Merge branch 'main' into enh-array_ufunc-arrow

jbrockmendel · jbrockmendel · commit c5e9f17f1436 · 2025-10-29T13:34:19.000-07:00
diff --git a/doc/make.py b/doc/make.py
@@ -105,7 +105,7 @@ def _process_single_doc(self, single_doc):
     @staticmethod
     def _run_os(*args) -> None:
         """
-        Execute a command as a OS terminal.
+        Execute a command as an OS terminal.
 
         Parameters
         ----------
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -1236,6 +1236,7 @@ Other
 - Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
 - Bug in :meth:`DataFrame.query` which raised an exception when querying integer column names using backticks. (:issue:`60494`)
+- Bug in :meth:`DataFrame.rename` and :meth:`Series.rename` when passed a ``mapper``, ``index``, or ``columns`` argument that is a :class:`Series` with non-unique ``ser.index`` producing a corrupted result instead of raising ``ValueError`` (:issue:`58621`)
 - Bug in :meth:`DataFrame.sample` with ``replace=False`` and ``(n * max(weights) / sum(weights)) > 1``, the method would return biased results. Now raises ``ValueError``. (:issue:`61516`)
 - Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)
diff --git a/pandas/_config/localization.py b/pandas/_config/localization.py
@@ -79,7 +79,7 @@ def can_set_locale(lc: str, lc_var: int = locale.LC_ALL) -> bool:
         with set_locale(lc, lc_var=lc_var):
             pass
     except (ValueError, locale.Error):
-        # horrible name for a Exception subclass
+        # horrible name for an Exception subclass
         return False
     else:
         return True
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -269,7 +269,7 @@ class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMi
         categories are assumed to be the unique values of `values` (sorted, if
         possible, otherwise in the order in which they appear).
     ordered : bool, default False
-        Whether or not this categorical is treated as a ordered categorical.
+        Whether or not this categorical is treated as an ordered categorical.
         If True, the resulting categorical will be ordered.
         An ordered categorical respects, when sorted, the order of its
         `categories` attribute (which in turn is the `categories` argument, if
@@ -1103,7 +1103,7 @@ def set_categories(
         new_categories : Index-like
            The categories in new order.
         ordered : bool, default None
-           Whether or not the categorical is treated as a ordered categorical.
+           Whether or not the categorical is treated as an ordered categorical.
            If not given, do not change the ordered information.
         rename : bool, default False
            Whether or not the new_categories should be considered as a rename
@@ -1277,7 +1277,7 @@ def reorder_categories(self, new_categories, ordered=None) -> Self:
         new_categories : Index-like
            The categories in new order.
         ordered : bool, optional
-           Whether or not the categorical is treated as a ordered categorical.
+           Whether or not the categorical is treated as an ordered categorical.
            If not given, do not change the ordered information.
 
         Returns
diff --git a/pandas/core/arrays/timedeltas.py b/pandas/core/arrays/timedeltas.py
@@ -1212,7 +1212,7 @@ def _objects_to_td64ns(
     data, unit=None, errors: DateTimeErrorChoices = "raise"
 ) -> np.ndarray:
     """
-    Convert a object-dtyped or string-dtyped array into an
+    Convert an object-dtyped or string-dtyped array into a
     timedelta64[ns]-dtyped array.
 
     Parameters
diff --git a/pandas/core/dtypes/base.py b/pandas/core/dtypes/base.py
@@ -517,7 +517,7 @@ class Registry:
     """
     Registry for dtype inference.
 
-    The registry allows one to map a string repr of a extension
+    The registry allows one to map a string repr of an extension
     dtype to an extension dtype. The string alias can be used in several
     places, including
 
diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
@@ -176,7 +176,7 @@ class CategoricalDtype(PandasExtensionDtype, ExtensionDtype):
         The categories are stored in an Index,
         and if an index is provided the dtype of that index will be used.
     ordered : bool or None, default False
-        Whether or not this categorical is treated as a ordered categorical.
+        Whether or not this categorical is treated as an ordered categorical.
         None can be used to maintain the ordered value of existing categoricals when
         used in operations that combine categoricals, e.g. astype, and will resolve to
         False if there is no existing ordered to maintain.
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -1054,6 +1054,10 @@ def _rename(
             if level is not None:
                 level = ax._get_level_number(level)
 
+            if isinstance(replacements, ABCSeries) and not replacements.index.is_unique:
+                # GH#58621
+                raise ValueError("Cannot rename with a Series with non-unique index.")
+
             # GH 13473
             if not callable(replacements):
                 if ax._is_multi and level is not None:
diff --git a/pandas/core/indexes/range.py b/pandas/core/indexes/range.py
@@ -88,13 +88,13 @@ class RangeIndex(Index):
 
     Parameters
     ----------
-    start : int (default: 0), range, or other RangeIndex instance
+    start : int, range, or other RangeIndex instance, default None
         If int and "stop" is not given, interpreted as "stop" instead.
-    stop : int (default: 0)
+    stop : int, default None
         The end value of the range (exclusive).
-    step : int (default: 1)
+    step : int, default None
         The step size of the range.
-    dtype : np.int64
+    dtype : np.int64, default None
         Unused, accepted for homogeneity with other index types.
     copy : bool, default False
         Unused, accepted for homogeneity with other index types.
diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py
@@ -215,7 +215,7 @@ def ndarray_to_mgr(
         # GH#19157
 
         if isinstance(values, (np.ndarray, ExtensionArray)) and values.ndim > 1:
-            # GH#12513 a EA dtype passed with a 2D array, split into
+            # GH#12513 an EA dtype passed with a 2D array, split into
             #  multiple EAs that view the values
             # error: No overload variant of "__getitem__" of "ExtensionArray"
             # matches argument type "Tuple[slice, int]"
diff --git a/pandas/core/window/expanding.py b/pandas/core/window/expanding.py
@@ -1454,7 +1454,7 @@ def corr(
 
 class ExpandingGroupby(BaseWindowGroupby, Expanding):
     """
-    Provide a expanding groupby implementation.
+    Provide an expanding groupby implementation.
     """
 
     __module__ = "pandas.api.typing"
diff --git a/pandas/core/window/numba_.py b/pandas/core/window/numba_.py
@@ -189,7 +189,7 @@ def generate_numba_table_func(
     """
     Generate a numba jitted function to apply window calculations table-wise.
 
-    Func will be passed a M window size x N number of columns array, and
+    Func will be passed an M window size x N number of columns array, and
     must return a 1 x N number of columns array.
 
     1. jit the user's function
diff --git a/pandas/io/excel/_odswriter.py b/pandas/io/excel/_odswriter.py
@@ -246,7 +246,7 @@ def _process_style(self, style: dict[str, Any]) -> str: ...
     def _process_style(self, style: None) -> None: ...
 
     def _process_style(self, style: dict[str, Any] | None) -> str | None:
-        """Convert a style dictionary to a OpenDocument style sheet
+        """Convert a style dictionary to an OpenDocument style sheet
 
         Parameters
         ----------
diff --git a/pandas/io/json/_normalize.py b/pandas/io/json/_normalize.py
@@ -219,7 +219,7 @@ def _simple_json_normalize(
     sep: str = ".",
 ) -> dict | list[dict] | Any:
     """
-    A optimized basic json_normalize
+    An optimized basic json_normalize
 
     Converts a nested dict into a flat dict ("record"), unlike
     json_normalize and nested_to_record it doesn't do anything clever.
diff --git a/pandas/plotting/_misc.py b/pandas/plotting/_misc.py
@@ -282,12 +282,12 @@ def radviz(
     """
     Plot a multidimensional dataset in 2D.
 
-    Each Series in the DataFrame is represented as a evenly distributed
+    Each Series in the DataFrame is represented as an evenly distributed
     slice on a circle. Each data point is rendered in the circle according to
     the value on each Series. Highly correlated `Series` in the `DataFrame`
     are placed closer on the unit circle.
 
-    RadViz allow to project a N-dimensional data set into a 2D space where the
+    RadViz allow to project an N-dimensional data set into a 2D space where the
     influence of each dimension can be interpreted as a balance between the
     influence of all dimensions.
 
diff --git a/pandas/tests/arrays/sparse/test_constructors.py b/pandas/tests/arrays/sparse/test_constructors.py
@@ -77,7 +77,10 @@ def test_constructor_object_dtype_bool_fill(self):
         assert arr.dtype == SparseDtype(object, False)
         assert arr.fill_value is False
         arr_expected = np.array(data, dtype=object)
-        it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
+        it = (
+            type(x) == type(y) and x == y
+            for x, y in zip(arr, arr_expected, strict=True)
+        )
         assert np.fromiter(it, dtype=np.bool_).all()
 
     @pytest.mark.parametrize("dtype", [SparseDtype(int, 0), int])
diff --git a/pandas/tests/arrays/test_datetimes.py b/pandas/tests/arrays/test_datetimes.py
@@ -144,7 +144,7 @@ def test_iter(self, dta):
     def test_astype_object(self, dta):
         result = dta.astype(object)
         assert all(x._creso == dta._creso for x in result)
-        assert all(x == y for x, y in zip(result, dta))
+        assert all(x == y for x, y in zip(result, dta, strict=True))
 
     def test_to_pydatetime(self, dta_dti):
         dta, dti = dta_dti
diff --git a/pandas/tests/extension/base/setitem.py b/pandas/tests/extension/base/setitem.py
@@ -221,28 +221,28 @@ def test_setitem_integer_array_with_repeats(self, data, idx, box_in_series):
         tm.assert_equal(arr, expected)
 
     @pytest.mark.parametrize(
-        "idx, box_in_series",
+        "idx",
         [
-            ([0, 1, 2, pd.NA], False),
-            pytest.param(
-                [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
-            ),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            # TODO: change False to True?
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),  # noqa: PT014
+            [0, 1, 2, pd.NA],
+            pd.array([0, 1, 2, pd.NA], dtype="Int64"),
         ],
-        ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
+        ids=["list", "integer-array"],
     )
+    @pytest.mark.parametrize("box_in_series", [True, False])
     def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
         arr = data.copy()
 
-        # TODO(xfail) this raises KeyError about labels not found (it tries label-based)
-        # for list of labels with Series
+        msg = "Cannot index with an integer indexer containing NA values"
+        err = ValueError
+
         if box_in_series:
+            # The integer labels are not present in the (string) index, so
+            #  we get KeyErrors
             arr = pd.Series(data, index=[chr(100 + i) for i in range(len(data))])
+            msg = "0"
+            err = KeyError
 
-        msg = "Cannot index with an integer indexer containing NA values"
-        with pytest.raises(ValueError, match=msg):
+        with pytest.raises(err, match=msg):
             arr[idx] = arr[0]
 
     @pytest.mark.parametrize("as_callable", [True, False])
diff --git a/pandas/tests/extension/json/test_json.py b/pandas/tests/extension/json/test_json.py
@@ -356,18 +356,25 @@ def test_setitem_integer_array(self, data, idx, box_in_series, request):
             request.applymarker(mark)
         super().test_setitem_integer_array(data, idx, box_in_series)
 
-    @pytest.mark.xfail(reason="list indices must be integers or slices, not NAType")
     @pytest.mark.parametrize(
-        "idx, box_in_series",
+        "idx",
+        [
+            [0, 1, 2, pd.NA],
+            pd.array([0, 1, 2, pd.NA], dtype="Int64"),
+        ],
+        ids=["list", "integer-array"],
+    )
+    @pytest.mark.parametrize(
+        "box_in_series",
         [
-            ([0, 1, 2, pd.NA], False),
+            True,
             pytest.param(
-                [0, 1, 2, pd.NA], True, marks=pytest.mark.xfail(reason="GH-31948")
+                False,
+                marks=pytest.mark.xfail(
+                    reason="list indices must be integers or slices, not NAType"
+                ),
             ),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), False),
-            (pd.array([0, 1, 2, pd.NA], dtype="Int64"), True),
         ],
-        ids=["list-False", "list-True", "integer-array-False", "integer-array-True"],
     )
     def test_setitem_integer_with_missing_raises(self, data, idx, box_in_series):
         super().test_setitem_integer_with_missing_raises(data, idx, box_in_series)
diff --git a/pandas/tests/frame/methods/test_rename.py b/pandas/tests/frame/methods/test_rename.py
@@ -8,6 +8,7 @@
     DataFrame,
     Index,
     MultiIndex,
+    Series,
     merge,
 )
 import pandas._testing as tm
@@ -409,3 +410,33 @@ def test_rename_boolean_index(self):
             index=["foo", "bar", "bah"],
         )
         tm.assert_frame_equal(res, exp)
+
+    def test_rename_non_unique_index_series(self):
+        # GH#58621
+        df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
+        orig = df.copy(deep=True)
+
+        rename_series = Series(["X", "Y", "Z", "W"], index=["A", "B", "B", "C"])
+
+        msg = "Cannot rename with a Series with non-unique index"
+        with pytest.raises(ValueError, match=msg):
+            df.rename(rename_series)
+        with pytest.raises(ValueError, match=msg):
+            df.rename(columns=rename_series)
+        with pytest.raises(ValueError, match=msg):
+            df.rename(columns=rename_series, inplace=True)
+
+        # check we didn't corrupt the original
+        tm.assert_frame_equal(df, orig)
+
+        # Check the Series method while we're here
+        ser = df.iloc[0]
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(rename_series)
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(index=rename_series)
+        with pytest.raises(ValueError, match=msg):
+            ser.rename(index=rename_series, inplace=True)
+
+        # check we didn't corrupt the original
+        tm.assert_series_equal(ser, orig.iloc[0])
diff --git a/pandas/tests/indexes/datetimes/test_date_range.py b/pandas/tests/indexes/datetimes/test_date_range.py
@@ -215,7 +215,7 @@ def test_date_range_multiplication_overflow(self):
         # check that overflows in calculating `addend = periods * stride`
         #  are caught
         with tm.assert_produces_warning(None):
-            # we should _not_ be seeing a overflow RuntimeWarning
+            # we should _not_ be seeing an overflow RuntimeWarning
             dti = date_range(start="1677-09-22", periods=213503, freq="D")
 
         assert dti[0] == Timestamp("1677-09-22")
diff --git a/pandas/tests/reshape/test_melt.py b/pandas/tests/reshape/test_melt.py
@@ -933,7 +933,7 @@ def test_character_overlap(self):
         tm.assert_frame_equal(result.sort_index(axis=1), expected.sort_index(axis=1))
 
     def test_invalid_separator(self):
-        # if an invalid separator is supplied a empty data frame is returned
+        # if an invalid separator is supplied an empty data frame is returned
         sep = "nope!"
         df = DataFrame(
             {
diff --git a/pandas/tests/scalar/timestamp/test_constructors.py b/pandas/tests/scalar/timestamp/test_constructors.py
@@ -49,7 +49,7 @@ def test_constructor_int_float_with_YM_unit(self, typ):
 
     @pytest.mark.parametrize("typ", [int, float])
     def test_construct_from_int_float_with_unit_out_of_bound_raises(self, typ):
-        # GH#50870  make sure we get a OutOfBoundsDatetime instead of OverflowError
+        # GH#50870  make sure we get an OutOfBoundsDatetime instead of OverflowError
         val = typ(150000000000000)
 
         msg = f"cannot convert input {val} with the unit 'D'"
diff --git a/pandas/tests/util/test_shares_memory.py b/pandas/tests/util/test_shares_memory.py
@@ -30,3 +30,17 @@ def test_shares_memory_string():
 
     obj = pd.array(["a", "b"], dtype=pd.ArrowDtype(pa.string()))
     assert tm.shares_memory(obj, obj)
+
+
+def test_shares_memory_numpy():
+    arr = np.arange(10)
+    view = arr[:5]
+    assert tm.shares_memory(arr, view)
+    arr2 = np.arange(10)
+    assert not tm.shares_memory(arr, arr2)
+
+
+def test_shares_memory_rangeindex():
+    idx = pd.RangeIndex(10)
+    arr = np.arange(10)
+    assert not tm.shares_memory(idx, arr)
