Initial commit: 首次建仓，建立目录结构

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/common.py

@@ -0,0 +1,158 @@
+"""
+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 function to assert that two objects cannot be added.
+
+    Parameters
+    ----------
+    left : object
+        The first operand.
+    right : object
+        The second operand.
+    msg : str, default "cannot add"
+        The error message expected in the TypeError.
+    """
+    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 function to assert that two objects can
+    neither be added nor subtracted.
+
+    Parameters
+    ----------
+    left : object
+        The first operand.
+    right : object
+        The second operand.
+    msg : str or None, default None
+        The error message expected in the TypeError.
+    """
+    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
+
+    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, xbox(expected))
+
+    result = xbox2(left != right)
+    tm.assert_equal(result, ~expected)
+
+    result = xbox2(right != left)
+    tm.assert_equal(result, xbox(~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

dashboard/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

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/test_array_ops.py

@@ -0,0 +1,78 @@
+import operator
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.missing import isna
+
+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)
+
+
+@pytest.mark.parametrize("rvalues", [1, [1, 1, 1], np.nan, None])
+@pytest.mark.parametrize(
+    "op", [operator.eq, operator.ne, operator.lt, operator.le, operator.gt, operator.ge]
+)
+def test_comparison_for_subclasses(rvalues, op):
+    # GH#63205 Ensure subclasses of ndarray are correctly handled in comparison_op
+    # Define a custom ndarray subclass
+    class TestArray(np.ndarray):
+        def __new__(cls, input_array):
+            return np.asarray(input_array).view(cls)
+
+        def __array_finalize__(self, obj) -> None:
+            self._is_test_array = True
+
+    def expected_with_na_handling(lvalues, rvalues, op):
+        # Similar to comparison_op, handle zerodim arrays with na value separately
+        if (rvalues.ndim == 0) and isna(rvalues.item()):
+            # numpy does not like comparisons vs None
+            if op is operator.ne:
+                return np.ones(lvalues.shape, dtype=bool)
+            else:
+                return np.zeros(lvalues.shape, dtype=bool)
+        return op(lvalues, rvalues)
+
+    # Define test data
+    lvalues = [1, 2, 3]
+
+    # Test with both ndarray and TestArray
+    result = comparison_op(np.array(lvalues), np.array(rvalues), op)
+    expected = expected_with_na_handling(np.array(lvalues), np.array(rvalues), op)
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = comparison_op(TestArray(lvalues), TestArray(rvalues), op)
+    expected = expected_with_na_handling(TestArray(lvalues), TestArray(rvalues), op)
+    tm.assert_numpy_array_equal(result, expected)

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/test_bool.py

@@ -0,0 +1,28 @@
+import pytest
+
+from pandas import (
+    DataFrame,
+    Series,
+)
+import pandas._testing as tm
+
+
+def test_divmod_bool_raises(box_with_array):
+    # GH#46043 // raises, so divmod should too
+    ser = Series([True, False])
+    obj = tm.box_expected(ser, box_with_array)
+
+    msg = "operator 'floordiv' not implemented for bool dtypes"
+    with pytest.raises(NotImplementedError, match=msg):
+        obj // obj
+
+    if box_with_array is DataFrame:
+        msg = "operator 'floordiv' not implemented for bool dtypes"
+    else:
+        msg = "operator 'divmod' not implemented for bool dtypes"
+    with pytest.raises(NotImplementedError, match=msg):
+        divmod(obj, obj)
+
+    # go through __rdivmod__
+    with pytest.raises(NotImplementedError, match=msg):
+        divmod(True, obj)

dashboard/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)

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/test_interval.py

@@ -0,0 +1,308 @@
+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, strict=True)]
+        )
+        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)

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/test_object.py

@@ -0,0 +1,410 @@
+# 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
+
+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
+
+    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):
+        index = pd.Index([str(i) for i in range(10)])
+
+        msg = "unsupported operand type|Cannot broadcast|sub' not supported"
+        with pytest.raises(TypeError, match=msg):
+            index - "a"
+        with pytest.raises(TypeError, match=msg):
+            index - index
+        with pytest.raises(TypeError, match=msg):
+            index - index.tolist()
+        with pytest.raises(TypeError, 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

dashboard/venv/lib/python3.12/site-packages/pandas/tests/arithmetic/test_string.py

@@ -0,0 +1,487 @@
+import operator
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+from pandas.compat import HAS_PYARROW
+from pandas.errors import Pandas4Warning
+import pandas.util._test_decorators as td
+
+import pandas as pd
+from pandas import (
+    NA,
+    ArrowDtype,
+    Series,
+    StringDtype,
+)
+import pandas._testing as tm
+from pandas.core.construction import extract_array
+
+
+def string_dtype_highest_priority(dtype1, dtype2):
+    if HAS_PYARROW:
+        DTYPE_HIERARCHY = [
+            StringDtype("python", na_value=np.nan),
+            StringDtype("pyarrow", na_value=np.nan),
+            StringDtype("python", na_value=NA),
+            StringDtype("pyarrow", na_value=NA),
+        ]
+    else:
+        DTYPE_HIERARCHY = [
+            StringDtype("python", na_value=np.nan),
+            StringDtype("python", na_value=NA),
+        ]
+
+    h1 = DTYPE_HIERARCHY.index(dtype1)
+    h2 = DTYPE_HIERARCHY.index(dtype2)
+    return DTYPE_HIERARCHY[max(h1, h2)]
+
+
+def test_eq_all_na():
+    pytest.importorskip("pyarrow")
+    a = pd.array([NA, NA], dtype=StringDtype("pyarrow"))
+    result = a == a
+    expected = pd.array([NA, NA], dtype="boolean[pyarrow]")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_reversed_logical_ops(any_string_dtype):
+    # GH#60234
+    dtype = any_string_dtype
+    warn = None if dtype == object else Pandas4Warning
+    left = Series([True, False, False, True])
+    right = Series(["", "", "b", "c"], dtype=dtype)
+
+    msg = "operations between boolean dtype and"
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left | right
+    expected = left | right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left & right
+    expected = left & right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+    with tm.assert_produces_warning(warn, match=msg):
+        result = left ^ right
+    expected = left ^ right.astype(bool)
+    tm.assert_series_equal(result, expected)
+
+
+def test_pathlib_path_division(any_string_dtype, request):
+    # GH#61940
+    if any_string_dtype == object:
+        mark = pytest.mark.xfail(
+            reason="with NA present we go through _masked_arith_op which "
+            "raises TypeError bc Path is not recognized by lib.is_scalar."
+        )
+        request.applymarker(mark)
+
+    item = Path("/Users/Irv/")
+    ser = Series(["A", "B", NA], dtype=any_string_dtype)
+
+    result = item / ser
+    expected = Series([item / "A", item / "B", ser.dtype.na_value], dtype=object)
+    tm.assert_series_equal(result, expected)
+
+    result = ser / item
+    expected = Series(["A" / item, "B" / item, ser.dtype.na_value], dtype=object)
+    tm.assert_series_equal(result, expected)
+
+
+def test_mixed_object_comparison(any_string_dtype):
+    # GH#60228
+    dtype = any_string_dtype
+    ser = Series(["a", "b"], dtype=dtype)
+
+    mixed = Series([1, "b"], dtype=object)
+
+    result = ser == mixed
+    expected = Series([False, True], dtype=bool)
+    if dtype == object:
+        pass
+    elif dtype.storage == "python" and dtype.na_value is NA:
+        expected = expected.astype("boolean")
+    elif dtype.storage == "pyarrow" and dtype.na_value is NA:
+        expected = expected.astype("bool[pyarrow]")
+
+    tm.assert_series_equal(result, expected)
+
+
+def test_pyarrow_numpy_string_invalid():
+    # GH#56008
+    pa = pytest.importorskip("pyarrow")
+    ser = Series([False, True])
+    ser2 = Series(["a", "b"], dtype=StringDtype(na_value=np.nan))
+    result = ser == ser2
+    expected_eq = Series(False, index=ser.index)
+    tm.assert_series_equal(result, expected_eq)
+
+    result = ser != ser2
+    expected_ne = Series(True, index=ser.index)
+    tm.assert_series_equal(result, expected_ne)
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser2
+
+    # GH#59505
+    ser3 = ser2.astype("string[pyarrow]")
+    result3_eq = ser3 == ser
+    tm.assert_series_equal(result3_eq, expected_eq.astype("bool[pyarrow]"))
+    result3_ne = ser3 != ser
+    tm.assert_series_equal(result3_ne, expected_ne.astype("bool[pyarrow]"))
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser3
+
+    ser4 = ser2.astype(ArrowDtype(pa.string()))
+    result4_eq = ser4 == ser
+    tm.assert_series_equal(result4_eq, expected_eq.astype("bool[pyarrow]"))
+    result4_ne = ser4 != ser
+    tm.assert_series_equal(result4_ne, expected_ne.astype("bool[pyarrow]"))
+
+    with pytest.raises(TypeError, match="Invalid comparison"):
+        ser > ser4
+
+
+def test_mul_bool_invalid(any_string_dtype):
+    # GH#62595
+    dtype = any_string_dtype
+    ser = Series(["a", "b", "c"], dtype=dtype)
+
+    if dtype == object:
+        pytest.skip("This is not expect to raise")
+    elif dtype.storage == "python":
+        msg = "Cannot multiply StringArray by bools. Explicitly cast to integers"
+    else:
+        msg = "Can only string multiply by an integer"
+
+    with pytest.raises(TypeError, match=msg):
+        False * ser
+    with pytest.raises(TypeError, match=msg):
+        ser * True
+    with pytest.raises(TypeError, match=msg):
+        ser * np.array([True, False, True], dtype=bool)
+    with pytest.raises(TypeError, match=msg):
+        np.array([True, False, True], dtype=bool) * ser
+
+
+def test_add(any_string_dtype, request):
+    dtype = any_string_dtype
+    if dtype == object:
+        mark = pytest.mark.xfail(
+            reason="Need to update expected for numpy object dtype"
+        )
+        request.applymarker(mark)
+
+    a = Series(["a", "b", "c", None, None], dtype=dtype)
+    b = Series(["x", "y", None, "z", None], dtype=dtype)
+
+    result = a + b
+    expected = Series(["ax", "by", None, None, None], dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+    result = a.add(b)
+    tm.assert_series_equal(result, expected)
+
+    result = a.radd(b)
+    expected = Series(["xa", "yb", None, None, None], dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+    result = a.add(b, fill_value="-")
+    expected = Series(["ax", "by", "c-", "-z", None], dtype=dtype)
+    tm.assert_series_equal(result, expected)
+
+
+def test_add_2d(any_string_dtype, request):
+    dtype = any_string_dtype
+
+    if dtype == object or dtype.storage == "pyarrow":
+        reason = "Failed: DID NOT RAISE <class 'ValueError'>"
+        mark = pytest.mark.xfail(raises=None, reason=reason)
+        request.applymarker(mark)
+
+    a = pd.array(["a", "b", "c"], dtype=dtype)
+    b = np.array([["a", "b", "c"]], dtype=object)
+    with pytest.raises(ValueError, match="3 != 1"):
+        a + b
+
+    s = Series(a)
+    with pytest.raises(ValueError, match="3 != 1"):
+        s + b
+
+
+def test_add_sequence(any_string_dtype, request, using_infer_string):
+    dtype = any_string_dtype
+    if (
+        dtype != object
+        and dtype.storage == "python"
+        and dtype.na_value is np.nan
+        and HAS_PYARROW
+        and using_infer_string
+    ):
+        mark = pytest.mark.xfail(
+            reason="As of GH#62522, the list gets wrapped with sanitize_array, "
+            "which casts to a higher-priority StringArray, so we get "
+            "NotImplemented."
+        )
+        request.applymarker(mark)
+    if dtype == np.dtype(object) and using_infer_string:
+        mark = pytest.mark.xfail(reason="Cannot broadcast list")
+        request.applymarker(mark)
+
+    a = pd.array(["a", "b", None, None], dtype=dtype)
+    other = ["x", None, "y", None]
+
+    result = a + other
+    expected = pd.array(["ax", None, None, None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = other + a
+    expected = pd.array(["xa", None, None, None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_string_add_missing_values(string_dtype_no_object):
+    # GH#64968 Arrow-backed str arrays should return NA when added to missing
+    arr = pd.array(["y"], dtype=string_dtype_no_object)
+    expected = pd.array([NA], dtype=string_dtype_no_object)
+
+    for na_val in [None, np.nan, NA]:
+        # left side
+        result = arr + na_val
+        tm.assert_extension_array_equal(result, expected)
+
+        # right side
+        result = na_val + arr
+        tm.assert_extension_array_equal(result, expected)
+
+
+def test_mul(any_string_dtype):
+    dtype = any_string_dtype
+    a = pd.array(["a", "b", None], dtype=dtype)
+    result = a * 2
+    expected = pd.array(["aa", "bb", None], dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = 2 * a
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_add_strings(any_string_dtype, request):
+    dtype = any_string_dtype
+    if dtype != np.dtype(object):
+        mark = pytest.mark.xfail(reason="GH-28527")
+        request.applymarker(mark)
+    arr = pd.array(["a", "b", "c", "d"], dtype=dtype)
+    df = pd.DataFrame([["t", "y", "v", "w"]], dtype=object)
+    assert arr.__add__(df) is NotImplemented
+
+    result = arr + df
+    expected = pd.DataFrame([["at", "by", "cv", "dw"]]).astype(dtype)
+    tm.assert_frame_equal(result, expected)
+
+    result = df + arr
+    expected = pd.DataFrame([["ta", "yb", "vc", "wd"]]).astype(dtype)
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.xfail(reason="GH-28527")
+def test_add_frame(dtype):
+    arr = pd.array(["a", "b", np.nan, np.nan], dtype=dtype)
+    df = pd.DataFrame([["x", np.nan, "y", np.nan]])
+
+    assert arr.__add__(df) is NotImplemented
+
+    result = arr + df
+    expected = pd.DataFrame([["ax", np.nan, np.nan, np.nan]]).astype(dtype)
+    tm.assert_frame_equal(result, expected)
+
+    result = df + arr
+    expected = pd.DataFrame([["xa", np.nan, np.nan, np.nan]]).astype(dtype)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_comparison_methods_scalar(comparison_op, any_string_dtype):
+    dtype = any_string_dtype
+    op_name = f"__{comparison_op.__name__}__"
+    a = pd.array(["a", None, "c"], dtype=dtype)
+    other = "a"
+    result = getattr(a, op_name)(other)
+    if dtype == object or dtype.na_value is np.nan:
+        expected = np.array([getattr(item, op_name)(other) for item in a])
+        if comparison_op == operator.ne:
+            expected[1] = True
+        else:
+            expected[1] = False
+        result = extract_array(result, extract_numpy=True)
+        tm.assert_numpy_array_equal(result, expected.astype(np.bool_))
+    else:
+        expected_dtype = "boolean[pyarrow]" if dtype.storage == "pyarrow" else "boolean"
+        expected = np.array([getattr(item, op_name)(other) for item in a], dtype=object)
+        expected = pd.array(expected, dtype=expected_dtype)
+        tm.assert_extension_array_equal(result, expected)
+
+
+def test_comparison_methods_scalar_pd_na(comparison_op, any_string_dtype):
+    dtype = any_string_dtype
+    op_name = f"__{comparison_op.__name__}__"
+    a = pd.array(["a", None, "c"], dtype=dtype)
+    result = getattr(a, op_name)(NA)
+
+    if dtype == np.dtype(object) or dtype.na_value is np.nan:
+        if operator.ne == comparison_op:
+            expected = np.array([True, True, True])
+        else:
+            expected = np.array([False, False, False])
+        result = extract_array(result, extract_numpy=True)
+        tm.assert_numpy_array_equal(result, expected)
+    else:
+        expected_dtype = "boolean[pyarrow]" if dtype.storage == "pyarrow" else "boolean"
+        expected = pd.array([None, None, None], dtype=expected_dtype)
+        tm.assert_extension_array_equal(result, expected)
+        tm.assert_extension_array_equal(result, expected)
+
+
+def test_comparison_methods_scalar_not_string(comparison_op, any_string_dtype):
+    op_name = f"__{comparison_op.__name__}__"
+    dtype = any_string_dtype
+
+    a = pd.array(["a", None, "c"], dtype=dtype)
+    other = 42
+
+    if op_name not in ["__eq__", "__ne__"]:
+        with pytest.raises(TypeError, match="Invalid comparison|not supported between"):
+            getattr(a, op_name)(other)
+
+        return
+
+    result = getattr(a, op_name)(other)
+    result = extract_array(result, extract_numpy=True)
+
+    if dtype == np.dtype(object) or dtype.na_value is np.nan:
+        expected_data = {
+            "__eq__": [False, False, False],
+            "__ne__": [True, True, True],
+        }[op_name]
+        expected = np.array(expected_data)
+        tm.assert_numpy_array_equal(result, expected)
+    else:
+        expected_data = {"__eq__": [False, None, False], "__ne__": [True, None, True]}[
+            op_name
+        ]
+        expected_dtype = "boolean[pyarrow]" if dtype.storage == "pyarrow" else "boolean"
+        expected = pd.array(expected_data, dtype=expected_dtype)
+        tm.assert_extension_array_equal(result, expected)
+
+
+def test_comparison_methods_array(comparison_op, any_string_dtype, any_string_dtype2):
+    op_name = f"__{comparison_op.__name__}__"
+    dtype = any_string_dtype
+    dtype2 = any_string_dtype2
+
+    a = pd.array(["a", None, "c"], dtype=dtype)
+    other = pd.array([None, None, "c"], dtype=dtype2)
+    result = comparison_op(a, other)
+    result = extract_array(result, extract_numpy=True)
+
+    # ensure operation is commutative
+    result2 = comparison_op(other, a)
+    result2 = extract_array(result2, extract_numpy=True)
+    tm.assert_equal(result, result2)
+
+    if (dtype == object or dtype.na_value is np.nan) and (
+        dtype2 == object or dtype2.na_value is np.nan
+    ):
+        if operator.ne == comparison_op:
+            expected = np.array([True, True, False])
+        else:
+            expected = np.array([False, False, False])
+            expected[-1] = getattr(other[-1], op_name)(a[-1])
+        result = extract_array(result, extract_numpy=True)
+        tm.assert_numpy_array_equal(result, expected)
+
+    else:
+        if dtype == object:
+            max_dtype = dtype2
+        elif dtype2 == object:
+            max_dtype = dtype
+        else:
+            max_dtype = string_dtype_highest_priority(dtype, dtype2)
+        if max_dtype.storage == "python":
+            expected_dtype = "boolean"
+        else:
+            expected_dtype = "bool[pyarrow]"
+
+        expected = np.full(len(a), fill_value=None, dtype="object")
+        expected[-1] = getattr(other[-1], op_name)(a[-1])
+        expected = pd.array(expected, dtype=expected_dtype)
+        tm.assert_equal(result, expected)
+
+
+@td.skip_if_no("pyarrow")
+def test_comparison_methods_array_arrow_extension(comparison_op, any_string_dtype):
+    # Test pd.ArrowDtype(pa.string()) against other string arrays
+    import pyarrow as pa
+
+    dtype2 = any_string_dtype
+
+    op_name = f"__{comparison_op.__name__}__"
+    dtype = ArrowDtype(pa.string())
+    a = pd.array(["a", None, "c"], dtype=dtype)
+    other = pd.array([None, None, "c"], dtype=dtype2)
+    result = comparison_op(a, other)
+
+    # ensure operation is commutative
+    result2 = comparison_op(other, a)
+    tm.assert_equal(result, result2)
+
+    expected = pd.array([None, None, True], dtype="bool[pyarrow]")
+    expected[-1] = getattr(other[-1], op_name)(a[-1])
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("box", [pd.array, pd.Index, Series])
+def test_comparison_methods_list(comparison_op, any_string_dtype, box, request):
+    dtype = any_string_dtype
+
+    if box is pd.array and dtype != object and dtype.na_value is np.nan:
+        mark = pytest.mark.xfail(
+            reason="After wrapping list, op returns NotImplemented, see GH#62522"
+        )
+        request.applymarker(mark)
+
+    op_name = f"__{comparison_op.__name__}__"
+
+    a = box(pd.array(["a", None, "c"], dtype=dtype))
+    item = "c"
+    other = [None, None, "c"]
+    result = comparison_op(a, other)
+
+    # ensure operation is commutative
+    result2 = comparison_op(other, a)
+    tm.assert_equal(result, result2)
+
+    if dtype == np.dtype(object) or dtype.na_value is np.nan:
+        if operator.ne == comparison_op:
+            expected = np.array([True, True, False])
+        else:
+            expected = np.array([False, False, False])
+            expected[-1] = getattr(item, op_name)(item)
+        if box is not pd.Index:
+            # if GH#62766 is addressed this check can be removed
+            expected = box(expected, dtype=expected.dtype)
+        tm.assert_equal(result, expected)
+
+    else:
+        expected_dtype = "boolean[pyarrow]" if dtype.storage == "pyarrow" else "boolean"
+        expected = np.full(len(a), fill_value=None, dtype="object")
+        expected[-1] = getattr(item, op_name)(item)
+        expected = pd.array(expected, dtype=expected_dtype)
+        expected = extract_array(expected, extract_numpy=True)
+        if box is not pd.Index:
+            # if GH#62766 is addressed this check can be removed
+            expected = tm.box_expected(expected, box)
+        tm.assert_equal(result, expected)