venv

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/__init__.py

@@ -0,0 +1,7 @@
+"""
+Test files dedicated to individual (stand-alone) DataFrame methods
+
+Ideally these files/tests should correspond 1-to-1 with tests.series.methods
+
+These may also present opportunities for sharing/de-duplicating test code.
+"""

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_add_prefix_suffix.py

@@ -0,0 +1,49 @@
+import pytest
+
+from pandas import Index
+import pandas._testing as tm
+
+
+def test_add_prefix_suffix(float_frame):
+    with_prefix = float_frame.add_prefix("foo#")
+    expected = Index([f"foo#{c}" for c in float_frame.columns])
+    tm.assert_index_equal(with_prefix.columns, expected)
+
+    with_suffix = float_frame.add_suffix("#foo")
+    expected = Index([f"{c}#foo" for c in float_frame.columns])
+    tm.assert_index_equal(with_suffix.columns, expected)
+
+    with_pct_prefix = float_frame.add_prefix("%")
+    expected = Index([f"%{c}" for c in float_frame.columns])
+    tm.assert_index_equal(with_pct_prefix.columns, expected)
+
+    with_pct_suffix = float_frame.add_suffix("%")
+    expected = Index([f"{c}%" for c in float_frame.columns])
+    tm.assert_index_equal(with_pct_suffix.columns, expected)
+
+
+def test_add_prefix_suffix_axis(float_frame):
+    # GH 47819
+    with_prefix = float_frame.add_prefix("foo#", axis=0)
+    expected = Index([f"foo#{c}" for c in float_frame.index])
+    tm.assert_index_equal(with_prefix.index, expected)
+
+    with_prefix = float_frame.add_prefix("foo#", axis=1)
+    expected = Index([f"foo#{c}" for c in float_frame.columns])
+    tm.assert_index_equal(with_prefix.columns, expected)
+
+    with_pct_suffix = float_frame.add_suffix("#foo", axis=0)
+    expected = Index([f"{c}#foo" for c in float_frame.index])
+    tm.assert_index_equal(with_pct_suffix.index, expected)
+
+    with_pct_suffix = float_frame.add_suffix("#foo", axis=1)
+    expected = Index([f"{c}#foo" for c in float_frame.columns])
+    tm.assert_index_equal(with_pct_suffix.columns, expected)
+
+
+def test_add_prefix_suffix_invalid_axis(float_frame):
+    with pytest.raises(ValueError, match="No axis named 2 for object type DataFrame"):
+        float_frame.add_prefix("foo#", axis=2)
+
+    with pytest.raises(ValueError, match="No axis named 2 for object type DataFrame"):
+        float_frame.add_suffix("foo#", axis=2)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_align.py

@@ -0,0 +1,484 @@
+from datetime import timezone
+
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Index,
+    Series,
+    date_range,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameAlign:
+    def test_align_asfreq_method_raises(self):
+        df = DataFrame({"A": [1, np.nan, 2]})
+        msg = "Invalid fill method"
+        msg2 = "The 'method', 'limit', and 'fill_axis' keywords"
+        with pytest.raises(ValueError, match=msg):
+            with tm.assert_produces_warning(FutureWarning, match=msg2):
+                df.align(df.iloc[::-1], method="asfreq")
+
+    def test_frame_align_aware(self):
+        idx1 = date_range("2001", periods=5, freq="h", tz="US/Eastern")
+        idx2 = date_range("2001", periods=5, freq="2h", tz="US/Eastern")
+        df1 = DataFrame(np.random.default_rng(2).standard_normal((len(idx1), 3)), idx1)
+        df2 = DataFrame(np.random.default_rng(2).standard_normal((len(idx2), 3)), idx2)
+        new1, new2 = df1.align(df2)
+        assert df1.index.tz == new1.index.tz
+        assert df2.index.tz == new2.index.tz
+
+        # different timezones convert to UTC
+
+        # frame with frame
+        df1_central = df1.tz_convert("US/Central")
+        new1, new2 = df1.align(df1_central)
+        assert new1.index.tz is timezone.utc
+        assert new2.index.tz is timezone.utc
+
+        # frame with Series
+        new1, new2 = df1.align(df1_central[0], axis=0)
+        assert new1.index.tz is timezone.utc
+        assert new2.index.tz is timezone.utc
+
+        df1[0].align(df1_central, axis=0)
+        assert new1.index.tz is timezone.utc
+        assert new2.index.tz is timezone.utc
+
+    def test_align_float(self, float_frame, using_copy_on_write):
+        af, bf = float_frame.align(float_frame)
+        assert af._mgr is not float_frame._mgr
+
+        af, bf = float_frame.align(float_frame, copy=False)
+        if not using_copy_on_write:
+            assert af._mgr is float_frame._mgr
+        else:
+            assert af._mgr is not float_frame._mgr
+
+        # axis = 0
+        other = float_frame.iloc[:-5, :3]
+        af, bf = float_frame.align(other, axis=0, fill_value=-1)
+
+        tm.assert_index_equal(bf.columns, other.columns)
+
+        # test fill value
+        join_idx = float_frame.index.join(other.index)
+        diff_a = float_frame.index.difference(join_idx)
+        diff_a_vals = af.reindex(diff_a).values
+        assert (diff_a_vals == -1).all()
+
+        af, bf = float_frame.align(other, join="right", axis=0)
+        tm.assert_index_equal(bf.columns, other.columns)
+        tm.assert_index_equal(bf.index, other.index)
+        tm.assert_index_equal(af.index, other.index)
+
+        # axis = 1
+        other = float_frame.iloc[:-5, :3].copy()
+        af, bf = float_frame.align(other, axis=1)
+        tm.assert_index_equal(bf.columns, float_frame.columns)
+        tm.assert_index_equal(bf.index, other.index)
+
+        # test fill value
+        join_idx = float_frame.index.join(other.index)
+        diff_a = float_frame.index.difference(join_idx)
+        diff_a_vals = af.reindex(diff_a).values
+
+        assert (diff_a_vals == -1).all()
+
+        af, bf = float_frame.align(other, join="inner", axis=1)
+        tm.assert_index_equal(bf.columns, other.columns)
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = float_frame.align(other, join="inner", axis=1, method="pad")
+        tm.assert_index_equal(bf.columns, other.columns)
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = float_frame.align(
+                other.iloc[:, 0], join="inner", axis=1, method=None, fill_value=None
+            )
+        tm.assert_index_equal(bf.index, Index([]).astype(bf.index.dtype))
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = float_frame.align(
+                other.iloc[:, 0], join="inner", axis=1, method=None, fill_value=0
+            )
+        tm.assert_index_equal(bf.index, Index([]).astype(bf.index.dtype))
+
+        # Try to align DataFrame to Series along bad axis
+        msg = "No axis named 2 for object type DataFrame"
+        with pytest.raises(ValueError, match=msg):
+            float_frame.align(af.iloc[0, :3], join="inner", axis=2)
+
+    def test_align_frame_with_series(self, float_frame):
+        # align dataframe to series with broadcast or not
+        idx = float_frame.index
+        s = Series(range(len(idx)), index=idx)
+
+        left, right = float_frame.align(s, axis=0)
+        tm.assert_index_equal(left.index, float_frame.index)
+        tm.assert_index_equal(right.index, float_frame.index)
+        assert isinstance(right, Series)
+
+        msg = "The 'broadcast_axis' keyword in DataFrame.align is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            left, right = float_frame.align(s, broadcast_axis=1)
+        tm.assert_index_equal(left.index, float_frame.index)
+        expected = {c: s for c in float_frame.columns}
+        expected = DataFrame(
+            expected, index=float_frame.index, columns=float_frame.columns
+        )
+        tm.assert_frame_equal(right, expected)
+
+    def test_align_series_condition(self):
+        # see gh-9558
+        df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
+        result = df[df["a"] == 2]
+        expected = DataFrame([[2, 5]], index=[1], columns=["a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+        result = df.where(df["a"] == 2, 0)
+        expected = DataFrame({"a": [0, 2, 0], "b": [0, 5, 0]})
+        tm.assert_frame_equal(result, expected)
+
+    def test_align_int(self, int_frame):
+        # test other non-float types
+        other = DataFrame(index=range(5), columns=["A", "B", "C"])
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = int_frame.align(other, join="inner", axis=1, method="pad")
+        tm.assert_index_equal(bf.columns, other.columns)
+
+    def test_align_mixed_type(self, float_string_frame):
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = float_string_frame.align(
+                float_string_frame, join="inner", axis=1, method="pad"
+            )
+        tm.assert_index_equal(bf.columns, float_string_frame.columns)
+
+    def test_align_mixed_float(self, mixed_float_frame):
+        # mixed floats/ints
+        other = DataFrame(index=range(5), columns=["A", "B", "C"])
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = mixed_float_frame.align(
+                other.iloc[:, 0], join="inner", axis=1, method=None, fill_value=0
+            )
+        tm.assert_index_equal(bf.index, Index([]))
+
+    def test_align_mixed_int(self, mixed_int_frame):
+        other = DataFrame(index=range(5), columns=["A", "B", "C"])
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            af, bf = mixed_int_frame.align(
+                other.iloc[:, 0], join="inner", axis=1, method=None, fill_value=0
+            )
+        tm.assert_index_equal(bf.index, Index([]))
+
+    @pytest.mark.parametrize(
+        "l_ordered,r_ordered,expected",
+        [
+            [True, True, pd.CategoricalIndex],
+            [True, False, Index],
+            [False, True, Index],
+            [False, False, pd.CategoricalIndex],
+        ],
+    )
+    def test_align_categorical(self, l_ordered, r_ordered, expected):
+        # GH-28397
+        df_1 = DataFrame(
+            {
+                "A": np.arange(6, dtype="int64"),
+                "B": Series(list("aabbca")).astype(
+                    pd.CategoricalDtype(list("cab"), ordered=l_ordered)
+                ),
+            }
+        ).set_index("B")
+        df_2 = DataFrame(
+            {
+                "A": np.arange(5, dtype="int64"),
+                "B": Series(list("babca")).astype(
+                    pd.CategoricalDtype(list("cab"), ordered=r_ordered)
+                ),
+            }
+        ).set_index("B")
+
+        aligned_1, aligned_2 = df_1.align(df_2)
+        assert isinstance(aligned_1.index, expected)
+        assert isinstance(aligned_2.index, expected)
+        tm.assert_index_equal(aligned_1.index, aligned_2.index)
+
+    def test_align_multiindex(self):
+        # GH#10665
+        # same test cases as test_align_multiindex in test_series.py
+
+        midx = pd.MultiIndex.from_product(
+            [range(2), range(3), range(2)], names=("a", "b", "c")
+        )
+        idx = Index(range(2), name="b")
+        df1 = DataFrame(np.arange(12, dtype="int64"), index=midx)
+        df2 = DataFrame(np.arange(2, dtype="int64"), index=idx)
+
+        # these must be the same results (but flipped)
+        res1l, res1r = df1.align(df2, join="left")
+        res2l, res2r = df2.align(df1, join="right")
+
+        expl = df1
+        tm.assert_frame_equal(expl, res1l)
+        tm.assert_frame_equal(expl, res2r)
+        expr = DataFrame([0, 0, 1, 1, np.nan, np.nan] * 2, index=midx)
+        tm.assert_frame_equal(expr, res1r)
+        tm.assert_frame_equal(expr, res2l)
+
+        res1l, res1r = df1.align(df2, join="right")
+        res2l, res2r = df2.align(df1, join="left")
+
+        exp_idx = pd.MultiIndex.from_product(
+            [range(2), range(2), range(2)], names=("a", "b", "c")
+        )
+        expl = DataFrame([0, 1, 2, 3, 6, 7, 8, 9], index=exp_idx)
+        tm.assert_frame_equal(expl, res1l)
+        tm.assert_frame_equal(expl, res2r)
+        expr = DataFrame([0, 0, 1, 1] * 2, index=exp_idx)
+        tm.assert_frame_equal(expr, res1r)
+        tm.assert_frame_equal(expr, res2l)
+
+    def test_align_series_combinations(self):
+        df = DataFrame({"a": [1, 3, 5], "b": [1, 3, 5]}, index=list("ACE"))
+        s = Series([1, 2, 4], index=list("ABD"), name="x")
+
+        # frame + series
+        res1, res2 = df.align(s, axis=0)
+        exp1 = DataFrame(
+            {"a": [1, np.nan, 3, np.nan, 5], "b": [1, np.nan, 3, np.nan, 5]},
+            index=list("ABCDE"),
+        )
+        exp2 = Series([1, 2, np.nan, 4, np.nan], index=list("ABCDE"), name="x")
+
+        tm.assert_frame_equal(res1, exp1)
+        tm.assert_series_equal(res2, exp2)
+
+        # series + frame
+        res1, res2 = s.align(df)
+        tm.assert_series_equal(res1, exp2)
+        tm.assert_frame_equal(res2, exp1)
+
+    def test_multiindex_align_to_series_with_common_index_level(self):
+        #  GH-46001
+        foo_index = Index([1, 2, 3], name="foo")
+        bar_index = Index([1, 2], name="bar")
+
+        series = Series([1, 2], index=bar_index, name="foo_series")
+        df = DataFrame(
+            {"col": np.arange(6)},
+            index=pd.MultiIndex.from_product([foo_index, bar_index]),
+        )
+
+        expected_r = Series([1, 2] * 3, index=df.index, name="foo_series")
+        result_l, result_r = df.align(series, axis=0)
+
+        tm.assert_frame_equal(result_l, df)
+        tm.assert_series_equal(result_r, expected_r)
+
+    def test_multiindex_align_to_series_with_common_index_level_missing_in_left(self):
+        #  GH-46001
+        foo_index = Index([1, 2, 3], name="foo")
+        bar_index = Index([1, 2], name="bar")
+
+        series = Series(
+            [1, 2, 3, 4], index=Index([1, 2, 3, 4], name="bar"), name="foo_series"
+        )
+        df = DataFrame(
+            {"col": np.arange(6)},
+            index=pd.MultiIndex.from_product([foo_index, bar_index]),
+        )
+
+        expected_r = Series([1, 2] * 3, index=df.index, name="foo_series")
+        result_l, result_r = df.align(series, axis=0)
+
+        tm.assert_frame_equal(result_l, df)
+        tm.assert_series_equal(result_r, expected_r)
+
+    def test_multiindex_align_to_series_with_common_index_level_missing_in_right(self):
+        #  GH-46001
+        foo_index = Index([1, 2, 3], name="foo")
+        bar_index = Index([1, 2, 3, 4], name="bar")
+
+        series = Series([1, 2], index=Index([1, 2], name="bar"), name="foo_series")
+        df = DataFrame(
+            {"col": np.arange(12)},
+            index=pd.MultiIndex.from_product([foo_index, bar_index]),
+        )
+
+        expected_r = Series(
+            [1, 2, np.nan, np.nan] * 3, index=df.index, name="foo_series"
+        )
+        result_l, result_r = df.align(series, axis=0)
+
+        tm.assert_frame_equal(result_l, df)
+        tm.assert_series_equal(result_r, expected_r)
+
+    def test_multiindex_align_to_series_with_common_index_level_missing_in_both(self):
+        #  GH-46001
+        foo_index = Index([1, 2, 3], name="foo")
+        bar_index = Index([1, 3, 4], name="bar")
+
+        series = Series(
+            [1, 2, 3], index=Index([1, 2, 4], name="bar"), name="foo_series"
+        )
+        df = DataFrame(
+            {"col": np.arange(9)},
+            index=pd.MultiIndex.from_product([foo_index, bar_index]),
+        )
+
+        expected_r = Series([1, np.nan, 3] * 3, index=df.index, name="foo_series")
+        result_l, result_r = df.align(series, axis=0)
+
+        tm.assert_frame_equal(result_l, df)
+        tm.assert_series_equal(result_r, expected_r)
+
+    def test_multiindex_align_to_series_with_common_index_level_non_unique_cols(self):
+        #  GH-46001
+        foo_index = Index([1, 2, 3], name="foo")
+        bar_index = Index([1, 2], name="bar")
+
+        series = Series([1, 2], index=bar_index, name="foo_series")
+        df = DataFrame(
+            np.arange(18).reshape(6, 3),
+            index=pd.MultiIndex.from_product([foo_index, bar_index]),
+        )
+        df.columns = ["cfoo", "cbar", "cfoo"]
+
+        expected = Series([1, 2] * 3, index=df.index, name="foo_series")
+        result_left, result_right = df.align(series, axis=0)
+
+        tm.assert_series_equal(result_right, expected)
+        tm.assert_index_equal(result_left.columns, df.columns)
+
+    def test_missing_axis_specification_exception(self):
+        df = DataFrame(np.arange(50).reshape((10, 5)))
+        series = Series(np.arange(5))
+
+        with pytest.raises(ValueError, match=r"axis=0 or 1"):
+            df.align(series)
+
+    @pytest.mark.parametrize("method", ["pad", "bfill"])
+    @pytest.mark.parametrize("axis", [0, 1, None])
+    @pytest.mark.parametrize("fill_axis", [0, 1])
+    @pytest.mark.parametrize("how", ["inner", "outer", "left", "right"])
+    @pytest.mark.parametrize(
+        "left_slice",
+        [
+            [slice(4), slice(10)],
+            [slice(0), slice(0)],
+        ],
+    )
+    @pytest.mark.parametrize(
+        "right_slice",
+        [
+            [slice(2, None), slice(6, None)],
+            [slice(0), slice(0)],
+        ],
+    )
+    @pytest.mark.parametrize("limit", [1, None])
+    def test_align_fill_method(
+        self, how, method, axis, fill_axis, float_frame, left_slice, right_slice, limit
+    ):
+        frame = float_frame
+        left = frame.iloc[left_slice[0], left_slice[1]]
+        right = frame.iloc[right_slice[0], right_slice[1]]
+
+        msg = (
+            "The 'method', 'limit', and 'fill_axis' keywords in DataFrame.align "
+            "are deprecated"
+        )
+
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            aa, ab = left.align(
+                right,
+                axis=axis,
+                join=how,
+                method=method,
+                limit=limit,
+                fill_axis=fill_axis,
+            )
+
+        join_index, join_columns = None, None
+
+        ea, eb = left, right
+        if axis is None or axis == 0:
+            join_index = left.index.join(right.index, how=how)
+            ea = ea.reindex(index=join_index)
+            eb = eb.reindex(index=join_index)
+
+        if axis is None or axis == 1:
+            join_columns = left.columns.join(right.columns, how=how)
+            ea = ea.reindex(columns=join_columns)
+            eb = eb.reindex(columns=join_columns)
+
+        msg = "DataFrame.fillna with 'method' is deprecated"
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            ea = ea.fillna(axis=fill_axis, method=method, limit=limit)
+            eb = eb.fillna(axis=fill_axis, method=method, limit=limit)
+
+        tm.assert_frame_equal(aa, ea)
+        tm.assert_frame_equal(ab, eb)
+
+    def test_align_series_check_copy(self):
+        # GH#
+        df = DataFrame({0: [1, 2]})
+        ser = Series([1], name=0)
+        expected = ser.copy()
+        result, other = df.align(ser, axis=1)
+        ser.iloc[0] = 100
+        tm.assert_series_equal(other, expected)
+
+    def test_align_identical_different_object(self):
+        # GH#51032
+        df = DataFrame({"a": [1, 2]})
+        ser = Series([3, 4])
+        result, result2 = df.align(ser, axis=0)
+        tm.assert_frame_equal(result, df)
+        tm.assert_series_equal(result2, ser)
+        assert df is not result
+        assert ser is not result2
+
+    def test_align_identical_different_object_columns(self):
+        # GH#51032
+        df = DataFrame({"a": [1, 2]})
+        ser = Series([1], index=["a"])
+        result, result2 = df.align(ser, axis=1)
+        tm.assert_frame_equal(result, df)
+        tm.assert_series_equal(result2, ser)
+        assert df is not result
+        assert ser is not result2

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_asfreq.py

@@ -0,0 +1,263 @@
+from datetime import datetime
+
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs.offsets import MonthEnd
+
+from pandas import (
+    DataFrame,
+    DatetimeIndex,
+    Series,
+    date_range,
+    period_range,
+    to_datetime,
+)
+import pandas._testing as tm
+
+from pandas.tseries import offsets
+
+
+class TestAsFreq:
+    @pytest.fixture(params=["s", "ms", "us", "ns"])
+    def unit(self, request):
+        return request.param
+
+    def test_asfreq2(self, frame_or_series):
+        ts = frame_or_series(
+            [0.0, 1.0, 2.0],
+            index=DatetimeIndex(
+                [
+                    datetime(2009, 10, 30),
+                    datetime(2009, 11, 30),
+                    datetime(2009, 12, 31),
+                ],
+                dtype="M8[ns]",
+                freq="BME",
+            ),
+        )
+
+        daily_ts = ts.asfreq("B")
+        monthly_ts = daily_ts.asfreq("BME")
+        tm.assert_equal(monthly_ts, ts)
+
+        daily_ts = ts.asfreq("B", method="pad")
+        monthly_ts = daily_ts.asfreq("BME")
+        tm.assert_equal(monthly_ts, ts)
+
+        daily_ts = ts.asfreq(offsets.BDay())
+        monthly_ts = daily_ts.asfreq(offsets.BMonthEnd())
+        tm.assert_equal(monthly_ts, ts)
+
+        result = ts[:0].asfreq("ME")
+        assert len(result) == 0
+        assert result is not ts
+
+        if frame_or_series is Series:
+            daily_ts = ts.asfreq("D", fill_value=-1)
+            result = daily_ts.value_counts().sort_index()
+            expected = Series(
+                [60, 1, 1, 1], index=[-1.0, 2.0, 1.0, 0.0], name="count"
+            ).sort_index()
+            tm.assert_series_equal(result, expected)
+
+    def test_asfreq_datetimeindex_empty(self, frame_or_series):
+        # GH#14320
+        index = DatetimeIndex(["2016-09-29 11:00"])
+        expected = frame_or_series(index=index, dtype=object).asfreq("h")
+        result = frame_or_series([3], index=index.copy()).asfreq("h")
+        tm.assert_index_equal(expected.index, result.index)
+
+    @pytest.mark.parametrize("tz", ["US/Eastern", "dateutil/US/Eastern"])
+    def test_tz_aware_asfreq_smoke(self, tz, frame_or_series):
+        dr = date_range("2011-12-01", "2012-07-20", freq="D", tz=tz)
+
+        obj = frame_or_series(
+            np.random.default_rng(2).standard_normal(len(dr)), index=dr
+        )
+
+        # it works!
+        obj.asfreq("min")
+
+    def test_asfreq_normalize(self, frame_or_series):
+        rng = date_range("1/1/2000 09:30", periods=20)
+        norm = date_range("1/1/2000", periods=20)
+
+        vals = np.random.default_rng(2).standard_normal((20, 3))
+
+        obj = DataFrame(vals, index=rng)
+        expected = DataFrame(vals, index=norm)
+        if frame_or_series is Series:
+            obj = obj[0]
+            expected = expected[0]
+
+        result = obj.asfreq("D", normalize=True)
+        tm.assert_equal(result, expected)
+
+    def test_asfreq_keep_index_name(self, frame_or_series):
+        # GH#9854
+        index_name = "bar"
+        index = date_range("20130101", periods=20, name=index_name)
+        obj = DataFrame(list(range(20)), columns=["foo"], index=index)
+        obj = tm.get_obj(obj, frame_or_series)
+
+        assert index_name == obj.index.name
+        assert index_name == obj.asfreq("10D").index.name
+
+    def test_asfreq_ts(self, frame_or_series):
+        index = period_range(freq="Y", start="1/1/2001", end="12/31/2010")
+        obj = DataFrame(
+            np.random.default_rng(2).standard_normal((len(index), 3)), index=index
+        )
+        obj = tm.get_obj(obj, frame_or_series)
+
+        result = obj.asfreq("D", how="end")
+        exp_index = index.asfreq("D", how="end")
+        assert len(result) == len(obj)
+        tm.assert_index_equal(result.index, exp_index)
+
+        result = obj.asfreq("D", how="start")
+        exp_index = index.asfreq("D", how="start")
+        assert len(result) == len(obj)
+        tm.assert_index_equal(result.index, exp_index)
+
+    def test_asfreq_resample_set_correct_freq(self, frame_or_series):
+        # GH#5613
+        # we test if .asfreq() and .resample() set the correct value for .freq
+        dti = to_datetime(["2012-01-01", "2012-01-02", "2012-01-03"])
+        obj = DataFrame({"col": [1, 2, 3]}, index=dti)
+        obj = tm.get_obj(obj, frame_or_series)
+
+        # testing the settings before calling .asfreq() and .resample()
+        assert obj.index.freq is None
+        assert obj.index.inferred_freq == "D"
+
+        # does .asfreq() set .freq correctly?
+        assert obj.asfreq("D").index.freq == "D"
+
+        # does .resample() set .freq correctly?
+        assert obj.resample("D").asfreq().index.freq == "D"
+
+    def test_asfreq_empty(self, datetime_frame):
+        # test does not blow up on length-0 DataFrame
+        zero_length = datetime_frame.reindex([])
+        result = zero_length.asfreq("BME")
+        assert result is not zero_length
+
+    def test_asfreq(self, datetime_frame):
+        offset_monthly = datetime_frame.asfreq(offsets.BMonthEnd())
+        rule_monthly = datetime_frame.asfreq("BME")
+
+        tm.assert_frame_equal(offset_monthly, rule_monthly)
+
+        rule_monthly.asfreq("B", method="pad")
+        # TODO: actually check that this worked.
+
+        # don't forget!
+        rule_monthly.asfreq("B", method="pad")
+
+    def test_asfreq_datetimeindex(self):
+        df = DataFrame(
+            {"A": [1, 2, 3]},
+            index=[datetime(2011, 11, 1), datetime(2011, 11, 2), datetime(2011, 11, 3)],
+        )
+        df = df.asfreq("B")
+        assert isinstance(df.index, DatetimeIndex)
+
+        ts = df["A"].asfreq("B")
+        assert isinstance(ts.index, DatetimeIndex)
+
+    def test_asfreq_fillvalue(self):
+        # test for fill value during upsampling, related to issue 3715
+
+        # setup
+        rng = date_range("1/1/2016", periods=10, freq="2s")
+        # Explicit cast to 'float' to avoid implicit cast when setting None
+        ts = Series(np.arange(len(rng)), index=rng, dtype="float")
+        df = DataFrame({"one": ts})
+
+        # insert pre-existing missing value
+        df.loc["2016-01-01 00:00:08", "one"] = None
+
+        actual_df = df.asfreq(freq="1s", fill_value=9.0)
+        expected_df = df.asfreq(freq="1s").fillna(9.0)
+        expected_df.loc["2016-01-01 00:00:08", "one"] = None
+        tm.assert_frame_equal(expected_df, actual_df)
+
+        expected_series = ts.asfreq(freq="1s").fillna(9.0)
+        actual_series = ts.asfreq(freq="1s", fill_value=9.0)
+        tm.assert_series_equal(expected_series, actual_series)
+
+    def test_asfreq_with_date_object_index(self, frame_or_series):
+        rng = date_range("1/1/2000", periods=20)
+        ts = frame_or_series(np.random.default_rng(2).standard_normal(20), index=rng)
+
+        ts2 = ts.copy()
+        ts2.index = [x.date() for x in ts2.index]
+
+        result = ts2.asfreq("4h", method="ffill")
+        expected = ts.asfreq("4h", method="ffill")
+        tm.assert_equal(result, expected)
+
+    def test_asfreq_with_unsorted_index(self, frame_or_series):
+        # GH#39805
+        # Test that rows are not dropped when the datetime index is out of order
+        index = to_datetime(["2021-01-04", "2021-01-02", "2021-01-03", "2021-01-01"])
+        result = frame_or_series(range(4), index=index)
+
+        expected = result.reindex(sorted(index))
+        expected.index = expected.index._with_freq("infer")
+
+        result = result.asfreq("D")
+        tm.assert_equal(result, expected)
+
+    def test_asfreq_after_normalize(self, unit):
+        # https://github.com/pandas-dev/pandas/issues/50727
+        result = DatetimeIndex(
+            date_range("2000", periods=2).as_unit(unit).normalize(), freq="D"
+        )
+        expected = DatetimeIndex(["2000-01-01", "2000-01-02"], freq="D").as_unit(unit)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "freq, freq_half",
+        [
+            ("2ME", "ME"),
+            (MonthEnd(2), MonthEnd(1)),
+        ],
+    )
+    def test_asfreq_2ME(self, freq, freq_half):
+        index = date_range("1/1/2000", periods=6, freq=freq_half)
+        df = DataFrame({"s": Series([0.0, 1.0, 2.0, 3.0, 4.0, 5.0], index=index)})
+        expected = df.asfreq(freq=freq)
+
+        index = date_range("1/1/2000", periods=3, freq=freq)
+        result = DataFrame({"s": Series([0.0, 2.0, 4.0], index=index)})
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "freq, freq_depr",
+        [
+            ("2ME", "2M"),
+            ("2QE", "2Q"),
+            ("2QE-SEP", "2Q-SEP"),
+            ("1BQE", "1BQ"),
+            ("2BQE-SEP", "2BQ-SEP"),
+            ("1YE", "1Y"),
+            ("2YE-MAR", "2Y-MAR"),
+            ("1YE", "1A"),
+            ("2YE-MAR", "2A-MAR"),
+            ("2BYE-MAR", "2BA-MAR"),
+        ],
+    )
+    def test_asfreq_frequency_M_Q_Y_A_deprecated(self, freq, freq_depr):
+        # GH#9586, #55978
+        depr_msg = f"'{freq_depr[1:]}' is deprecated and will be removed "
+        f"in a future version, please use '{freq[1:]}' instead."
+
+        index = date_range("1/1/2000", periods=4, freq=f"{freq[1:]}")
+        df = DataFrame({"s": Series([0.0, 1.0, 2.0, 3.0], index=index)})
+        expected = df.asfreq(freq=freq)
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            result = df.asfreq(freq=freq_depr)
+        tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_asof.py

@@ -0,0 +1,198 @@
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import IncompatibleFrequency
+
+from pandas import (
+    DataFrame,
+    Period,
+    Series,
+    Timestamp,
+    date_range,
+    period_range,
+    to_datetime,
+)
+import pandas._testing as tm
+
+
+@pytest.fixture
+def date_range_frame():
+    """
+    Fixture for DataFrame of ints with date_range index
+
+    Columns are ['A', 'B'].
+    """
+    N = 50
+    rng = date_range("1/1/1990", periods=N, freq="53s")
+    return DataFrame({"A": np.arange(N), "B": np.arange(N)}, index=rng)
+
+
+class TestFrameAsof:
+    def test_basic(self, date_range_frame):
+        # Explicitly cast to float to avoid implicit cast when setting np.nan
+        df = date_range_frame.astype({"A": "float"})
+        N = 50
+        df.loc[df.index[15:30], "A"] = np.nan
+        dates = date_range("1/1/1990", periods=N * 3, freq="25s")
+
+        result = df.asof(dates)
+        assert result.notna().all(1).all()
+        lb = df.index[14]
+        ub = df.index[30]
+
+        dates = list(dates)
+
+        result = df.asof(dates)
+        assert result.notna().all(1).all()
+
+        mask = (result.index >= lb) & (result.index < ub)
+        rs = result[mask]
+        assert (rs == 14).all(1).all()
+
+    def test_subset(self, date_range_frame):
+        N = 10
+        # explicitly cast to float to avoid implicit upcast when setting to np.nan
+        df = date_range_frame.iloc[:N].copy().astype({"A": "float"})
+        df.loc[df.index[4:8], "A"] = np.nan
+        dates = date_range("1/1/1990", periods=N * 3, freq="25s")
+
+        # with a subset of A should be the same
+        result = df.asof(dates, subset="A")
+        expected = df.asof(dates)
+        tm.assert_frame_equal(result, expected)
+
+        # same with A/B
+        result = df.asof(dates, subset=["A", "B"])
+        expected = df.asof(dates)
+        tm.assert_frame_equal(result, expected)
+
+        # B gives df.asof
+        result = df.asof(dates, subset="B")
+        expected = df.resample("25s", closed="right").ffill().reindex(dates)
+        expected.iloc[20:] = 9
+        # no "missing", so "B" can retain int dtype (df["A"].dtype platform-dependent)
+        expected["B"] = expected["B"].astype(df["B"].dtype)
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_missing(self, date_range_frame):
+        # GH 15118
+        # no match found - `where` value before earliest date in index
+        N = 10
+        # Cast to 'float64' to avoid upcast when introducing nan in df.asof
+        df = date_range_frame.iloc[:N].copy().astype("float64")
+
+        result = df.asof("1989-12-31")
+
+        expected = Series(
+            index=["A", "B"], name=Timestamp("1989-12-31"), dtype=np.float64
+        )
+        tm.assert_series_equal(result, expected)
+
+        result = df.asof(to_datetime(["1989-12-31"]))
+        expected = DataFrame(
+            index=to_datetime(["1989-12-31"]), columns=["A", "B"], dtype="float64"
+        )
+        tm.assert_frame_equal(result, expected)
+
+        # Check that we handle PeriodIndex correctly, dont end up with
+        #  period.ordinal for series name
+        df = df.to_period("D")
+        result = df.asof("1989-12-31")
+        assert isinstance(result.name, Period)
+
+    def test_asof_all_nans(self, frame_or_series):
+        # GH 15713
+        # DataFrame/Series is all nans
+        result = frame_or_series([np.nan]).asof([0])
+        expected = frame_or_series([np.nan])
+        tm.assert_equal(result, expected)
+
+    def test_all_nans(self, date_range_frame):
+        # GH 15713
+        # DataFrame is all nans
+
+        # testing non-default indexes, multiple inputs
+        N = 150
+        rng = date_range_frame.index
+        dates = date_range("1/1/1990", periods=N, freq="25s")
+        result = DataFrame(np.nan, index=rng, columns=["A"]).asof(dates)
+        expected = DataFrame(np.nan, index=dates, columns=["A"])
+        tm.assert_frame_equal(result, expected)
+
+        # testing multiple columns
+        dates = date_range("1/1/1990", periods=N, freq="25s")
+        result = DataFrame(np.nan, index=rng, columns=["A", "B", "C"]).asof(dates)
+        expected = DataFrame(np.nan, index=dates, columns=["A", "B", "C"])
+        tm.assert_frame_equal(result, expected)
+
+        # testing scalar input
+        result = DataFrame(np.nan, index=[1, 2], columns=["A", "B"]).asof([3])
+        expected = DataFrame(np.nan, index=[3], columns=["A", "B"])
+        tm.assert_frame_equal(result, expected)
+
+        result = DataFrame(np.nan, index=[1, 2], columns=["A", "B"]).asof(3)
+        expected = Series(np.nan, index=["A", "B"], name=3)
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "stamp,expected",
+        [
+            (
+                Timestamp("2018-01-01 23:22:43.325+00:00"),
+                Series(2, name=Timestamp("2018-01-01 23:22:43.325+00:00")),
+            ),
+            (
+                Timestamp("2018-01-01 22:33:20.682+01:00"),
+                Series(1, name=Timestamp("2018-01-01 22:33:20.682+01:00")),
+            ),
+        ],
+    )
+    def test_time_zone_aware_index(self, stamp, expected):
+        # GH21194
+        # Testing awareness of DataFrame index considering different
+        # UTC and timezone
+        df = DataFrame(
+            data=[1, 2],
+            index=[
+                Timestamp("2018-01-01 21:00:05.001+00:00"),
+                Timestamp("2018-01-01 22:35:10.550+00:00"),
+            ],
+        )
+
+        result = df.asof(stamp)
+        tm.assert_series_equal(result, expected)
+
+    def test_is_copy(self, date_range_frame):
+        # GH-27357, GH-30784: ensure the result of asof is an actual copy and
+        # doesn't track the parent dataframe / doesn't give SettingWithCopy warnings
+        df = date_range_frame.astype({"A": "float"})
+        N = 50
+        df.loc[df.index[15:30], "A"] = np.nan
+        dates = date_range("1/1/1990", periods=N * 3, freq="25s")
+
+        result = df.asof(dates)
+
+        with tm.assert_produces_warning(None):
+            result["C"] = 1
+
+    def test_asof_periodindex_mismatched_freq(self):
+        N = 50
+        rng = period_range("1/1/1990", periods=N, freq="h")
+        df = DataFrame(np.random.default_rng(2).standard_normal(N), index=rng)
+
+        # Mismatched freq
+        msg = "Input has different freq"
+        with pytest.raises(IncompatibleFrequency, match=msg):
+            df.asof(rng.asfreq("D"))
+
+    def test_asof_preserves_bool_dtype(self):
+        # GH#16063 was casting bools to floats
+        dti = date_range("2017-01-01", freq="MS", periods=4)
+        ser = Series([True, False, True], index=dti[:-1])
+
+        ts = dti[-1]
+        res = ser.asof([ts])
+
+        expected = Series([True], index=[ts])
+        tm.assert_series_equal(res, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_assign.py

@@ -0,0 +1,84 @@
+import pytest
+
+from pandas import DataFrame
+import pandas._testing as tm
+
+
+class TestAssign:
+    def test_assign(self):
+        df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
+        original = df.copy()
+        result = df.assign(C=df.B / df.A)
+        expected = df.copy()
+        expected["C"] = [4, 2.5, 2]
+        tm.assert_frame_equal(result, expected)
+
+        # lambda syntax
+        result = df.assign(C=lambda x: x.B / x.A)
+        tm.assert_frame_equal(result, expected)
+
+        # original is unmodified
+        tm.assert_frame_equal(df, original)
+
+        # Non-Series array-like
+        result = df.assign(C=[4, 2.5, 2])
+        tm.assert_frame_equal(result, expected)
+        # original is unmodified
+        tm.assert_frame_equal(df, original)
+
+        result = df.assign(B=df.B / df.A)
+        expected = expected.drop("B", axis=1).rename(columns={"C": "B"})
+        tm.assert_frame_equal(result, expected)
+
+        # overwrite
+        result = df.assign(A=df.A + df.B)
+        expected = df.copy()
+        expected["A"] = [5, 7, 9]
+        tm.assert_frame_equal(result, expected)
+
+        # lambda
+        result = df.assign(A=lambda x: x.A + x.B)
+        tm.assert_frame_equal(result, expected)
+
+    def test_assign_multiple(self):
+        df = DataFrame([[1, 4], [2, 5], [3, 6]], columns=["A", "B"])
+        result = df.assign(C=[7, 8, 9], D=df.A, E=lambda x: x.B)
+        expected = DataFrame(
+            [[1, 4, 7, 1, 4], [2, 5, 8, 2, 5], [3, 6, 9, 3, 6]], columns=list("ABCDE")
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_assign_order(self):
+        # GH 9818
+        df = DataFrame([[1, 2], [3, 4]], columns=["A", "B"])
+        result = df.assign(D=df.A + df.B, C=df.A - df.B)
+
+        expected = DataFrame([[1, 2, 3, -1], [3, 4, 7, -1]], columns=list("ABDC"))
+        tm.assert_frame_equal(result, expected)
+        result = df.assign(C=df.A - df.B, D=df.A + df.B)
+
+        expected = DataFrame([[1, 2, -1, 3], [3, 4, -1, 7]], columns=list("ABCD"))
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_assign_bad(self):
+        df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
+
+        # non-keyword argument
+        msg = r"assign\(\) takes 1 positional argument but 2 were given"
+        with pytest.raises(TypeError, match=msg):
+            df.assign(lambda x: x.A)
+        msg = "'DataFrame' object has no attribute 'C'"
+        with pytest.raises(AttributeError, match=msg):
+            df.assign(C=df.A, D=df.A + df.C)
+
+    def test_assign_dependent(self):
+        df = DataFrame({"A": [1, 2], "B": [3, 4]})
+
+        result = df.assign(C=df.A, D=lambda x: x["A"] + x["C"])
+        expected = DataFrame([[1, 3, 1, 2], [2, 4, 2, 4]], columns=list("ABCD"))
+        tm.assert_frame_equal(result, expected)
+
+        result = df.assign(C=lambda df: df.A, D=lambda df: df["A"] + df["C"])
+        expected = DataFrame([[1, 3, 1, 2], [2, 4, 2, 4]], columns=list("ABCD"))
+        tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_astype.py

@@ -0,0 +1,911 @@
+import re
+
+import numpy as np
+import pytest
+
+import pandas.util._test_decorators as td
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    CategoricalDtype,
+    DataFrame,
+    DatetimeTZDtype,
+    Index,
+    Interval,
+    IntervalDtype,
+    NaT,
+    Series,
+    Timedelta,
+    Timestamp,
+    concat,
+    date_range,
+    option_context,
+)
+import pandas._testing as tm
+
+
+def _check_cast(df, v):
+    """
+    Check if all dtypes of df are equal to v
+    """
+    assert all(s.dtype.name == v for _, s in df.items())
+
+
+class TestAstype:
+    def test_astype_float(self, float_frame):
+        casted = float_frame.astype(int)
+        expected = DataFrame(
+            float_frame.values.astype(int),
+            index=float_frame.index,
+            columns=float_frame.columns,
+        )
+        tm.assert_frame_equal(casted, expected)
+
+        casted = float_frame.astype(np.int32)
+        expected = DataFrame(
+            float_frame.values.astype(np.int32),
+            index=float_frame.index,
+            columns=float_frame.columns,
+        )
+        tm.assert_frame_equal(casted, expected)
+
+        float_frame["foo"] = "5"
+        casted = float_frame.astype(int)
+        expected = DataFrame(
+            float_frame.values.astype(int),
+            index=float_frame.index,
+            columns=float_frame.columns,
+        )
+        tm.assert_frame_equal(casted, expected)
+
+    def test_astype_mixed_float(self, mixed_float_frame):
+        # mixed casting
+        casted = mixed_float_frame.reindex(columns=["A", "B"]).astype("float32")
+        _check_cast(casted, "float32")
+
+        casted = mixed_float_frame.reindex(columns=["A", "B"]).astype("float16")
+        _check_cast(casted, "float16")
+
+    def test_astype_mixed_type(self):
+        # mixed casting
+        df = DataFrame(
+            {
+                "a": 1.0,
+                "b": 2,
+                "c": "foo",
+                "float32": np.array([1.0] * 10, dtype="float32"),
+                "int32": np.array([1] * 10, dtype="int32"),
+            },
+            index=np.arange(10),
+        )
+        mn = df._get_numeric_data().copy()
+        mn["little_float"] = np.array(12345.0, dtype="float16")
+        mn["big_float"] = np.array(123456789101112.0, dtype="float64")
+
+        casted = mn.astype("float64")
+        _check_cast(casted, "float64")
+
+        casted = mn.astype("int64")
+        _check_cast(casted, "int64")
+
+        casted = mn.reindex(columns=["little_float"]).astype("float16")
+        _check_cast(casted, "float16")
+
+        casted = mn.astype("float32")
+        _check_cast(casted, "float32")
+
+        casted = mn.astype("int32")
+        _check_cast(casted, "int32")
+
+        # to object
+        casted = mn.astype("O")
+        _check_cast(casted, "object")
+
+    def test_astype_with_exclude_string(self, float_frame):
+        df = float_frame.copy()
+        expected = float_frame.astype(int)
+        df["string"] = "foo"
+        casted = df.astype(int, errors="ignore")
+
+        expected["string"] = "foo"
+        tm.assert_frame_equal(casted, expected)
+
+        df = float_frame.copy()
+        expected = float_frame.astype(np.int32)
+        df["string"] = "foo"
+        casted = df.astype(np.int32, errors="ignore")
+
+        expected["string"] = "foo"
+        tm.assert_frame_equal(casted, expected)
+
+    def test_astype_with_view_float(self, float_frame):
+        # this is the only real reason to do it this way
+        tf = np.round(float_frame).astype(np.int32)
+        tf.astype(np.float32, copy=False)
+
+        # TODO(wesm): verification?
+        tf = float_frame.astype(np.float64)
+        tf.astype(np.int64, copy=False)
+
+    def test_astype_with_view_mixed_float(self, mixed_float_frame):
+        tf = mixed_float_frame.reindex(columns=["A", "B", "C"])
+
+        tf.astype(np.int64)
+        tf.astype(np.float32)
+
+    @pytest.mark.parametrize("dtype", [np.int32, np.int64])
+    @pytest.mark.parametrize("val", [np.nan, np.inf])
+    def test_astype_cast_nan_inf_int(self, val, dtype):
+        # see GH#14265
+        #
+        # Check NaN and inf --> raise error when converting to int.
+        msg = "Cannot convert non-finite values \\(NA or inf\\) to integer"
+        df = DataFrame([val])
+
+        with pytest.raises(ValueError, match=msg):
+            df.astype(dtype)
+
+    def test_astype_str(self):
+        # see GH#9757
+        a = Series(date_range("2010-01-04", periods=5))
+        b = Series(date_range("3/6/2012 00:00", periods=5, tz="US/Eastern"))
+        c = Series([Timedelta(x, unit="d") for x in range(5)])
+        d = Series(range(5))
+        e = Series([0.0, 0.2, 0.4, 0.6, 0.8])
+
+        df = DataFrame({"a": a, "b": b, "c": c, "d": d, "e": e})
+
+        # Datetime-like
+        result = df.astype(str)
+
+        expected = DataFrame(
+            {
+                "a": list(map(str, (Timestamp(x)._date_repr for x in a._values))),
+                "b": list(map(str, map(Timestamp, b._values))),
+                "c": [Timedelta(x)._repr_base() for x in c._values],
+                "d": list(map(str, d._values)),
+                "e": list(map(str, e._values)),
+            },
+            dtype="object",
+        )
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_astype_str_float(self):
+        # see GH#11302
+        result = DataFrame([np.nan]).astype(str)
+        expected = DataFrame(["nan"], dtype="object")
+
+        tm.assert_frame_equal(result, expected)
+        result = DataFrame([1.12345678901234567890]).astype(str)
+
+        val = "1.1234567890123457"
+        expected = DataFrame([val], dtype="object")
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype_class", [dict, Series])
+    def test_astype_dict_like(self, dtype_class):
+        # GH7271 & GH16717
+        a = Series(date_range("2010-01-04", periods=5))
+        b = Series(range(5))
+        c = Series([0.0, 0.2, 0.4, 0.6, 0.8])
+        d = Series(["1.0", "2", "3.14", "4", "5.4"])
+        df = DataFrame({"a": a, "b": b, "c": c, "d": d})
+        original = df.copy(deep=True)
+
+        # change type of a subset of columns
+        dt1 = dtype_class({"b": "str", "d": "float32"})
+        result = df.astype(dt1)
+        expected = DataFrame(
+            {
+                "a": a,
+                "b": Series(["0", "1", "2", "3", "4"], dtype="object"),
+                "c": c,
+                "d": Series([1.0, 2.0, 3.14, 4.0, 5.4], dtype="float32"),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+        tm.assert_frame_equal(df, original)
+
+        dt2 = dtype_class({"b": np.float32, "c": "float32", "d": np.float64})
+        result = df.astype(dt2)
+        expected = DataFrame(
+            {
+                "a": a,
+                "b": Series([0.0, 1.0, 2.0, 3.0, 4.0], dtype="float32"),
+                "c": Series([0.0, 0.2, 0.4, 0.6, 0.8], dtype="float32"),
+                "d": Series([1.0, 2.0, 3.14, 4.0, 5.4], dtype="float64"),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+        tm.assert_frame_equal(df, original)
+
+        # change all columns
+        dt3 = dtype_class({"a": str, "b": str, "c": str, "d": str})
+        tm.assert_frame_equal(df.astype(dt3), df.astype(str))
+        tm.assert_frame_equal(df, original)
+
+        # error should be raised when using something other than column labels
+        # in the keys of the dtype dict
+        dt4 = dtype_class({"b": str, 2: str})
+        dt5 = dtype_class({"e": str})
+        msg_frame = (
+            "Only a column name can be used for the key in a dtype mappings argument. "
+            "'{}' not found in columns."
+        )
+        with pytest.raises(KeyError, match=msg_frame.format(2)):
+            df.astype(dt4)
+        with pytest.raises(KeyError, match=msg_frame.format("e")):
+            df.astype(dt5)
+        tm.assert_frame_equal(df, original)
+
+        # if the dtypes provided are the same as the original dtypes, the
+        # resulting DataFrame should be the same as the original DataFrame
+        dt6 = dtype_class({col: df[col].dtype for col in df.columns})
+        equiv = df.astype(dt6)
+        tm.assert_frame_equal(df, equiv)
+        tm.assert_frame_equal(df, original)
+
+        # GH#16717
+        # if dtypes provided is empty, the resulting DataFrame
+        # should be the same as the original DataFrame
+        dt7 = dtype_class({}) if dtype_class is dict else dtype_class({}, dtype=object)
+        equiv = df.astype(dt7)
+        tm.assert_frame_equal(df, equiv)
+        tm.assert_frame_equal(df, original)
+
+    def test_astype_duplicate_col(self):
+        a1 = Series([1, 2, 3, 4, 5], name="a")
+        b = Series([0.1, 0.2, 0.4, 0.6, 0.8], name="b")
+        a2 = Series([0, 1, 2, 3, 4], name="a")
+        df = concat([a1, b, a2], axis=1)
+
+        result = df.astype(str)
+        a1_str = Series(["1", "2", "3", "4", "5"], dtype="str", name="a")
+        b_str = Series(["0.1", "0.2", "0.4", "0.6", "0.8"], dtype=str, name="b")
+        a2_str = Series(["0", "1", "2", "3", "4"], dtype="str", name="a")
+        expected = concat([a1_str, b_str, a2_str], axis=1)
+        tm.assert_frame_equal(result, expected)
+
+        result = df.astype({"a": "str"})
+        expected = concat([a1_str, b, a2_str], axis=1)
+        tm.assert_frame_equal(result, expected)
+
+    def test_astype_duplicate_col_series_arg(self):
+        # GH#44417
+        vals = np.random.default_rng(2).standard_normal((3, 4))
+        df = DataFrame(vals, columns=["A", "B", "C", "A"])
+        dtypes = df.dtypes
+        dtypes.iloc[0] = str
+        dtypes.iloc[2] = "Float64"
+
+        result = df.astype(dtypes)
+        expected = DataFrame(
+            {
+                0: Series(vals[:, 0].astype(str), dtype=object),
+                1: vals[:, 1],
+                2: pd.array(vals[:, 2], dtype="Float64"),
+                3: vals[:, 3],
+            }
+        )
+        expected.columns = df.columns
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "dtype",
+        [
+            "category",
+            CategoricalDtype(),
+            CategoricalDtype(ordered=True),
+            CategoricalDtype(ordered=False),
+            CategoricalDtype(categories=list("abcdef")),
+            CategoricalDtype(categories=list("edba"), ordered=False),
+            CategoricalDtype(categories=list("edcb"), ordered=True),
+        ],
+        ids=repr,
+    )
+    def test_astype_categorical(self, dtype):
+        # GH#18099
+        d = {"A": list("abbc"), "B": list("bccd"), "C": list("cdde")}
+        df = DataFrame(d)
+        result = df.astype(dtype)
+        expected = DataFrame({k: Categorical(v, dtype=dtype) for k, v in d.items()})
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("cls", [CategoricalDtype, DatetimeTZDtype, IntervalDtype])
+    def test_astype_categoricaldtype_class_raises(self, cls):
+        df = DataFrame({"A": ["a", "a", "b", "c"]})
+        xpr = f"Expected an instance of {cls.__name__}"
+        with pytest.raises(TypeError, match=xpr):
+            df.astype({"A": cls})
+
+        with pytest.raises(TypeError, match=xpr):
+            df["A"].astype(cls)
+
+    @pytest.mark.parametrize("dtype", ["Int64", "Int32", "Int16"])
+    def test_astype_extension_dtypes(self, dtype):
+        # GH#22578
+        df = DataFrame([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], columns=["a", "b"])
+
+        expected1 = DataFrame(
+            {
+                "a": pd.array([1, 3, 5], dtype=dtype),
+                "b": pd.array([2, 4, 6], dtype=dtype),
+            }
+        )
+        tm.assert_frame_equal(df.astype(dtype), expected1)
+        tm.assert_frame_equal(df.astype("int64").astype(dtype), expected1)
+        tm.assert_frame_equal(df.astype(dtype).astype("float64"), df)
+
+        df = DataFrame([[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]], columns=["a", "b"])
+        df["b"] = df["b"].astype(dtype)
+        expected2 = DataFrame(
+            {"a": [1.0, 3.0, 5.0], "b": pd.array([2, 4, 6], dtype=dtype)}
+        )
+        tm.assert_frame_equal(df, expected2)
+
+        tm.assert_frame_equal(df.astype(dtype), expected1)
+        tm.assert_frame_equal(df.astype("int64").astype(dtype), expected1)
+
+    @pytest.mark.parametrize("dtype", ["Int64", "Int32", "Int16"])
+    def test_astype_extension_dtypes_1d(self, dtype):
+        # GH#22578
+        df = DataFrame({"a": [1.0, 2.0, 3.0]})
+
+        expected1 = DataFrame({"a": pd.array([1, 2, 3], dtype=dtype)})
+        tm.assert_frame_equal(df.astype(dtype), expected1)
+        tm.assert_frame_equal(df.astype("int64").astype(dtype), expected1)
+
+        df = DataFrame({"a": [1.0, 2.0, 3.0]})
+        df["a"] = df["a"].astype(dtype)
+        expected2 = DataFrame({"a": pd.array([1, 2, 3], dtype=dtype)})
+        tm.assert_frame_equal(df, expected2)
+
+        tm.assert_frame_equal(df.astype(dtype), expected1)
+        tm.assert_frame_equal(df.astype("int64").astype(dtype), expected1)
+
+    @pytest.mark.parametrize("dtype", ["category", "Int64"])
+    def test_astype_extension_dtypes_duplicate_col(self, dtype):
+        # GH#24704
+        a1 = Series([0, np.nan, 4], name="a")
+        a2 = Series([np.nan, 3, 5], name="a")
+        df = concat([a1, a2], axis=1)
+
+        result = df.astype(dtype)
+        expected = concat([a1.astype(dtype), a2.astype(dtype)], axis=1)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "dtype", [{100: "float64", 200: "uint64"}, "category", "float64"]
+    )
+    def test_astype_column_metadata(self, dtype):
+        # GH#19920
+        columns = Index([100, 200, 300], dtype=np.uint64, name="foo")
+        df = DataFrame(np.arange(15).reshape(5, 3), columns=columns)
+        df = df.astype(dtype)
+        tm.assert_index_equal(df.columns, columns)
+
+    @pytest.mark.parametrize("unit", ["Y", "M", "W", "D", "h", "m"])
+    def test_astype_from_object_to_datetime_unit(self, unit):
+        vals = [
+            ["2015-01-01", "2015-01-02", "2015-01-03"],
+            ["2017-01-01", "2017-01-02", "2017-02-03"],
+        ]
+        df = DataFrame(vals, dtype=object)
+        msg = (
+            rf"Unexpected value for 'dtype': 'datetime64\[{unit}\]'. "
+            r"Must be 'datetime64\[s\]', 'datetime64\[ms\]', 'datetime64\[us\]', "
+            r"'datetime64\[ns\]' or DatetimeTZDtype"
+        )
+        with pytest.raises(ValueError, match=msg):
+            df.astype(f"M8[{unit}]")
+
+    @pytest.mark.parametrize("unit", ["Y", "M", "W", "D", "h", "m"])
+    def test_astype_from_object_to_timedelta_unit(self, unit):
+        vals = [
+            ["1 Day", "2 Days", "3 Days"],
+            ["4 Days", "5 Days", "6 Days"],
+        ]
+        df = DataFrame(vals, dtype=object)
+        msg = (
+            r"Cannot convert from timedelta64\[ns\] to timedelta64\[.*\]. "
+            "Supported resolutions are 's', 'ms', 'us', 'ns'"
+        )
+        with pytest.raises(ValueError, match=msg):
+            # TODO: this is ValueError while for DatetimeArray it is TypeError;
+            #  get these consistent
+            df.astype(f"m8[{unit}]")
+
+    @pytest.mark.parametrize("dtype", ["M8", "m8"])
+    @pytest.mark.parametrize("unit", ["ns", "us", "ms", "s", "h", "m", "D"])
+    def test_astype_from_datetimelike_to_object(self, dtype, unit):
+        # tests astype to object dtype
+        # GH#19223 / GH#12425
+        dtype = f"{dtype}[{unit}]"
+        arr = np.array([[1, 2, 3]], dtype=dtype)
+        df = DataFrame(arr)
+        result = df.astype(object)
+        assert (result.dtypes == object).all()
+
+        if dtype.startswith("M8"):
+            assert result.iloc[0, 0] == Timestamp(1, unit=unit)
+        else:
+            assert result.iloc[0, 0] == Timedelta(1, unit=unit)
+
+    @pytest.mark.parametrize("arr_dtype", [np.int64, np.float64])
+    @pytest.mark.parametrize("dtype", ["M8", "m8"])
+    @pytest.mark.parametrize("unit", ["ns", "us", "ms", "s", "h", "m", "D"])
+    def test_astype_to_datetimelike_unit(self, arr_dtype, dtype, unit):
+        # tests all units from numeric origination
+        # GH#19223 / GH#12425
+        dtype = f"{dtype}[{unit}]"
+        arr = np.array([[1, 2, 3]], dtype=arr_dtype)
+        df = DataFrame(arr)
+        result = df.astype(dtype)
+        expected = DataFrame(arr.astype(dtype))
+
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("unit", ["ns", "us", "ms", "s", "h", "m", "D"])
+    def test_astype_to_datetime_unit(self, unit):
+        # tests all units from datetime origination
+        # GH#19223
+        dtype = f"M8[{unit}]"
+        arr = np.array([[1, 2, 3]], dtype=dtype)
+        df = DataFrame(arr)
+        ser = df.iloc[:, 0]
+        idx = Index(ser)
+        dta = ser._values
+
+        if unit in ["ns", "us", "ms", "s"]:
+            # GH#48928
+            result = df.astype(dtype)
+        else:
+            # we use the nearest supported dtype (i.e. M8[s])
+            msg = rf"Cannot cast DatetimeArray to dtype datetime64\[{unit}\]"
+            with pytest.raises(TypeError, match=msg):
+                df.astype(dtype)
+
+            with pytest.raises(TypeError, match=msg):
+                ser.astype(dtype)
+
+            with pytest.raises(TypeError, match=msg.replace("Array", "Index")):
+                idx.astype(dtype)
+
+            with pytest.raises(TypeError, match=msg):
+                dta.astype(dtype)
+
+            return
+
+        exp_df = DataFrame(arr.astype(dtype))
+        assert (exp_df.dtypes == dtype).all()
+        tm.assert_frame_equal(result, exp_df)
+
+        res_ser = ser.astype(dtype)
+        exp_ser = exp_df.iloc[:, 0]
+        assert exp_ser.dtype == dtype
+        tm.assert_series_equal(res_ser, exp_ser)
+
+        exp_dta = exp_ser._values
+
+        res_index = idx.astype(dtype)
+        exp_index = Index(exp_ser)
+        assert exp_index.dtype == dtype
+        tm.assert_index_equal(res_index, exp_index)
+
+        res_dta = dta.astype(dtype)
+        assert exp_dta.dtype == dtype
+        tm.assert_extension_array_equal(res_dta, exp_dta)
+
+    @pytest.mark.parametrize("unit", ["ns"])
+    def test_astype_to_timedelta_unit_ns(self, unit):
+        # preserver the timedelta conversion
+        # GH#19223
+        dtype = f"m8[{unit}]"
+        arr = np.array([[1, 2, 3]], dtype=dtype)
+        df = DataFrame(arr)
+        result = df.astype(dtype)
+        expected = DataFrame(arr.astype(dtype))
+
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("unit", ["us", "ms", "s", "h", "m", "D"])
+    def test_astype_to_timedelta_unit(self, unit):
+        # coerce to float
+        # GH#19223 until 2.0 used to coerce to float
+        dtype = f"m8[{unit}]"
+        arr = np.array([[1, 2, 3]], dtype=dtype)
+        df = DataFrame(arr)
+        ser = df.iloc[:, 0]
+        tdi = Index(ser)
+        tda = tdi._values
+
+        if unit in ["us", "ms", "s"]:
+            assert (df.dtypes == dtype).all()
+            result = df.astype(dtype)
+        else:
+            # We get the nearest supported unit, i.e. "s"
+            assert (df.dtypes == "m8[s]").all()
+
+            msg = (
+                rf"Cannot convert from timedelta64\[s\] to timedelta64\[{unit}\]. "
+                "Supported resolutions are 's', 'ms', 'us', 'ns'"
+            )
+            with pytest.raises(ValueError, match=msg):
+                df.astype(dtype)
+            with pytest.raises(ValueError, match=msg):
+                ser.astype(dtype)
+            with pytest.raises(ValueError, match=msg):
+                tdi.astype(dtype)
+            with pytest.raises(ValueError, match=msg):
+                tda.astype(dtype)
+
+            return
+
+        result = df.astype(dtype)
+        # The conversion is a no-op, so we just get a copy
+        expected = df
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("unit", ["ns", "us", "ms", "s", "h", "m", "D"])
+    def test_astype_to_incorrect_datetimelike(self, unit):
+        # trying to astype a m to a M, or vice-versa
+        # GH#19224
+        dtype = f"M8[{unit}]"
+        other = f"m8[{unit}]"
+
+        df = DataFrame(np.array([[1, 2, 3]], dtype=dtype))
+        msg = "|".join(
+            [
+                # BlockManager path
+                rf"Cannot cast DatetimeArray to dtype timedelta64\[{unit}\]",
+                # ArrayManager path
+                "cannot astype a datetimelike from "
+                rf"\[datetime64\[ns\]\] to \[timedelta64\[{unit}\]\]",
+            ]
+        )
+        with pytest.raises(TypeError, match=msg):
+            df.astype(other)
+
+        msg = "|".join(
+            [
+                # BlockManager path
+                rf"Cannot cast TimedeltaArray to dtype datetime64\[{unit}\]",
+                # ArrayManager path
+                "cannot astype a timedelta from "
+                rf"\[timedelta64\[ns\]\] to \[datetime64\[{unit}\]\]",
+            ]
+        )
+        df = DataFrame(np.array([[1, 2, 3]], dtype=other))
+        with pytest.raises(TypeError, match=msg):
+            df.astype(dtype)
+
+    def test_astype_arg_for_errors(self):
+        # GH#14878
+
+        df = DataFrame([1, 2, 3])
+
+        msg = (
+            "Expected value of kwarg 'errors' to be one of "
+            "['raise', 'ignore']. Supplied value is 'True'"
+        )
+        with pytest.raises(ValueError, match=re.escape(msg)):
+            df.astype(np.float64, errors=True)
+
+        df.astype(np.int8, errors="ignore")
+
+    def test_astype_invalid_conversion(self):
+        # GH#47571
+        df = DataFrame({"a": [1, 2, "text"], "b": [1, 2, 3]})
+
+        msg = (
+            "invalid literal for int() with base 10: 'text': "
+            "Error while type casting for column 'a'"
+        )
+
+        with pytest.raises(ValueError, match=re.escape(msg)):
+            df.astype({"a": int})
+
+    def test_astype_arg_for_errors_dictlist(self):
+        # GH#25905
+        df = DataFrame(
+            [
+                {"a": "1", "b": "16.5%", "c": "test"},
+                {"a": "2.2", "b": "15.3", "c": "another_test"},
+            ]
+        )
+        expected = DataFrame(
+            [
+                {"a": 1.0, "b": "16.5%", "c": "test"},
+                {"a": 2.2, "b": "15.3", "c": "another_test"},
+            ]
+        )
+        expected["c"] = expected["c"].astype("object")
+        type_dict = {"a": "float64", "b": "float64", "c": "object"}
+
+        result = df.astype(dtype=type_dict, errors="ignore")
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_astype_dt64tz(self, timezone_frame):
+        # astype
+        expected = np.array(
+            [
+                [
+                    Timestamp("2013-01-01 00:00:00"),
+                    Timestamp("2013-01-02 00:00:00"),
+                    Timestamp("2013-01-03 00:00:00"),
+                ],
+                [
+                    Timestamp("2013-01-01 00:00:00-0500", tz="US/Eastern"),
+                    NaT,
+                    Timestamp("2013-01-03 00:00:00-0500", tz="US/Eastern"),
+                ],
+                [
+                    Timestamp("2013-01-01 00:00:00+0100", tz="CET"),
+                    NaT,
+                    Timestamp("2013-01-03 00:00:00+0100", tz="CET"),
+                ],
+            ],
+            dtype=object,
+        ).T
+        expected = DataFrame(
+            expected,
+            index=timezone_frame.index,
+            columns=timezone_frame.columns,
+            dtype=object,
+        )
+        result = timezone_frame.astype(object)
+        tm.assert_frame_equal(result, expected)
+
+        msg = "Cannot use .astype to convert from timezone-aware dtype to timezone-"
+        with pytest.raises(TypeError, match=msg):
+            # dt64tz->dt64 deprecated
+            timezone_frame.astype("datetime64[ns]")
+
+    def test_astype_dt64tz_to_str(self, timezone_frame):
+        # str formatting
+        result = timezone_frame.astype(str)
+        expected = DataFrame(
+            [
+                [
+                    "2013-01-01",
+                    "2013-01-01 00:00:00-05:00",
+                    "2013-01-01 00:00:00+01:00",
+                ],
+                ["2013-01-02", "NaT", "NaT"],
+                [
+                    "2013-01-03",
+                    "2013-01-03 00:00:00-05:00",
+                    "2013-01-03 00:00:00+01:00",
+                ],
+            ],
+            columns=timezone_frame.columns,
+            dtype="object",
+        )
+        tm.assert_frame_equal(result, expected)
+
+        with option_context("display.max_columns", 20):
+            result = str(timezone_frame)
+            assert (
+                "0 2013-01-01 2013-01-01 00:00:00-05:00 2013-01-01 00:00:00+01:00"
+            ) in result
+            assert (
+                "1 2013-01-02                       NaT                       NaT"
+            ) in result
+            assert (
+                "2 2013-01-03 2013-01-03 00:00:00-05:00 2013-01-03 00:00:00+01:00"
+            ) in result
+
+    def test_astype_empty_dtype_dict(self):
+        # issue mentioned further down in the following issue's thread
+        # https://github.com/pandas-dev/pandas/issues/33113
+        df = DataFrame()
+        result = df.astype({})
+        tm.assert_frame_equal(result, df)
+        assert result is not df
+
+    @pytest.mark.parametrize(
+        "data, dtype",
+        [
+            (["x", "y", "z"], "string[python]"),
+            pytest.param(
+                ["x", "y", "z"],
+                "string[pyarrow]",
+                marks=td.skip_if_no("pyarrow"),
+            ),
+            (["x", "y", "z"], "category"),
+            (3 * [Timestamp("2020-01-01", tz="UTC")], None),
+            (3 * [Interval(0, 1)], None),
+        ],
+    )
+    @pytest.mark.parametrize("errors", ["raise", "ignore"])
+    def test_astype_ignores_errors_for_extension_dtypes(self, data, dtype, errors):
+        # https://github.com/pandas-dev/pandas/issues/35471
+        df = DataFrame(Series(data, dtype=dtype))
+        if errors == "ignore":
+            expected = df
+            result = df.astype(float, errors=errors)
+            tm.assert_frame_equal(result, expected)
+        else:
+            msg = "(Cannot cast)|(could not convert)"
+            with pytest.raises((ValueError, TypeError), match=msg):
+                df.astype(float, errors=errors)
+
+    def test_astype_tz_conversion(self):
+        # GH 35973
+        val = {"tz": date_range("2020-08-30", freq="d", periods=2, tz="Europe/London")}
+        df = DataFrame(val)
+        result = df.astype({"tz": "datetime64[ns, Europe/Berlin]"})
+
+        expected = df
+        expected["tz"] = expected["tz"].dt.tz_convert("Europe/Berlin")
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("tz", ["UTC", "Europe/Berlin"])
+    def test_astype_tz_object_conversion(self, tz):
+        # GH 35973
+        val = {"tz": date_range("2020-08-30", freq="d", periods=2, tz="Europe/London")}
+        expected = DataFrame(val)
+
+        # convert expected to object dtype from other tz str (independently tested)
+        result = expected.astype({"tz": f"datetime64[ns, {tz}]"})
+        result = result.astype({"tz": "object"})
+
+        # do real test: object dtype to a specified tz, different from construction tz.
+        result = result.astype({"tz": "datetime64[ns, Europe/London]"})
+        tm.assert_frame_equal(result, expected)
+
+    def test_astype_dt64_to_string(
+        self, frame_or_series, tz_naive_fixture, using_infer_string
+    ):
+        # GH#41409
+        tz = tz_naive_fixture
+
+        dti = date_range("2016-01-01", periods=3, tz=tz)
+        dta = dti._data
+        dta[0] = NaT
+
+        obj = frame_or_series(dta)
+        result = obj.astype("string")
+
+        # Check that Series/DataFrame.astype matches DatetimeArray.astype
+        expected = frame_or_series(dta.astype("string"))
+        tm.assert_equal(result, expected)
+
+        item = result.iloc[0]
+        if frame_or_series is DataFrame:
+            item = item.iloc[0]
+        if using_infer_string:
+            assert item is np.nan
+        else:
+            assert item is pd.NA
+
+        # For non-NA values, we should match what we get for non-EA str
+        alt = obj.astype(str)
+        assert np.all(alt.iloc[1:] == result.iloc[1:])
+
+    def test_astype_td64_to_string(self, frame_or_series):
+        # GH#41409
+        tdi = pd.timedelta_range("1 Day", periods=3)
+        obj = frame_or_series(tdi)
+
+        expected = frame_or_series(["1 days", "2 days", "3 days"], dtype="string")
+        result = obj.astype("string")
+        tm.assert_equal(result, expected)
+
+    def test_astype_bytes(self):
+        # GH#39474
+        result = DataFrame(["foo", "bar", "baz"]).astype(bytes)
+        assert result.dtypes[0] == np.dtype("S3")
+
+    @pytest.mark.parametrize(
+        "index_slice",
+        [
+            np.s_[:2, :2],
+            np.s_[:1, :2],
+            np.s_[:2, :1],
+            np.s_[::2, ::2],
+            np.s_[::1, ::2],
+            np.s_[::2, ::1],
+        ],
+    )
+    def test_astype_noncontiguous(self, index_slice):
+        # GH#42396
+        data = np.arange(16).reshape(4, 4)
+        df = DataFrame(data)
+
+        result = df.iloc[index_slice].astype("int16")
+        expected = df.iloc[index_slice]
+        tm.assert_frame_equal(result, expected, check_dtype=False)
+
+    def test_astype_retain_attrs(self, any_numpy_dtype):
+        # GH#44414
+        df = DataFrame({"a": [0, 1, 2], "b": [3, 4, 5]})
+        df.attrs["Location"] = "Michigan"
+
+        result = df.astype({"a": any_numpy_dtype}).attrs
+        expected = df.attrs
+
+        tm.assert_dict_equal(expected, result)
+
+
+class TestAstypeCategorical:
+    def test_astype_from_categorical3(self):
+        df = DataFrame({"cats": [1, 2, 3, 4, 5, 6], "vals": [1, 2, 3, 4, 5, 6]})
+        cats = Categorical([1, 2, 3, 4, 5, 6])
+        exp_df = DataFrame({"cats": cats, "vals": [1, 2, 3, 4, 5, 6]})
+        df["cats"] = df["cats"].astype("category")
+        tm.assert_frame_equal(exp_df, df)
+
+    def test_astype_from_categorical4(self):
+        df = DataFrame(
+            {"cats": ["a", "b", "b", "a", "a", "d"], "vals": [1, 2, 3, 4, 5, 6]}
+        )
+        cats = Categorical(["a", "b", "b", "a", "a", "d"])
+        exp_df = DataFrame({"cats": cats, "vals": [1, 2, 3, 4, 5, 6]})
+        df["cats"] = df["cats"].astype("category")
+        tm.assert_frame_equal(exp_df, df)
+
+    def test_categorical_astype_to_int(self, any_int_dtype):
+        # GH#39402
+
+        df = DataFrame(data={"col1": pd.array([2.0, 1.0, 3.0])})
+        df.col1 = df.col1.astype("category")
+        df.col1 = df.col1.astype(any_int_dtype)
+        expected = DataFrame({"col1": pd.array([2, 1, 3], dtype=any_int_dtype)})
+        tm.assert_frame_equal(df, expected)
+
+    def test_astype_categorical_to_string_missing(self):
+        # https://github.com/pandas-dev/pandas/issues/41797
+        df = DataFrame(["a", "b", np.nan])
+        expected = df.astype(str)
+        cat = df.astype("category")
+        result = cat.astype(str)
+        tm.assert_frame_equal(result, expected)
+
+
+class IntegerArrayNoCopy(pd.core.arrays.IntegerArray):
+    # GH 42501
+
+    def copy(self):
+        assert False
+
+
+class Int16DtypeNoCopy(pd.Int16Dtype):
+    # GH 42501
+
+    @classmethod
+    def construct_array_type(cls):
+        return IntegerArrayNoCopy
+
+
+def test_frame_astype_no_copy():
+    # GH 42501
+    df = DataFrame({"a": [1, 4, None, 5], "b": [6, 7, 8, 9]}, dtype=object)
+    result = df.astype({"a": Int16DtypeNoCopy()}, copy=False)
+
+    assert result.a.dtype == pd.Int16Dtype()
+    assert np.shares_memory(df.b.values, result.b.values)
+
+
+@pytest.mark.parametrize("dtype", ["int64", "Int64"])
+def test_astype_copies(dtype):
+    # GH#50984
+    pytest.importorskip("pyarrow")
+    df = DataFrame({"a": [1, 2, 3]}, dtype=dtype)
+    result = df.astype("int64[pyarrow]", copy=True)
+    df.iloc[0, 0] = 100
+    expected = DataFrame({"a": [1, 2, 3]}, dtype="int64[pyarrow]")
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("val", [None, 1, 1.5, np.nan, NaT])
+def test_astype_to_string_not_modifying_input(string_storage, val):
+    # GH#51073
+    df = DataFrame({"a": ["a", "b", val]})
+    expected = df.copy()
+    with option_context("mode.string_storage", string_storage):
+        df.astype("string", copy=False)
+    tm.assert_frame_equal(df, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_at_time.py

@@ -0,0 +1,132 @@
+from datetime import time
+
+import numpy as np
+import pytest
+import pytz
+
+from pandas._libs.tslibs import timezones
+
+from pandas import (
+    DataFrame,
+    date_range,
+)
+import pandas._testing as tm
+
+
+class TestAtTime:
+    @pytest.mark.parametrize("tzstr", ["US/Eastern", "dateutil/US/Eastern"])
+    def test_localized_at_time(self, tzstr, frame_or_series):
+        tz = timezones.maybe_get_tz(tzstr)
+
+        rng = date_range("4/16/2012", "5/1/2012", freq="h")
+        ts = frame_or_series(
+            np.random.default_rng(2).standard_normal(len(rng)), index=rng
+        )
+
+        ts_local = ts.tz_localize(tzstr)
+
+        result = ts_local.at_time(time(10, 0))
+        expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
+        tm.assert_equal(result, expected)
+        assert timezones.tz_compare(result.index.tz, tz)
+
+    def test_at_time(self, frame_or_series):
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 2)), index=rng
+        )
+        ts = tm.get_obj(ts, frame_or_series)
+        rs = ts.at_time(rng[1])
+        assert (rs.index.hour == rng[1].hour).all()
+        assert (rs.index.minute == rng[1].minute).all()
+        assert (rs.index.second == rng[1].second).all()
+
+        result = ts.at_time("9:30")
+        expected = ts.at_time(time(9, 30))
+        tm.assert_equal(result, expected)
+
+    def test_at_time_midnight(self, frame_or_series):
+        # midnight, everything
+        rng = date_range("1/1/2000", "1/31/2000")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 3)), index=rng
+        )
+        ts = tm.get_obj(ts, frame_or_series)
+
+        result = ts.at_time(time(0, 0))
+        tm.assert_equal(result, ts)
+
+    def test_at_time_nonexistent(self, frame_or_series):
+        # time doesn't exist
+        rng = date_range("1/1/2012", freq="23Min", periods=384)
+        ts = DataFrame(np.random.default_rng(2).standard_normal(len(rng)), rng)
+        ts = tm.get_obj(ts, frame_or_series)
+        rs = ts.at_time("16:00")
+        assert len(rs) == 0
+
+    @pytest.mark.parametrize(
+        "hour", ["1:00", "1:00AM", time(1), time(1, tzinfo=pytz.UTC)]
+    )
+    def test_at_time_errors(self, hour):
+        # GH#24043
+        dti = date_range("2018", periods=3, freq="h")
+        df = DataFrame(list(range(len(dti))), index=dti)
+        if getattr(hour, "tzinfo", None) is None:
+            result = df.at_time(hour)
+            expected = df.iloc[1:2]
+            tm.assert_frame_equal(result, expected)
+        else:
+            with pytest.raises(ValueError, match="Index must be timezone"):
+                df.at_time(hour)
+
+    def test_at_time_tz(self):
+        # GH#24043
+        dti = date_range("2018", periods=3, freq="h", tz="US/Pacific")
+        df = DataFrame(list(range(len(dti))), index=dti)
+        result = df.at_time(time(4, tzinfo=pytz.timezone("US/Eastern")))
+        expected = df.iloc[1:2]
+        tm.assert_frame_equal(result, expected)
+
+    def test_at_time_raises(self, frame_or_series):
+        # GH#20725
+        obj = DataFrame([[1, 2, 3], [4, 5, 6]])
+        obj = tm.get_obj(obj, frame_or_series)
+        msg = "Index must be DatetimeIndex"
+        with pytest.raises(TypeError, match=msg):  # index is not a DatetimeIndex
+            obj.at_time("00:00")
+
+    @pytest.mark.parametrize("axis", ["index", "columns", 0, 1])
+    def test_at_time_axis(self, axis):
+        # issue 8839
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(np.random.default_rng(2).standard_normal((len(rng), len(rng))))
+        ts.index, ts.columns = rng, rng
+
+        indices = rng[(rng.hour == 9) & (rng.minute == 30) & (rng.second == 0)]
+
+        if axis in ["index", 0]:
+            expected = ts.loc[indices, :]
+        elif axis in ["columns", 1]:
+            expected = ts.loc[:, indices]
+
+        result = ts.at_time("9:30", axis=axis)
+
+        # Without clearing freq, result has freq 1440T and expected 5T
+        result.index = result.index._with_freq(None)
+        expected.index = expected.index._with_freq(None)
+        tm.assert_frame_equal(result, expected)
+
+    def test_at_time_datetimeindex(self):
+        index = date_range("2012-01-01", "2012-01-05", freq="30min")
+        df = DataFrame(
+            np.random.default_rng(2).standard_normal((len(index), 5)), index=index
+        )
+        akey = time(12, 0, 0)
+        ainds = [24, 72, 120, 168]
+
+        result = df.at_time(akey)
+        expected = df.loc[akey]
+        expected2 = df.iloc[ainds]
+        tm.assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected2)
+        assert len(result) == 4

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_between_time.py

@@ -0,0 +1,227 @@
+from datetime import (
+    datetime,
+    time,
+)
+
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import timezones
+import pandas.util._test_decorators as td
+
+from pandas import (
+    DataFrame,
+    Series,
+    date_range,
+)
+import pandas._testing as tm
+
+
+class TestBetweenTime:
+    @td.skip_if_not_us_locale
+    def test_between_time_formats(self, frame_or_series):
+        # GH#11818
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 2)), index=rng
+        )
+        ts = tm.get_obj(ts, frame_or_series)
+
+        strings = [
+            ("2:00", "2:30"),
+            ("0200", "0230"),
+            ("2:00am", "2:30am"),
+            ("0200am", "0230am"),
+            ("2:00:00", "2:30:00"),
+            ("020000", "023000"),
+            ("2:00:00am", "2:30:00am"),
+            ("020000am", "023000am"),
+        ]
+        expected_length = 28
+
+        for time_string in strings:
+            assert len(ts.between_time(*time_string)) == expected_length
+
+    @pytest.mark.parametrize("tzstr", ["US/Eastern", "dateutil/US/Eastern"])
+    def test_localized_between_time(self, tzstr, frame_or_series):
+        tz = timezones.maybe_get_tz(tzstr)
+
+        rng = date_range("4/16/2012", "5/1/2012", freq="h")
+        ts = Series(np.random.default_rng(2).standard_normal(len(rng)), index=rng)
+        if frame_or_series is DataFrame:
+            ts = ts.to_frame()
+
+        ts_local = ts.tz_localize(tzstr)
+
+        t1, t2 = time(10, 0), time(11, 0)
+        result = ts_local.between_time(t1, t2)
+        expected = ts.between_time(t1, t2).tz_localize(tzstr)
+        tm.assert_equal(result, expected)
+        assert timezones.tz_compare(result.index.tz, tz)
+
+    def test_between_time_types(self, frame_or_series):
+        # GH11818
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        obj = DataFrame({"A": 0}, index=rng)
+        obj = tm.get_obj(obj, frame_or_series)
+
+        msg = r"Cannot convert arg \[datetime\.datetime\(2010, 1, 2, 1, 0\)\] to a time"
+        with pytest.raises(ValueError, match=msg):
+            obj.between_time(datetime(2010, 1, 2, 1), datetime(2010, 1, 2, 5))
+
+    def test_between_time(self, inclusive_endpoints_fixture, frame_or_series):
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 2)), index=rng
+        )
+        ts = tm.get_obj(ts, frame_or_series)
+
+        stime = time(0, 0)
+        etime = time(1, 0)
+        inclusive = inclusive_endpoints_fixture
+
+        filtered = ts.between_time(stime, etime, inclusive=inclusive)
+        exp_len = 13 * 4 + 1
+
+        if inclusive in ["right", "neither"]:
+            exp_len -= 5
+        if inclusive in ["left", "neither"]:
+            exp_len -= 4
+
+        assert len(filtered) == exp_len
+        for rs in filtered.index:
+            t = rs.time()
+            if inclusive in ["left", "both"]:
+                assert t >= stime
+            else:
+                assert t > stime
+
+            if inclusive in ["right", "both"]:
+                assert t <= etime
+            else:
+                assert t < etime
+
+        result = ts.between_time("00:00", "01:00")
+        expected = ts.between_time(stime, etime)
+        tm.assert_equal(result, expected)
+
+        # across midnight
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 2)), index=rng
+        )
+        ts = tm.get_obj(ts, frame_or_series)
+        stime = time(22, 0)
+        etime = time(9, 0)
+
+        filtered = ts.between_time(stime, etime, inclusive=inclusive)
+        exp_len = (12 * 11 + 1) * 4 + 1
+        if inclusive in ["right", "neither"]:
+            exp_len -= 4
+        if inclusive in ["left", "neither"]:
+            exp_len -= 4
+
+        assert len(filtered) == exp_len
+        for rs in filtered.index:
+            t = rs.time()
+            if inclusive in ["left", "both"]:
+                assert (t >= stime) or (t <= etime)
+            else:
+                assert (t > stime) or (t <= etime)
+
+            if inclusive in ["right", "both"]:
+                assert (t <= etime) or (t >= stime)
+            else:
+                assert (t < etime) or (t >= stime)
+
+    def test_between_time_raises(self, frame_or_series):
+        # GH#20725
+        obj = DataFrame([[1, 2, 3], [4, 5, 6]])
+        obj = tm.get_obj(obj, frame_or_series)
+
+        msg = "Index must be DatetimeIndex"
+        with pytest.raises(TypeError, match=msg):  # index is not a DatetimeIndex
+            obj.between_time(start_time="00:00", end_time="12:00")
+
+    def test_between_time_axis(self, frame_or_series):
+        # GH#8839
+        rng = date_range("1/1/2000", periods=100, freq="10min")
+        ts = Series(np.random.default_rng(2).standard_normal(len(rng)), index=rng)
+        if frame_or_series is DataFrame:
+            ts = ts.to_frame()
+
+        stime, etime = ("08:00:00", "09:00:00")
+        expected_length = 7
+
+        assert len(ts.between_time(stime, etime)) == expected_length
+        assert len(ts.between_time(stime, etime, axis=0)) == expected_length
+        msg = f"No axis named {ts.ndim} for object type {type(ts).__name__}"
+        with pytest.raises(ValueError, match=msg):
+            ts.between_time(stime, etime, axis=ts.ndim)
+
+    def test_between_time_axis_aliases(self, axis):
+        # GH#8839
+        rng = date_range("1/1/2000", periods=100, freq="10min")
+        ts = DataFrame(np.random.default_rng(2).standard_normal((len(rng), len(rng))))
+        stime, etime = ("08:00:00", "09:00:00")
+        exp_len = 7
+
+        if axis in ["index", 0]:
+            ts.index = rng
+            assert len(ts.between_time(stime, etime)) == exp_len
+            assert len(ts.between_time(stime, etime, axis=0)) == exp_len
+
+        if axis in ["columns", 1]:
+            ts.columns = rng
+            selected = ts.between_time(stime, etime, axis=1).columns
+            assert len(selected) == exp_len
+
+    def test_between_time_axis_raises(self, axis):
+        # issue 8839
+        rng = date_range("1/1/2000", periods=100, freq="10min")
+        mask = np.arange(0, len(rng))
+        rand_data = np.random.default_rng(2).standard_normal((len(rng), len(rng)))
+        ts = DataFrame(rand_data, index=rng, columns=rng)
+        stime, etime = ("08:00:00", "09:00:00")
+
+        msg = "Index must be DatetimeIndex"
+        if axis in ["columns", 1]:
+            ts.index = mask
+            with pytest.raises(TypeError, match=msg):
+                ts.between_time(stime, etime)
+            with pytest.raises(TypeError, match=msg):
+                ts.between_time(stime, etime, axis=0)
+
+        if axis in ["index", 0]:
+            ts.columns = mask
+            with pytest.raises(TypeError, match=msg):
+                ts.between_time(stime, etime, axis=1)
+
+    def test_between_time_datetimeindex(self):
+        index = date_range("2012-01-01", "2012-01-05", freq="30min")
+        df = DataFrame(
+            np.random.default_rng(2).standard_normal((len(index), 5)), index=index
+        )
+        bkey = slice(time(13, 0, 0), time(14, 0, 0))
+        binds = [26, 27, 28, 74, 75, 76, 122, 123, 124, 170, 171, 172]
+
+        result = df.between_time(bkey.start, bkey.stop)
+        expected = df.loc[bkey]
+        expected2 = df.iloc[binds]
+        tm.assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected2)
+        assert len(result) == 12
+
+    def test_between_time_incorrect_arg_inclusive(self):
+        # GH40245
+        rng = date_range("1/1/2000", "1/5/2000", freq="5min")
+        ts = DataFrame(
+            np.random.default_rng(2).standard_normal((len(rng), 2)), index=rng
+        )
+
+        stime = time(0, 0)
+        etime = time(1, 0)
+        inclusive = "bad_string"
+        msg = "Inclusive has to be either 'both', 'neither', 'left' or 'right'"
+        with pytest.raises(ValueError, match=msg):
+            ts.between_time(stime, etime, inclusive=inclusive)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_clip.py

@@ -0,0 +1,199 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    DataFrame,
+    Series,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameClip:
+    def test_clip(self, float_frame):
+        median = float_frame.median().median()
+        original = float_frame.copy()
+
+        double = float_frame.clip(upper=median, lower=median)
+        assert not (double.values != median).any()
+
+        # Verify that float_frame was not changed inplace
+        assert (float_frame.values == original.values).all()
+
+    def test_inplace_clip(self, float_frame):
+        # GH#15388
+        median = float_frame.median().median()
+        frame_copy = float_frame.copy()
+
+        return_value = frame_copy.clip(upper=median, lower=median, inplace=True)
+        assert return_value is None
+        assert not (frame_copy.values != median).any()
+
+    def test_dataframe_clip(self):
+        # GH#2747
+        df = DataFrame(np.random.default_rng(2).standard_normal((1000, 2)))
+
+        for lb, ub in [(-1, 1), (1, -1)]:
+            clipped_df = df.clip(lb, ub)
+
+            lb, ub = min(lb, ub), max(ub, lb)
+            lb_mask = df.values <= lb
+            ub_mask = df.values >= ub
+            mask = ~lb_mask & ~ub_mask
+            assert (clipped_df.values[lb_mask] == lb).all()
+            assert (clipped_df.values[ub_mask] == ub).all()
+            assert (clipped_df.values[mask] == df.values[mask]).all()
+
+    def test_clip_mixed_numeric(self):
+        # clip on mixed integer or floats
+        # GH#24162, clipping now preserves numeric types per column
+        df = DataFrame({"A": [1, 2, 3], "B": [1.0, np.nan, 3.0]})
+        result = df.clip(1, 2)
+        expected = DataFrame({"A": [1, 2, 2], "B": [1.0, np.nan, 2.0]})
+        tm.assert_frame_equal(result, expected)
+
+        df = DataFrame([[1, 2, 3.4], [3, 4, 5.6]], columns=["foo", "bar", "baz"])
+        expected = df.dtypes
+        result = df.clip(upper=3).dtypes
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize("inplace", [True, False])
+    def test_clip_against_series(self, inplace):
+        # GH#6966
+
+        df = DataFrame(np.random.default_rng(2).standard_normal((1000, 2)))
+        lb = Series(np.random.default_rng(2).standard_normal(1000))
+        ub = lb + 1
+
+        original = df.copy()
+        clipped_df = df.clip(lb, ub, axis=0, inplace=inplace)
+
+        if inplace:
+            clipped_df = df
+
+        for i in range(2):
+            lb_mask = original.iloc[:, i] <= lb
+            ub_mask = original.iloc[:, i] >= ub
+            mask = ~lb_mask & ~ub_mask
+
+            result = clipped_df.loc[lb_mask, i]
+            tm.assert_series_equal(result, lb[lb_mask], check_names=False)
+            assert result.name == i
+
+            result = clipped_df.loc[ub_mask, i]
+            tm.assert_series_equal(result, ub[ub_mask], check_names=False)
+            assert result.name == i
+
+            tm.assert_series_equal(clipped_df.loc[mask, i], df.loc[mask, i])
+
+    @pytest.mark.parametrize("inplace", [True, False])
+    @pytest.mark.parametrize("lower", [[2, 3, 4], np.asarray([2, 3, 4])])
+    @pytest.mark.parametrize(
+        "axis,res",
+        [
+            (0, [[2.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 7.0, 7.0]]),
+            (1, [[2.0, 3.0, 4.0], [4.0, 5.0, 6.0], [5.0, 6.0, 7.0]]),
+        ],
+    )
+    def test_clip_against_list_like(self, inplace, lower, axis, res):
+        # GH#15390
+        arr = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
+
+        original = DataFrame(
+            arr, columns=["one", "two", "three"], index=["a", "b", "c"]
+        )
+
+        result = original.clip(lower=lower, upper=[5, 6, 7], axis=axis, inplace=inplace)
+
+        expected = DataFrame(res, columns=original.columns, index=original.index)
+        if inplace:
+            result = original
+        tm.assert_frame_equal(result, expected, check_exact=True)
+
+    @pytest.mark.parametrize("axis", [0, 1, None])
+    def test_clip_against_frame(self, axis):
+        df = DataFrame(np.random.default_rng(2).standard_normal((1000, 2)))
+        lb = DataFrame(np.random.default_rng(2).standard_normal((1000, 2)))
+        ub = lb + 1
+
+        clipped_df = df.clip(lb, ub, axis=axis)
+
+        lb_mask = df <= lb
+        ub_mask = df >= ub
+        mask = ~lb_mask & ~ub_mask
+
+        tm.assert_frame_equal(clipped_df[lb_mask], lb[lb_mask])
+        tm.assert_frame_equal(clipped_df[ub_mask], ub[ub_mask])
+        tm.assert_frame_equal(clipped_df[mask], df[mask])
+
+    def test_clip_against_unordered_columns(self):
+        # GH#20911
+        df1 = DataFrame(
+            np.random.default_rng(2).standard_normal((1000, 4)),
+            columns=["A", "B", "C", "D"],
+        )
+        df2 = DataFrame(
+            np.random.default_rng(2).standard_normal((1000, 4)),
+            columns=["D", "A", "B", "C"],
+        )
+        df3 = DataFrame(df2.values - 1, columns=["B", "D", "C", "A"])
+        result_upper = df1.clip(lower=0, upper=df2)
+        expected_upper = df1.clip(lower=0, upper=df2[df1.columns])
+        result_lower = df1.clip(lower=df3, upper=3)
+        expected_lower = df1.clip(lower=df3[df1.columns], upper=3)
+        result_lower_upper = df1.clip(lower=df3, upper=df2)
+        expected_lower_upper = df1.clip(lower=df3[df1.columns], upper=df2[df1.columns])
+        tm.assert_frame_equal(result_upper, expected_upper)
+        tm.assert_frame_equal(result_lower, expected_lower)
+        tm.assert_frame_equal(result_lower_upper, expected_lower_upper)
+
+    def test_clip_with_na_args(self, float_frame):
+        """Should process np.nan argument as None"""
+        # GH#17276
+        tm.assert_frame_equal(float_frame.clip(np.nan), float_frame)
+        tm.assert_frame_equal(float_frame.clip(upper=np.nan, lower=np.nan), float_frame)
+
+        # GH#19992 and adjusted in GH#40420
+        df = DataFrame({"col_0": [1, 2, 3], "col_1": [4, 5, 6], "col_2": [7, 8, 9]})
+
+        msg = "Downcasting behavior in Series and DataFrame methods 'where'"
+        # TODO: avoid this warning here?  seems like we should never be upcasting
+        #  in the first place?
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            result = df.clip(lower=[4, 5, np.nan], axis=0)
+        expected = DataFrame(
+            {"col_0": [4, 5, 3], "col_1": [4, 5, 6], "col_2": [7, 8, 9]}
+        )
+        tm.assert_frame_equal(result, expected)
+
+        result = df.clip(lower=[4, 5, np.nan], axis=1)
+        expected = DataFrame(
+            {"col_0": [4, 4, 4], "col_1": [5, 5, 6], "col_2": [7, 8, 9]}
+        )
+        tm.assert_frame_equal(result, expected)
+
+        # GH#40420
+        data = {"col_0": [9, -3, 0, -1, 5], "col_1": [-2, -7, 6, 8, -5]}
+        df = DataFrame(data)
+        t = Series([2, -4, np.nan, 6, 3])
+        with tm.assert_produces_warning(FutureWarning, match=msg):
+            result = df.clip(lower=t, axis=0)
+        expected = DataFrame({"col_0": [9, -3, 0, 6, 5], "col_1": [2, -4, 6, 8, 3]})
+        tm.assert_frame_equal(result, expected)
+
+    def test_clip_int_data_with_float_bound(self):
+        # GH51472
+        df = DataFrame({"a": [1, 2, 3]})
+        result = df.clip(lower=1.5)
+        expected = DataFrame({"a": [1.5, 2.0, 3.0]})
+        tm.assert_frame_equal(result, expected)
+
+    def test_clip_with_list_bound(self):
+        # GH#54817
+        df = DataFrame([1, 5])
+        expected = DataFrame([3, 5])
+        result = df.clip([3])
+        tm.assert_frame_equal(result, expected)
+
+        expected = DataFrame([1, 3])
+        result = df.clip(upper=[3])
+        tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_combine.py

@@ -0,0 +1,47 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+class TestCombine:
+    @pytest.mark.parametrize(
+        "data",
+        [
+            pd.date_range("2000", periods=4),
+            pd.date_range("2000", periods=4, tz="US/Central"),
+            pd.period_range("2000", periods=4),
+            pd.timedelta_range(0, periods=4),
+        ],
+    )
+    def test_combine_datetlike_udf(self, data):
+        # GH#23079
+        df = pd.DataFrame({"A": data})
+        other = df.copy()
+        df.iloc[1, 0] = None
+
+        def combiner(a, b):
+            return b
+
+        result = df.combine(other, combiner)
+        tm.assert_frame_equal(result, other)
+
+    def test_combine_generic(self, float_frame):
+        df1 = float_frame
+        df2 = float_frame.loc[float_frame.index[:-5], ["A", "B", "C"]]
+
+        combined = df1.combine(df2, np.add)
+        combined2 = df2.combine(df1, np.add)
+        assert combined["D"].isna().all()
+        assert combined2["D"].isna().all()
+
+        chunk = combined.loc[combined.index[:-5], ["A", "B", "C"]]
+        chunk2 = combined2.loc[combined2.index[:-5], ["A", "B", "C"]]
+
+        exp = (
+            float_frame.loc[float_frame.index[:-5], ["A", "B", "C"]].reindex_like(chunk)
+            * 2
+        )
+        tm.assert_frame_equal(chunk, exp)
+        tm.assert_frame_equal(chunk2, exp)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_combine_first.py

@@ -0,0 +1,556 @@
+from datetime import datetime
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.cast import find_common_type
+from pandas.core.dtypes.common import is_dtype_equal
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Index,
+    MultiIndex,
+    Series,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameCombineFirst:
+    def test_combine_first_mixed(self):
+        a = Series(["a", "b"], index=range(2))
+        b = Series(range(2), index=range(2))
+        f = DataFrame({"A": a, "B": b})
+
+        a = Series(["a", "b"], index=range(5, 7))
+        b = Series(range(2), index=range(5, 7))
+        g = DataFrame({"A": a, "B": b})
+
+        exp = DataFrame({"A": list("abab"), "B": [0, 1, 0, 1]}, index=[0, 1, 5, 6])
+        combined = f.combine_first(g)
+        tm.assert_frame_equal(combined, exp)
+
+    def test_combine_first(self, float_frame, using_infer_string):
+        # disjoint
+        head, tail = float_frame[:5], float_frame[5:]
+
+        combined = head.combine_first(tail)
+        reordered_frame = float_frame.reindex(combined.index)
+        tm.assert_frame_equal(combined, reordered_frame)
+        tm.assert_index_equal(combined.columns, float_frame.columns)
+        tm.assert_series_equal(combined["A"], reordered_frame["A"])
+
+        # same index
+        fcopy = float_frame.copy()
+        fcopy["A"] = 1
+        del fcopy["C"]
+
+        fcopy2 = float_frame.copy()
+        fcopy2["B"] = 0
+        del fcopy2["D"]
+
+        combined = fcopy.combine_first(fcopy2)
+
+        assert (combined["A"] == 1).all()
+        tm.assert_series_equal(combined["B"], fcopy["B"])
+        tm.assert_series_equal(combined["C"], fcopy2["C"])
+        tm.assert_series_equal(combined["D"], fcopy["D"])
+
+        # overlap
+        head, tail = reordered_frame[:10].copy(), reordered_frame
+        head["A"] = 1
+
+        combined = head.combine_first(tail)
+        assert (combined["A"][:10] == 1).all()
+
+        # reverse overlap
+        tail.iloc[:10, tail.columns.get_loc("A")] = 0
+        combined = tail.combine_first(head)
+        assert (combined["A"][:10] == 0).all()
+
+        # no overlap
+        f = float_frame[:10]
+        g = float_frame[10:]
+        combined = f.combine_first(g)
+        tm.assert_series_equal(combined["A"].reindex(f.index), f["A"])
+        tm.assert_series_equal(combined["A"].reindex(g.index), g["A"])
+
+        # corner cases
+        warning = FutureWarning if using_infer_string else None
+        with tm.assert_produces_warning(warning, match="empty entries"):
+            comb = float_frame.combine_first(DataFrame())
+        tm.assert_frame_equal(comb, float_frame)
+
+        comb = DataFrame().combine_first(float_frame)
+        tm.assert_frame_equal(comb, float_frame.sort_index())
+
+        comb = float_frame.combine_first(DataFrame(index=["faz", "boo"]))
+        assert "faz" in comb.index
+
+        # #2525
+        df = DataFrame({"a": [1]}, index=[datetime(2012, 1, 1)])
+        df2 = DataFrame(columns=["b"])
+        result = df.combine_first(df2)
+        assert "b" in result
+
+    def test_combine_first_mixed_bug(self):
+        idx = Index(["a", "b", "c", "e"])
+        ser1 = Series([5.0, -9.0, 4.0, 100.0], index=idx)
+        ser2 = Series(["a", "b", "c", "e"], index=idx)
+        ser3 = Series([12, 4, 5, 97], index=idx)
+
+        frame1 = DataFrame({"col0": ser1, "col2": ser2, "col3": ser3})
+
+        idx = Index(["a", "b", "c", "f"])
+        ser1 = Series([5.0, -9.0, 4.0, 100.0], index=idx)
+        ser2 = Series(["a", "b", "c", "f"], index=idx)
+        ser3 = Series([12, 4, 5, 97], index=idx)
+
+        frame2 = DataFrame({"col1": ser1, "col2": ser2, "col5": ser3})
+
+        combined = frame1.combine_first(frame2)
+        assert len(combined.columns) == 5
+
+    def test_combine_first_same_as_in_update(self):
+        # gh 3016 (same as in update)
+        df = DataFrame(
+            [[1.0, 2.0, False, True], [4.0, 5.0, True, False]],
+            columns=["A", "B", "bool1", "bool2"],
+        )
+
+        other = DataFrame([[45, 45]], index=[0], columns=["A", "B"])
+        result = df.combine_first(other)
+        tm.assert_frame_equal(result, df)
+
+        df.loc[0, "A"] = np.nan
+        result = df.combine_first(other)
+        df.loc[0, "A"] = 45
+        tm.assert_frame_equal(result, df)
+
+    def test_combine_first_doc_example(self):
+        # doc example
+        df1 = DataFrame(
+            {"A": [1.0, np.nan, 3.0, 5.0, np.nan], "B": [np.nan, 2.0, 3.0, np.nan, 6.0]}
+        )
+
+        df2 = DataFrame(
+            {
+                "A": [5.0, 2.0, 4.0, np.nan, 3.0, 7.0],
+                "B": [np.nan, np.nan, 3.0, 4.0, 6.0, 8.0],
+            }
+        )
+
+        result = df1.combine_first(df2)
+        expected = DataFrame({"A": [1, 2, 3, 5, 3, 7.0], "B": [np.nan, 2, 3, 4, 6, 8]})
+        tm.assert_frame_equal(result, expected)
+
+    def test_combine_first_return_obj_type_with_bools(self):
+        # GH3552
+
+        df1 = DataFrame(
+            [[np.nan, 3.0, True], [-4.6, np.nan, True], [np.nan, 7.0, False]]
+        )
+        df2 = DataFrame([[-42.6, np.nan, True], [-5.0, 1.6, False]], index=[1, 2])
+
+        expected = Series([True, True, False], name=2, dtype=bool)
+
+        result_12 = df1.combine_first(df2)[2]
+        tm.assert_series_equal(result_12, expected)
+
+        result_21 = df2.combine_first(df1)[2]
+        tm.assert_series_equal(result_21, expected)
+
+    @pytest.mark.parametrize(
+        "data1, data2, data_expected",
+        (
+            (
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+                [pd.NaT, pd.NaT, pd.NaT],
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+            ),
+            (
+                [pd.NaT, pd.NaT, pd.NaT],
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+            ),
+            (
+                [datetime(2000, 1, 2), pd.NaT, pd.NaT],
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+                [datetime(2000, 1, 2), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+            ),
+            (
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+                [datetime(2000, 1, 2), pd.NaT, pd.NaT],
+                [datetime(2000, 1, 1), datetime(2000, 1, 2), datetime(2000, 1, 3)],
+            ),
+        ),
+    )
+    def test_combine_first_convert_datatime_correctly(
+        self, data1, data2, data_expected
+    ):
+        # GH 3593
+
+        df1, df2 = DataFrame({"a": data1}), DataFrame({"a": data2})
+        result = df1.combine_first(df2)
+        expected = DataFrame({"a": data_expected})
+        tm.assert_frame_equal(result, expected)
+
+    def test_combine_first_align_nan(self):
+        # GH 7509 (not fixed)
+        dfa = DataFrame([[pd.Timestamp("2011-01-01"), 2]], columns=["a", "b"])
+        dfb = DataFrame([[4], [5]], columns=["b"])
+        assert dfa["a"].dtype == "datetime64[ns]"
+        assert dfa["b"].dtype == "int64"
+
+        res = dfa.combine_first(dfb)
+        exp = DataFrame(
+            {"a": [pd.Timestamp("2011-01-01"), pd.NaT], "b": [2, 5]},
+            columns=["a", "b"],
+        )
+        tm.assert_frame_equal(res, exp)
+        assert res["a"].dtype == "datetime64[ns]"
+        # TODO: this must be int64
+        assert res["b"].dtype == "int64"
+
+        res = dfa.iloc[:0].combine_first(dfb)
+        exp = DataFrame({"a": [np.nan, np.nan], "b": [4, 5]}, columns=["a", "b"])
+        tm.assert_frame_equal(res, exp)
+        # TODO: this must be datetime64
+        assert res["a"].dtype == "float64"
+        # TODO: this must be int64
+        assert res["b"].dtype == "int64"
+
+    def test_combine_first_timezone(self, unit):
+        # see gh-7630
+        data1 = pd.to_datetime("20100101 01:01").tz_localize("UTC").as_unit(unit)
+        df1 = DataFrame(
+            columns=["UTCdatetime", "abc"],
+            data=data1,
+            index=pd.date_range("20140627", periods=1),
+        )
+        data2 = pd.to_datetime("20121212 12:12").tz_localize("UTC").as_unit(unit)
+        df2 = DataFrame(
+            columns=["UTCdatetime", "xyz"],
+            data=data2,
+            index=pd.date_range("20140628", periods=1),
+        )
+        res = df2[["UTCdatetime"]].combine_first(df1)
+        exp = DataFrame(
+            {
+                "UTCdatetime": [
+                    pd.Timestamp("2010-01-01 01:01", tz="UTC"),
+                    pd.Timestamp("2012-12-12 12:12", tz="UTC"),
+                ],
+                "abc": [pd.Timestamp("2010-01-01 01:01:00", tz="UTC"), pd.NaT],
+            },
+            columns=["UTCdatetime", "abc"],
+            index=pd.date_range("20140627", periods=2, freq="D"),
+            dtype=f"datetime64[{unit}, UTC]",
+        )
+        assert res["UTCdatetime"].dtype == f"datetime64[{unit}, UTC]"
+        assert res["abc"].dtype == f"datetime64[{unit}, UTC]"
+
+        tm.assert_frame_equal(res, exp)
+
+    def test_combine_first_timezone2(self, unit):
+        # see gh-10567
+        dts1 = pd.date_range("2015-01-01", "2015-01-05", tz="UTC", unit=unit)
+        df1 = DataFrame({"DATE": dts1})
+        dts2 = pd.date_range("2015-01-03", "2015-01-05", tz="UTC", unit=unit)
+        df2 = DataFrame({"DATE": dts2})
+
+        res = df1.combine_first(df2)
+        tm.assert_frame_equal(res, df1)
+        assert res["DATE"].dtype == f"datetime64[{unit}, UTC]"
+
+    def test_combine_first_timezone3(self, unit):
+        dts1 = pd.DatetimeIndex(
+            ["2011-01-01", "NaT", "2011-01-03", "2011-01-04"], tz="US/Eastern"
+        ).as_unit(unit)
+        df1 = DataFrame({"DATE": dts1}, index=[1, 3, 5, 7])
+        dts2 = pd.DatetimeIndex(
+            ["2012-01-01", "2012-01-02", "2012-01-03"], tz="US/Eastern"
+        ).as_unit(unit)
+        df2 = DataFrame({"DATE": dts2}, index=[2, 4, 5])
+
+        res = df1.combine_first(df2)
+        exp_dts = pd.DatetimeIndex(
+            [
+                "2011-01-01",
+                "2012-01-01",
+                "NaT",
+                "2012-01-02",
+                "2011-01-03",
+                "2011-01-04",
+            ],
+            tz="US/Eastern",
+        ).as_unit(unit)
+        exp = DataFrame({"DATE": exp_dts}, index=[1, 2, 3, 4, 5, 7])
+        tm.assert_frame_equal(res, exp)
+
+    # FIXME: parametrizing over unit breaks on non-nano
+    def test_combine_first_timezone4(self):
+        # different tz
+        dts1 = pd.date_range("2015-01-01", "2015-01-05", tz="US/Eastern")
+        df1 = DataFrame({"DATE": dts1})
+        dts2 = pd.date_range("2015-01-03", "2015-01-05")
+        df2 = DataFrame({"DATE": dts2})
+
+        # if df1 doesn't have NaN, keep its dtype
+        res = df1.combine_first(df2)
+        tm.assert_frame_equal(res, df1)
+        assert res["DATE"].dtype == "datetime64[ns, US/Eastern]"
+
+    def test_combine_first_timezone5(self, unit):
+        dts1 = pd.date_range("2015-01-01", "2015-01-02", tz="US/Eastern", unit=unit)
+        df1 = DataFrame({"DATE": dts1})
+        dts2 = pd.date_range("2015-01-01", "2015-01-03", unit=unit)
+        df2 = DataFrame({"DATE": dts2})
+
+        res = df1.combine_first(df2)
+        exp_dts = [
+            pd.Timestamp("2015-01-01", tz="US/Eastern"),
+            pd.Timestamp("2015-01-02", tz="US/Eastern"),
+            pd.Timestamp("2015-01-03"),
+        ]
+        exp = DataFrame({"DATE": exp_dts})
+        tm.assert_frame_equal(res, exp)
+        assert res["DATE"].dtype == "object"
+
+    def test_combine_first_timedelta(self):
+        data1 = pd.TimedeltaIndex(["1 day", "NaT", "3 day", "4day"])
+        df1 = DataFrame({"TD": data1}, index=[1, 3, 5, 7])
+        data2 = pd.TimedeltaIndex(["10 day", "11 day", "12 day"])
+        df2 = DataFrame({"TD": data2}, index=[2, 4, 5])
+
+        res = df1.combine_first(df2)
+        exp_dts = pd.TimedeltaIndex(
+            ["1 day", "10 day", "NaT", "11 day", "3 day", "4 day"]
+        )
+        exp = DataFrame({"TD": exp_dts}, index=[1, 2, 3, 4, 5, 7])
+        tm.assert_frame_equal(res, exp)
+        assert res["TD"].dtype == "timedelta64[ns]"
+
+    def test_combine_first_period(self):
+        data1 = pd.PeriodIndex(["2011-01", "NaT", "2011-03", "2011-04"], freq="M")
+        df1 = DataFrame({"P": data1}, index=[1, 3, 5, 7])
+        data2 = pd.PeriodIndex(["2012-01-01", "2012-02", "2012-03"], freq="M")
+        df2 = DataFrame({"P": data2}, index=[2, 4, 5])
+
+        res = df1.combine_first(df2)
+        exp_dts = pd.PeriodIndex(
+            ["2011-01", "2012-01", "NaT", "2012-02", "2011-03", "2011-04"], freq="M"
+        )
+        exp = DataFrame({"P": exp_dts}, index=[1, 2, 3, 4, 5, 7])
+        tm.assert_frame_equal(res, exp)
+        assert res["P"].dtype == data1.dtype
+
+        # different freq
+        dts2 = pd.PeriodIndex(["2012-01-01", "2012-01-02", "2012-01-03"], freq="D")
+        df2 = DataFrame({"P": dts2}, index=[2, 4, 5])
+
+        res = df1.combine_first(df2)
+        exp_dts = [
+            pd.Period("2011-01", freq="M"),
+            pd.Period("2012-01-01", freq="D"),
+            pd.NaT,
+            pd.Period("2012-01-02", freq="D"),
+            pd.Period("2011-03", freq="M"),
+            pd.Period("2011-04", freq="M"),
+        ]
+        exp = DataFrame({"P": exp_dts}, index=[1, 2, 3, 4, 5, 7])
+        tm.assert_frame_equal(res, exp)
+        assert res["P"].dtype == "object"
+
+    def test_combine_first_int(self):
+        # GH14687 - integer series that do no align exactly
+
+        df1 = DataFrame({"a": [0, 1, 3, 5]}, dtype="int64")
+        df2 = DataFrame({"a": [1, 4]}, dtype="int64")
+
+        result_12 = df1.combine_first(df2)
+        expected_12 = DataFrame({"a": [0, 1, 3, 5]})
+        tm.assert_frame_equal(result_12, expected_12)
+
+        result_21 = df2.combine_first(df1)
+        expected_21 = DataFrame({"a": [1, 4, 3, 5]})
+        tm.assert_frame_equal(result_21, expected_21)
+
+    @pytest.mark.parametrize("val", [1, 1.0])
+    def test_combine_first_with_asymmetric_other(self, val):
+        # see gh-20699
+        df1 = DataFrame({"isNum": [val]})
+        df2 = DataFrame({"isBool": [True]})
+
+        res = df1.combine_first(df2)
+        exp = DataFrame({"isBool": [True], "isNum": [val]})
+
+        tm.assert_frame_equal(res, exp)
+
+    def test_combine_first_string_dtype_only_na(self, nullable_string_dtype):
+        # GH: 37519
+        df = DataFrame(
+            {"a": ["962", "85"], "b": [pd.NA] * 2}, dtype=nullable_string_dtype
+        )
+        df2 = DataFrame({"a": ["85"], "b": [pd.NA]}, dtype=nullable_string_dtype)
+        df.set_index(["a", "b"], inplace=True)
+        df2.set_index(["a", "b"], inplace=True)
+        result = df.combine_first(df2)
+        expected = DataFrame(
+            {"a": ["962", "85"], "b": [pd.NA] * 2}, dtype=nullable_string_dtype
+        ).set_index(["a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "scalar1, scalar2",
+    [
+        (datetime(2020, 1, 1), datetime(2020, 1, 2)),
+        (pd.Period("2020-01-01", "D"), pd.Period("2020-01-02", "D")),
+        (pd.Timedelta("89 days"), pd.Timedelta("60 min")),
+        (pd.Interval(left=0, right=1), pd.Interval(left=2, right=3, closed="left")),
+    ],
+)
+def test_combine_first_timestamp_bug(scalar1, scalar2, nulls_fixture):
+    # GH28481
+    na_value = nulls_fixture
+
+    frame = DataFrame([[na_value, na_value]], columns=["a", "b"])
+    other = DataFrame([[scalar1, scalar2]], columns=["b", "c"])
+
+    common_dtype = find_common_type([frame.dtypes["b"], other.dtypes["b"]])
+
+    if is_dtype_equal(common_dtype, "object") or frame.dtypes["b"] == other.dtypes["b"]:
+        val = scalar1
+    else:
+        val = na_value
+
+    result = frame.combine_first(other)
+
+    expected = DataFrame([[na_value, val, scalar2]], columns=["a", "b", "c"])
+
+    expected["b"] = expected["b"].astype(common_dtype)
+
+    tm.assert_frame_equal(result, expected)
+
+
+def test_combine_first_timestamp_bug_NaT():
+    # GH28481
+    frame = DataFrame([[pd.NaT, pd.NaT]], columns=["a", "b"])
+    other = DataFrame(
+        [[datetime(2020, 1, 1), datetime(2020, 1, 2)]], columns=["b", "c"]
+    )
+
+    result = frame.combine_first(other)
+    expected = DataFrame(
+        [[pd.NaT, datetime(2020, 1, 1), datetime(2020, 1, 2)]], columns=["a", "b", "c"]
+    )
+
+    tm.assert_frame_equal(result, expected)
+
+
+def test_combine_first_with_nan_multiindex():
+    # gh-36562
+
+    mi1 = MultiIndex.from_arrays(
+        [["b", "b", "c", "a", "b", np.nan], [1, 2, 3, 4, 5, 6]], names=["a", "b"]
+    )
+    df = DataFrame({"c": [1, 1, 1, 1, 1, 1]}, index=mi1)
+    mi2 = MultiIndex.from_arrays(
+        [["a", "b", "c", "a", "b", "d"], [1, 1, 1, 1, 1, 1]], names=["a", "b"]
+    )
+    s = Series([1, 2, 3, 4, 5, 6], index=mi2)
+    res = df.combine_first(DataFrame({"d": s}))
+    mi_expected = MultiIndex.from_arrays(
+        [
+            ["a", "a", "a", "b", "b", "b", "b", "c", "c", "d", np.nan],
+            [1, 1, 4, 1, 1, 2, 5, 1, 3, 1, 6],
+        ],
+        names=["a", "b"],
+    )
+    expected = DataFrame(
+        {
+            "c": [np.nan, np.nan, 1, 1, 1, 1, 1, np.nan, 1, np.nan, 1],
+            "d": [1.0, 4.0, np.nan, 2.0, 5.0, np.nan, np.nan, 3.0, np.nan, 6.0, np.nan],
+        },
+        index=mi_expected,
+    )
+    tm.assert_frame_equal(res, expected)
+
+
+def test_combine_preserve_dtypes():
+    # GH7509
+    a_column = Series(["a", "b"], index=range(2))
+    b_column = Series(range(2), index=range(2))
+    df1 = DataFrame({"A": a_column, "B": b_column})
+
+    c_column = Series(["a", "b"], index=range(5, 7))
+    b_column = Series(range(-1, 1), index=range(5, 7))
+    df2 = DataFrame({"B": b_column, "C": c_column})
+
+    expected = DataFrame(
+        {
+            "A": ["a", "b", np.nan, np.nan],
+            "B": [0, 1, -1, 0],
+            "C": [np.nan, np.nan, "a", "b"],
+        },
+        index=[0, 1, 5, 6],
+    )
+    combined = df1.combine_first(df2)
+    tm.assert_frame_equal(combined, expected)
+
+
+def test_combine_first_duplicates_rows_for_nan_index_values():
+    # GH39881
+    df1 = DataFrame(
+        {"x": [9, 10, 11]},
+        index=MultiIndex.from_arrays([[1, 2, 3], [np.nan, 5, 6]], names=["a", "b"]),
+    )
+
+    df2 = DataFrame(
+        {"y": [12, 13, 14]},
+        index=MultiIndex.from_arrays([[1, 2, 4], [np.nan, 5, 7]], names=["a", "b"]),
+    )
+
+    expected = DataFrame(
+        {
+            "x": [9.0, 10.0, 11.0, np.nan],
+            "y": [12.0, 13.0, np.nan, 14.0],
+        },
+        index=MultiIndex.from_arrays(
+            [[1, 2, 3, 4], [np.nan, 5, 6, 7]], names=["a", "b"]
+        ),
+    )
+    combined = df1.combine_first(df2)
+    tm.assert_frame_equal(combined, expected)
+
+
+def test_combine_first_int64_not_cast_to_float64():
+    # GH 28613
+    df_1 = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
+    df_2 = DataFrame({"A": [1, 20, 30], "B": [40, 50, 60], "C": [12, 34, 65]})
+    result = df_1.combine_first(df_2)
+    expected = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [12, 34, 65]})
+    tm.assert_frame_equal(result, expected)
+
+
+def test_midx_losing_dtype():
+    # GH#49830
+    midx = MultiIndex.from_arrays([[0, 0], [np.nan, np.nan]])
+    midx2 = MultiIndex.from_arrays([[1, 1], [np.nan, np.nan]])
+    df1 = DataFrame({"a": [None, 4]}, index=midx)
+    df2 = DataFrame({"a": [3, 3]}, index=midx2)
+    result = df1.combine_first(df2)
+    expected_midx = MultiIndex.from_arrays(
+        [[0, 0, 1, 1], [np.nan, np.nan, np.nan, np.nan]]
+    )
+    expected = DataFrame({"a": [np.nan, 4, 3, 3]}, index=expected_midx)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_combine_first_empty_columns():
+    left = DataFrame(columns=["a", "b"])
+    right = DataFrame(columns=["a", "c"])
+    result = left.combine_first(right)
+    expected = DataFrame(columns=["a", "b", "c"])
+    tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_compare.py

@@ -0,0 +1,305 @@
+import numpy as np
+import pytest
+
+from pandas.compat.numpy import np_version_gte1p25
+
+import pandas as pd
+import pandas._testing as tm
+
+
+@pytest.mark.parametrize("align_axis", [0, 1, "index", "columns"])
+def test_compare_axis(align_axis):
+    # GH#30429
+    df = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+        columns=["col1", "col2", "col3"],
+    )
+    df2 = df.copy()
+    df2.loc[0, "col1"] = "c"
+    df2.loc[2, "col3"] = 4.0
+
+    result = df.compare(df2, align_axis=align_axis)
+
+    if align_axis in (1, "columns"):
+        indices = pd.Index([0, 2])
+        columns = pd.MultiIndex.from_product([["col1", "col3"], ["self", "other"]])
+        expected = pd.DataFrame(
+            [["a", "c", np.nan, np.nan], [np.nan, np.nan, 3.0, 4.0]],
+            index=indices,
+            columns=columns,
+        )
+    else:
+        indices = pd.MultiIndex.from_product([[0, 2], ["self", "other"]])
+        columns = pd.Index(["col1", "col3"])
+        expected = pd.DataFrame(
+            [["a", np.nan], ["c", np.nan], [np.nan, 3.0], [np.nan, 4.0]],
+            index=indices,
+            columns=columns,
+        )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "keep_shape, keep_equal",
+    [
+        (True, False),
+        (False, True),
+        (True, True),
+        # False, False case is already covered in test_compare_axis
+    ],
+)
+def test_compare_various_formats(keep_shape, keep_equal):
+    df = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+        columns=["col1", "col2", "col3"],
+    )
+    df2 = df.copy()
+    df2.loc[0, "col1"] = "c"
+    df2.loc[2, "col3"] = 4.0
+
+    result = df.compare(df2, keep_shape=keep_shape, keep_equal=keep_equal)
+
+    if keep_shape:
+        indices = pd.Index([0, 1, 2])
+        columns = pd.MultiIndex.from_product(
+            [["col1", "col2", "col3"], ["self", "other"]]
+        )
+        if keep_equal:
+            expected = pd.DataFrame(
+                [
+                    ["a", "c", 1.0, 1.0, 1.0, 1.0],
+                    ["b", "b", 2.0, 2.0, 2.0, 2.0],
+                    ["c", "c", np.nan, np.nan, 3.0, 4.0],
+                ],
+                index=indices,
+                columns=columns,
+            )
+        else:
+            expected = pd.DataFrame(
+                [
+                    ["a", "c", np.nan, np.nan, np.nan, np.nan],
+                    [np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
+                    [np.nan, np.nan, np.nan, np.nan, 3.0, 4.0],
+                ],
+                index=indices,
+                columns=columns,
+            )
+    else:
+        indices = pd.Index([0, 2])
+        columns = pd.MultiIndex.from_product([["col1", "col3"], ["self", "other"]])
+        expected = pd.DataFrame(
+            [["a", "c", 1.0, 1.0], ["c", "c", 3.0, 4.0]], index=indices, columns=columns
+        )
+    tm.assert_frame_equal(result, expected)
+
+
+def test_compare_with_equal_nulls():
+    # We want to make sure two NaNs are considered the same
+    # and dropped where applicable
+    df = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+        columns=["col1", "col2", "col3"],
+    )
+    df2 = df.copy()
+    df2.loc[0, "col1"] = "c"
+
+    result = df.compare(df2)
+    indices = pd.Index([0])
+    columns = pd.MultiIndex.from_product([["col1"], ["self", "other"]])
+    expected = pd.DataFrame([["a", "c"]], index=indices, columns=columns)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_compare_with_non_equal_nulls():
+    # We want to make sure the relevant NaNs do not get dropped
+    # even if the entire row or column are NaNs
+    df = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+        columns=["col1", "col2", "col3"],
+    )
+    df2 = df.copy()
+    df2.loc[0, "col1"] = "c"
+    df2.loc[2, "col3"] = np.nan
+
+    result = df.compare(df2)
+
+    indices = pd.Index([0, 2])
+    columns = pd.MultiIndex.from_product([["col1", "col3"], ["self", "other"]])
+    expected = pd.DataFrame(
+        [["a", "c", np.nan, np.nan], [np.nan, np.nan, 3.0, np.nan]],
+        index=indices,
+        columns=columns,
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("align_axis", [0, 1])
+def test_compare_multi_index(align_axis):
+    df = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]}
+    )
+    df.columns = pd.MultiIndex.from_arrays([["a", "a", "b"], ["col1", "col2", "col3"]])
+    df.index = pd.MultiIndex.from_arrays([["x", "x", "y"], [0, 1, 2]])
+
+    df2 = df.copy()
+    df2.iloc[0, 0] = "c"
+    df2.iloc[2, 2] = 4.0
+
+    result = df.compare(df2, align_axis=align_axis)
+
+    if align_axis == 0:
+        indices = pd.MultiIndex.from_arrays(
+            [["x", "x", "y", "y"], [0, 0, 2, 2], ["self", "other", "self", "other"]]
+        )
+        columns = pd.MultiIndex.from_arrays([["a", "b"], ["col1", "col3"]])
+        data = [["a", np.nan], ["c", np.nan], [np.nan, 3.0], [np.nan, 4.0]]
+    else:
+        indices = pd.MultiIndex.from_arrays([["x", "y"], [0, 2]])
+        columns = pd.MultiIndex.from_arrays(
+            [
+                ["a", "a", "b", "b"],
+                ["col1", "col1", "col3", "col3"],
+                ["self", "other", "self", "other"],
+            ]
+        )
+        data = [["a", "c", np.nan, np.nan], [np.nan, np.nan, 3.0, 4.0]]
+
+    expected = pd.DataFrame(data=data, index=indices, columns=columns)
+    tm.assert_frame_equal(result, expected)
+
+
+def test_compare_unaligned_objects():
+    # test DataFrames with different indices
+    msg = (
+        r"Can only compare identically-labeled \(both index and columns\) DataFrame "
+        "objects"
+    )
+    with pytest.raises(ValueError, match=msg):
+        df1 = pd.DataFrame([1, 2, 3], index=["a", "b", "c"])
+        df2 = pd.DataFrame([1, 2, 3], index=["a", "b", "d"])
+        df1.compare(df2)
+
+    # test DataFrames with different shapes
+    msg = (
+        r"Can only compare identically-labeled \(both index and columns\) DataFrame "
+        "objects"
+    )
+    with pytest.raises(ValueError, match=msg):
+        df1 = pd.DataFrame(np.ones((3, 3)))
+        df2 = pd.DataFrame(np.zeros((2, 1)))
+        df1.compare(df2)
+
+
+def test_compare_result_names():
+    # GH 44354
+    df1 = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+    )
+    df2 = pd.DataFrame(
+        {
+            "col1": ["c", "b", "c"],
+            "col2": [1.0, 2.0, np.nan],
+            "col3": [1.0, 2.0, np.nan],
+        },
+    )
+    result = df1.compare(df2, result_names=("left", "right"))
+    expected = pd.DataFrame(
+        {
+            ("col1", "left"): {0: "a", 2: np.nan},
+            ("col1", "right"): {0: "c", 2: np.nan},
+            ("col3", "left"): {0: np.nan, 2: 3.0},
+            ("col3", "right"): {0: np.nan, 2: np.nan},
+        }
+    )
+    tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "result_names",
+    [
+        [1, 2],
+        "HK",
+        {"2": 2, "3": 3},
+        3,
+        3.0,
+    ],
+)
+def test_invalid_input_result_names(result_names):
+    # GH 44354
+    df1 = pd.DataFrame(
+        {"col1": ["a", "b", "c"], "col2": [1.0, 2.0, np.nan], "col3": [1.0, 2.0, 3.0]},
+    )
+    df2 = pd.DataFrame(
+        {
+            "col1": ["c", "b", "c"],
+            "col2": [1.0, 2.0, np.nan],
+            "col3": [1.0, 2.0, np.nan],
+        },
+    )
+    with pytest.raises(
+        TypeError,
+        match=(
+            f"Passing 'result_names' as a {type(result_names)} is not "
+            "supported. Provide 'result_names' as a tuple instead."
+        ),
+    ):
+        df1.compare(df2, result_names=result_names)
+
+
+@pytest.mark.parametrize(
+    "val1,val2",
+    [(4, pd.NA), (pd.NA, pd.NA), (pd.NA, 4)],
+)
+def test_compare_ea_and_np_dtype(val1, val2):
+    # GH 48966
+    arr = [4.0, val1]
+    ser = pd.Series([1, val2], dtype="Int64")
+
+    df1 = pd.DataFrame({"a": arr, "b": [1.0, 2]})
+    df2 = pd.DataFrame({"a": ser, "b": [1.0, 2]})
+    expected = pd.DataFrame(
+        {
+            ("a", "self"): arr,
+            ("a", "other"): ser,
+            ("b", "self"): np.nan,
+            ("b", "other"): np.nan,
+        }
+    )
+    if val1 is pd.NA and val2 is pd.NA:
+        # GH#18463 TODO: is this really the desired behavior?
+        expected.loc[1, ("a", "self")] = np.nan
+
+    if val1 is pd.NA and np_version_gte1p25:
+        # can't compare with numpy array if it contains pd.NA
+        with pytest.raises(TypeError, match="boolean value of NA is ambiguous"):
+            result = df1.compare(df2, keep_shape=True)
+    else:
+        result = df1.compare(df2, keep_shape=True)
+        tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "df1_val,df2_val,diff_self,diff_other",
+    [
+        (4, 3, 4, 3),
+        (4, 4, pd.NA, pd.NA),
+        (4, pd.NA, 4, pd.NA),
+        (pd.NA, pd.NA, pd.NA, pd.NA),
+    ],
+)
+def test_compare_nullable_int64_dtype(df1_val, df2_val, diff_self, diff_other):
+    # GH 48966
+    df1 = pd.DataFrame({"a": pd.Series([df1_val, pd.NA], dtype="Int64"), "b": [1.0, 2]})
+    df2 = df1.copy()
+    df2.loc[0, "a"] = df2_val
+
+    expected = pd.DataFrame(
+        {
+            ("a", "self"): pd.Series([diff_self, pd.NA], dtype="Int64"),
+            ("a", "other"): pd.Series([diff_other, pd.NA], dtype="Int64"),
+            ("b", "self"): np.nan,
+            ("b", "other"): np.nan,
+        }
+    )
+    result = df1.compare(df2, keep_shape=True)
+    tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_convert_dtypes.py

@@ -0,0 +1,202 @@
+import datetime
+
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+
+
+class TestConvertDtypes:
+    @pytest.mark.parametrize(
+        "convert_integer, expected", [(False, np.dtype("int32")), (True, "Int32")]
+    )
+    def test_convert_dtypes(
+        self, convert_integer, expected, string_storage, using_infer_string
+    ):
+        # Specific types are tested in tests/series/test_dtypes.py
+        # Just check that it works for DataFrame here
+        if using_infer_string:
+            string_storage = "pyarrow_numpy"
+        df = pd.DataFrame(
+            {
+                "a": pd.Series([1, 2, 3], dtype=np.dtype("int32")),
+                "b": pd.Series(["x", "y", "z"], dtype=np.dtype("O")),
+            }
+        )
+        with pd.option_context("string_storage", string_storage):
+            result = df.convert_dtypes(True, True, convert_integer, False)
+        expected = pd.DataFrame(
+            {
+                "a": pd.Series([1, 2, 3], dtype=expected),
+                "b": pd.Series(["x", "y", "z"], dtype=f"string[{string_storage}]"),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_convert_empty(self):
+        # Empty DataFrame can pass convert_dtypes, see GH#40393
+        empty_df = pd.DataFrame()
+        tm.assert_frame_equal(empty_df, empty_df.convert_dtypes())
+
+    def test_convert_dtypes_retain_column_names(self):
+        # GH#41435
+        df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
+        df.columns.name = "cols"
+
+        result = df.convert_dtypes()
+        tm.assert_index_equal(result.columns, df.columns)
+        assert result.columns.name == "cols"
+
+    def test_pyarrow_dtype_backend(self):
+        pa = pytest.importorskip("pyarrow")
+        df = pd.DataFrame(
+            {
+                "a": pd.Series([1, 2, 3], dtype=np.dtype("int32")),
+                "b": pd.Series(["x", "y", None], dtype=np.dtype("O")),
+                "c": pd.Series([True, False, None], dtype=np.dtype("O")),
+                "d": pd.Series([np.nan, 100.5, 200], dtype=np.dtype("float")),
+                "e": pd.Series(pd.date_range("2022", periods=3)),
+                "f": pd.Series(pd.date_range("2022", periods=3, tz="UTC").as_unit("s")),
+                "g": pd.Series(pd.timedelta_range("1D", periods=3)),
+            }
+        )
+        result = df.convert_dtypes(dtype_backend="pyarrow")
+        expected = pd.DataFrame(
+            {
+                "a": pd.arrays.ArrowExtensionArray(
+                    pa.array([1, 2, 3], type=pa.int32())
+                ),
+                "b": pd.arrays.ArrowExtensionArray(pa.array(["x", "y", None])),
+                "c": pd.arrays.ArrowExtensionArray(pa.array([True, False, None])),
+                "d": pd.arrays.ArrowExtensionArray(pa.array([None, 100.5, 200.0])),
+                "e": pd.arrays.ArrowExtensionArray(
+                    pa.array(
+                        [
+                            datetime.datetime(2022, 1, 1),
+                            datetime.datetime(2022, 1, 2),
+                            datetime.datetime(2022, 1, 3),
+                        ],
+                        type=pa.timestamp(unit="ns"),
+                    )
+                ),
+                "f": pd.arrays.ArrowExtensionArray(
+                    pa.array(
+                        [
+                            datetime.datetime(2022, 1, 1),
+                            datetime.datetime(2022, 1, 2),
+                            datetime.datetime(2022, 1, 3),
+                        ],
+                        type=pa.timestamp(unit="s", tz="UTC"),
+                    )
+                ),
+                "g": pd.arrays.ArrowExtensionArray(
+                    pa.array(
+                        [
+                            datetime.timedelta(1),
+                            datetime.timedelta(2),
+                            datetime.timedelta(3),
+                        ],
+                        type=pa.duration("ns"),
+                    )
+                ),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_pyarrow_dtype_backend_already_pyarrow(self):
+        pytest.importorskip("pyarrow")
+        expected = pd.DataFrame([1, 2, 3], dtype="int64[pyarrow]")
+        result = expected.convert_dtypes(dtype_backend="pyarrow")
+        tm.assert_frame_equal(result, expected)
+
+    def test_pyarrow_dtype_backend_from_pandas_nullable(self):
+        pa = pytest.importorskip("pyarrow")
+        df = pd.DataFrame(
+            {
+                "a": pd.Series([1, 2, None], dtype="Int32"),
+                "b": pd.Series(["x", "y", None], dtype="string[python]"),
+                "c": pd.Series([True, False, None], dtype="boolean"),
+                "d": pd.Series([None, 100.5, 200], dtype="Float64"),
+            }
+        )
+        result = df.convert_dtypes(dtype_backend="pyarrow")
+        expected = pd.DataFrame(
+            {
+                "a": pd.arrays.ArrowExtensionArray(
+                    pa.array([1, 2, None], type=pa.int32())
+                ),
+                "b": pd.arrays.ArrowExtensionArray(pa.array(["x", "y", None])),
+                "c": pd.arrays.ArrowExtensionArray(pa.array([True, False, None])),
+                "d": pd.arrays.ArrowExtensionArray(pa.array([None, 100.5, 200.0])),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_pyarrow_dtype_empty_object(self):
+        # GH 50970
+        pytest.importorskip("pyarrow")
+        expected = pd.DataFrame(columns=[0])
+        result = expected.convert_dtypes(dtype_backend="pyarrow")
+        tm.assert_frame_equal(result, expected)
+
+    def test_pyarrow_engine_lines_false(self):
+        # GH 48893
+        df = pd.DataFrame({"a": [1, 2, 3]})
+        msg = (
+            "dtype_backend numpy is invalid, only 'numpy_nullable' and "
+            "'pyarrow' are allowed."
+        )
+        with pytest.raises(ValueError, match=msg):
+            df.convert_dtypes(dtype_backend="numpy")
+
+    def test_pyarrow_backend_no_conversion(self):
+        # GH#52872
+        pytest.importorskip("pyarrow")
+        df = pd.DataFrame({"a": [1, 2], "b": 1.5, "c": True, "d": "x"})
+        expected = df.copy()
+        result = df.convert_dtypes(
+            convert_floating=False,
+            convert_integer=False,
+            convert_boolean=False,
+            convert_string=False,
+            dtype_backend="pyarrow",
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_convert_dtypes_pyarrow_to_np_nullable(self):
+        # GH 53648
+        pytest.importorskip("pyarrow")
+        ser = pd.DataFrame(range(2), dtype="int32[pyarrow]")
+        result = ser.convert_dtypes(dtype_backend="numpy_nullable")
+        expected = pd.DataFrame(range(2), dtype="Int32")
+        tm.assert_frame_equal(result, expected)
+
+    def test_convert_dtypes_pyarrow_timestamp(self):
+        # GH 54191
+        pytest.importorskip("pyarrow")
+        ser = pd.Series(pd.date_range("2020-01-01", "2020-01-02", freq="1min"))
+        expected = ser.astype("timestamp[ms][pyarrow]")
+        result = expected.convert_dtypes(dtype_backend="pyarrow")
+        tm.assert_series_equal(result, expected)
+
+    def test_convert_dtypes_avoid_block_splitting(self):
+        # GH#55341
+        df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": "a"})
+        result = df.convert_dtypes(convert_integer=False)
+        expected = pd.DataFrame(
+            {
+                "a": [1, 2, 3],
+                "b": [4, 5, 6],
+                "c": pd.Series(["a"] * 3, dtype="string[python]"),
+            }
+        )
+        tm.assert_frame_equal(result, expected)
+        assert result._mgr.nblocks == 2
+
+    def test_convert_dtypes_from_arrow(self):
+        # GH#56581
+        df = pd.DataFrame([["a", datetime.time(18, 12)]], columns=["a", "b"])
+        result = df.convert_dtypes()
+        expected = df.astype({"a": "string[python]"})
+        tm.assert_frame_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_copy.py

@@ -0,0 +1,64 @@
+import numpy as np
+import pytest
+
+import pandas.util._test_decorators as td
+
+from pandas import DataFrame
+import pandas._testing as tm
+
+
+class TestCopy:
+    @pytest.mark.parametrize("attr", ["index", "columns"])
+    def test_copy_index_name_checking(self, float_frame, attr):
+        # don't want to be able to modify the index stored elsewhere after
+        # making a copy
+        ind = getattr(float_frame, attr)
+        ind.name = None
+        cp = float_frame.copy()
+        getattr(cp, attr).name = "foo"
+        assert getattr(float_frame, attr).name is None
+
+    @td.skip_copy_on_write_invalid_test
+    def test_copy_cache(self):
+        # GH#31784 _item_cache not cleared on copy causes incorrect reads after updates
+        df = DataFrame({"a": [1]})
+
+        df["x"] = [0]
+        df["a"]
+
+        df.copy()
+
+        df["a"].values[0] = -1
+
+        tm.assert_frame_equal(df, DataFrame({"a": [-1], "x": [0]}))
+
+        df["y"] = [0]
+
+        assert df["a"].values[0] == -1
+        tm.assert_frame_equal(df, DataFrame({"a": [-1], "x": [0], "y": [0]}))
+
+    def test_copy(self, float_frame, float_string_frame):
+        cop = float_frame.copy()
+        cop["E"] = cop["A"]
+        assert "E" not in float_frame
+
+        # copy objects
+        copy = float_string_frame.copy()
+        assert copy._mgr is not float_string_frame._mgr
+
+    @td.skip_array_manager_invalid_test
+    def test_copy_consolidates(self):
+        # GH#42477
+        df = DataFrame(
+            {
+                "a": np.random.default_rng(2).integers(0, 100, size=55),
+                "b": np.random.default_rng(2).integers(0, 100, size=55),
+            }
+        )
+
+        for i in range(10):
+            df.loc[:, f"n_{i}"] = np.random.default_rng(2).integers(0, 100, size=55)
+
+        assert len(df._mgr.blocks) == 11
+        result = df.copy()
+        assert len(result._mgr.blocks) == 1

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_count.py

@@ -0,0 +1,39 @@
+from pandas import (
+    DataFrame,
+    Series,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameCount:
+    def test_count(self):
+        # corner case
+        frame = DataFrame()
+        ct1 = frame.count(1)
+        assert isinstance(ct1, Series)
+
+        ct2 = frame.count(0)
+        assert isinstance(ct2, Series)
+
+        # GH#423
+        df = DataFrame(index=range(10))
+        result = df.count(1)
+        expected = Series(0, index=df.index)
+        tm.assert_series_equal(result, expected)
+
+        df = DataFrame(columns=range(10))
+        result = df.count(0)
+        expected = Series(0, index=df.columns)
+        tm.assert_series_equal(result, expected)
+
+        df = DataFrame()
+        result = df.count()
+        expected = Series(dtype="int64")
+        tm.assert_series_equal(result, expected)
+
+    def test_count_objects(self, float_string_frame):
+        dm = DataFrame(float_string_frame._series)
+        df = DataFrame(float_string_frame._series)
+
+        tm.assert_series_equal(dm.count(), df.count())
+        tm.assert_series_equal(dm.count(1), df.count(1))

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_cov_corr.py

@@ -0,0 +1,471 @@
+import numpy as np
+import pytest
+
+import pandas.util._test_decorators as td
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Index,
+    Series,
+    date_range,
+    isna,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameCov:
+    def test_cov(self, float_frame, float_string_frame):
+        # min_periods no NAs (corner case)
+        expected = float_frame.cov()
+        result = float_frame.cov(min_periods=len(float_frame))
+
+        tm.assert_frame_equal(expected, result)
+
+        result = float_frame.cov(min_periods=len(float_frame) + 1)
+        assert isna(result.values).all()
+
+        # with NAs
+        frame = float_frame.copy()
+        frame.iloc[:5, frame.columns.get_loc("A")] = np.nan
+        frame.iloc[5:10, frame.columns.get_loc("B")] = np.nan
+        result = frame.cov(min_periods=len(frame) - 8)
+        expected = frame.cov()
+        expected.loc["A", "B"] = np.nan
+        expected.loc["B", "A"] = np.nan
+        tm.assert_frame_equal(result, expected)
+
+        # regular
+        result = frame.cov()
+        expected = frame["A"].cov(frame["C"])
+        tm.assert_almost_equal(result["A"]["C"], expected)
+
+        # fails on non-numeric types
+        with pytest.raises(ValueError, match="could not convert string to float"):
+            float_string_frame.cov()
+        result = float_string_frame.cov(numeric_only=True)
+        expected = float_string_frame.loc[:, ["A", "B", "C", "D"]].cov()
+        tm.assert_frame_equal(result, expected)
+
+        # Single column frame
+        df = DataFrame(np.linspace(0.0, 1.0, 10))
+        result = df.cov()
+        expected = DataFrame(
+            np.cov(df.values.T).reshape((1, 1)), index=df.columns, columns=df.columns
+        )
+        tm.assert_frame_equal(result, expected)
+        df.loc[0] = np.nan
+        result = df.cov()
+        expected = DataFrame(
+            np.cov(df.values[1:].T).reshape((1, 1)),
+            index=df.columns,
+            columns=df.columns,
+        )
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("test_ddof", [None, 0, 1, 2, 3])
+    def test_cov_ddof(self, test_ddof):
+        # GH#34611
+        np_array1 = np.random.default_rng(2).random(10)
+        np_array2 = np.random.default_rng(2).random(10)
+        df = DataFrame({0: np_array1, 1: np_array2})
+        result = df.cov(ddof=test_ddof)
+        expected_np = np.cov(np_array1, np_array2, ddof=test_ddof)
+        expected = DataFrame(expected_np)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "other_column", [pd.array([1, 2, 3]), np.array([1.0, 2.0, 3.0])]
+    )
+    def test_cov_nullable_integer(self, other_column):
+        # https://github.com/pandas-dev/pandas/issues/33803
+        data = DataFrame({"a": pd.array([1, 2, None]), "b": other_column})
+        result = data.cov()
+        arr = np.array([[0.5, 0.5], [0.5, 1.0]])
+        expected = DataFrame(arr, columns=["a", "b"], index=["a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("numeric_only", [True, False])
+    def test_cov_numeric_only(self, numeric_only):
+        # when dtypes of pandas series are different
+        # then ndarray will have dtype=object,
+        # so it need to be properly handled
+        df = DataFrame({"a": [1, 0], "c": ["x", "y"]})
+        expected = DataFrame(0.5, index=["a"], columns=["a"])
+        if numeric_only:
+            result = df.cov(numeric_only=numeric_only)
+            tm.assert_frame_equal(result, expected)
+        else:
+            with pytest.raises(ValueError, match="could not convert string to float"):
+                df.cov(numeric_only=numeric_only)
+
+
+class TestDataFrameCorr:
+    # DataFrame.corr(), as opposed to DataFrame.corrwith
+
+    @pytest.mark.parametrize("method", ["pearson", "kendall", "spearman"])
+    def test_corr_scipy_method(self, float_frame, method):
+        pytest.importorskip("scipy")
+        float_frame.loc[float_frame.index[:5], "A"] = np.nan
+        float_frame.loc[float_frame.index[5:10], "B"] = np.nan
+        float_frame.loc[float_frame.index[:10], "A"] = float_frame["A"][10:20].copy()
+
+        correls = float_frame.corr(method=method)
+        expected = float_frame["A"].corr(float_frame["C"], method=method)
+        tm.assert_almost_equal(correls["A"]["C"], expected)
+
+    # ---------------------------------------------------------------------
+
+    def test_corr_non_numeric(self, float_string_frame):
+        with pytest.raises(ValueError, match="could not convert string to float"):
+            float_string_frame.corr()
+        result = float_string_frame.corr(numeric_only=True)
+        expected = float_string_frame.loc[:, ["A", "B", "C", "D"]].corr()
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("meth", ["pearson", "kendall", "spearman"])
+    def test_corr_nooverlap(self, meth):
+        # nothing in common
+        pytest.importorskip("scipy")
+        df = DataFrame(
+            {
+                "A": [1, 1.5, 1, np.nan, np.nan, np.nan],
+                "B": [np.nan, np.nan, np.nan, 1, 1.5, 1],
+                "C": [np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
+            }
+        )
+        rs = df.corr(meth)
+        assert isna(rs.loc["A", "B"])
+        assert isna(rs.loc["B", "A"])
+        assert rs.loc["A", "A"] == 1
+        assert rs.loc["B", "B"] == 1
+        assert isna(rs.loc["C", "C"])
+
+    @pytest.mark.parametrize("meth", ["pearson", "spearman"])
+    def test_corr_constant(self, meth):
+        # constant --> all NA
+        df = DataFrame(
+            {
+                "A": [1, 1, 1, np.nan, np.nan, np.nan],
+                "B": [np.nan, np.nan, np.nan, 1, 1, 1],
+            }
+        )
+        rs = df.corr(meth)
+        assert isna(rs.values).all()
+
+    @pytest.mark.filterwarnings("ignore::RuntimeWarning")
+    @pytest.mark.parametrize("meth", ["pearson", "kendall", "spearman"])
+    def test_corr_int_and_boolean(self, meth):
+        # when dtypes of pandas series are different
+        # then ndarray will have dtype=object,
+        # so it need to be properly handled
+        pytest.importorskip("scipy")
+        df = DataFrame({"a": [True, False], "b": [1, 0]})
+
+        expected = DataFrame(np.ones((2, 2)), index=["a", "b"], columns=["a", "b"])
+        result = df.corr(meth)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("method", ["cov", "corr"])
+    def test_corr_cov_independent_index_column(self, method):
+        # GH#14617
+        df = DataFrame(
+            np.random.default_rng(2).standard_normal(4 * 10).reshape(10, 4),
+            columns=list("abcd"),
+        )
+        result = getattr(df, method)()
+        assert result.index is not result.columns
+        assert result.index.equals(result.columns)
+
+    def test_corr_invalid_method(self):
+        # GH#22298
+        df = DataFrame(np.random.default_rng(2).normal(size=(10, 2)))
+        msg = "method must be either 'pearson', 'spearman', 'kendall', or a callable, "
+        with pytest.raises(ValueError, match=msg):
+            df.corr(method="____")
+
+    def test_corr_int(self):
+        # dtypes other than float64 GH#1761
+        df = DataFrame({"a": [1, 2, 3, 4], "b": [1, 2, 3, 4]})
+
+        df.cov()
+        df.corr()
+
+    @pytest.mark.parametrize(
+        "nullable_column", [pd.array([1, 2, 3]), pd.array([1, 2, None])]
+    )
+    @pytest.mark.parametrize(
+        "other_column",
+        [pd.array([1, 2, 3]), np.array([1.0, 2.0, 3.0]), np.array([1.0, 2.0, np.nan])],
+    )
+    @pytest.mark.parametrize("method", ["pearson", "spearman", "kendall"])
+    def test_corr_nullable_integer(self, nullable_column, other_column, method):
+        # https://github.com/pandas-dev/pandas/issues/33803
+        pytest.importorskip("scipy")
+        data = DataFrame({"a": nullable_column, "b": other_column})
+        result = data.corr(method=method)
+        expected = DataFrame(np.ones((2, 2)), columns=["a", "b"], index=["a", "b"])
+        tm.assert_frame_equal(result, expected)
+
+    def test_corr_item_cache(self, using_copy_on_write, warn_copy_on_write):
+        # Check that corr does not lead to incorrect entries in item_cache
+
+        df = DataFrame({"A": range(10)})
+        df["B"] = range(10)[::-1]
+
+        ser = df["A"]  # populate item_cache
+        assert len(df._mgr.arrays) == 2  # i.e. 2 blocks
+
+        _ = df.corr(numeric_only=True)
+
+        if using_copy_on_write:
+            ser.iloc[0] = 99
+            assert df.loc[0, "A"] == 0
+        else:
+            # Check that the corr didn't break link between ser and df
+            ser.values[0] = 99
+            assert df.loc[0, "A"] == 99
+            if not warn_copy_on_write:
+                assert df["A"] is ser
+            assert df.values[0, 0] == 99
+
+    @pytest.mark.parametrize("length", [2, 20, 200, 2000])
+    def test_corr_for_constant_columns(self, length):
+        # GH: 37448
+        df = DataFrame(length * [[0.4, 0.1]], columns=["A", "B"])
+        result = df.corr()
+        expected = DataFrame(
+            {"A": [np.nan, np.nan], "B": [np.nan, np.nan]}, index=["A", "B"]
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_calc_corr_small_numbers(self):
+        # GH: 37452
+        df = DataFrame(
+            {"A": [1.0e-20, 2.0e-20, 3.0e-20], "B": [1.0e-20, 2.0e-20, 3.0e-20]}
+        )
+        result = df.corr()
+        expected = DataFrame({"A": [1.0, 1.0], "B": [1.0, 1.0]}, index=["A", "B"])
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("method", ["pearson", "spearman", "kendall"])
+    def test_corr_min_periods_greater_than_length(self, method):
+        pytest.importorskip("scipy")
+        df = DataFrame({"A": [1, 2], "B": [1, 2]})
+        result = df.corr(method=method, min_periods=3)
+        expected = DataFrame(
+            {"A": [np.nan, np.nan], "B": [np.nan, np.nan]}, index=["A", "B"]
+        )
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("meth", ["pearson", "kendall", "spearman"])
+    @pytest.mark.parametrize("numeric_only", [True, False])
+    def test_corr_numeric_only(self, meth, numeric_only):
+        # when dtypes of pandas series are different
+        # then ndarray will have dtype=object,
+        # so it need to be properly handled
+        pytest.importorskip("scipy")
+        df = DataFrame({"a": [1, 0], "b": [1, 0], "c": ["x", "y"]})
+        expected = DataFrame(np.ones((2, 2)), index=["a", "b"], columns=["a", "b"])
+        if numeric_only:
+            result = df.corr(meth, numeric_only=numeric_only)
+            tm.assert_frame_equal(result, expected)
+        else:
+            with pytest.raises(ValueError, match="could not convert string to float"):
+                df.corr(meth, numeric_only=numeric_only)
+
+
+class TestDataFrameCorrWith:
+    @pytest.mark.parametrize(
+        "dtype",
+        [
+            "float64",
+            "Float64",
+            pytest.param("float64[pyarrow]", marks=td.skip_if_no("pyarrow")),
+        ],
+    )
+    def test_corrwith(self, datetime_frame, dtype):
+        datetime_frame = datetime_frame.astype(dtype)
+
+        a = datetime_frame
+        noise = Series(np.random.default_rng(2).standard_normal(len(a)), index=a.index)
+
+        b = datetime_frame.add(noise, axis=0)
+
+        # make sure order does not matter
+        b = b.reindex(columns=b.columns[::-1], index=b.index[::-1][10:])
+        del b["B"]
+
+        colcorr = a.corrwith(b, axis=0)
+        tm.assert_almost_equal(colcorr["A"], a["A"].corr(b["A"]))
+
+        rowcorr = a.corrwith(b, axis=1)
+        tm.assert_series_equal(rowcorr, a.T.corrwith(b.T, axis=0))
+
+        dropped = a.corrwith(b, axis=0, drop=True)
+        tm.assert_almost_equal(dropped["A"], a["A"].corr(b["A"]))
+        assert "B" not in dropped
+
+        dropped = a.corrwith(b, axis=1, drop=True)
+        assert a.index[-1] not in dropped.index
+
+        # non time-series data
+        index = ["a", "b", "c", "d", "e"]
+        columns = ["one", "two", "three", "four"]
+        df1 = DataFrame(
+            np.random.default_rng(2).standard_normal((5, 4)),
+            index=index,
+            columns=columns,
+        )
+        df2 = DataFrame(
+            np.random.default_rng(2).standard_normal((4, 4)),
+            index=index[:4],
+            columns=columns,
+        )
+        correls = df1.corrwith(df2, axis=1)
+        for row in index[:4]:
+            tm.assert_almost_equal(correls[row], df1.loc[row].corr(df2.loc[row]))
+
+    def test_corrwith_with_objects(self, using_infer_string):
+        df1 = DataFrame(
+            np.random.default_rng(2).standard_normal((10, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=date_range("2000-01-01", periods=10, freq="B"),
+        )
+        df2 = df1.copy()
+        cols = ["A", "B", "C", "D"]
+
+        df1["obj"] = "foo"
+        df2["obj"] = "bar"
+
+        if using_infer_string:
+            import pyarrow as pa
+
+            with pytest.raises(pa.lib.ArrowNotImplementedError, match="has no kernel"):
+                df1.corrwith(df2)
+        else:
+            with pytest.raises(TypeError, match="Could not convert"):
+                df1.corrwith(df2)
+        result = df1.corrwith(df2, numeric_only=True)
+        expected = df1.loc[:, cols].corrwith(df2.loc[:, cols])
+        tm.assert_series_equal(result, expected)
+
+        with pytest.raises(TypeError, match="unsupported operand type"):
+            df1.corrwith(df2, axis=1)
+        result = df1.corrwith(df2, axis=1, numeric_only=True)
+        expected = df1.loc[:, cols].corrwith(df2.loc[:, cols], axis=1)
+        tm.assert_series_equal(result, expected)
+
+    def test_corrwith_series(self, datetime_frame):
+        result = datetime_frame.corrwith(datetime_frame["A"])
+        expected = datetime_frame.apply(datetime_frame["A"].corr)
+
+        tm.assert_series_equal(result, expected)
+
+    def test_corrwith_matches_corrcoef(self):
+        df1 = DataFrame(np.arange(10000), columns=["a"])
+        df2 = DataFrame(np.arange(10000) ** 2, columns=["a"])
+        c1 = df1.corrwith(df2)["a"]
+        c2 = np.corrcoef(df1["a"], df2["a"])[0][1]
+
+        tm.assert_almost_equal(c1, c2)
+        assert c1 < 1
+
+    @pytest.mark.parametrize("numeric_only", [True, False])
+    def test_corrwith_mixed_dtypes(self, numeric_only):
+        # GH#18570
+        df = DataFrame(
+            {"a": [1, 4, 3, 2], "b": [4, 6, 7, 3], "c": ["a", "b", "c", "d"]}
+        )
+        s = Series([0, 6, 7, 3])
+        if numeric_only:
+            result = df.corrwith(s, numeric_only=numeric_only)
+            corrs = [df["a"].corr(s), df["b"].corr(s)]
+            expected = Series(data=corrs, index=["a", "b"])
+            tm.assert_series_equal(result, expected)
+        else:
+            with pytest.raises(
+                ValueError,
+                match="could not convert string to float",
+            ):
+                df.corrwith(s, numeric_only=numeric_only)
+
+    def test_corrwith_index_intersection(self):
+        df1 = DataFrame(
+            np.random.default_rng(2).random(size=(10, 2)), columns=["a", "b"]
+        )
+        df2 = DataFrame(
+            np.random.default_rng(2).random(size=(10, 3)), columns=["a", "b", "c"]
+        )
+
+        result = df1.corrwith(df2, drop=True).index.sort_values()
+        expected = df1.columns.intersection(df2.columns).sort_values()
+        tm.assert_index_equal(result, expected)
+
+    def test_corrwith_index_union(self):
+        df1 = DataFrame(
+            np.random.default_rng(2).random(size=(10, 2)), columns=["a", "b"]
+        )
+        df2 = DataFrame(
+            np.random.default_rng(2).random(size=(10, 3)), columns=["a", "b", "c"]
+        )
+
+        result = df1.corrwith(df2, drop=False).index.sort_values()
+        expected = df1.columns.union(df2.columns).sort_values()
+        tm.assert_index_equal(result, expected)
+
+    def test_corrwith_dup_cols(self):
+        # GH#21925
+        df1 = DataFrame(np.vstack([np.arange(10)] * 3).T)
+        df2 = df1.copy()
+        df2 = pd.concat((df2, df2[0]), axis=1)
+
+        result = df1.corrwith(df2)
+        expected = Series(np.ones(4), index=[0, 0, 1, 2])
+        tm.assert_series_equal(result, expected)
+
+    def test_corr_numerical_instabilities(self):
+        # GH#45640
+        df = DataFrame([[0.2, 0.4], [0.4, 0.2]])
+        result = df.corr()
+        expected = DataFrame({0: [1.0, -1.0], 1: [-1.0, 1.0]})
+        tm.assert_frame_equal(result - 1, expected - 1, atol=1e-17)
+
+    def test_corrwith_spearman(self):
+        # GH#21925
+        pytest.importorskip("scipy")
+        df = DataFrame(np.random.default_rng(2).random(size=(100, 3)))
+        result = df.corrwith(df**2, method="spearman")
+        expected = Series(np.ones(len(result)))
+        tm.assert_series_equal(result, expected)
+
+    def test_corrwith_kendall(self):
+        # GH#21925
+        pytest.importorskip("scipy")
+        df = DataFrame(np.random.default_rng(2).random(size=(100, 3)))
+        result = df.corrwith(df**2, method="kendall")
+        expected = Series(np.ones(len(result)))
+        tm.assert_series_equal(result, expected)
+
+    def test_corrwith_spearman_with_tied_data(self):
+        # GH#48826
+        pytest.importorskip("scipy")
+        df1 = DataFrame(
+            {
+                "A": [1, np.nan, 7, 8],
+                "B": [False, True, True, False],
+                "C": [10, 4, 9, 3],
+            }
+        )
+        df2 = df1[["B", "C"]]
+        result = (df1 + 1).corrwith(df2.B, method="spearman")
+        expected = Series([0.0, 1.0, 0.0], index=["A", "B", "C"])
+        tm.assert_series_equal(result, expected)
+
+        df_bool = DataFrame(
+            {"A": [True, True, False, False], "B": [True, False, False, True]}
+        )
+        ser_bool = Series([True, True, False, True])
+        result = df_bool.corrwith(ser_bool)
+        expected = Series([0.57735, 0.57735], index=["A", "B"])
+        tm.assert_series_equal(result, expected)

venv/lib/python3.12/site-packages/pandas/tests/frame/methods/test_describe.py

@@ -0,0 +1,417 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    DataFrame,
+    Series,
+    Timestamp,
+    date_range,
+)
+import pandas._testing as tm
+
+
+class TestDataFrameDescribe:
+    def test_describe_bool_in_mixed_frame(self):
+        df = DataFrame(
+            {
+                "string_data": ["a", "b", "c", "d", "e"],
+                "bool_data": [True, True, False, False, False],
+                "int_data": [10, 20, 30, 40, 50],
+            }
+        )
+
+        # Integer data are included in .describe() output,
+        # Boolean and string data are not.
+        result = df.describe()
+        expected = DataFrame(
+            {"int_data": [5, 30, df.int_data.std(), 10, 20, 30, 40, 50]},
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+        # Top value is a boolean value that is False
+        result = df.describe(include=["bool"])
+
+        expected = DataFrame(
+            {"bool_data": [5, 2, False, 3]}, index=["count", "unique", "top", "freq"]
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_empty_object(self):
+        # GH#27183
+        df = DataFrame({"A": [None, None]}, dtype=object)
+        result = df.describe()
+        expected = DataFrame(
+            {"A": [0, 0, np.nan, np.nan]},
+            dtype=object,
+            index=["count", "unique", "top", "freq"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+        result = df.iloc[:0].describe()
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_bool_frame(self):
+        # GH#13891
+        df = DataFrame(
+            {
+                "bool_data_1": [False, False, True, True],
+                "bool_data_2": [False, True, True, True],
+            }
+        )
+        result = df.describe()
+        expected = DataFrame(
+            {"bool_data_1": [4, 2, False, 2], "bool_data_2": [4, 2, True, 3]},
+            index=["count", "unique", "top", "freq"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+        df = DataFrame(
+            {
+                "bool_data": [False, False, True, True, False],
+                "int_data": [0, 1, 2, 3, 4],
+            }
+        )
+        result = df.describe()
+        expected = DataFrame(
+            {"int_data": [5, 2, df.int_data.std(), 0, 1, 2, 3, 4]},
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+        df = DataFrame(
+            {"bool_data": [False, False, True, True], "str_data": ["a", "b", "c", "a"]}
+        )
+        result = df.describe()
+        expected = DataFrame(
+            {"bool_data": [4, 2, False, 2], "str_data": [4, 3, "a", 2]},
+            index=["count", "unique", "top", "freq"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_categorical(self):
+        df = DataFrame({"value": np.random.default_rng(2).integers(0, 10000, 100)})
+        labels = [f"{i} - {i + 499}" for i in range(0, 10000, 500)]
+        cat_labels = Categorical(labels, labels)
+
+        df = df.sort_values(by=["value"], ascending=True)
+        df["value_group"] = pd.cut(
+            df.value, range(0, 10500, 500), right=False, labels=cat_labels
+        )
+        cat = df
+
+        # Categoricals should not show up together with numerical columns
+        result = cat.describe()
+        assert len(result.columns) == 1
+
+        # In a frame, describe() for the cat should be the same as for string
+        # arrays (count, unique, top, freq)
+
+        cat = Categorical(
+            ["a", "b", "b", "b"], categories=["a", "b", "c"], ordered=True
+        )
+        s = Series(cat)
+        result = s.describe()
+        expected = Series([4, 2, "b", 3], index=["count", "unique", "top", "freq"])
+        tm.assert_series_equal(result, expected)
+
+        cat = Series(Categorical(["a", "b", "c", "c"]))
+        df3 = DataFrame({"cat": cat, "s": ["a", "b", "c", "c"]})
+        result = df3.describe()
+        tm.assert_numpy_array_equal(result["cat"].values, result["s"].values)
+
+    def test_describe_empty_categorical_column(self):
+        # GH#26397
+        # Ensure the index of an empty categorical DataFrame column
+        # also contains (count, unique, top, freq)
+        df = DataFrame({"empty_col": Categorical([])})
+        result = df.describe()
+        expected = DataFrame(
+            {"empty_col": [0, 0, np.nan, np.nan]},
+            index=["count", "unique", "top", "freq"],
+            dtype="object",
+        )
+        tm.assert_frame_equal(result, expected)
+        # ensure NaN, not None
+        assert np.isnan(result.iloc[2, 0])
+        assert np.isnan(result.iloc[3, 0])
+
+    def test_describe_categorical_columns(self):
+        # GH#11558
+        columns = pd.CategoricalIndex(["int1", "int2", "obj"], ordered=True, name="XXX")
+        df = DataFrame(
+            {
+                "int1": [10, 20, 30, 40, 50],
+                "int2": [10, 20, 30, 40, 50],
+                "obj": ["A", 0, None, "X", 1],
+            },
+            columns=columns,
+        )
+        result = df.describe()
+
+        exp_columns = pd.CategoricalIndex(
+            ["int1", "int2"],
+            categories=["int1", "int2", "obj"],
+            ordered=True,
+            name="XXX",
+        )
+        expected = DataFrame(
+            {
+                "int1": [5, 30, df.int1.std(), 10, 20, 30, 40, 50],
+                "int2": [5, 30, df.int2.std(), 10, 20, 30, 40, 50],
+            },
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+            columns=exp_columns,
+        )
+
+        tm.assert_frame_equal(result, expected)
+        tm.assert_categorical_equal(result.columns.values, expected.columns.values)
+
+    def test_describe_datetime_columns(self):
+        columns = pd.DatetimeIndex(
+            ["2011-01-01", "2011-02-01", "2011-03-01"],
+            freq="MS",
+            tz="US/Eastern",
+            name="XXX",
+        )
+        df = DataFrame(
+            {
+                0: [10, 20, 30, 40, 50],
+                1: [10, 20, 30, 40, 50],
+                2: ["A", 0, None, "X", 1],
+            }
+        )
+        df.columns = columns
+        result = df.describe()
+
+        exp_columns = pd.DatetimeIndex(
+            ["2011-01-01", "2011-02-01"], freq="MS", tz="US/Eastern", name="XXX"
+        )
+        expected = DataFrame(
+            {
+                0: [5, 30, df.iloc[:, 0].std(), 10, 20, 30, 40, 50],
+                1: [5, 30, df.iloc[:, 1].std(), 10, 20, 30, 40, 50],
+            },
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+        )
+        expected.columns = exp_columns
+        tm.assert_frame_equal(result, expected)
+        assert result.columns.freq == "MS"
+        assert result.columns.tz == expected.columns.tz
+
+    def test_describe_timedelta_values(self):
+        # GH#6145
+        t1 = pd.timedelta_range("1 days", freq="D", periods=5)
+        t2 = pd.timedelta_range("1 hours", freq="h", periods=5)
+        df = DataFrame({"t1": t1, "t2": t2})
+
+        expected = DataFrame(
+            {
+                "t1": [
+                    5,
+                    pd.Timedelta("3 days"),
+                    df.iloc[:, 0].std(),
+                    pd.Timedelta("1 days"),
+                    pd.Timedelta("2 days"),
+                    pd.Timedelta("3 days"),
+                    pd.Timedelta("4 days"),
+                    pd.Timedelta("5 days"),
+                ],
+                "t2": [
+                    5,
+                    pd.Timedelta("3 hours"),
+                    df.iloc[:, 1].std(),
+                    pd.Timedelta("1 hours"),
+                    pd.Timedelta("2 hours"),
+                    pd.Timedelta("3 hours"),
+                    pd.Timedelta("4 hours"),
+                    pd.Timedelta("5 hours"),
+                ],
+            },
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+        )
+
+        result = df.describe()
+        tm.assert_frame_equal(result, expected)
+
+        exp_repr = (
+            "                              t1                         t2\n"
+            "count                          5                          5\n"
+            "mean             3 days 00:00:00            0 days 03:00:00\n"
+            "std    1 days 13:56:50.394919273  0 days 01:34:52.099788303\n"
+            "min              1 days 00:00:00            0 days 01:00:00\n"
+            "25%              2 days 00:00:00            0 days 02:00:00\n"
+            "50%              3 days 00:00:00            0 days 03:00:00\n"
+            "75%              4 days 00:00:00            0 days 04:00:00\n"
+            "max              5 days 00:00:00            0 days 05:00:00"
+        )
+        assert repr(result) == exp_repr
+
+    def test_describe_tz_values(self, tz_naive_fixture):
+        # GH#21332
+        tz = tz_naive_fixture
+        s1 = Series(range(5))
+        start = Timestamp(2018, 1, 1)
+        end = Timestamp(2018, 1, 5)
+        s2 = Series(date_range(start, end, tz=tz))
+        df = DataFrame({"s1": s1, "s2": s2})
+
+        expected = DataFrame(
+            {
+                "s1": [5, 2, 0, 1, 2, 3, 4, 1.581139],
+                "s2": [
+                    5,
+                    Timestamp(2018, 1, 3).tz_localize(tz),
+                    start.tz_localize(tz),
+                    s2[1],
+                    s2[2],
+                    s2[3],
+                    end.tz_localize(tz),
+                    np.nan,
+                ],
+            },
+            index=["count", "mean", "min", "25%", "50%", "75%", "max", "std"],
+        )
+        result = df.describe(include="all")
+        tm.assert_frame_equal(result, expected)
+
+    def test_datetime_is_numeric_includes_datetime(self):
+        df = DataFrame({"a": date_range("2012", periods=3), "b": [1, 2, 3]})
+        result = df.describe()
+        expected = DataFrame(
+            {
+                "a": [
+                    3,
+                    Timestamp("2012-01-02"),
+                    Timestamp("2012-01-01"),
+                    Timestamp("2012-01-01T12:00:00"),
+                    Timestamp("2012-01-02"),
+                    Timestamp("2012-01-02T12:00:00"),
+                    Timestamp("2012-01-03"),
+                    np.nan,
+                ],
+                "b": [3, 2, 1, 1.5, 2, 2.5, 3, 1],
+            },
+            index=["count", "mean", "min", "25%", "50%", "75%", "max", "std"],
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_tz_values2(self):
+        tz = "CET"
+        s1 = Series(range(5))
+        start = Timestamp(2018, 1, 1)
+        end = Timestamp(2018, 1, 5)
+        s2 = Series(date_range(start, end, tz=tz))
+        df = DataFrame({"s1": s1, "s2": s2})
+
+        s1_ = s1.describe()
+        s2_ = s2.describe()
+        idx = [
+            "count",
+            "mean",
+            "min",
+            "25%",
+            "50%",
+            "75%",
+            "max",
+            "std",
+        ]
+        expected = pd.concat([s1_, s2_], axis=1, keys=["s1", "s2"]).reindex(
+            idx, copy=False
+        )
+
+        result = df.describe(include="all")
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_percentiles_integer_idx(self):
+        # GH#26660
+        df = DataFrame({"x": [1]})
+        pct = np.linspace(0, 1, 10 + 1)
+        result = df.describe(percentiles=pct)
+
+        expected = DataFrame(
+            {"x": [1.0, 1.0, np.nan, 1.0, *(1.0 for _ in pct), 1.0]},
+            index=[
+                "count",
+                "mean",
+                "std",
+                "min",
+                "0%",
+                "10%",
+                "20%",
+                "30%",
+                "40%",
+                "50%",
+                "60%",
+                "70%",
+                "80%",
+                "90%",
+                "100%",
+                "max",
+            ],
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_does_not_raise_error_for_dictlike_elements(self):
+        # GH#32409
+        df = DataFrame([{"test": {"a": "1"}}, {"test": {"a": "2"}}])
+        expected = DataFrame(
+            {"test": [2, 2, {"a": "1"}, 1]}, index=["count", "unique", "top", "freq"]
+        )
+        result = df.describe()
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("exclude", ["x", "y", ["x", "y"], ["x", "z"]])
+    def test_describe_when_include_all_exclude_not_allowed(self, exclude):
+        """
+        When include is 'all', then setting exclude != None is not allowed.
+        """
+        df = DataFrame({"x": [1], "y": [2], "z": [3]})
+        msg = "exclude must be None when include is 'all'"
+        with pytest.raises(ValueError, match=msg):
+            df.describe(include="all", exclude=exclude)
+
+    def test_describe_with_duplicate_columns(self):
+        df = DataFrame(
+            [[1, 1, 1], [2, 2, 2], [3, 3, 3]],
+            columns=["bar", "a", "a"],
+            dtype="float64",
+        )
+        result = df.describe()
+        ser = df.iloc[:, 0].describe()
+        expected = pd.concat([ser, ser, ser], keys=df.columns, axis=1)
+        tm.assert_frame_equal(result, expected)
+
+    def test_ea_with_na(self, any_numeric_ea_dtype):
+        # GH#48778
+
+        df = DataFrame({"a": [1, pd.NA, pd.NA], "b": pd.NA}, dtype=any_numeric_ea_dtype)
+        result = df.describe()
+        expected = DataFrame(
+            {"a": [1.0, 1.0, pd.NA] + [1.0] * 5, "b": [0.0] + [pd.NA] * 7},
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+            dtype="Float64",
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_describe_exclude_pa_dtype(self):
+        # GH#52570
+        pa = pytest.importorskip("pyarrow")
+        df = DataFrame(
+            {
+                "a": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int8())),
+                "b": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int16())),
+                "c": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int32())),
+            }
+        )
+        result = df.describe(
+            include=pd.ArrowDtype(pa.int8()), exclude=pd.ArrowDtype(pa.int32())
+        )
+        expected = DataFrame(
+            {"a": [3, 2, 1, 1, 1.5, 2, 2.5, 3]},
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+            dtype=pd.ArrowDtype(pa.float64()),
+        )
+        tm.assert_frame_equal(result, expected)