venv

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

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

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

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

venv/lib/python3.12/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"]

venv/lib/python3.12/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)

venv/lib/python3.12/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"])

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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

venv/lib/python3.12/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

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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

venv/lib/python3.12/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))

venv/lib/python3.12/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)

venv/lib/python3.12/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")
+        )

venv/lib/python3.12/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"))

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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))

venv/lib/python3.12/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)

venv/lib/python3.12/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)

venv/lib/python3.12/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