Merge remote-tracking branch 'upstream/main' into pr/jorisvandenbossche/ruff

Author: MarcoGorelli

pandas/core/generic.py

@@ -1209,7 +1209,8 @@ class  name
         axes, kwargs = self._construct_axes_from_arguments(
             (), kwargs, sentinel=lib.no_default
         )
-        copy = kwargs.pop("copy", True)
+        copy: bool_t | None = kwargs.pop("copy", None)
+
         inplace = kwargs.pop("inplace", False)
         axis = kwargs.pop("axis", 0)
         if axis is not None:
@@ -1229,7 +1230,9 @@ class  name
                 is_list_like(mapper) and not is_dict_like(mapper)
             )
             if non_mapper:
-                return self._set_axis_name(mapper, axis=axis, inplace=inplace)
+                return self._set_axis_name(
+                    mapper, axis=axis, inplace=inplace, copy=copy
+                )
             else:
                 raise ValueError("Use `.rename` to alter labels with a mapper.")
         else:
@@ -1248,13 +1251,15 @@ class  name
                     f = common.get_rename_function(v)
                     curnames = self._get_axis(axis).names
                     newnames = [f(name) for name in curnames]
-                result._set_axis_name(newnames, axis=axis, inplace=True)
+                result._set_axis_name(newnames, axis=axis, inplace=True, copy=copy)
             if not inplace:
                 return result
             return None
 
     @final
-    def _set_axis_name(self, name, axis: Axis = 0, inplace: bool_t = False):
+    def _set_axis_name(
+        self, name, axis: Axis = 0, inplace: bool_t = False, copy: bool_t | None = True
+    ):
         """
         Set the name(s) of the axis.
 
@@ -1267,6 +1272,8 @@ def _set_axis_name(self, name, axis: Axis = 0, inplace: bool_t = False):
             and the value 1 or 'columns' specifies columns.
         inplace : bool, default False
             If `True`, do operation inplace and return None.
+        copy:
+            Whether to make a copy of the result.
 
         Returns
         -------
@@ -1308,7 +1315,7 @@ def _set_axis_name(self, name, axis: Axis = 0, inplace: bool_t = False):
         idx = self._get_axis(axis).set_names(name)
 
         inplace = validate_bool_kwarg(inplace, "inplace")
-        renamed = self if inplace else self.copy()
+        renamed = self if inplace else self.copy(deep=copy)
         if axis == 0:
             renamed.index = idx
         else:

pandas/tests/copy_view/test_methods.py

@@ -3,6 +3,7 @@
 
 from pandas import (
     DataFrame,
+    Index,
     MultiIndex,
     Series,
 )
@@ -456,3 +457,21 @@ def test_series_set_axis(using_copy_on_write):
     ser2.iloc[0] = 0
     assert not np.shares_memory(ser2, ser)
     tm.assert_series_equal(ser, ser_orig)
+
+
+@pytest.mark.parametrize("copy_kwargs", [{"copy": True}, {}])
+@pytest.mark.parametrize("kwargs", [{"mapper": "test"}, {"index": "test"}])
+def test_rename_axis(using_copy_on_write, kwargs, copy_kwargs):
+    df = DataFrame({"a": [1, 2, 3, 4]}, index=Index([1, 2, 3, 4], name="a"))
+    df_orig = df.copy()
+    df2 = df.rename_axis(**kwargs, **copy_kwargs)
+
+    if using_copy_on_write and not copy_kwargs:
+        assert np.shares_memory(get_array(df2, "a"), get_array(df, "a"))
+    else:
+        assert not np.shares_memory(get_array(df2, "a"), get_array(df, "a"))
+
+    df2.iloc[0, 0] = 0
+    if using_copy_on_write:
+        assert not np.shares_memory(get_array(df2, "a"), get_array(df, "a"))
+    tm.assert_frame_equal(df, df_orig)

pandas/tests/frame/methods/test_equals.py

@@ -36,7 +36,8 @@ def test_equals(self):
         df1["start"] = date_range("2000-1-1", periods=10, freq="T")
         df1["end"] = date_range("2000-1-1", periods=10, freq="D")
         df1["diff"] = df1["end"] - df1["start"]
-        df1["bool"] = np.arange(10) % 3 == 0
+        # Explicitly cast to object, to avoid implicit cast when setting np.nan
+        df1["bool"] = (np.arange(10) % 3 == 0).astype(object)
         df1.loc[::2] = np.nan
         df2 = df1.copy()
         assert df1["text"].equals(df2["text"])

pandas/tests/frame/test_query_eval.py

@@ -448,7 +448,8 @@ def test_date_index_query(self):
     def test_date_index_query_with_NaT(self):
         engine, parser = self.engine, self.parser
         n = 10
-        df = DataFrame(np.random.randn(n, 3))
+        # Cast to object to avoid implicit cast when setting entry to pd.NaT below
+        df = DataFrame(np.random.randn(n, 3)).astype({0: object})
         df["dates1"] = date_range("1/1/2012", periods=n)
         df["dates3"] = date_range("1/1/2014", periods=n)
         df.iloc[0, 0] = pd.NaT
@@ -808,7 +809,8 @@ def test_date_index_query(self):
     def test_date_index_query_with_NaT(self):
         engine, parser = self.engine, self.parser
         n = 10
-        df = DataFrame(np.random.randn(n, 3))
+        # Cast to object to avoid implicit cast when setting entry to pd.NaT below
+        df = DataFrame(np.random.randn(n, 3)).astype({0: object})
         df["dates1"] = date_range("1/1/2012", periods=n)
         df["dates3"] = date_range("1/1/2014", periods=n)
         df.iloc[0, 0] = pd.NaT

pandas/tests/frame/test_reductions.py

@@ -449,10 +449,14 @@ def test_var_std(self, datetime_frame):
     def test_numeric_only_flag(self, meth):
         # GH 9201
         df1 = DataFrame(np.random.randn(5, 3), columns=["foo", "bar", "baz"])
+        # Cast to object to avoid implicit cast when setting entry to "100" below
+        df1 = df1.astype({"foo": object})
         # set one entry to a number in str format
         df1.loc[0, "foo"] = "100"
 
         df2 = DataFrame(np.random.randn(5, 3), columns=["foo", "bar", "baz"])
+        # Cast to object to avoid implicit cast when setting entry to "a" below
+        df2 = df2.astype({"foo": object})
         # set one entry to a non-number str
         df2.loc[0, "foo"] = "a"
 

pandas/tests/groupby/test_timegrouper.py

@@ -103,6 +103,8 @@ def test_groupby_with_timegrouper(self):
                     "20130901", "20131205", freq="5D", name="Date", inclusive="left"
                 ),
             )
+            # Cast to object to avoid implicit cast when setting entry to "CarlCarlCarl"
+            expected = expected.astype({"Buyer": object})
             expected.iloc[0, 0] = "CarlCarlCarl"
             expected.iloc[6, 0] = "CarlCarl"
             expected.iloc[18, 0] = "Joe"

pandas/tests/series/methods/test_replace.py

@@ -16,7 +16,8 @@ def test_replace_explicit_none(self):
         expected = pd.Series([0, 0, None], dtype=object)
         tm.assert_series_equal(result, expected)
 
-        df = pd.DataFrame(np.zeros((3, 3)))
+        # Cast column 2 to object to avoid implicit cast when setting entry to ""
+        df = pd.DataFrame(np.zeros((3, 3))).astype({2: object})
         df.iloc[2, 2] = ""
         result = df.replace("", None)
         expected = pd.DataFrame(