=False)
+    expected = np.array([False, True, False], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = arr.to_numpy(dtype="int64", na_value=-99)
+    expected = np.array([0, 1, -99], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_to_numpy_na_value_with_nan():
+    # array with both NaN and NA -> only fill NA with `na_value`
+    arr = FloatingArray(np.array([0.0, np.nan, 0.0]), np.array([False, False, True]))
+    result = arr.to_numpy(dtype="float64", na_value=-1)
+    expected = np.array([0.0, np.nan, -1.0], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["float64", "float32", "int32", "int64", "bool"])
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_dtype(box, dtype):
+    con = pd.Series if box else pd.array
+    arr = con([0.0, 1.0], dtype="Float64")
+
+    result = arr.to_numpy(dtype=dtype)
+    expected = np.array([0, 1], dtype=dtype)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["int32", "int64", "bool"])
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_na_raises(box, dtype):
+    con = pd.Series if box else pd.array
+    arr = con([0.0, 1.0, None], dtype="Float64")
+    with pytest.raises(ValueError, match=dtype):
+        arr.to_numpy(dtype=dtype)
+
+
+@pytest.mark.parametrize("box", [True, False], ids=["series", "array"])
+def test_to_numpy_string(box, dtype):
+    con = pd.Series if box else pd.array
+    arr = con([0.0, 1.0, None], dtype="Float64")
+
+    result = arr.to_numpy(dtype="str")
+    expected = np.array([0.0, 1.0, pd.NA], dtype=f"{tm.ENDIAN}U32")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_to_numpy_copy():
+    # to_numpy can be zero-copy if no missing values
+    arr = pd.array([0.1, 0.2, 0.3], dtype="Float64")
+    result = arr.to_numpy(dtype="float64")
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, pd.array([10, 0.2, 0.3], dtype="Float64"))
+
+    arr = pd.array([0.1, 0.2, 0.3], dtype="Float64")
+    result = arr.to_numpy(dtype="float64", copy=True)
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, pd.array([0.1, 0.2, 0.3], dtype="Float64"))

lib/python3.13/site-packages/pandas/tests/arrays/integer/conftest.py

@@ -0,0 +1,68 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    Int16Dtype,
+    Int32Dtype,
+    Int64Dtype,
+    UInt8Dtype,
+    UInt16Dtype,
+    UInt32Dtype,
+    UInt64Dtype,
+)
+
+
+@pytest.fixture(
+    params=[
+        Int8Dtype,
+        Int16Dtype,
+        Int32Dtype,
+        Int64Dtype,
+        UInt8Dtype,
+        UInt16Dtype,
+        UInt32Dtype,
+        UInt64Dtype,
+    ]
+)
+def dtype(request):
+    """Parametrized fixture returning integer 'dtype'"""
+    return request.param()
+
+
+@pytest.fixture
+def data(dtype):
+    """
+    Fixture returning 'data' array with valid and missing values according to
+    parametrized integer 'dtype'.
+
+    Used to test dtype conversion with and without missing values.
+    """
+    return pd.array(
+        list(range(8)) + [np.nan] + list(range(10, 98)) + [np.nan] + [99, 100],
+        dtype=dtype,
+    )
+
+
+@pytest.fixture
+def data_missing(dtype):
+    """
+    Fixture returning array with exactly one NaN and one valid integer,
+    according to parametrized integer 'dtype'.
+
+    Used to test dtype conversion with and without missing values.
+    """
+    return pd.array([np.nan, 1], dtype=dtype)
+
+
+@pytest.fixture(params=["data", "data_missing"])
+def all_data(request, data, data_missing):
+    """Parametrized fixture returning 'data' or 'data_missing' integer arrays.
+
+    Used to test dtype conversion with and without missing values.
+    """
+    if request.param == "data":
+        return data
+    elif request.param == "data_missing":
+        return data_missing

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_arithmetic.py

@@ -0,0 +1,385 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core import ops
+from pandas.core.arrays import FloatingArray
+
+# Basic test for the arithmetic array ops
+# -----------------------------------------------------------------------------
+
+
+@pytest.mark.parametrize(
+    "opname, exp",
+    [("add", [1, 3, None, None, 9]), ("mul", [0, 2, None, None, 20])],
+    ids=["add", "mul"],
+)
+def test_add_mul(dtype, opname, exp):
+    a = pd.array([0, 1, None, 3, 4], dtype=dtype)
+    b = pd.array([1, 2, 3, None, 5], dtype=dtype)
+
+    # array / array
+    expected = pd.array(exp, dtype=dtype)
+
+    op = getattr(operator, opname)
+    result = op(a, b)
+    tm.assert_extension_array_equal(result, expected)
+
+    op = getattr(ops, "r" + opname)
+    result = op(a, b)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_sub(dtype):
+    a = pd.array([1, 2, 3, None, 5], dtype=dtype)
+    b = pd.array([0, 1, None, 3, 4], dtype=dtype)
+
+    result = a - b
+    expected = pd.array([1, 1, None, None, 1], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_div(dtype):
+    a = pd.array([1, 2, 3, None, 5], dtype=dtype)
+    b = pd.array([0, 1, None, 3, 4], dtype=dtype)
+
+    result = a / b
+    expected = pd.array([np.inf, 2, None, None, 1.25], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("zero, negative", [(0, False), (0.0, False), (-0.0, True)])
+def test_divide_by_zero(zero, negative):
+    # https://github.com/pandas-dev/pandas/issues/27398, GH#22793
+    a = pd.array([0, 1, -1, None], dtype="Int64")
+    result = a / zero
+    expected = FloatingArray(
+        np.array([np.nan, np.inf, -np.inf, 1], dtype="float64"),
+        np.array([False, False, False, True]),
+    )
+    if negative:
+        expected *= -1
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_floordiv(dtype):
+    a = pd.array([1, 2, 3, None, 5], dtype=dtype)
+    b = pd.array([0, 1, None, 3, 4], dtype=dtype)
+
+    result = a // b
+    # Series op sets 1//0 to np.inf, which IntegerArray does not do (yet)
+    expected = pd.array([0, 2, None, None, 1], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_floordiv_by_int_zero_no_mask(any_int_ea_dtype):
+    # GH 48223: Aligns with non-masked floordiv
+    # but differs from numpy
+    # https://github.com/pandas-dev/pandas/issues/30188#issuecomment-564452740
+    ser = pd.Series([0, 1], dtype=any_int_ea_dtype)
+    result = 1 // ser
+    expected = pd.Series([np.inf, 1.0], dtype="Float64")
+    tm.assert_series_equal(result, expected)
+
+    ser_non_nullable = ser.astype(ser.dtype.numpy_dtype)
+    result = 1 // ser_non_nullable
+    expected = expected.astype(np.float64)
+    tm.assert_series_equal(result, expected)
+
+
+def test_mod(dtype):
+    a = pd.array([1, 2, 3, None, 5], dtype=dtype)
+    b = pd.array([0, 1, None, 3, 4], dtype=dtype)
+
+    result = a % b
+    expected = pd.array([0, 0, None, None, 1], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_pow_scalar():
+    a = pd.array([-1, 0, 1, None, 2], dtype="Int64")
+    result = a**0
+    expected = pd.array([1, 1, 1, 1, 1], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**1
+    expected = pd.array([-1, 0, 1, None, 2], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**pd.NA
+    expected = pd.array([None, None, 1, None, None], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = a**np.nan
+    expected = FloatingArray(
+        np.array([np.nan, np.nan, 1, np.nan, np.nan], dtype="float64"),
+        np.array([False, False, False, True, False]),
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    # reversed
+    a = a[1:]  # Can't raise integers to negative powers.
+
+    result = 0**a
+    expected = pd.array([1, 0, None, 0], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = 1**a
+    expected = pd.array([1, 1, 1, 1], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = pd.NA**a
+    expected = pd.array([1, None, None, None], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = np.nan**a
+    expected = FloatingArray(
+        np.array([1, np.nan, np.nan, np.nan], dtype="float64"),
+        np.array([False, False, True, False]),
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_pow_array():
+    a = pd.array([0, 0, 0, 1, 1, 1, None, None, None])
+    b = pd.array([0, 1, None, 0, 1, None, 0, 1, None])
+    result = a**b
+    expected = pd.array([1, 0, None, 1, 1, 1, 1, None, None])
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_rpow_one_to_na():
+    # https://github.com/pandas-dev/pandas/issues/22022
+    # https://github.com/pandas-dev/pandas/issues/29997
+    arr = pd.array([np.nan, np.nan], dtype="Int64")
+    result = np.array([1.0, 2.0]) ** arr
+    expected = pd.array([1.0, np.nan], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("other", [0, 0.5])
+def test_numpy_zero_dim_ndarray(other):
+    arr = pd.array([1, None, 2])
+    result = arr + np.array(other)
+    expected = arr + other
+    tm.assert_equal(result, expected)
+
+
+# Test generic characteristics / errors
+# -----------------------------------------------------------------------------
+
+
+def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
+    op = all_arithmetic_operators
+    s = pd.Series(data)
+    ops = getattr(s, op)
+
+    if using_infer_string:
+        import pyarrow as pa
+
+        errs = (TypeError, pa.lib.ArrowNotImplementedError, NotImplementedError)
+    else:
+        errs = TypeError
+
+    # invalid scalars
+    msg = "|".join(
+        [
+            r"can only perform ops with numeric values",
+            r"IntegerArray cannot perform the operation mod",
+            r"unsupported operand type",
+            r"can only concatenate str \(not \"int\"\) to str",
+            "not all arguments converted during string",
+            "ufunc '.*' not supported for the input types, and the inputs could not",
+            "ufunc '.*' did not contain a loop with signature matching types",
+            "Addition/subtraction of integers and integer-arrays with Timestamp",
+            "has no kernel",
+            "not implemented",
+            "The 'out' kwarg is necessary. Use numpy.strings.multiply without it.",
+        ]
+    )
+    with pytest.raises(errs, match=msg):
+        ops("foo")
+    with pytest.raises(errs, match=msg):
+        ops(pd.Timestamp("20180101"))
+
+    # invalid array-likes
+    str_ser = pd.Series("foo", index=s.index)
+    # with pytest.raises(TypeError, match=msg):
+    if (
+        all_arithmetic_operators
+        in [
+            "__mul__",
+            "__rmul__",
+        ]
+        and not using_infer_string
+    ):  # (data[~data.isna()] >= 0).all():
+        res = ops(str_ser)
+        expected = pd.Series(["foo" * x for x in data], index=s.index)
+        expected = expected.fillna(np.nan)
+        # TODO: doing this fillna to keep tests passing as we make
+        #  assert_almost_equal stricter, but the expected with pd.NA seems
+        #  more-correct than np.nan here.
+        tm.assert_series_equal(res, expected)
+    else:
+        with pytest.raises(errs, match=msg):
+            ops(str_ser)
+
+    msg = "|".join(
+        [
+            "can only perform ops with numeric values",
+            "cannot perform .* with this index type: DatetimeArray",
+            "Addition/subtraction of integers and integer-arrays "
+            "with DatetimeArray is no longer supported. *",
+            "unsupported operand type",
+            r"can only concatenate str \(not \"int\"\) to str",
+            "not all arguments converted during string",
+            "cannot subtract DatetimeArray from ndarray",
+            "has no kernel",
+            "not implemented",
+        ]
+    )
+    with pytest.raises(errs, match=msg):
+        ops(pd.Series(pd.date_range("20180101", periods=len(s))))
+
+
+# Various
+# -----------------------------------------------------------------------------
+
+
+# TODO test unsigned overflow
+
+
+def test_arith_coerce_scalar(data, all_arithmetic_operators):
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    s = pd.Series(data)
+    other = 0.01
+
+    result = op(s, other)
+    expected = op(s.astype(float), other)
+    expected = expected.astype("Float64")
+
+    # rmod results in NaN that wasn't NA in original nullable Series -> unmask it
+    if all_arithmetic_operators == "__rmod__":
+        mask = (s == 0).fillna(False).to_numpy(bool)
+        expected.array._mask[mask] = False
+
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("other", [1.0, np.array(1.0)])
+def test_arithmetic_conversion(all_arithmetic_operators, other):
+    # if we have a float operand we should have a float result
+    # if that is equal to an integer
+    op = tm.get_op_from_name(all_arithmetic_operators)
+
+    s = pd.Series([1, 2, 3], dtype="Int64")
+    result = op(s, other)
+    assert result.dtype == "Float64"
+
+
+def test_cross_type_arithmetic():
+    df = pd.DataFrame(
+        {
+            "A": pd.Series([1, 2, np.nan], dtype="Int64"),
+            "B": pd.Series([1, np.nan, 3], dtype="UInt8"),
+            "C": [1, 2, 3],
+        }
+    )
+
+    result = df.A + df.C
+    expected = pd.Series([2, 4, np.nan], dtype="Int64")
+    tm.assert_series_equal(result, expected)
+
+    result = (df.A + df.C) * 3 == 12
+    expected = pd.Series([False, True, None], dtype="boolean")
+    tm.assert_series_equal(result, expected)
+
+    result = df.A + df.B
+    expected = pd.Series([2, np.nan, np.nan], dtype="Int64")
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("op", ["mean"])
+def test_reduce_to_float(op):
+    # some reduce ops always return float, even if the result
+    # is a rounded number
+    df = pd.DataFrame(
+        {
+            "A": ["a", "b", "b"],
+            "B": [1, None, 3],
+            "C": pd.array([1, None, 3], dtype="Int64"),
+        }
+    )
+
+    # op
+    result = getattr(df.C, op)()
+    assert isinstance(result, float)
+
+    # groupby
+    result = getattr(df.groupby("A"), op)()
+
+    expected = pd.DataFrame(
+        {"B": np.array([1.0, 3.0]), "C": pd.array([1, 3], dtype="Float64")},
+        index=pd.Index(["a", "b"], name="A"),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "source, neg_target, abs_target",
+    [
+        ([1, 2, 3], [-1, -2, -3], [1, 2, 3]),
+        ([1, 2, None], [-1, -2, None], [1, 2, None]),
+        ([-1, 0, 1], [1, 0, -1], [1, 0, 1]),
+    ],
+)
+def test_unary_int_operators(any_signed_int_ea_dtype, source, neg_target, abs_target):
+    dtype = any_signed_int_ea_dtype
+    arr = pd.array(source, dtype=dtype)
+    neg_result, pos_result, abs_result = -arr, +arr, abs(arr)
+    neg_target = pd.array(neg_target, dtype=dtype)
+    abs_target = pd.array(abs_target, dtype=dtype)
+
+    tm.assert_extension_array_equal(neg_result, neg_target)
+    tm.assert_extension_array_equal(pos_result, arr)
+    assert not tm.shares_memory(pos_result, arr)
+    tm.assert_extension_array_equal(abs_result, abs_target)
+
+
+def test_values_multiplying_large_series_by_NA():
+    # GH#33701
+
+    result = pd.NA * pd.Series(np.zeros(10001))
+    expected = pd.Series([pd.NA] * 10001)
+
+    tm.assert_series_equal(result, expected)
+
+
+def test_bitwise(dtype):
+    left = pd.array([1, None, 3, 4], dtype=dtype)
+    right = pd.array([None, 3, 5, 4], dtype=dtype)
+
+    result = left | right
+    expected = pd.array([None, None, 3 | 5, 4 | 4], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = left & right
+    expected = pd.array([None, None, 3 & 5, 4 & 4], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = left ^ right
+    expected = pd.array([None, None, 3 ^ 5, 4 ^ 4], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    # TODO: desired behavior when operating with boolean?  defer?
+
+    floats = right.astype("Float64")
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left | floats
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left & floats
+    with pytest.raises(TypeError, match="unsupported operand type"):
+        left ^ floats

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_comparison.py

@@ -0,0 +1,39 @@
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.tests.arrays.masked_shared import (
+    ComparisonOps,
+    NumericOps,
+)
+
+
+class TestComparisonOps(NumericOps, ComparisonOps):
+    @pytest.mark.parametrize("other", [True, False, pd.NA, -1, 0, 1])
+    def test_scalar(self, other, comparison_op, dtype):
+        ComparisonOps.test_scalar(self, other, comparison_op, dtype)
+
+    def test_compare_to_int(self, dtype, comparison_op):
+        # GH 28930
+        op_name = f"__{comparison_op.__name__}__"
+        s1 = pd.Series([1, None, 3], dtype=dtype)
+        s2 = pd.Series([1, None, 3], dtype="float")
+
+        method = getattr(s1, op_name)
+        result = method(2)
+
+        method = getattr(s2, op_name)
+        expected = method(2).astype("boolean")
+        expected[s2.isna()] = pd.NA
+
+        tm.assert_series_equal(result, expected)
+
+
+def test_equals():
+    # GH-30652
+    # equals is generally tested in /tests/extension/base/methods, but this
+    # specifically tests that two arrays of the same class but different dtype
+    # do not evaluate equal
+    a1 = pd.array([1, 2, None], dtype="Int64")
+    a2 = pd.array([1, 2, None], dtype="Int32")
+    assert a1.equals(a2) is False

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_concat.py

@@ -0,0 +1,69 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "to_concat_dtypes, result_dtype",
+    [
+        (["Int64", "Int64"], "Int64"),
+        (["UInt64", "UInt64"], "UInt64"),
+        (["Int8", "Int8"], "Int8"),
+        (["Int8", "Int16"], "Int16"),
+        (["UInt8", "Int8"], "Int16"),
+        (["Int32", "UInt32"], "Int64"),
+        (["Int64", "UInt64"], "Float64"),
+        (["Int64", "boolean"], "object"),
+        (["UInt8", "boolean"], "object"),
+    ],
+)
+def test_concat_series(to_concat_dtypes, result_dtype):
+    # we expect the same dtypes as we would get with non-masked inputs,
+    #  just masked where available.
+
+    result = pd.concat([pd.Series([0, 1, pd.NA], dtype=t) for t in to_concat_dtypes])
+    expected = pd.concat([pd.Series([0, 1, pd.NA], dtype=object)] * 2).astype(
+        result_dtype
+    )
+    tm.assert_series_equal(result, expected)
+
+    # order doesn't matter for result
+    result = pd.concat(
+        [pd.Series([0, 1, pd.NA], dtype=t) for t in to_concat_dtypes[::-1]]
+    )
+    expected = pd.concat([pd.Series([0, 1, pd.NA], dtype=object)] * 2).astype(
+        result_dtype
+    )
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "to_concat_dtypes, result_dtype",
+    [
+        (["Int64", "int64"], "Int64"),
+        (["UInt64", "uint64"], "UInt64"),
+        (["Int8", "int8"], "Int8"),
+        (["Int8", "int16"], "Int16"),
+        (["UInt8", "int8"], "Int16"),
+        (["Int32", "uint32"], "Int64"),
+        (["Int64", "uint64"], "Float64"),
+        (["Int64", "bool"], "object"),
+        (["UInt8", "bool"], "object"),
+    ],
+)
+def test_concat_series_with_numpy(to_concat_dtypes, result_dtype):
+    # we expect the same dtypes as we would get with non-masked inputs,
+    #  just masked where available.
+
+    s1 = pd.Series([0, 1, pd.NA], dtype=to_concat_dtypes[0])
+    s2 = pd.Series(np.array([0, 1], dtype=to_concat_dtypes[1]))
+    result = pd.concat([s1, s2], ignore_index=True)
+    expected = pd.Series([0, 1, pd.NA, 0, 1], dtype=object).astype(result_dtype)
+    tm.assert_series_equal(result, expected)
+
+    # order doesn't matter for result
+    result = pd.concat([s2, s1], ignore_index=True)
+    expected = pd.Series([0, 1, 0, 1, pd.NA], dtype=object).astype(result_dtype)
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_construction.py

@@ -0,0 +1,245 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.api.types import is_integer
+from pandas.core.arrays import IntegerArray
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    Int32Dtype,
+    Int64Dtype,
+)
+
+
+@pytest.fixture(params=[pd.array, IntegerArray._from_sequence])
+def constructor(request):
+    """Fixture returning parametrized IntegerArray from given sequence.
+
+    Used to test dtype conversions.
+    """
+    return request.param
+
+
+def test_uses_pandas_na():
+    a = pd.array([1, None], dtype=Int64Dtype())
+    assert a[1] is pd.NA
+
+
+def test_from_dtype_from_float(data):
+    # construct from our dtype & string dtype
+    dtype = data.dtype
+
+    # from float
+    expected = pd.Series(data)
+    result = pd.Series(data.to_numpy(na_value=np.nan, dtype="float"), dtype=str(dtype))
+    tm.assert_series_equal(result, expected)
+
+    # from int / list
+    expected = pd.Series(data)
+    result = pd.Series(np.array(data).tolist(), dtype=str(dtype))
+    tm.assert_series_equal(result, expected)
+
+    # from int / array
+    expected = pd.Series(data).dropna().reset_index(drop=True)
+    dropped = np.array(data.dropna()).astype(np.dtype(dtype.type))
+    result = pd.Series(dropped, dtype=str(dtype))
+    tm.assert_series_equal(result, expected)
+
+
+def test_conversions(data_missing):
+    # astype to object series
+    df = pd.DataFrame({"A": data_missing})
+    result = df["A"].astype("object")
+    expected = pd.Series(np.array([pd.NA, 1], dtype=object), name="A")
+    tm.assert_series_equal(result, expected)
+
+    # convert to object ndarray
+    # we assert that we are exactly equal
+    # including type conversions of scalars
+    result = df["A"].astype("object").values
+    expected = np.array([pd.NA, 1], dtype=object)
+    tm.assert_numpy_array_equal(result, expected)
+
+    for r, e in zip(result, expected):
+        if pd.isnull(r):
+            assert pd.isnull(e)
+        elif is_integer(r):
+            assert r == e
+            assert is_integer(e)
+        else:
+            assert r == e
+            assert type(r) == type(e)
+
+
+def test_integer_array_constructor():
+    values = np.array([1, 2, 3, 4], dtype="int64")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = IntegerArray(values, mask)
+    expected = pd.array([1, 2, 3, np.nan], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    msg = r".* should be .* numpy array. Use the 'pd.array' function instead"
+    with pytest.raises(TypeError, match=msg):
+        IntegerArray(values.tolist(), mask)
+
+    with pytest.raises(TypeError, match=msg):
+        IntegerArray(values, mask.tolist())
+
+    with pytest.raises(TypeError, match=msg):
+        IntegerArray(values.astype(float), mask)
+    msg = r"__init__\(\) missing 1 required positional argument: 'mask'"
+    with pytest.raises(TypeError, match=msg):
+        IntegerArray(values)
+
+
+def test_integer_array_constructor_copy():
+    values = np.array([1, 2, 3, 4], dtype="int64")
+    mask = np.array([False, False, False, True], dtype="bool")
+
+    result = IntegerArray(values, mask)
+    assert result._data is values
+    assert result._mask is mask
+
+    result = IntegerArray(values, mask, copy=True)
+    assert result._data is not values
+    assert result._mask is not mask
+
+
+@pytest.mark.parametrize(
+    "a, b",
+    [
+        ([1, None], [1, np.nan]),
+        ([None], [np.nan]),
+        ([None, np.nan], [np.nan, np.nan]),
+        ([np.nan, np.nan], [np.nan, np.nan]),
+    ],
+)
+def test_to_integer_array_none_is_nan(a, b):
+    result = pd.array(a, dtype="Int64")
+    expected = pd.array(b, dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values",
+    [
+        ["foo", "bar"],
+        "foo",
+        1,
+        1.0,
+        pd.date_range("20130101", periods=2),
+        np.array(["foo"]),
+        [[1, 2], [3, 4]],
+        [np.nan, {"a": 1}],
+    ],
+)
+def test_to_integer_array_error(values):
+    # error in converting existing arrays to IntegerArrays
+    msg = "|".join(
+        [
+            r"cannot be converted to IntegerDtype",
+            r"invalid literal for int\(\) with base 10:",
+            r"values must be a 1D list-like",
+            r"Cannot pass scalar",
+            r"int\(\) argument must be a string",
+        ]
+    )
+    with pytest.raises((ValueError, TypeError), match=msg):
+        pd.array(values, dtype="Int64")
+
+    with pytest.raises((ValueError, TypeError), match=msg):
+        IntegerArray._from_sequence(values)
+
+
+def test_to_integer_array_inferred_dtype(constructor):
+    # if values has dtype -> respect it
+    result = constructor(np.array([1, 2], dtype="int8"))
+    assert result.dtype == Int8Dtype()
+    result = constructor(np.array([1, 2], dtype="int32"))
+    assert result.dtype == Int32Dtype()
+
+    # if values have no dtype -> always int64
+    result = constructor([1, 2])
+    assert result.dtype == Int64Dtype()
+
+
+def test_to_integer_array_dtype_keyword(constructor):
+    result = constructor([1, 2], dtype="Int8")
+    assert result.dtype == Int8Dtype()
+
+    # if values has dtype -> override it
+    result = constructor(np.array([1, 2], dtype="int8"), dtype="Int32")
+    assert result.dtype == Int32Dtype()
+
+
+def test_to_integer_array_float():
+    result = IntegerArray._from_sequence([1.0, 2.0], dtype="Int64")
+    expected = pd.array([1, 2], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    with pytest.raises(TypeError, match="cannot safely cast non-equivalent"):
+        IntegerArray._from_sequence([1.5, 2.0], dtype="Int64")
+
+    # for float dtypes, the itemsize is not preserved
+    result = IntegerArray._from_sequence(
+        np.array([1.0, 2.0], dtype="float32"), dtype="Int64"
+    )
+    assert result.dtype == Int64Dtype()
+
+
+def test_to_integer_array_str():
+    result = IntegerArray._from_sequence(["1", "2", None], dtype="Int64")
+    expected = pd.array([1, 2, np.nan], dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    with pytest.raises(
+        ValueError, match=r"invalid literal for int\(\) with base 10: .*"
+    ):
+        IntegerArray._from_sequence(["1", "2", ""], dtype="Int64")
+
+    with pytest.raises(
+        ValueError, match=r"invalid literal for int\(\) with base 10: .*"
+    ):
+        IntegerArray._from_sequence(["1.5", "2.0"], dtype="Int64")
+
+
+@pytest.mark.parametrize(
+    "bool_values, int_values, target_dtype, expected_dtype",
+    [
+        ([False, True], [0, 1], Int64Dtype(), Int64Dtype()),
+        ([False, True], [0, 1], "Int64", Int64Dtype()),
+        ([False, True, np.nan], [0, 1, np.nan], Int64Dtype(), Int64Dtype()),
+    ],
+)
+def test_to_integer_array_bool(
+    constructor, bool_values, int_values, target_dtype, expected_dtype
+):
+    result = constructor(bool_values, dtype=target_dtype)
+    assert result.dtype == expected_dtype
+    expected = pd.array(int_values, dtype=target_dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values, to_dtype, result_dtype",
+    [
+        (np.array([1], dtype="int64"), None, Int64Dtype),
+        (np.array([1, np.nan]), None, Int64Dtype),
+        (np.array([1, np.nan]), "int8", Int8Dtype),
+    ],
+)
+def test_to_integer_array(values, to_dtype, result_dtype):
+    # convert existing arrays to IntegerArrays
+    result = IntegerArray._from_sequence(values, dtype=to_dtype)
+    assert result.dtype == result_dtype()
+    expected = pd.array(values, dtype=result_dtype())
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_integer_array_from_boolean():
+    # GH31104
+    expected = pd.array(np.array([True, False]), dtype="Int64")
+    result = pd.array(np.array([True, False], dtype=object), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_dtypes.py

@@ -0,0 +1,294 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.generic import ABCIndex
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    UInt32Dtype,
+)
+
+
+def test_dtypes(dtype):
+    # smoke tests on auto dtype construction
+
+    if dtype.is_signed_integer:
+        assert np.dtype(dtype.type).kind == "i"
+    else:
+        assert np.dtype(dtype.type).kind == "u"
+    assert dtype.name is not None
+
+
+@pytest.mark.parametrize("op", ["sum", "min", "max", "prod"])
+def test_preserve_dtypes(op):
+    # for ops that enable (mean would actually work here
+    # but generally it is a float return value)
+    df = pd.DataFrame(
+        {
+            "A": ["a", "b", "b"],
+            "B": [1, None, 3],
+            "C": pd.array([1, None, 3], dtype="Int64"),
+        }
+    )
+
+    # op
+    result = getattr(df.C, op)()
+    if op in {"sum", "prod", "min", "max"}:
+        assert isinstance(result, np.int64)
+    else:
+        assert isinstance(result, int)
+
+    # groupby
+    result = getattr(df.groupby("A"), op)()
+
+    expected = pd.DataFrame(
+        {"B": np.array([1.0, 3.0]), "C": pd.array([1, 3], dtype="Int64")},
+        index=pd.Index(["a", "b"], name="A"),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+def test_astype_nansafe():
+    # see gh-22343
+    arr = pd.array([np.nan, 1, 2], dtype="Int8")
+    msg = "cannot convert NA to integer"
+
+    with pytest.raises(ValueError, match=msg):
+        arr.astype("uint32")
+
+
+@pytest.mark.parametrize("dropna", [True, False])
+def test_construct_index(all_data, dropna):
+    # ensure that we do not coerce to different Index dtype or non-index
+
+    all_data = all_data[:10]
+    if dropna:
+        other = np.array(all_data[~all_data.isna()])
+    else:
+        other = all_data
+
+    result = pd.Index(pd.array(other, dtype=all_data.dtype))
+    expected = pd.Index(other, dtype=all_data.dtype)
+    assert all_data.dtype == expected.dtype  # dont coerce to object
+
+    tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize("dropna", [True, False])
+def test_astype_index(all_data, dropna):
+    # as an int/uint index to Index
+
+    all_data = all_data[:10]
+    if dropna:
+        other = all_data[~all_data.isna()]
+    else:
+        other = all_data
+
+    dtype = all_data.dtype
+    idx = pd.Index(np.array(other))
+    assert isinstance(idx, ABCIndex)
+
+    result = idx.astype(dtype)
+    expected = idx.astype(object).astype(dtype)
+    tm.assert_index_equal(result, expected)
+
+
+def test_astype(all_data):
+    all_data = all_data[:10]
+
+    ints = all_data[~all_data.isna()]
+    mixed = all_data
+    dtype = Int8Dtype()
+
+    # coerce to same type - ints
+    s = pd.Series(ints)
+    result = s.astype(all_data.dtype)
+    expected = pd.Series(ints)
+    tm.assert_series_equal(result, expected)
+
+    # coerce to same other - ints
+    s = pd.Series(ints)
+    result = s.astype(dtype)
+    expected = pd.Series(ints, dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+    # coerce to same numpy_dtype - ints
+    s = pd.Series(ints)
+    result = s.astype(all_data.dtype.numpy_dtype)
+    expected = pd.Series(ints._data.astype(all_data.dtype.numpy_dtype))
+    tm.assert_series_equal(result, expected)
+
+    # coerce to same type - mixed
+    s = pd.Series(mixed)
+    result = s.astype(all_data.dtype)
+    expected = pd.Series(mixed)
+    tm.assert_series_equal(result, expected)
+
+    # coerce to same other - mixed
+    s = pd.Series(mixed)
+    result = s.astype(dtype)
+    expected = pd.Series(mixed, dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+    # coerce to same numpy_dtype - mixed
+    s = pd.Series(mixed)
+    msg = "cannot convert NA to integer"
+    with pytest.raises(ValueError, match=msg):
+        s.astype(all_data.dtype.numpy_dtype)
+
+    # coerce to object
+    s = pd.Series(mixed)
+    result = s.astype("object")
+    expected = pd.Series(np.asarray(mixed, dtype=object))
+    tm.assert_series_equal(result, expected)
+
+
+def test_astype_copy():
+    arr = pd.array([1, 2, 3, None], dtype="Int64")
+    orig = pd.array([1, 2, 3, None], dtype="Int64")
+
+    # copy=True -> ensure both data and mask are actual copies
+    result = arr.astype("Int64", copy=True)
+    assert result is not arr
+    assert not tm.shares_memory(result, arr)
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, orig)
+    result[0] = pd.NA
+    tm.assert_extension_array_equal(arr, orig)
+
+    # copy=False
+    result = arr.astype("Int64", copy=False)
+    assert result is arr
+    assert np.shares_memory(result._data, arr._data)
+    assert np.shares_memory(result._mask, arr._mask)
+    result[0] = 10
+    assert arr[0] == 10
+    result[0] = pd.NA
+    assert arr[0] is pd.NA
+
+    # astype to different dtype -> always needs a copy -> even with copy=False
+    # we need to ensure that also the mask is actually copied
+    arr = pd.array([1, 2, 3, None], dtype="Int64")
+    orig = pd.array([1, 2, 3, None], dtype="Int64")
+
+    result = arr.astype("Int32", copy=False)
+    assert not tm.shares_memory(result, arr)
+    result[0] = 10
+    tm.assert_extension_array_equal(arr, orig)
+    result[0] = pd.NA
+    tm.assert_extension_array_equal(arr, orig)
+
+
+def test_astype_to_larger_numpy():
+    a = pd.array([1, 2], dtype="Int32")
+    result = a.astype("int64")
+    expected = np.array([1, 2], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    a = pd.array([1, 2], dtype="UInt32")
+    result = a.astype("uint64")
+    expected = np.array([1, 2], dtype="uint64")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", [Int8Dtype(), "Int8", UInt32Dtype(), "UInt32"])
+def test_astype_specific_casting(dtype):
+    s = pd.Series([1, 2, 3], dtype="Int64")
+    result = s.astype(dtype)
+    expected = pd.Series([1, 2, 3], dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+    s = pd.Series([1, 2, 3, None], dtype="Int64")
+    result = s.astype(dtype)
+    expected = pd.Series([1, 2, 3, None], dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+
+def test_astype_floating():
+    arr = pd.array([1, 2, None], dtype="Int64")
+    result = arr.astype("Float64")
+    expected = pd.array([1.0, 2.0, None], dtype="Float64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_astype_dt64():
+    # GH#32435
+    arr = pd.array([1, 2, 3, pd.NA]) * 10**9
+
+    result = arr.astype("datetime64[ns]")
+
+    expected = np.array([1, 2, 3, "NaT"], dtype="M8[s]").astype("M8[ns]")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_construct_cast_invalid(dtype):
+    msg = "cannot safely"
+    arr = [1.2, 2.3, 3.7]
+    with pytest.raises(TypeError, match=msg):
+        pd.array(arr, dtype=dtype)
+
+    with pytest.raises(TypeError, match=msg):
+        pd.Series(arr).astype(dtype)
+
+    arr = [1.2, 2.3, 3.7, np.nan]
+    with pytest.raises(TypeError, match=msg):
+        pd.array(arr, dtype=dtype)
+
+    with pytest.raises(TypeError, match=msg):
+        pd.Series(arr).astype(dtype)
+
+
+@pytest.mark.parametrize("in_series", [True, False])
+def test_to_numpy_na_nan(in_series):
+    a = pd.array([0, 1, None], dtype="Int64")
+    if in_series:
+        a = pd.Series(a)
+
+    result = a.to_numpy(dtype="float64", na_value=np.nan)
+    expected = np.array([0.0, 1.0, np.nan], dtype="float64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = a.to_numpy(dtype="int64", na_value=-1)
+    expected = np.array([0, 1, -1], dtype="int64")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = a.to_numpy(dtype="bool", na_value=False)
+    expected = np.array([False, True, False], dtype="bool")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("in_series", [True, False])
+@pytest.mark.parametrize("dtype", ["int32", "int64", "bool"])
+def test_to_numpy_dtype(dtype, in_series):
+    a = pd.array([0, 1], dtype="Int64")
+    if in_series:
+        a = pd.Series(a)
+
+    result = a.to_numpy(dtype=dtype)
+    expected = np.array([0, 1], dtype=dtype)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["int64", "bool"])
+def test_to_numpy_na_raises(dtype):
+    a = pd.array([0, 1, None], dtype="Int64")
+    with pytest.raises(ValueError, match=dtype):
+        a.to_numpy(dtype=dtype)
+
+
+def test_astype_str():
+    a = pd.array([1, 2, None], dtype="Int64")
+    expected = np.array(["1", "2", "<NA>"], dtype=f"{tm.ENDIAN}U21")
+
+    tm.assert_numpy_array_equal(a.astype(str), expected)
+    tm.assert_numpy_array_equal(a.astype("str"), expected)
+
+
+def test_astype_boolean():
+    # https://github.com/pandas-dev/pandas/issues/31102
+    a = pd.array([1, 0, -1, 2, None], dtype="Int64")
+    result = a.astype("boolean")
+    expected = pd.array([True, False, True, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_function.py

@@ -0,0 +1,203 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import FloatingArray
+
+
+@pytest.mark.parametrize("ufunc", [np.abs, np.sign])
+# np.sign emits a warning with nans, <https://github.com/numpy/numpy/issues/15127>
+@pytest.mark.filterwarnings("ignore:invalid value encountered in sign:RuntimeWarning")
+def test_ufuncs_single_int(ufunc):
+    a = pd.array([1, 2, -3, np.nan])
+    result = ufunc(a)
+    expected = pd.array(ufunc(a.astype(float)), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    s = pd.Series(a)
+    result = ufunc(s)
+    expected = pd.Series(pd.array(ufunc(a.astype(float)), dtype="Int64"))
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("ufunc", [np.log, np.exp, np.sin, np.cos, np.sqrt])
+def test_ufuncs_single_float(ufunc):
+    a = pd.array([1, 2, -3, np.nan])
+    with np.errstate(invalid="ignore"):
+        result = ufunc(a)
+        expected = FloatingArray(ufunc(a.astype(float)), mask=a._mask)
+    tm.assert_extension_array_equal(result, expected)
+
+    s = pd.Series(a)
+    with np.errstate(invalid="ignore"):
+        result = ufunc(s)
+    expected = pd.Series(expected)
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("ufunc", [np.add, np.subtract])
+def test_ufuncs_binary_int(ufunc):
+    # two IntegerArrays
+    a = pd.array([1, 2, -3, np.nan])
+    result = ufunc(a, a)
+    expected = pd.array(ufunc(a.astype(float), a.astype(float)), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    # IntegerArray with numpy array
+    arr = np.array([1, 2, 3, 4])
+    result = ufunc(a, arr)
+    expected = pd.array(ufunc(a.astype(float), arr), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(arr, a)
+    expected = pd.array(ufunc(arr, a.astype(float)), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    # IntegerArray with scalar
+    result = ufunc(a, 1)
+    expected = pd.array(ufunc(a.astype(float), 1), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = ufunc(1, a)
+    expected = pd.array(ufunc(1, a.astype(float)), dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_ufunc_binary_output():
+    a = pd.array([1, 2, np.nan])
+    result = np.modf(a)
+    expected = np.modf(a.to_numpy(na_value=np.nan, dtype="float"))
+    expected = (pd.array(expected[0]), pd.array(expected[1]))
+
+    assert isinstance(result, tuple)
+    assert len(result) == 2
+
+    for x, y in zip(result, expected):
+        tm.assert_extension_array_equal(x, y)
+
+
+@pytest.mark.parametrize("values", [[0, 1], [0, None]])
+def test_ufunc_reduce_raises(values):
+    arr = pd.array(values)
+
+    res = np.add.reduce(arr)
+    expected = arr.sum(skipna=False)
+    tm.assert_almost_equal(res, expected)
+
+
+@pytest.mark.parametrize(
+    "pandasmethname, kwargs",
+    [
+        ("var", {"ddof": 0}),
+        ("var", {"ddof": 1}),
+        ("std", {"ddof": 0}),
+        ("std", {"ddof": 1}),
+        ("kurtosis", {}),
+        ("skew", {}),
+        ("sem", {}),
+    ],
+)
+def test_stat_method(pandasmethname, kwargs):
+    s = pd.Series(data=[1, 2, 3, 4, 5, 6, np.nan, np.nan], dtype="Int64")
+    pandasmeth = getattr(s, pandasmethname)
+    result = pandasmeth(**kwargs)
+    s2 = pd.Series(data=[1, 2, 3, 4, 5, 6], dtype="Int64")
+    pandasmeth = getattr(s2, pandasmethname)
+    expected = pandasmeth(**kwargs)
+    assert expected == result
+
+
+def test_value_counts_na():
+    arr = pd.array([1, 2, 1, pd.NA], dtype="Int64")
+    result = arr.value_counts(dropna=False)
+    ex_index = pd.Index([1, 2, pd.NA], dtype="Int64")
+    assert ex_index.dtype == "Int64"
+    expected = pd.Series([2, 1, 1], index=ex_index, dtype="Int64", name="count")
+    tm.assert_series_equal(result, expected)
+
+    result = arr.value_counts(dropna=True)
+    expected = pd.Series([2, 1], index=arr[:2], dtype="Int64", name="count")
+    assert expected.index.dtype == arr.dtype
+    tm.assert_series_equal(result, expected)
+
+
+def test_value_counts_empty():
+    # https://github.com/pandas-dev/pandas/issues/33317
+    ser = pd.Series([], dtype="Int64")
+    result = ser.value_counts()
+    idx = pd.Index([], dtype=ser.dtype)
+    assert idx.dtype == ser.dtype
+    expected = pd.Series([], index=idx, dtype="Int64", name="count")
+    tm.assert_series_equal(result, expected)
+
+
+def test_value_counts_with_normalize():
+    # GH 33172
+    ser = pd.Series([1, 2, 1, pd.NA], dtype="Int64")
+    result = ser.value_counts(normalize=True)
+    expected = pd.Series([2, 1], index=ser[:2], dtype="Float64", name="proportion") / 3
+    assert expected.index.dtype == ser.dtype
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("min_count", [0, 4])
+def test_integer_array_sum(skipna, min_count, any_int_ea_dtype):
+    dtype = any_int_ea_dtype
+    arr = pd.array([1, 2, 3, None], dtype=dtype)
+    result = arr.sum(skipna=skipna, min_count=min_count)
+    if skipna and min_count == 0:
+        assert result == 6
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("method", ["min", "max"])
+def test_integer_array_min_max(skipna, method, any_int_ea_dtype):
+    dtype = any_int_ea_dtype
+    arr = pd.array([0, 1, None], dtype=dtype)
+    func = getattr(arr, method)
+    result = func(skipna=skipna)
+    if skipna:
+        assert result == (0 if method == "min" else 1)
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize("skipna", [True, False])
+@pytest.mark.parametrize("min_count", [0, 9])
+def test_integer_array_prod(skipna, min_count, any_int_ea_dtype):
+    dtype = any_int_ea_dtype
+    arr = pd.array([1, 2, None], dtype=dtype)
+    result = arr.prod(skipna=skipna, min_count=min_count)
+    if skipna and min_count == 0:
+        assert result == 2
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize(
+    "values, expected", [([1, 2, 3], 6), ([1, 2, 3, None], 6), ([None], 0)]
+)
+def test_integer_array_numpy_sum(values, expected):
+    arr = pd.array(values, dtype="Int64")
+    result = np.sum(arr)
+    assert result == expected
+
+
+@pytest.mark.parametrize("op", ["sum", "prod", "min", "max"])
+def test_dataframe_reductions(op):
+    # https://github.com/pandas-dev/pandas/pull/32867
+    # ensure the integers are not cast to float during reductions
+    df = pd.DataFrame({"a": pd.array([1, 2], dtype="Int64")})
+    result = df.max()
+    assert isinstance(result["a"], np.int64)
+
+
+# TODO(jreback) - these need testing / are broken
+
+# shift
+
+# set_index (destroys type)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_indexing.py

@@ -0,0 +1,19 @@
+import pandas as pd
+import pandas._testing as tm
+
+
+def test_array_setitem_nullable_boolean_mask():
+    # GH 31446
+    ser = pd.Series([1, 2], dtype="Int64")
+    result = ser.where(ser > 1)
+    expected = pd.Series([pd.NA, 2], dtype="Int64")
+    tm.assert_series_equal(result, expected)
+
+
+def test_array_setitem():
+    # GH 31446
+    arr = pd.Series([1, 2], dtype="Int64").array
+    arr[arr > 1] = 1
+
+    expected = pd.array([1, 1], dtype="Int64")
+    tm.assert_extension_array_equal(arr, expected)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_reduction.py

@@ -0,0 +1,125 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Series,
+    array,
+)
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize(
+    "op, expected",
+    [
+        ["sum", np.int64(3)],
+        ["prod", np.int64(2)],
+        ["min", np.int64(1)],
+        ["max", np.int64(2)],
+        ["mean", np.float64(1.5)],
+        ["median", np.float64(1.5)],
+        ["var", np.float64(0.5)],
+        ["std", np.float64(0.5**0.5)],
+        ["skew", pd.NA],
+        ["kurt", pd.NA],
+        ["any", True],
+        ["all", True],
+    ],
+)
+def test_series_reductions(op, expected):
+    ser = Series([1, 2], dtype="Int64")
+    result = getattr(ser, op)()
+    tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "op, expected",
+    [
+        ["sum", Series([3], index=["a"], dtype="Int64")],
+        ["prod", Series([2], index=["a"], dtype="Int64")],
+        ["min", Series([1], index=["a"], dtype="Int64")],
+        ["max", Series([2], index=["a"], dtype="Int64")],
+        ["mean", Series([1.5], index=["a"], dtype="Float64")],
+        ["median", Series([1.5], index=["a"], dtype="Float64")],
+        ["var", Series([0.5], index=["a"], dtype="Float64")],
+        ["std", Series([0.5**0.5], index=["a"], dtype="Float64")],
+        ["skew", Series([pd.NA], index=["a"], dtype="Float64")],
+        ["kurt", Series([pd.NA], index=["a"], dtype="Float64")],
+        ["any", Series([True], index=["a"], dtype="boolean")],
+        ["all", Series([True], index=["a"], dtype="boolean")],
+    ],
+)
+def test_dataframe_reductions(op, expected):
+    df = DataFrame({"a": array([1, 2], dtype="Int64")})
+    result = getattr(df, op)()
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "op, expected",
+    [
+        ["sum", array([1, 3], dtype="Int64")],
+        ["prod", array([1, 3], dtype="Int64")],
+        ["min", array([1, 3], dtype="Int64")],
+        ["max", array([1, 3], dtype="Int64")],
+        ["mean", array([1, 3], dtype="Float64")],
+        ["median", array([1, 3], dtype="Float64")],
+        ["var", array([pd.NA], dtype="Float64")],
+        ["std", array([pd.NA], dtype="Float64")],
+        ["skew", array([pd.NA], dtype="Float64")],
+        ["any", array([True, True], dtype="boolean")],
+        ["all", array([True, True], dtype="boolean")],
+    ],
+)
+def test_groupby_reductions(op, expected):
+    df = DataFrame(
+        {
+            "A": ["a", "b", "b"],
+            "B": array([1, None, 3], dtype="Int64"),
+        }
+    )
+    result = getattr(df.groupby("A"), op)()
+    expected = DataFrame(expected, index=pd.Index(["a", "b"], name="A"), columns=["B"])
+
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "op, expected",
+    [
+        ["sum", Series([4, 4], index=["B", "C"], dtype="Float64")],
+        ["prod", Series([3, 3], index=["B", "C"], dtype="Float64")],
+        ["min", Series([1, 1], index=["B", "C"], dtype="Float64")],
+        ["max", Series([3, 3], index=["B", "C"], dtype="Float64")],
+        ["mean", Series([2, 2], index=["B", "C"], dtype="Float64")],
+        ["median", Series([2, 2], index=["B", "C"], dtype="Float64")],
+        ["var", Series([2, 2], index=["B", "C"], dtype="Float64")],
+        ["std", Series([2**0.5, 2**0.5], index=["B", "C"], dtype="Float64")],
+        ["skew", Series([pd.NA, pd.NA], index=["B", "C"], dtype="Float64")],
+        ["kurt", Series([pd.NA, pd.NA], index=["B", "C"], dtype="Float64")],
+        ["any", Series([True, True, True], index=["A", "B", "C"], dtype="boolean")],
+        ["all", Series([True, True, True], index=["A", "B", "C"], dtype="boolean")],
+    ],
+)
+def test_mixed_reductions(op, expected, using_infer_string):
+    if op in ["any", "all"] and using_infer_string:
+        expected = expected.astype("bool")
+    df = DataFrame(
+        {
+            "A": ["a", "b", "b"],
+            "B": [1, None, 3],
+            "C": array([1, None, 3], dtype="Int64"),
+        }
+    )
+
+    # series
+    result = getattr(df.C, op)()
+    tm.assert_equal(result, expected["C"])
+
+    # frame
+    if op in ["any", "all"]:
+        result = getattr(df, op)()
+    else:
+        result = getattr(df, op)(numeric_only=True)
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/integer/test_repr.py

@@ -0,0 +1,67 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    Int16Dtype,
+    Int32Dtype,
+    Int64Dtype,
+    UInt8Dtype,
+    UInt16Dtype,
+    UInt32Dtype,
+    UInt64Dtype,
+)
+
+
+def test_dtypes(dtype):
+    # smoke tests on auto dtype construction
+
+    if dtype.is_signed_integer:
+        assert np.dtype(dtype.type).kind == "i"
+    else:
+        assert np.dtype(dtype.type).kind == "u"
+    assert dtype.name is not None
+
+
+@pytest.mark.parametrize(
+    "dtype, expected",
+    [
+        (Int8Dtype(), "Int8Dtype()"),
+        (Int16Dtype(), "Int16Dtype()"),
+        (Int32Dtype(), "Int32Dtype()"),
+        (Int64Dtype(), "Int64Dtype()"),
+        (UInt8Dtype(), "UInt8Dtype()"),
+        (UInt16Dtype(), "UInt16Dtype()"),
+        (UInt32Dtype(), "UInt32Dtype()"),
+        (UInt64Dtype(), "UInt64Dtype()"),
+    ],
+)
+def test_repr_dtype(dtype, expected):
+    assert repr(dtype) == expected
+
+
+def test_repr_array():
+    result = repr(pd.array([1, None, 3]))
+    expected = "<IntegerArray>\n[1, <NA>, 3]\nLength: 3, dtype: Int64"
+    assert result == expected
+
+
+def test_repr_array_long():
+    data = pd.array([1, 2, None] * 1000)
+    expected = (
+        "<IntegerArray>\n"
+        "[   1,    2, <NA>,    1,    2, <NA>,    1,    2, <NA>,    1,\n"
+        " ...\n"
+        " <NA>,    1,    2, <NA>,    1,    2, <NA>,    1,    2, <NA>]\n"
+        "Length: 3000, dtype: Int64"
+    )
+    result = repr(data)
+    assert result == expected
+
+
+def test_frame_repr(data_missing):
+    df = pd.DataFrame({"A": data_missing})
+    result = repr(df)
+    expected = "      A\n0  <NA>\n1     1"
+    assert result == expected

lib/python3.13/site-packages/pandas/tests/arrays/interval/test_astype.py

@@ -0,0 +1,28 @@
+import pytest
+
+from pandas import (
+    Categorical,
+    CategoricalDtype,
+    Index,
+    IntervalIndex,
+)
+import pandas._testing as tm
+
+
+class TestAstype:
+    @pytest.mark.parametrize("ordered", [True, False])
+    def test_astype_categorical_retains_ordered(self, ordered):
+        index = IntervalIndex.from_breaks(range(5))
+        arr = index._data
+
+        dtype = CategoricalDtype(None, ordered=ordered)
+
+        expected = Categorical(list(arr), ordered=ordered)
+        result = arr.astype(dtype)
+        assert result.ordered is ordered
+        tm.assert_categorical_equal(result, expected)
+
+        # test IntervalIndex.astype while we're at it.
+        result = index.astype(dtype)
+        expected = Index(expected)
+        tm.assert_index_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/interval/test_formats.py

@@ -0,0 +1,13 @@
+from pandas.core.arrays import IntervalArray
+
+
+def test_repr():
+    # GH#25022
+    arr = IntervalArray.from_tuples([(0, 1), (1, 2)])
+    result = repr(arr)
+    expected = (
+        "<IntervalArray>\n"
+        "[(0, 1], (1, 2]]\n"
+        "Length: 2, dtype: interval[int64, right]"
+    )
+    assert result == expected

lib/python3.13/site-packages/pandas/tests/arrays/interval/test_interval.py

@@ -0,0 +1,231 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    Index,
+    Interval,
+    IntervalIndex,
+    Timedelta,
+    Timestamp,
+    date_range,
+    timedelta_range,
+)
+import pandas._testing as tm
+from pandas.core.arrays import IntervalArray
+
+
+@pytest.fixture(
+    params=[
+        (Index([0, 2, 4]), Index([1, 3, 5])),
+        (Index([0.0, 1.0, 2.0]), Index([1.0, 2.0, 3.0])),
+        (timedelta_range("0 days", periods=3), timedelta_range("1 day", periods=3)),
+        (date_range("20170101", periods=3), date_range("20170102", periods=3)),
+        (
+            date_range("20170101", periods=3, tz="US/Eastern"),
+            date_range("20170102", periods=3, tz="US/Eastern"),
+        ),
+    ],
+    ids=lambda x: str(x[0].dtype),
+)
+def left_right_dtypes(request):
+    """
+    Fixture for building an IntervalArray from various dtypes
+    """
+    return request.param
+
+
+class TestAttributes:
+    @pytest.mark.parametrize(
+        "left, right",
+        [
+            (0, 1),
+            (Timedelta("0 days"), Timedelta("1 day")),
+            (Timestamp("2018-01-01"), Timestamp("2018-01-02")),
+            (
+                Timestamp("2018-01-01", tz="US/Eastern"),
+                Timestamp("2018-01-02", tz="US/Eastern"),
+            ),
+        ],
+    )
+    @pytest.mark.parametrize("constructor", [IntervalArray, IntervalIndex])
+    def test_is_empty(self, constructor, left, right, closed):
+        # GH27219
+        tuples = [(left, left), (left, right), np.nan]
+        expected = np.array([closed != "both", False, False])
+        result = constructor.from_tuples(tuples, closed=closed).is_empty
+        tm.assert_numpy_array_equal(result, expected)
+
+
+class TestMethods:
+    @pytest.mark.parametrize("new_closed", ["left", "right", "both", "neither"])
+    def test_set_closed(self, closed, new_closed):
+        # GH 21670
+        array = IntervalArray.from_breaks(range(10), closed=closed)
+        result = array.set_closed(new_closed)
+        expected = IntervalArray.from_breaks(range(10), closed=new_closed)
+        tm.assert_extension_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            Interval(0, 1, closed="right"),
+            IntervalArray.from_breaks([1, 2, 3, 4], closed="right"),
+        ],
+    )
+    def test_where_raises(self, other):
+        # GH#45768 The IntervalArray methods raises; the Series method coerces
+        ser = pd.Series(IntervalArray.from_breaks([1, 2, 3, 4], closed="left"))
+        mask = np.array([True, False, True])
+        match = "'value.closed' is 'right', expected 'left'."
+        with pytest.raises(ValueError, match=match):
+            ser.array._where(mask, other)
+
+        res = ser.where(mask, other=other)
+        expected = ser.astype(object).where(mask, other)
+        tm.assert_series_equal(res, expected)
+
+    def test_shift(self):
+        # https://github.com/pandas-dev/pandas/issues/31495, GH#22428, GH#31502
+        a = IntervalArray.from_breaks([1, 2, 3])
+        result = a.shift()
+        # int -> float
+        expected = IntervalArray.from_tuples([(np.nan, np.nan), (1.0, 2.0)])
+        tm.assert_interval_array_equal(result, expected)
+
+        msg = "can only insert Interval objects and NA into an IntervalArray"
+        with pytest.raises(TypeError, match=msg):
+            a.shift(1, fill_value=pd.NaT)
+
+    def test_shift_datetime(self):
+        # GH#31502, GH#31504
+        a = IntervalArray.from_breaks(date_range("2000", periods=4))
+        result = a.shift(2)
+        expected = a.take([-1, -1, 0], allow_fill=True)
+        tm.assert_interval_array_equal(result, expected)
+
+        result = a.shift(-1)
+        expected = a.take([1, 2, -1], allow_fill=True)
+        tm.assert_interval_array_equal(result, expected)
+
+        msg = "can only insert Interval objects and NA into an IntervalArray"
+        with pytest.raises(TypeError, match=msg):
+            a.shift(1, fill_value=np.timedelta64("NaT", "ns"))
+
+
+class TestSetitem:
+    def test_set_na(self, left_right_dtypes):
+        left, right = left_right_dtypes
+        left = left.copy(deep=True)
+        right = right.copy(deep=True)
+        result = IntervalArray.from_arrays(left, right)
+
+        if result.dtype.subtype.kind not in ["m", "M"]:
+            msg = "'value' should be an interval type, got <.*NaTType'> instead."
+            with pytest.raises(TypeError, match=msg):
+                result[0] = pd.NaT
+        if result.dtype.subtype.kind in ["i", "u"]:
+            msg = "Cannot set float NaN to integer-backed IntervalArray"
+            # GH#45484 TypeError, not ValueError, matches what we get with
+            # non-NA un-holdable value.
+            with pytest.raises(TypeError, match=msg):
+                result[0] = np.nan
+            return
+
+        result[0] = np.nan
+
+        expected_left = Index([left._na_value] + list(left[1:]))
+        expected_right = Index([right._na_value] + list(right[1:]))
+        expected = IntervalArray.from_arrays(expected_left, expected_right)
+
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_setitem_mismatched_closed(self):
+        arr = IntervalArray.from_breaks(range(4))
+        orig = arr.copy()
+        other = arr.set_closed("both")
+
+        msg = "'value.closed' is 'both', expected 'right'"
+        with pytest.raises(ValueError, match=msg):
+            arr[0] = other[0]
+        with pytest.raises(ValueError, match=msg):
+            arr[:1] = other[:1]
+        with pytest.raises(ValueError, match=msg):
+            arr[:0] = other[:0]
+        with pytest.raises(ValueError, match=msg):
+            arr[:] = other[::-1]
+        with pytest.raises(ValueError, match=msg):
+            arr[:] = list(other[::-1])
+        with pytest.raises(ValueError, match=msg):
+            arr[:] = other[::-1].astype(object)
+        with pytest.raises(ValueError, match=msg):
+            arr[:] = other[::-1].astype("category")
+
+        # empty list should be no-op
+        arr[:0] = []
+        tm.assert_interval_array_equal(arr, orig)
+
+
+class TestReductions:
+    def test_min_max_invalid_axis(self, left_right_dtypes):
+        left, right = left_right_dtypes
+        left = left.copy(deep=True)
+        right = right.copy(deep=True)
+        arr = IntervalArray.from_arrays(left, right)
+
+        msg = "`axis` must be fewer than the number of dimensions"
+        for axis in [-2, 1]:
+            with pytest.raises(ValueError, match=msg):
+                arr.min(axis=axis)
+            with pytest.raises(ValueError, match=msg):
+                arr.max(axis=axis)
+
+        msg = "'>=' not supported between"
+        with pytest.raises(TypeError, match=msg):
+            arr.min(axis="foo")
+        with pytest.raises(TypeError, match=msg):
+            arr.max(axis="foo")
+
+    def test_min_max(self, left_right_dtypes, index_or_series_or_array):
+        # GH#44746
+        left, right = left_right_dtypes
+        left = left.copy(deep=True)
+        right = right.copy(deep=True)
+        arr = IntervalArray.from_arrays(left, right)
+
+        # The expected results below are only valid if monotonic
+        assert left.is_monotonic_increasing
+        assert Index(arr).is_monotonic_increasing
+
+        MIN = arr[0]
+        MAX = arr[-1]
+
+        indexer = np.arange(len(arr))
+        np.random.default_rng(2).shuffle(indexer)
+        arr = arr.take(indexer)
+
+        arr_na = arr.insert(2, np.nan)
+
+        arr = index_or_series_or_array(arr)
+        arr_na = index_or_series_or_array(arr_na)
+
+        for skipna in [True, False]:
+            res = arr.min(skipna=skipna)
+            assert res == MIN
+            assert type(res) == type(MIN)
+
+            res = arr.max(skipna=skipna)
+            assert res == MAX
+            assert type(res) == type(MAX)
+
+        res = arr_na.min(skipna=False)
+        assert np.isnan(res)
+        res = arr_na.max(skipna=False)
+        assert np.isnan(res)
+
+        res = arr_na.min(skipna=True)
+        assert res == MIN
+        assert type(res) == type(MIN)
+        res = arr_na.max(skipna=True)
+        assert res == MAX
+        assert type(res) == type(MAX)

lib/python3.13/site-packages/pandas/tests/arrays/interval/test_interval_pyarrow.py

@@ -0,0 +1,160 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import IntervalArray
+
+
+def test_arrow_extension_type():
+    pa = pytest.importorskip("pyarrow")
+
+    from pandas.core.arrays.arrow.extension_types import ArrowIntervalType
+
+    p1 = ArrowIntervalType(pa.int64(), "left")
+    p2 = ArrowIntervalType(pa.int64(), "left")
+    p3 = ArrowIntervalType(pa.int64(), "right")
+
+    assert p1.closed == "left"
+    assert p1 == p2
+    assert p1 != p3
+    assert hash(p1) == hash(p2)
+    assert hash(p1) != hash(p3)
+
+
+def test_arrow_array():
+    pa = pytest.importorskip("pyarrow")
+
+    from pandas.core.arrays.arrow.extension_types import ArrowIntervalType
+
+    intervals = pd.interval_range(1, 5, freq=1).array
+
+    result = pa.array(intervals)
+    assert isinstance(result.type, ArrowIntervalType)
+    assert result.type.closed == intervals.closed
+    assert result.type.subtype == pa.int64()
+    assert result.storage.field("left").equals(pa.array([1, 2, 3, 4], type="int64"))
+    assert result.storage.field("right").equals(pa.array([2, 3, 4, 5], type="int64"))
+
+    expected = pa.array([{"left": i, "right": i + 1} for i in range(1, 5)])
+    assert result.storage.equals(expected)
+
+    # convert to its storage type
+    result = pa.array(intervals, type=expected.type)
+    assert result.equals(expected)
+
+    # unsupported conversions
+    with pytest.raises(TypeError, match="Not supported to convert IntervalArray"):
+        pa.array(intervals, type="float64")
+
+    with pytest.raises(TypeError, match="Not supported to convert IntervalArray"):
+        pa.array(intervals, type=ArrowIntervalType(pa.float64(), "left"))
+
+
+def test_arrow_array_missing():
+    pa = pytest.importorskip("pyarrow")
+
+    from pandas.core.arrays.arrow.extension_types import ArrowIntervalType
+
+    arr = IntervalArray.from_breaks([0.0, 1.0, 2.0, 3.0])
+    arr[1] = None
+
+    result = pa.array(arr)
+    assert isinstance(result.type, ArrowIntervalType)
+    assert result.type.closed == arr.closed
+    assert result.type.subtype == pa.float64()
+
+    # fields have missing values (not NaN)
+    left = pa.array([0.0, None, 2.0], type="float64")
+    right = pa.array([1.0, None, 3.0], type="float64")
+    assert result.storage.field("left").equals(left)
+    assert result.storage.field("right").equals(right)
+
+    # structarray itself also has missing values on the array level
+    vals = [
+        {"left": 0.0, "right": 1.0},
+        {"left": None, "right": None},
+        {"left": 2.0, "right": 3.0},
+    ]
+    expected = pa.StructArray.from_pandas(vals, mask=np.array([False, True, False]))
+    assert result.storage.equals(expected)
+
+
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+@pytest.mark.parametrize(
+    "breaks",
+    [[0.0, 1.0, 2.0, 3.0], pd.date_range("2017", periods=4, freq="D")],
+    ids=["float", "datetime64[ns]"],
+)
+def test_arrow_table_roundtrip(breaks):
+    pa = pytest.importorskip("pyarrow")
+
+    from pandas.core.arrays.arrow.extension_types import ArrowIntervalType
+
+    arr = IntervalArray.from_breaks(breaks)
+    arr[1] = None
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    assert isinstance(table.field("a").type, ArrowIntervalType)
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, pd.IntervalDtype)
+    tm.assert_frame_equal(result, df)
+
+    table2 = pa.concat_tables([table, table])
+    result = table2.to_pandas()
+    expected = pd.concat([df, df], ignore_index=True)
+    tm.assert_frame_equal(result, expected)
+
+    # GH#41040
+    table = pa.table(
+        [pa.chunked_array([], type=table.column(0).type)], schema=table.schema
+    )
+    result = table.to_pandas()
+    tm.assert_frame_equal(result, expected[0:0])
+
+
+@pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+@pytest.mark.parametrize(
+    "breaks",
+    [[0.0, 1.0, 2.0, 3.0], pd.date_range("2017", periods=4, freq="D")],
+    ids=["float", "datetime64[ns]"],
+)
+def test_arrow_table_roundtrip_without_metadata(breaks):
+    pa = pytest.importorskip("pyarrow")
+
+    arr = IntervalArray.from_breaks(breaks)
+    arr[1] = None
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    # remove the metadata
+    table = table.replace_schema_metadata()
+    assert table.schema.metadata is None
+
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, pd.IntervalDtype)
+    tm.assert_frame_equal(result, df)
+
+
+def test_from_arrow_from_raw_struct_array():
+    # in case pyarrow lost the Interval extension type (eg on parquet roundtrip
+    # with datetime64[ns] subtype, see GH-45881), still allow conversion
+    # from arrow to IntervalArray
+    pa = pytest.importorskip("pyarrow")
+
+    arr = pa.array([{"left": 0, "right": 1}, {"left": 1, "right": 2}])
+    dtype = pd.IntervalDtype(np.dtype("int64"), closed="neither")
+
+    result = dtype.__from_arrow__(arr)
+    expected = IntervalArray.from_breaks(
+        np.array([0, 1, 2], dtype="int64"), closed="neither"
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    result = dtype.__from_arrow__(pa.chunked_array([arr]))
+    tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/interval/test_overlaps.py

@@ -0,0 +1,93 @@
+"""Tests for Interval-Interval operations, such as overlaps, contains, etc."""
+import numpy as np
+import pytest
+
+from pandas import (
+    Interval,
+    IntervalIndex,
+    Timedelta,
+    Timestamp,
+)
+import pandas._testing as tm
+from pandas.core.arrays import IntervalArray
+
+
+@pytest.fixture(params=[IntervalArray, IntervalIndex])
+def constructor(request):
+    """
+    Fixture for testing both interval container classes.
+    """
+    return request.param
+
+
+@pytest.fixture(
+    params=[
+        (Timedelta("0 days"), Timedelta("1 day")),
+        (Timestamp("2018-01-01"), Timedelta("1 day")),
+        (0, 1),
+    ],
+    ids=lambda x: type(x[0]).__name__,
+)
+def start_shift(request):
+    """
+    Fixture for generating intervals of different types from a start value
+    and a shift value that can be added to start to generate an endpoint.
+    """
+    return request.param
+
+
+class TestOverlaps:
+    def test_overlaps_interval(self, constructor, start_shift, closed, other_closed):
+        start, shift = start_shift
+        interval = Interval(start, start + 3 * shift, other_closed)
+
+        # intervals: identical, nested, spanning, partial, adjacent, disjoint
+        tuples = [
+            (start, start + 3 * shift),
+            (start + shift, start + 2 * shift),
+            (start - shift, start + 4 * shift),
+            (start + 2 * shift, start + 4 * shift),
+            (start + 3 * shift, start + 4 * shift),
+            (start + 4 * shift, start + 5 * shift),
+        ]
+        interval_container = constructor.from_tuples(tuples, closed)
+
+        adjacent = interval.closed_right and interval_container.closed_left
+        expected = np.array([True, True, True, True, adjacent, False])
+        result = interval_container.overlaps(interval)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("other_constructor", [IntervalArray, IntervalIndex])
+    def test_overlaps_interval_container(self, constructor, other_constructor):
+        # TODO: modify this test when implemented
+        interval_container = constructor.from_breaks(range(5))
+        other_container = other_constructor.from_breaks(range(5))
+        with pytest.raises(NotImplementedError, match="^$"):
+            interval_container.overlaps(other_container)
+
+    def test_overlaps_na(self, constructor, start_shift):
+        """NA values are marked as False"""
+        start, shift = start_shift
+        interval = Interval(start, start + shift)
+
+        tuples = [
+            (start, start + shift),
+            np.nan,
+            (start + 2 * shift, start + 3 * shift),
+        ]
+        interval_container = constructor.from_tuples(tuples)
+
+        expected = np.array([True, False, False])
+        result = interval_container.overlaps(interval)
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "other",
+        [10, True, "foo", Timedelta("1 day"), Timestamp("2018-01-01")],
+        ids=lambda x: type(x).__name__,
+    )
+    def test_overlaps_invalid_type(self, constructor, other):
+        interval_container = constructor.from_breaks(range(5))
+        msg = f"`other` must be Interval-like, got {type(other).__name__}"
+        with pytest.raises(TypeError, match=msg):
+            interval_container.overlaps(other)

lib/python3.13/site-packages/pandas/tests/arrays/masked/test_arithmetic.py

@@ -0,0 +1,248 @@
+from __future__ import annotations
+
+from typing import Any
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+# integer dtypes
+arrays = [pd.array([1, 2, 3, None], dtype=dtype) for dtype in tm.ALL_INT_EA_DTYPES]
+scalars: list[Any] = [2] * len(arrays)
+# floating dtypes
+arrays += [pd.array([0.1, 0.2, 0.3, None], dtype=dtype) for dtype in tm.FLOAT_EA_DTYPES]
+scalars += [0.2, 0.2]
+# boolean
+arrays += [pd.array([True, False, True, None], dtype="boolean")]
+scalars += [False]
+
+
+@pytest.fixture(params=zip(arrays, scalars), ids=[a.dtype.name for a in arrays])
+def data(request):
+    """Fixture returning parametrized (array, scalar) tuple.
+
+    Used to test equivalence of scalars, numpy arrays with array ops, and the
+    equivalence of DataFrame and Series ops.
+    """
+    return request.param
+
+
+def check_skip(data, op_name):
+    if isinstance(data.dtype, pd.BooleanDtype) and "sub" in op_name:
+        pytest.skip("subtract not implemented for boolean")
+
+
+def is_bool_not_implemented(data, op_name):
+    # match non-masked behavior
+    return data.dtype.kind == "b" and op_name.strip("_").lstrip("r") in [
+        "pow",
+        "truediv",
+        "floordiv",
+    ]
+
+
+# Test equivalence of scalars, numpy arrays with array ops
+# -----------------------------------------------------------------------------
+
+
+def test_array_scalar_like_equivalence(data, all_arithmetic_operators):
+    data, scalar = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    check_skip(data, all_arithmetic_operators)
+
+    scalar_array = pd.array([scalar] * len(data), dtype=data.dtype)
+
+    # TODO also add len-1 array (np.array([scalar], dtype=data.dtype.numpy_dtype))
+    for scalar in [scalar, data.dtype.type(scalar)]:
+        if is_bool_not_implemented(data, all_arithmetic_operators):
+            msg = "operator '.*' not implemented for bool dtypes"
+            with pytest.raises(NotImplementedError, match=msg):
+                op(data, scalar)
+            with pytest.raises(NotImplementedError, match=msg):
+                op(data, scalar_array)
+        else:
+            result = op(data, scalar)
+            expected = op(data, scalar_array)
+            tm.assert_extension_array_equal(result, expected)
+
+
+def test_array_NA(data, all_arithmetic_operators):
+    data, _ = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    check_skip(data, all_arithmetic_operators)
+
+    scalar = pd.NA
+    scalar_array = pd.array([pd.NA] * len(data), dtype=data.dtype)
+
+    mask = data._mask.copy()
+
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, scalar)
+        # GH#45421 check op doesn't alter data._mask inplace
+        tm.assert_numpy_array_equal(mask, data._mask)
+        return
+
+    result = op(data, scalar)
+    # GH#45421 check op doesn't alter data._mask inplace
+    tm.assert_numpy_array_equal(mask, data._mask)
+
+    expected = op(data, scalar_array)
+    tm.assert_numpy_array_equal(mask, data._mask)
+
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_numpy_array_equivalence(data, all_arithmetic_operators):
+    data, scalar = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    check_skip(data, all_arithmetic_operators)
+
+    numpy_array = np.array([scalar] * len(data), dtype=data.dtype.numpy_dtype)
+    pd_array = pd.array(numpy_array, dtype=data.dtype)
+
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, numpy_array)
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, pd_array)
+        return
+
+    result = op(data, numpy_array)
+    expected = op(data, pd_array)
+    tm.assert_extension_array_equal(result, expected)
+
+
+# Test equivalence with Series and DataFrame ops
+# -----------------------------------------------------------------------------
+
+
+def test_frame(data, all_arithmetic_operators):
+    data, scalar = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    check_skip(data, all_arithmetic_operators)
+
+    # DataFrame with scalar
+    df = pd.DataFrame({"A": data})
+
+    if is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        with pytest.raises(NotImplementedError, match=msg):
+            op(df, scalar)
+        with pytest.raises(NotImplementedError, match=msg):
+            op(data, scalar)
+        return
+
+    result = op(df, scalar)
+    expected = pd.DataFrame({"A": op(data, scalar)})
+    tm.assert_frame_equal(result, expected)
+
+
+def test_series(data, all_arithmetic_operators):
+    data, scalar = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+    check_skip(data, all_arithmetic_operators)
+
+    ser = pd.Series(data)
+
+    others = [
+        scalar,
+        np.array([scalar] * len(data), dtype=data.dtype.numpy_dtype),
+        pd.array([scalar] * len(data), dtype=data.dtype),
+        pd.Series([scalar] * len(data), dtype=data.dtype),
+    ]
+
+    for other in others:
+        if is_bool_not_implemented(data, all_arithmetic_operators):
+            msg = "operator '.*' not implemented for bool dtypes"
+            with pytest.raises(NotImplementedError, match=msg):
+                op(ser, other)
+
+        else:
+            result = op(ser, other)
+            expected = pd.Series(op(data, other))
+            tm.assert_series_equal(result, expected)
+
+
+# Test generic characteristics / errors
+# -----------------------------------------------------------------------------
+
+
+def test_error_invalid_object(data, all_arithmetic_operators):
+    data, _ = data
+
+    op = all_arithmetic_operators
+    opa = getattr(data, op)
+
+    # 2d -> return NotImplemented
+    result = opa(pd.DataFrame({"A": data}))
+    assert result is NotImplemented
+
+    msg = r"can only perform ops with 1-d structures"
+    with pytest.raises(NotImplementedError, match=msg):
+        opa(np.arange(len(data)).reshape(-1, len(data)))
+
+
+def test_error_len_mismatch(data, all_arithmetic_operators):
+    # operating with a list-like with non-matching length raises
+    data, scalar = data
+    op = tm.get_op_from_name(all_arithmetic_operators)
+
+    other = [scalar] * (len(data) - 1)
+
+    err = ValueError
+    msg = "|".join(
+        [
+            r"operands could not be broadcast together with shapes \(3,\) \(4,\)",
+            r"operands could not be broadcast together with shapes \(4,\) \(3,\)",
+        ]
+    )
+    if data.dtype.kind == "b" and all_arithmetic_operators.strip("_") in [
+        "sub",
+        "rsub",
+    ]:
+        err = TypeError
+        msg = (
+            r"numpy boolean subtract, the `\-` operator, is not supported, use "
+            r"the bitwise_xor, the `\^` operator, or the logical_xor function instead"
+        )
+    elif is_bool_not_implemented(data, all_arithmetic_operators):
+        msg = "operator '.*' not implemented for bool dtypes"
+        err = NotImplementedError
+
+    for other in [other, np.array(other)]:
+        with pytest.raises(err, match=msg):
+            op(data, other)
+
+        s = pd.Series(data)
+        with pytest.raises(err, match=msg):
+            op(s, other)
+
+
+@pytest.mark.parametrize("op", ["__neg__", "__abs__", "__invert__"])
+def test_unary_op_does_not_propagate_mask(data, op):
+    # https://github.com/pandas-dev/pandas/issues/39943
+    data, _ = data
+    ser = pd.Series(data)
+
+    if op == "__invert__" and data.dtype.kind == "f":
+        # we follow numpy in raising
+        msg = "ufunc 'invert' not supported for the input types"
+        with pytest.raises(TypeError, match=msg):
+            getattr(ser, op)()
+        with pytest.raises(TypeError, match=msg):
+            getattr(data, op)()
+        with pytest.raises(TypeError, match=msg):
+            # Check that this is still the numpy behavior
+            getattr(data._data, op)()
+
+        return
+
+    result = getattr(ser, op)()
+    expected = result.copy(deep=True)
+    ser[0] = None
+    tm.assert_series_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/masked/test_arrow_compat.py

@@ -0,0 +1,209 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+
+pa = pytest.importorskip("pyarrow")
+
+from pandas.core.arrays.arrow._arrow_utils import pyarrow_array_to_numpy_and_mask
+
+arrays = [pd.array([1, 2, 3, None], dtype=dtype) for dtype in tm.ALL_INT_EA_DTYPES]
+arrays += [pd.array([0.1, 0.2, 0.3, None], dtype=dtype) for dtype in tm.FLOAT_EA_DTYPES]
+arrays += [pd.array([True, False, True, None], dtype="boolean")]
+
+
+@pytest.fixture(params=arrays, ids=[a.dtype.name for a in arrays])
+def data(request):
+    """
+    Fixture returning parametrized array from given dtype, including integer,
+    float and boolean
+    """
+    return request.param
+
+
+def test_arrow_array(data):
+    arr = pa.array(data)
+    expected = pa.array(
+        data.to_numpy(object, na_value=None),
+        type=pa.from_numpy_dtype(data.dtype.numpy_dtype),
+    )
+    assert arr.equals(expected)
+
+
+def test_arrow_roundtrip(data):
+    df = pd.DataFrame({"a": data})
+    table = pa.table(df)
+    assert table.field("a").type == str(data.dtype.numpy_dtype)
+
+    result = table.to_pandas()
+    assert result["a"].dtype == data.dtype
+    tm.assert_frame_equal(result, df)
+
+
+def test_dataframe_from_arrow_types_mapper():
+    def types_mapper(arrow_type):
+        if pa.types.is_boolean(arrow_type):
+            return pd.BooleanDtype()
+        elif pa.types.is_integer(arrow_type):
+            return pd.Int64Dtype()
+
+    bools_array = pa.array([True, None, False], type=pa.bool_())
+    ints_array = pa.array([1, None, 2], type=pa.int64())
+    small_ints_array = pa.array([-1, 0, 7], type=pa.int8())
+    record_batch = pa.RecordBatch.from_arrays(
+        [bools_array, ints_array, small_ints_array], ["bools", "ints", "small_ints"]
+    )
+    result = record_batch.to_pandas(types_mapper=types_mapper)
+    bools = pd.Series([True, None, False], dtype="boolean")
+    ints = pd.Series([1, None, 2], dtype="Int64")
+    small_ints = pd.Series([-1, 0, 7], dtype="Int64")
+    expected = pd.DataFrame({"bools": bools, "ints": ints, "small_ints": small_ints})
+    tm.assert_frame_equal(result, expected)
+
+
+def test_arrow_load_from_zero_chunks(data):
+    # GH-41040
+
+    df = pd.DataFrame({"a": data[0:0]})
+    table = pa.table(df)
+    assert table.field("a").type == str(data.dtype.numpy_dtype)
+    table = pa.table(
+        [pa.chunked_array([], type=table.field("a").type)], schema=table.schema
+    )
+    result = table.to_pandas()
+    assert result["a"].dtype == data.dtype
+    tm.assert_frame_equal(result, df)
+
+
+def test_arrow_from_arrow_uint():
+    # https://github.com/pandas-dev/pandas/issues/31896
+    # possible mismatch in types
+
+    dtype = pd.UInt32Dtype()
+    result = dtype.__from_arrow__(pa.array([1, 2, 3, 4, None], type="int64"))
+    expected = pd.array([1, 2, 3, 4, None], dtype="UInt32")
+
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_arrow_sliced(data):
+    # https://github.com/pandas-dev/pandas/issues/38525
+
+    df = pd.DataFrame({"a": data})
+    table = pa.table(df)
+    result = table.slice(2, None).to_pandas()
+    expected = df.iloc[2:].reset_index(drop=True)
+    tm.assert_frame_equal(result, expected)
+
+    # no missing values
+    df2 = df.fillna(data[0])
+    table = pa.table(df2)
+    result = table.slice(2, None).to_pandas()
+    expected = df2.iloc[2:].reset_index(drop=True)
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.fixture
+def np_dtype_to_arrays(any_real_numpy_dtype):
+    """
+    Fixture returning actual and expected dtype, pandas and numpy arrays and
+    mask from a given numpy dtype
+    """
+    np_dtype = np.dtype(any_real_numpy_dtype)
+    pa_type = pa.from_numpy_dtype(np_dtype)
+
+    # None ensures the creation of a bitmask buffer.
+    pa_array = pa.array([0, 1, 2, None], type=pa_type)
+    # Since masked Arrow buffer slots are not required to contain a specific
+    # value, assert only the first three values of the created np.array
+    np_expected = np.array([0, 1, 2], dtype=np_dtype)
+    mask_expected = np.array([True, True, True, False])
+    return np_dtype, pa_array, np_expected, mask_expected
+
+
+def test_pyarrow_array_to_numpy_and_mask(np_dtype_to_arrays):
+    """
+    Test conversion from pyarrow array to numpy array.
+
+    Modifies the pyarrow buffer to contain padding and offset, which are
+    considered valid buffers by pyarrow.
+
+    Also tests empty pyarrow arrays with non empty buffers.
+    See https://github.com/pandas-dev/pandas/issues/40896
+    """
+    np_dtype, pa_array, np_expected, mask_expected = np_dtype_to_arrays
+    data, mask = pyarrow_array_to_numpy_and_mask(pa_array, np_dtype)
+    tm.assert_numpy_array_equal(data[:3], np_expected)
+    tm.assert_numpy_array_equal(mask, mask_expected)
+
+    mask_buffer = pa_array.buffers()[0]
+    data_buffer = pa_array.buffers()[1]
+    data_buffer_bytes = pa_array.buffers()[1].to_pybytes()
+
+    # Add trailing padding to the buffer.
+    data_buffer_trail = pa.py_buffer(data_buffer_bytes + b"\x00")
+    pa_array_trail = pa.Array.from_buffers(
+        type=pa_array.type,
+        length=len(pa_array),
+        buffers=[mask_buffer, data_buffer_trail],
+        offset=pa_array.offset,
+    )
+    pa_array_trail.validate()
+    data, mask = pyarrow_array_to_numpy_and_mask(pa_array_trail, np_dtype)
+    tm.assert_numpy_array_equal(data[:3], np_expected)
+    tm.assert_numpy_array_equal(mask, mask_expected)
+
+    # Add offset to the buffer.
+    offset = b"\x00" * (pa_array.type.bit_width // 8)
+    data_buffer_offset = pa.py_buffer(offset + data_buffer_bytes)
+    mask_buffer_offset = pa.py_buffer(b"\x0E")
+    pa_array_offset = pa.Array.from_buffers(
+        type=pa_array.type,
+        length=len(pa_array),
+        buffers=[mask_buffer_offset, data_buffer_offset],
+        offset=pa_array.offset + 1,
+    )
+    pa_array_offset.validate()
+    data, mask = pyarrow_array_to_numpy_and_mask(pa_array_offset, np_dtype)
+    tm.assert_numpy_array_equal(data[:3], np_expected)
+    tm.assert_numpy_array_equal(mask, mask_expected)
+
+    # Empty array
+    np_expected_empty = np.array([], dtype=np_dtype)
+    mask_expected_empty = np.array([], dtype=np.bool_)
+
+    pa_array_offset = pa.Array.from_buffers(
+        type=pa_array.type,
+        length=0,
+        buffers=[mask_buffer, data_buffer],
+        offset=pa_array.offset,
+    )
+    pa_array_offset.validate()
+    data, mask = pyarrow_array_to_numpy_and_mask(pa_array_offset, np_dtype)
+    tm.assert_numpy_array_equal(data[:3], np_expected_empty)
+    tm.assert_numpy_array_equal(mask, mask_expected_empty)
+
+
+@pytest.mark.parametrize(
+    "arr", [pa.nulls(10), pa.chunked_array([pa.nulls(4), pa.nulls(6)])]
+)
+def test_from_arrow_null(data, arr):
+    res = data.dtype.__from_arrow__(arr)
+    assert res.isna().all()
+    assert len(res) == 10
+
+
+def test_from_arrow_type_error(data):
+    # ensure that __from_arrow__ returns a TypeError when getting a wrong
+    # array type
+
+    arr = pa.array(data).cast("string")
+    with pytest.raises(TypeError, match=None):
+        # we don't test the exact error message, only the fact that it raises
+        # a TypeError is relevant
+        data.dtype.__from_arrow__(arr)

lib/python3.13/site-packages/pandas/tests/arrays/masked/test_function.py

@@ -0,0 +1,74 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.common import is_integer_dtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import BaseMaskedArray
+
+arrays = [pd.array([1, 2, 3, None], dtype=dtype) for dtype in tm.ALL_INT_EA_DTYPES]
+arrays += [
+    pd.array([0.141, -0.268, 5.895, None], dtype=dtype) for dtype in tm.FLOAT_EA_DTYPES
+]
+
+
+@pytest.fixture(params=arrays, ids=[a.dtype.name for a in arrays])
+def data(request):
+    """
+    Fixture returning parametrized 'data' array with different integer and
+    floating point types
+    """
+    return request.param
+
+
+@pytest.fixture()
+def numpy_dtype(data):
+    """
+    Fixture returning numpy dtype from 'data' input array.
+    """
+    # For integer dtype, the numpy conversion must be done to float
+    if is_integer_dtype(data):
+        numpy_dtype = float
+    else:
+        numpy_dtype = data.dtype.type
+    return numpy_dtype
+
+
+def test_round(data, numpy_dtype):
+    # No arguments
+    result = data.round()
+    expected = pd.array(
+        np.round(data.to_numpy(dtype=numpy_dtype, na_value=None)), dtype=data.dtype
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+    # Decimals argument
+    result = data.round(decimals=2)
+    expected = pd.array(
+        np.round(data.to_numpy(dtype=numpy_dtype, na_value=None), decimals=2),
+        dtype=data.dtype,
+    )
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_tolist(data):
+    result = data.tolist()
+    expected = list(data)
+    tm.assert_equal(result, expected)
+
+
+def test_to_numpy():
+    # GH#56991
+
+    class MyStringArray(BaseMaskedArray):
+        dtype = pd.StringDtype()
+        _dtype_cls = pd.StringDtype
+        _internal_fill_value = pd.NA
+
+    arr = MyStringArray(
+        values=np.array(["a", "b", "c"]), mask=np.array([False, True, False])
+    )
+    result = arr.to_numpy()
+    expected = np.array(["a", pd.NA, "c"])
+    tm.assert_numpy_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/masked/test_indexing.py

@@ -0,0 +1,60 @@
+import re
+
+import numpy as np
+import pytest
+
+import pandas as pd
+
+
+class TestSetitemValidation:
+    def _check_setitem_invalid(self, arr, invalid):
+        msg = f"Invalid value '{str(invalid)}' for dtype {arr.dtype}"
+        msg = re.escape(msg)
+        with pytest.raises(TypeError, match=msg):
+            arr[0] = invalid
+
+        with pytest.raises(TypeError, match=msg):
+            arr[:] = invalid
+
+        with pytest.raises(TypeError, match=msg):
+            arr[[0]] = invalid
+
+        # FIXME: don't leave commented-out
+        # with pytest.raises(TypeError):
+        #    arr[[0]] = [invalid]
+
+        # with pytest.raises(TypeError):
+        #    arr[[0]] = np.array([invalid], dtype=object)
+
+        # Series non-coercion, behavior subject to change
+        ser = pd.Series(arr)
+        with pytest.raises(TypeError, match=msg):
+            ser[0] = invalid
+            # TODO: so, so many other variants of this...
+
+    _invalid_scalars = [
+        1 + 2j,
+        "True",
+        "1",
+        "1.0",
+        pd.NaT,
+        np.datetime64("NaT"),
+        np.timedelta64("NaT"),
+    ]
+
+    @pytest.mark.parametrize(
+        "invalid", _invalid_scalars + [1, 1.0, np.int64(1), np.float64(1)]
+    )
+    def test_setitem_validation_scalar_bool(self, invalid):
+        arr = pd.array([True, False, None], dtype="boolean")
+        self._check_setitem_invalid(arr, invalid)
+
+    @pytest.mark.parametrize("invalid", _invalid_scalars + [True, 1.5, np.float64(1.5)])
+    def test_setitem_validation_scalar_int(self, invalid, any_int_ea_dtype):
+        arr = pd.array([1, 2, None], dtype=any_int_ea_dtype)
+        self._check_setitem_invalid(arr, invalid)
+
+    @pytest.mark.parametrize("invalid", _invalid_scalars + [True])
+    def test_setitem_validation_scalar_float(self, invalid, float_ea_dtype):
+        arr = pd.array([1, 2, None], dtype=float_ea_dtype)
+        self._check_setitem_invalid(arr, invalid)

lib/python3.13/site-packages/pandas/tests/arrays/masked_shared.py

@@ -0,0 +1,154 @@
+"""
+Tests shared by MaskedArray subclasses.
+"""
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.tests.extension.base import BaseOpsUtil
+
+
+class ComparisonOps(BaseOpsUtil):
+    def _compare_other(self, data, op, other):
+        # array
+        result = pd.Series(op(data, other))
+        expected = pd.Series(op(data._data, other), dtype="boolean")
+
+        # fill the nan locations
+        expected[data._mask] = pd.NA
+
+        tm.assert_series_equal(result, expected)
+
+        # series
+        ser = pd.Series(data)
+        result = op(ser, other)
+
+        # Set nullable dtype here to avoid upcasting when setting to pd.NA below
+        expected = op(pd.Series(data._data), other).astype("boolean")
+
+        # fill the nan locations
+        expected[data._mask] = pd.NA
+
+        tm.assert_series_equal(result, expected)
+
+    # subclass will override to parametrize 'other'
+    def test_scalar(self, other, comparison_op, dtype):
+        op = comparison_op
+        left = pd.array([1, 0, None], dtype=dtype)
+
+        result = op(left, other)
+
+        if other is pd.NA:
+            expected = pd.array([None, None, None], dtype="boolean")
+        else:
+            values = op(left._data, other)
+            expected = pd.arrays.BooleanArray(values, left._mask, copy=True)
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        result[0] = pd.NA
+        tm.assert_extension_array_equal(left, pd.array([1, 0, None], dtype=dtype))
+
+
+class NumericOps:
+    # Shared by IntegerArray and FloatingArray, not BooleanArray
+
+    def test_searchsorted_nan(self, dtype):
+        # The base class casts to object dtype, for which searchsorted returns
+        #  0 from the left and 10 from the right.
+        arr = pd.array(range(10), dtype=dtype)
+
+        assert arr.searchsorted(np.nan, side="left") == 10
+        assert arr.searchsorted(np.nan, side="right") == 10
+
+    def test_no_shared_mask(self, data):
+        result = data + 1
+        assert not tm.shares_memory(result, data)
+
+    def test_array(self, comparison_op, dtype):
+        op = comparison_op
+
+        left = pd.array([0, 1, 2, None, None, None], dtype=dtype)
+        right = pd.array([0, 1, None, 0, 1, None], dtype=dtype)
+
+        result = op(left, right)
+        values = op(left._data, right._data)
+        mask = left._mask | right._mask
+
+        expected = pd.arrays.BooleanArray(values, mask)
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        result[0] = pd.NA
+        tm.assert_extension_array_equal(
+            left, pd.array([0, 1, 2, None, None, None], dtype=dtype)
+        )
+        tm.assert_extension_array_equal(
+            right, pd.array([0, 1, None, 0, 1, None], dtype=dtype)
+        )
+
+    def test_compare_with_booleanarray(self, comparison_op, dtype):
+        op = comparison_op
+
+        left = pd.array([True, False, None] * 3, dtype="boolean")
+        right = pd.array([0] * 3 + [1] * 3 + [None] * 3, dtype=dtype)
+        other = pd.array([False] * 3 + [True] * 3 + [None] * 3, dtype="boolean")
+
+        expected = op(left, other)
+        result = op(left, right)
+        tm.assert_extension_array_equal(result, expected)
+
+        # reversed op
+        expected = op(other, left)
+        result = op(right, left)
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_compare_to_string(self, dtype):
+        # GH#28930
+        ser = pd.Series([1, None], dtype=dtype)
+        result = ser == "a"
+        expected = pd.Series([False, pd.NA], dtype="boolean")
+
+        tm.assert_series_equal(result, expected)
+
+    def test_ufunc_with_out(self, dtype):
+        arr = pd.array([1, 2, 3], dtype=dtype)
+        arr2 = pd.array([1, 2, pd.NA], dtype=dtype)
+
+        mask = arr == arr
+        mask2 = arr2 == arr2
+
+        result = np.zeros(3, dtype=bool)
+        result |= mask
+        # If MaskedArray.__array_ufunc__ handled "out" appropriately,
+        #  `result` should still be an ndarray.
+        assert isinstance(result, np.ndarray)
+        assert result.all()
+
+        # result |= mask worked because mask could be cast losslessly to
+        #  boolean ndarray. mask2 can't, so this raises
+        result = np.zeros(3, dtype=bool)
+        msg = "Specify an appropriate 'na_value' for this dtype"
+        with pytest.raises(ValueError, match=msg):
+            result |= mask2
+
+        # addition
+        res = np.add(arr, arr2)
+        expected = pd.array([2, 4, pd.NA], dtype=dtype)
+        tm.assert_extension_array_equal(res, expected)
+
+        # when passing out=arr, we will modify 'arr' inplace.
+        res = np.add(arr, arr2, out=arr)
+        assert res is arr
+        tm.assert_extension_array_equal(res, expected)
+        tm.assert_extension_array_equal(arr, expected)
+
+    def test_mul_td64_array(self, dtype):
+        # GH#45622
+        arr = pd.array([1, 2, pd.NA], dtype=dtype)
+        other = np.arange(3, dtype=np.int64).view("m8[ns]")
+
+        result = arr * other
+        expected = pd.array([pd.Timedelta(0), pd.Timedelta(2), pd.NaT])
+        tm.assert_extension_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/numpy_/test_indexing.py

@@ -0,0 +1,41 @@
+import numpy as np
+
+from pandas.core.dtypes.common import is_scalar
+
+import pandas as pd
+import pandas._testing as tm
+
+
+class TestSearchsorted:
+    def test_searchsorted_string(self, string_dtype):
+        arr = pd.array(["a", "b", "c"], dtype=string_dtype)
+
+        result = arr.searchsorted("a", side="left")
+        assert is_scalar(result)
+        assert result == 0
+
+        result = arr.searchsorted("a", side="right")
+        assert is_scalar(result)
+        assert result == 1
+
+    def test_searchsorted_numeric_dtypes_scalar(self, any_real_numpy_dtype):
+        arr = pd.array([1, 3, 90], dtype=any_real_numpy_dtype)
+        result = arr.searchsorted(30)
+        assert is_scalar(result)
+        assert result == 2
+
+        result = arr.searchsorted([30])
+        expected = np.array([2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_searchsorted_numeric_dtypes_vector(self, any_real_numpy_dtype):
+        arr = pd.array([1, 3, 90], dtype=any_real_numpy_dtype)
+        result = arr.searchsorted([2, 30])
+        expected = np.array([1, 2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_searchsorted_sorter(self, any_real_numpy_dtype):
+        arr = pd.array([3, 1, 2], dtype=any_real_numpy_dtype)
+        result = arr.searchsorted([0, 3], sorter=np.argsort(arr))
+        expected = np.array([0, 2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/numpy_/test_numpy.py

@@ -0,0 +1,324 @@
+"""
+Additional tests for NumpyExtensionArray that aren't covered by
+the interface tests.
+"""
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import NumpyEADtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.arrays import NumpyExtensionArray
+
+
+@pytest.fixture(
+    params=[
+        np.array(["a", "b"], dtype=object),
+        np.array([0, 1], dtype=float),
+        np.array([0, 1], dtype=int),
+        np.array([0, 1 + 2j], dtype=complex),
+        np.array([True, False], dtype=bool),
+        np.array([0, 1], dtype="datetime64[ns]"),
+        np.array([0, 1], dtype="timedelta64[ns]"),
+    ]
+)
+def any_numpy_array(request):
+    """
+    Parametrized fixture for NumPy arrays with different dtypes.
+
+    This excludes string and bytes.
+    """
+    return request.param
+
+
+# ----------------------------------------------------------------------------
+# NumpyEADtype
+
+
+@pytest.mark.parametrize(
+    "dtype, expected",
+    [
+        ("bool", True),
+        ("int", True),
+        ("uint", True),
+        ("float", True),
+        ("complex", True),
+        ("str", False),
+        ("bytes", False),
+        ("datetime64[ns]", False),
+        ("object", False),
+        ("void", False),
+    ],
+)
+def test_is_numeric(dtype, expected):
+    dtype = NumpyEADtype(dtype)
+    assert dtype._is_numeric is expected
+
+
+@pytest.mark.parametrize(
+    "dtype, expected",
+    [
+        ("bool", True),
+        ("int", False),
+        ("uint", False),
+        ("float", False),
+        ("complex", False),
+        ("str", False),
+        ("bytes", False),
+        ("datetime64[ns]", False),
+        ("object", False),
+        ("void", False),
+    ],
+)
+def test_is_boolean(dtype, expected):
+    dtype = NumpyEADtype(dtype)
+    assert dtype._is_boolean is expected
+
+
+def test_repr():
+    dtype = NumpyEADtype(np.dtype("int64"))
+    assert repr(dtype) == "NumpyEADtype('int64')"
+
+
+def test_constructor_from_string():
+    result = NumpyEADtype.construct_from_string("int64")
+    expected = NumpyEADtype(np.dtype("int64"))
+    assert result == expected
+
+
+def test_dtype_idempotent(any_numpy_dtype):
+    dtype = NumpyEADtype(any_numpy_dtype)
+
+    result = NumpyEADtype(dtype)
+    assert result == dtype
+
+
+# ----------------------------------------------------------------------------
+# Construction
+
+
+def test_constructor_no_coercion():
+    with pytest.raises(ValueError, match="NumPy array"):
+        NumpyExtensionArray([1, 2, 3])
+
+
+def test_series_constructor_with_copy():
+    ndarray = np.array([1, 2, 3])
+    ser = pd.Series(NumpyExtensionArray(ndarray), copy=True)
+
+    assert ser.values is not ndarray
+
+
+def test_series_constructor_with_astype():
+    ndarray = np.array([1, 2, 3])
+    result = pd.Series(NumpyExtensionArray(ndarray), dtype="float64")
+    expected = pd.Series([1.0, 2.0, 3.0], dtype="float64")
+    tm.assert_series_equal(result, expected)
+
+
+def test_from_sequence_dtype():
+    arr = np.array([1, 2, 3], dtype="int64")
+    result = NumpyExtensionArray._from_sequence(arr, dtype="uint64")
+    expected = NumpyExtensionArray(np.array([1, 2, 3], dtype="uint64"))
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_constructor_copy():
+    arr = np.array([0, 1])
+    result = NumpyExtensionArray(arr, copy=True)
+
+    assert not tm.shares_memory(result, arr)
+
+
+def test_constructor_with_data(any_numpy_array):
+    nparr = any_numpy_array
+    arr = NumpyExtensionArray(nparr)
+    assert arr.dtype.numpy_dtype == nparr.dtype
+
+
+# ----------------------------------------------------------------------------
+# Conversion
+
+
+def test_to_numpy():
+    arr = NumpyExtensionArray(np.array([1, 2, 3]))
+    result = arr.to_numpy()
+    assert result is arr._ndarray
+
+    result = arr.to_numpy(copy=True)
+    assert result is not arr._ndarray
+
+    result = arr.to_numpy(dtype="f8")
+    expected = np.array([1, 2, 3], dtype="f8")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+# ----------------------------------------------------------------------------
+# Setitem
+
+
+def test_setitem_series():
+    ser = pd.Series([1, 2, 3])
+    ser.array[0] = 10
+    expected = pd.Series([10, 2, 3])
+    tm.assert_series_equal(ser, expected)
+
+
+def test_setitem(any_numpy_array):
+    nparr = any_numpy_array
+    arr = NumpyExtensionArray(nparr, copy=True)
+
+    arr[0] = arr[1]
+    nparr[0] = nparr[1]
+
+    tm.assert_numpy_array_equal(arr.to_numpy(), nparr)
+
+
+# ----------------------------------------------------------------------------
+# Reductions
+
+
+def test_bad_reduce_raises():
+    arr = np.array([1, 2, 3], dtype="int64")
+    arr = NumpyExtensionArray(arr)
+    msg = "cannot perform not_a_method with type int"
+    with pytest.raises(TypeError, match=msg):
+        arr._reduce(msg)
+
+
+def test_validate_reduction_keyword_args():
+    arr = NumpyExtensionArray(np.array([1, 2, 3]))
+    msg = "the 'keepdims' parameter is not supported .*all"
+    with pytest.raises(ValueError, match=msg):
+        arr.all(keepdims=True)
+
+
+def test_np_max_nested_tuples():
+    # case where checking in ufunc.nout works while checking for tuples
+    #  does not
+    vals = [
+        (("j", "k"), ("l", "m")),
+        (("l", "m"), ("o", "p")),
+        (("o", "p"), ("j", "k")),
+    ]
+    ser = pd.Series(vals)
+    arr = ser.array
+
+    assert arr.max() is arr[2]
+    assert ser.max() is arr[2]
+
+    result = np.maximum.reduce(arr)
+    assert result == arr[2]
+
+    result = np.maximum.reduce(ser)
+    assert result == arr[2]
+
+
+def test_np_reduce_2d():
+    raw = np.arange(12).reshape(4, 3)
+    arr = NumpyExtensionArray(raw)
+
+    res = np.maximum.reduce(arr, axis=0)
+    tm.assert_extension_array_equal(res, arr[-1])
+
+    alt = arr.max(axis=0)
+    tm.assert_extension_array_equal(alt, arr[-1])
+
+
+# ----------------------------------------------------------------------------
+# Ops
+
+
+@pytest.mark.parametrize("ufunc", [np.abs, np.negative, np.positive])
+def test_ufunc_unary(ufunc):
+    arr = NumpyExtensionArray(np.array([-1.0, 0.0, 1.0]))
+    result = ufunc(arr)
+    expected = NumpyExtensionArray(ufunc(arr._ndarray))
+    tm.assert_extension_array_equal(result, expected)
+
+    # same thing but with the 'out' keyword
+    out = NumpyExtensionArray(np.array([-9.0, -9.0, -9.0]))
+    ufunc(arr, out=out)
+    tm.assert_extension_array_equal(out, expected)
+
+
+def test_ufunc():
+    arr = NumpyExtensionArray(np.array([-1.0, 0.0, 1.0]))
+
+    r1, r2 = np.divmod(arr, np.add(arr, 2))
+    e1, e2 = np.divmod(arr._ndarray, np.add(arr._ndarray, 2))
+    e1 = NumpyExtensionArray(e1)
+    e2 = NumpyExtensionArray(e2)
+    tm.assert_extension_array_equal(r1, e1)
+    tm.assert_extension_array_equal(r2, e2)
+
+
+def test_basic_binop():
+    # Just a basic smoke test. The EA interface tests exercise this
+    # more thoroughly.
+    x = NumpyExtensionArray(np.array([1, 2, 3]))
+    result = x + x
+    expected = NumpyExtensionArray(np.array([2, 4, 6]))
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", [None, object])
+def test_setitem_object_typecode(dtype):
+    arr = NumpyExtensionArray(np.array(["a", "b", "c"], dtype=dtype))
+    arr[0] = "t"
+    expected = NumpyExtensionArray(np.array(["t", "b", "c"], dtype=dtype))
+    tm.assert_extension_array_equal(arr, expected)
+
+
+def test_setitem_no_coercion():
+    # https://github.com/pandas-dev/pandas/issues/28150
+    arr = NumpyExtensionArray(np.array([1, 2, 3]))
+    with pytest.raises(ValueError, match="int"):
+        arr[0] = "a"
+
+    # With a value that we do coerce, check that we coerce the value
+    #  and not the underlying array.
+    arr[0] = 2.5
+    assert isinstance(arr[0], (int, np.integer)), type(arr[0])
+
+
+def test_setitem_preserves_views():
+    # GH#28150, see also extension test of the same name
+    arr = NumpyExtensionArray(np.array([1, 2, 3]))
+    view1 = arr.view()
+    view2 = arr[:]
+    view3 = np.asarray(arr)
+
+    arr[0] = 9
+    assert view1[0] == 9
+    assert view2[0] == 9
+    assert view3[0] == 9
+
+    arr[-1] = 2.5
+    view1[-1] = 5
+    assert arr[-1] == 5
+
+
+@pytest.mark.parametrize("dtype", [np.int64, np.uint64])
+def test_quantile_empty(dtype):
+    # we should get back np.nans, not -1s
+    arr = NumpyExtensionArray(np.array([], dtype=dtype))
+    idx = pd.Index([0.0, 0.5])
+
+    result = arr._quantile(idx, interpolation="linear")
+    expected = NumpyExtensionArray(np.array([np.nan, np.nan]))
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_factorize_unsigned():
+    # don't raise when calling factorize on unsigned int NumpyExtensionArray
+    arr = np.array([1, 2, 3], dtype=np.uint64)
+    obj = NumpyExtensionArray(arr)
+
+    res_codes, res_unique = obj.factorize()
+    exp_codes, exp_unique = pd.factorize(arr)
+
+    tm.assert_numpy_array_equal(res_codes, exp_codes)
+
+    tm.assert_extension_array_equal(res_unique, NumpyExtensionArray(exp_unique))

lib/python3.13/site-packages/pandas/tests/arrays/period/test_arrow_compat.py

@@ -0,0 +1,130 @@
+import pytest
+
+from pandas.compat.pyarrow import pa_version_under10p1
+
+from pandas.core.dtypes.dtypes import PeriodDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import (
+    PeriodArray,
+    period_array,
+)
+
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
+)
+
+
+pa = pytest.importorskip("pyarrow")
+
+
+def test_arrow_extension_type():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    p1 = ArrowPeriodType("D")
+    p2 = ArrowPeriodType("D")
+    p3 = ArrowPeriodType("M")
+
+    assert p1.freq == "D"
+    assert p1 == p2
+    assert p1 != p3
+    assert hash(p1) == hash(p2)
+    assert hash(p1) != hash(p3)
+
+
+@pytest.mark.xfail(not pa_version_under10p1, reason="Wrong behavior with pyarrow 10")
+@pytest.mark.parametrize(
+    "data, freq",
+    [
+        (pd.date_range("2017", periods=3), "D"),
+        (pd.date_range("2017", periods=3, freq="YE"), "Y-DEC"),
+    ],
+)
+def test_arrow_array(data, freq):
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    periods = period_array(data, freq=freq)
+    result = pa.array(periods)
+    assert isinstance(result.type, ArrowPeriodType)
+    assert result.type.freq == freq
+    expected = pa.array(periods.asi8, type="int64")
+    assert result.storage.equals(expected)
+
+    # convert to its storage type
+    result = pa.array(periods, type=pa.int64())
+    assert result.equals(expected)
+
+    # unsupported conversions
+    msg = "Not supported to convert PeriodArray to 'double' type"
+    with pytest.raises(TypeError, match=msg):
+        pa.array(periods, type="float64")
+
+    with pytest.raises(TypeError, match="different 'freq'"):
+        pa.array(periods, type=ArrowPeriodType("T"))
+
+
+def test_arrow_array_missing():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([1, 2, 3], dtype="period[D]")
+    arr[1] = pd.NaT
+
+    result = pa.array(arr)
+    assert isinstance(result.type, ArrowPeriodType)
+    assert result.type.freq == "D"
+    expected = pa.array([1, None, 3], type="int64")
+    assert result.storage.equals(expected)
+
+
+def test_arrow_table_roundtrip():
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([1, 2, 3], dtype="period[D]")
+    arr[1] = pd.NaT
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    assert isinstance(table.field("a").type, ArrowPeriodType)
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)
+
+    table2 = pa.concat_tables([table, table])
+    result = table2.to_pandas()
+    expected = pd.concat([df, df], ignore_index=True)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_arrow_load_from_zero_chunks():
+    # GH-41040
+
+    from pandas.core.arrays.arrow.extension_types import ArrowPeriodType
+
+    arr = PeriodArray([], dtype="period[D]")
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    assert isinstance(table.field("a").type, ArrowPeriodType)
+    table = pa.table(
+        [pa.chunked_array([], type=table.column(0).type)], schema=table.schema
+    )
+
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)
+
+
+def test_arrow_table_roundtrip_without_metadata():
+    arr = PeriodArray([1, 2, 3], dtype="period[h]")
+    arr[1] = pd.NaT
+    df = pd.DataFrame({"a": arr})
+
+    table = pa.table(df)
+    # remove the metadata
+    table = table.replace_schema_metadata()
+    assert table.schema.metadata is None
+
+    result = table.to_pandas()
+    assert isinstance(result["a"].dtype, PeriodDtype)
+    tm.assert_frame_equal(result, df)

lib/python3.13/site-packages/pandas/tests/arrays/period/test_astype.py

@@ -0,0 +1,67 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import PeriodDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import period_array
+
+
+@pytest.mark.parametrize("dtype", [int, np.int32, np.int64, "uint32", "uint64"])
+def test_astype_int(dtype):
+    # We choose to ignore the sign and size of integers for
+    # Period/Datetime/Timedelta astype
+    arr = period_array(["2000", "2001", None], freq="D")
+
+    if np.dtype(dtype) != np.int64:
+        with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"):
+            arr.astype(dtype)
+        return
+
+    result = arr.astype(dtype)
+    expected = arr._ndarray.view("i8")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_astype_copies():
+    arr = period_array(["2000", "2001", None], freq="D")
+    result = arr.astype(np.int64, copy=False)
+
+    # Add the `.base`, since we now use `.asi8` which returns a view.
+    # We could maybe override it in PeriodArray to return ._ndarray directly.
+    assert result.base is arr._ndarray
+
+    result = arr.astype(np.int64, copy=True)
+    assert result is not arr._ndarray
+    tm.assert_numpy_array_equal(result, arr._ndarray.view("i8"))
+
+
+def test_astype_categorical():
+    arr = period_array(["2000", "2001", "2001", None], freq="D")
+    result = arr.astype("category")
+    categories = pd.PeriodIndex(["2000", "2001"], freq="D")
+    expected = pd.Categorical.from_codes([0, 1, 1, -1], categories=categories)
+    tm.assert_categorical_equal(result, expected)
+
+
+def test_astype_period():
+    arr = period_array(["2000", "2001", None], freq="D")
+    result = arr.astype(PeriodDtype("M"))
+    expected = period_array(["2000", "2001", None], freq="M")
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["datetime64[ns]", "timedelta64[ns]"])
+def test_astype_datetime(dtype):
+    arr = period_array(["2000", "2001", None], freq="D")
+    # slice off the [ns] so that the regex matches.
+    if dtype == "timedelta64[ns]":
+        with pytest.raises(TypeError, match=dtype[:-4]):
+            arr.astype(dtype)
+
+    else:
+        # GH#45038 allow period->dt64 because we allow dt64->period
+        result = arr.astype(dtype)
+        expected = pd.DatetimeIndex(["2000", "2001", pd.NaT], dtype=dtype)._data
+        tm.assert_datetime_array_equal(result, expected)

lib/python3.13/site-packages/pandas/tests/arrays/period/test_constructors.py

@@ -0,0 +1,156 @@
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import iNaT
+from pandas._libs.tslibs.offsets import MonthEnd
+from pandas._libs.tslibs.period import IncompatibleFrequency
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import (
+    PeriodArray,
+    period_array,
+)
+
+
+@pytest.mark.parametrize(
+    "data, freq, expected",
+    [
+        ([pd.Period("2017", "D")], None, [17167]),
+        ([pd.Period("2017", "D")], "D", [17167]),
+        ([2017], "D", [17167]),
+        (["2017"], "D", [17167]),
+        ([pd.Period("2017", "D")], pd.tseries.offsets.Day(), [17167]),
+        ([pd.Period("2017", "D"), None], None, [17167, iNaT]),
+        (pd.Series(pd.date_range("2017", periods=3)), None, [17167, 17168, 17169]),
+        (pd.date_range("2017", periods=3), None, [17167, 17168, 17169]),
+        (pd.period_range("2017", periods=4, freq="Q"), None, [188, 189, 190, 191]),
+    ],
+)
+def test_period_array_ok(data, freq, expected):
+    result = period_array(data, freq=freq).asi8
+    expected = np.asarray(expected, dtype=np.int64)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_period_array_readonly_object():
+    # https://github.com/pandas-dev/pandas/issues/25403
+    pa = period_array([pd.Period("2019-01-01")])
+    arr = np.asarray(pa, dtype="object")
+    arr.setflags(write=False)
+
+    result = period_array(arr)
+    tm.assert_period_array_equal(result, pa)
+
+    result = pd.Series(arr)
+    tm.assert_series_equal(result, pd.Series(pa))
+
+    result = pd.DataFrame({"A": arr})
+    tm.assert_frame_equal(result, pd.DataFrame({"A": pa}))
+
+
+def test_from_datetime64_freq_changes():
+    # https://github.com/pandas-dev/pandas/issues/23438
+    arr = pd.date_range("2017", periods=3, freq="D")
+    result = PeriodArray._from_datetime64(arr, freq="M")
+    expected = period_array(["2017-01-01", "2017-01-01", "2017-01-01"], freq="M")
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("freq", ["2M", MonthEnd(2)])
+def test_from_datetime64_freq_2M(freq):
+    arr = np.array(
+        ["2020-01-01T00:00:00", "2020-01-02T00:00:00"], dtype="datetime64[ns]"
+    )
+    result = PeriodArray._from_datetime64(arr, freq)
+    expected = period_array(["2020-01", "2020-01"], freq=freq)
+    tm.assert_period_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "data, freq, msg",
+    [
+        (
+            [pd.Period("2017", "D"), pd.Period("2017", "Y")],
+            None,
+            "Input has different freq",
+        ),
+        ([pd.Period("2017", "D")], "Y", "Input has different freq"),
+    ],
+)
+def test_period_array_raises(data, freq, msg):
+    with pytest.raises(IncompatibleFrequency, match=msg):
+        period_array(data, freq)
+
+
+def test_period_array_non_period_series_raies():
+    ser = pd.Series([1, 2, 3])
+    with pytest.raises(TypeError, match="dtype"):
+        PeriodArray(ser, dtype="period[D]")
+
+
+def test_period_array_freq_mismatch():
+    arr = period_array(["2000", "2001"], freq="D")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        PeriodArray(arr, dtype="period[M]")
+
+    dtype = pd.PeriodDtype(pd.tseries.offsets.MonthEnd())
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        PeriodArray(arr, dtype=dtype)
+
+
+def test_from_sequence_disallows_i8():
+    arr = period_array(["2000", "2001"], freq="D")
+
+    msg = str(arr[0].ordinal)
+    with pytest.raises(TypeError, match=msg):
+        PeriodArray._from_sequence(arr.asi8, dtype=arr.dtype)
+
+    with pytest.raises(TypeError, match=msg):
+        PeriodArray._from_sequence(list(arr.asi8), dtype=arr.dtype)
+
+
+def test_from_td64nat_sequence_raises():
+    # GH#44507
+    td = pd.NaT.to_numpy("m8[ns]")
+
+    dtype = pd.period_range("2005-01-01", periods=3, freq="D").dtype
+
+    arr = np.array([None], dtype=object)
+    arr[0] = td
+
+    msg = "Value must be Period, string, integer, or datetime"
+    with pytest.raises(ValueError, match=msg):
+        PeriodArray._from_sequence(arr, dtype=dtype)
+
+    with pytest.raises(ValueError, match=msg):
+        pd.PeriodIndex(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.Index(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.array(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.Series(arr, dtype=dtype)
+    with pytest.raises(ValueError, match=msg):
+        pd.DataFrame(arr, dtype=dtype)
+
+
+def test_freq_deprecated():
+    # GH#52462
+    data = np.arange(5).astype(np.int64)
+    msg = "The 'freq' keyword in the PeriodArray constructor is deprecated"
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        res = PeriodArray(data, freq="M")
+
+    expected = PeriodArray(data, dtype="period[M]")
+    tm.assert_equal(res, expected)
+
+
+def test_period_array_from_datetime64():
+    arr = np.array(
+        ["2020-01-01T00:00:00", "2020-02-02T00:00:00"], dtype="datetime64[ns]"
+    )
+    result = PeriodArray._from_datetime64(arr, freq=MonthEnd(2))
+
+    expected = period_array(["2020-01-01", "2020-02-01"], freq=MonthEnd(2))
+    tm.assert_period_array_equal(result, expected)