Merge branch 'pandas-dev:main' into main

JoeDediop · web-flow · commit 9d40f2b4ac96 · 2025-08-07T14:55:31.000-07:00
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yaml b/.github/ISSUE_TEMPLATE/bug_report.yaml
@@ -26,7 +26,8 @@ body:
       label: Reproducible Example
       description: >
         Please follow [this guide](https://matthewrocklin.com/blog/work/2018/02/28/minimal-bug-reports) on how to
-        provide a minimal, copy-pastable example.
+        provide a minimal, copy-pastable example. Reports without reproducible examples will generally be closed
+        until they are provided.
       placeholder: >
         import pandas as pd
 
diff --git a/.github/ISSUE_TEMPLATE/documentation_improvement.yaml b/.github/ISSUE_TEMPLATE/documentation_improvement.yaml
@@ -28,7 +28,8 @@ body:
     attributes:
       label: Documentation problem
       description: >
-        Please provide a description of what documentation you believe needs to be fixed/improved
+        Please provide a description of what documentation you believe needs to be fixed/improved.
+        Reports without a clear, actionable request will generally be closed.
     validations:
       required: true
   - type: textarea
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yaml b/.github/ISSUE_TEMPLATE/feature_request.yaml
@@ -21,7 +21,8 @@ body:
     attributes:
       label: Problem Description
       description: >
-        Please describe what problem the feature would solve, e.g. "I wish I could use pandas to ..."
+        Please describe what problem the feature would solve, e.g. "I wish I could use pandas to ...".
+        Reports without a clear, actionable request will generally be closed.
       placeholder: >
         I wish I could use pandas to return a Series from a DataFrame when possible.
     validations:
diff --git a/.github/ISSUE_TEMPLATE/performance_issue.yaml b/.github/ISSUE_TEMPLATE/performance_issue.yaml
@@ -25,7 +25,9 @@ body:
       description: >
         Please provide a minimal, copy-pastable example that quantifies
         [slow runtime](https://docs.python.org/3/library/timeit.html) or
-        [memory](https://pypi.org/project/memory-profiler/) issues.
+        [memory](https://pypi.org/project/memory-profiler/) issues. Reports
+        without reproducible examples will generally be closed
+        until they are provided.
     validations:
       required: true
   - type: textarea
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -418,6 +418,7 @@ Other API changes
   an empty ``RangeIndex`` or empty ``Index`` with object dtype when determining
   the dtype of the resulting Index (:issue:`60797`)
 - :class:`IncompatibleFrequency` now subclasses ``TypeError`` instead of ``ValueError``. As a result, joins with mismatched frequencies now cast to object like other non-comparable joins, and arithmetic with indexes with mismatched frequencies align (:issue:`55782`)
+- :meth:`ExtensionDtype.construct_array_type` is now a regular method instead of a ``classmethod`` (:issue:`58663`)
 - Comparison operations between :class:`Index` and :class:`Series` now consistently return :class:`Series` regardless of which object is on the left or right (:issue:`36759`)
 - Numpy functions like ``np.isinf`` that return a bool dtype when called on a :class:`Index` object now return a bool-dtype :class:`Index` instead of ``np.ndarray`` (:issue:`52676`)
 
@@ -792,6 +793,7 @@ MultiIndex
 - Bug in :class:`DataFrame` arithmetic operations in case of unaligned MultiIndex columns (:issue:`60498`)
 - Bug in :class:`DataFrame` arithmetic operations with :class:`Series` in case of unaligned MultiIndex (:issue:`61009`)
 - Bug in :meth:`MultiIndex.from_tuples` causing wrong output with input of type tuples having NaN values (:issue:`60695`, :issue:`60988`)
+- Bug in :meth:`DataFrame.reindex` and :meth:`Series.reindex` where reindexing :class:`Index` to a :class:`MultiIndex` would incorrectly set all values to ``NaN``.(:issue:`60923`)
 
 I/O
 ^^^
diff --git a/pandas/core/arrays/boolean.py b/pandas/core/arrays/boolean.py
@@ -85,8 +85,7 @@ def kind(self) -> str:
     def numpy_dtype(self) -> np.dtype:
         return np.dtype("bool")
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[BooleanArray]:
+    def construct_array_type(self) -> type_t[BooleanArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/core/arrays/floating.py b/pandas/core/arrays/floating.py
@@ -28,8 +28,7 @@ class FloatingDtype(NumericDtype):
     _default_np_dtype = np.dtype(np.float64)
     _checker = is_float_dtype
 
-    @classmethod
-    def construct_array_type(cls) -> type[FloatingArray]:
+    def construct_array_type(self) -> type[FloatingArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/core/arrays/integer.py b/pandas/core/arrays/integer.py
@@ -28,8 +28,7 @@ class IntegerDtype(NumericDtype):
     _default_np_dtype = np.dtype(np.int64)
     _checker = is_integer_dtype
 
-    @classmethod
-    def construct_array_type(cls) -> type[IntegerArray]:
+    def construct_array_type(self) -> type[IntegerArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/core/arrays/numeric.py b/pandas/core/arrays/numeric.py
@@ -150,7 +150,7 @@ def _coerce_to_data_and_mask(
     if dtype is not None:
         dtype = dtype_cls._standardize_dtype(dtype)
 
-    cls = dtype_cls.construct_array_type()
+    cls = dtype_cls().construct_array_type()
     if isinstance(values, cls):
         values, mask = values._data, values._mask
         if dtype is not None:
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
@@ -283,12 +283,7 @@ def construct_from_string(cls, string) -> Self:
         else:
             raise TypeError(f"Cannot construct a '{cls.__name__}' from '{string}'")
 
-    # https://github.com/pandas-dev/pandas/issues/36126
-    # error: Signature of "construct_array_type" incompatible with supertype
-    # "ExtensionDtype"
-    def construct_array_type(  # type: ignore[override]
-        self,
-    ) -> type_t[BaseStringArray]:
+    def construct_array_type(self) -> type_t[BaseStringArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/core/dtypes/base.py b/pandas/core/dtypes/base.py
@@ -211,16 +211,15 @@ def names(self) -> list[str] | None:
         """
         return None
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[ExtensionArray]:
+    def construct_array_type(self) -> type_t[ExtensionArray]:
         """
         Return the array type associated with this dtype.
 
         Returns
         -------
         type
         """
-        raise AbstractMethodError(cls)
+        raise AbstractMethodError(self)
 
     def empty(self, shape: Shape) -> ExtensionArray:
         """
diff --git a/pandas/core/dtypes/dtypes.py b/pandas/core/dtypes/dtypes.py
@@ -527,8 +527,7 @@ def _hash_categories(self) -> int:
         combined_hashed = combine_hash_arrays(iter(cat_array), num_items=len(cat_array))
         return np.bitwise_xor.reduce(combined_hashed)
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[Categorical]:
+    def construct_array_type(self) -> type_t[Categorical]:
         """
         Return the array type associated with this dtype.
 
@@ -856,8 +855,7 @@ def tz(self) -> tzinfo:
         """
         return self._tz
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[DatetimeArray]:
+    def construct_array_type(self) -> type_t[DatetimeArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1174,8 +1172,7 @@ def is_dtype(cls, dtype: object) -> bool:
                 return False
         return super().is_dtype(dtype)
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[PeriodArray]:
+    def construct_array_type(self) -> type_t[PeriodArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1363,8 +1360,7 @@ def subtype(self):
         """
         return self._subtype
 
-    @classmethod
-    def construct_array_type(cls) -> type[IntervalArray]:
+    def construct_array_type(self) -> type[IntervalArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1576,8 +1572,7 @@ def construct_from_string(cls, string: str) -> NumpyEADtype:
             raise TypeError(msg) from err
         return cls(dtype)
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[NumpyExtensionArray]:
+    def construct_array_type(self) -> type_t[NumpyExtensionArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1649,8 +1644,7 @@ def itemsize(self) -> int:
         """Return the number of bytes in this dtype"""
         return self.numpy_dtype.itemsize
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[BaseMaskedArray]:
+    def construct_array_type(self) -> type_t[BaseMaskedArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1914,8 +1908,7 @@ def name(self) -> str:
     def __repr__(self) -> str:
         return self.name
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[SparseArray]:
+    def construct_array_type(self) -> type_t[SparseArray]:
         """
         Return the array type associated with this dtype.
 
@@ -2316,8 +2309,7 @@ def itemsize(self) -> int:
         """Return the number of bytes in this dtype"""
         return self.numpy_dtype.itemsize
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[ArrowExtensionArray]:
+    def construct_array_type(self) -> type_t[ArrowExtensionArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -5373,6 +5373,18 @@ def reindex(
         """
         # TODO: Decide if we care about having different examples for different
         # kinds
+
+        # Automatically detect matching level when reindexing from Index to MultiIndex.
+        # This prevents values from being incorrectly set to NaN when the source index
+        # name matches a index name in the target MultiIndex
+        if (
+            level is None
+            and index is not None
+            and isinstance(index, MultiIndex)
+            and not isinstance(self.index, MultiIndex)
+            and self.index.name in index.names
+        ):
+            level = self.index.name
         self._check_copy_deprecation(copy)
 
         if index is not None and columns is not None and labels is not None:
diff --git a/pandas/tests/arrays/test_array.py b/pandas/tests/arrays/test_array.py
@@ -487,8 +487,7 @@ def test_bounds_check():
 class DecimalDtype2(DecimalDtype):
     name = "decimal2"
 
-    @classmethod
-    def construct_array_type(cls):
+    def construct_array_type(self):
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/tests/dtypes/test_common.py b/pandas/tests/dtypes/test_common.py
@@ -576,8 +576,7 @@ def type(self):
         def name(self):
             raise NotImplementedError
 
-        @classmethod
-        def construct_array_type(cls):
+        def construct_array_type(self):
             raise NotImplementedError
 
         def _is_numeric(self) -> bool:
diff --git a/pandas/tests/extension/array_with_attr/array.py b/pandas/tests/extension/array_with_attr/array.py
@@ -24,8 +24,7 @@ class FloatAttrDtype(ExtensionDtype):
     name = "float_attr"
     na_value = np.nan
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[FloatAttrArray]:
+    def construct_array_type(self) -> type_t[FloatAttrArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/tests/extension/date/array.py b/pandas/tests/extension/date/array.py
@@ -48,8 +48,7 @@ def construct_from_string(cls, string: str):
         else:
             raise TypeError(f"Cannot construct a '{cls.__name__}' from '{string}'")
 
-    @classmethod
-    def construct_array_type(cls):
+    def construct_array_type(self):
         return DateArray
 
     @property
diff --git a/pandas/tests/extension/decimal/array.py b/pandas/tests/extension/decimal/array.py
@@ -50,8 +50,7 @@ def __init__(self, context=None) -> None:
     def __repr__(self) -> str:
         return f"DecimalDtype(context={self.context})"
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[DecimalArray]:
+    def construct_array_type(self) -> type_t[DecimalArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/tests/extension/decimal/test_decimal.py b/pandas/tests/extension/decimal/test_decimal.py
@@ -286,8 +286,7 @@ def test_combine_from_sequence_raises(monkeypatch):
     # https://github.com/pandas-dev/pandas/issues/22850
     cls = DecimalArrayWithoutFromSequence
 
-    @classmethod
-    def construct_array_type(cls):
+    def construct_array_type(self):
         return DecimalArrayWithoutFromSequence
 
     monkeypatch.setattr(DecimalDtype, "construct_array_type", construct_array_type)
diff --git a/pandas/tests/extension/json/array.py b/pandas/tests/extension/json/array.py
@@ -54,8 +54,7 @@ class JSONDtype(ExtensionDtype):
     name = "json"
     na_value: Mapping[str, Any] = UserDict()
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[JSONArray]:
+    def construct_array_type(self) -> type_t[JSONArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/tests/extension/list/array.py b/pandas/tests/extension/list/array.py
@@ -30,8 +30,7 @@ class ListDtype(ExtensionDtype):
     name = "list"
     na_value = np.nan
 
-    @classmethod
-    def construct_array_type(cls) -> type_t[ListArray]:
+    def construct_array_type(self) -> type_t[ListArray]:
         """
         Return the array type associated with this dtype.
 
diff --git a/pandas/tests/frame/methods/test_astype.py b/pandas/tests/frame/methods/test_astype.py
@@ -857,8 +857,7 @@ def copy(self):
 class Int16DtypeNoCopy(pd.Int16Dtype):
     # GH 42501
 
-    @classmethod
-    def construct_array_type(cls):
+    def construct_array_type(self):
         return IntegerArrayNoCopy
 
 
diff --git a/pandas/tests/frame/methods/test_reindex.py b/pandas/tests/frame/methods/test_reindex.py
@@ -1258,3 +1258,31 @@ def test_invalid_method(self):
         msg = "Invalid fill method"
         with pytest.raises(ValueError, match=msg):
             df.reindex([1, 0, 2], method="asfreq")
+
+    def test_reindex_index_name_matches_multiindex_level(self):
+        df = DataFrame(
+            {"value": [1, 2], "other": ["A", "B"]},
+            index=Index([10, 20], name="a"),
+        )
+        target = MultiIndex.from_product(
+            [[10, 20], ["x", "y"]],
+            names=["a", "b"],
+        )
+
+        result = df.reindex(index=target)
+        expected = DataFrame(
+            data={"value": [1, 1, 2, 2], "other": ["A", "A", "B", "B"]},
+            index=MultiIndex.from_product([[10, 20], ["x", "y"]], names=["a", "b"]),
+        )
+        tm.assert_frame_equal(result, expected)
+
+    def test_reindex_index_name_no_match_multiindex_level(self):
+        df = DataFrame({"value": [1, 2]}, index=Index([10, 20], name="different_name"))
+        target = MultiIndex.from_product([[10, 20], ["x", "y"]], names=["a", "b"])
+
+        result = df.reindex(index=target)
+        expected = DataFrame(
+            data={"value": [np.nan] * 4},
+            index=MultiIndex.from_product([[10, 20], ["x", "y"]], names=["a", "b"]),
+        )
+        tm.assert_frame_equal(result, expected)
diff --git a/pandas/tests/series/methods/test_reindex.py b/pandas/tests/series/methods/test_reindex.py
@@ -434,3 +434,41 @@ def test_reindex_expand_nonnano_nat(dtype):
         np.array([1, getattr(np, dtype)("nat", "s")], dtype=f"{dtype}[s]")
     )
     tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "name, expected_match_level_a",
+    [
+        ("a", True),
+        (None, False),
+        ("x", False),
+    ],
+)
+def test_reindex_multiindex_automatic_level(name, expected_match_level_a):
+    series = Series([26.73, 24.255], index=Index([81, 82], name=name))
+    target = MultiIndex.from_product(
+        [[81, 82], [np.nan], ["2018-06-01", "2018-07-01"]], names=["a", "b", "c"]
+    )
+
+    result = series.reindex(target)
+
+    if expected_match_level_a:
+        expected = Series(
+            data=[26.73, 26.73, 24.255, 24.255],
+            index=MultiIndex.from_product(
+                [[81, 82], [np.nan], ["2018-06-01", "2018-07-01"]],
+                names=["a", "b", "c"],
+            ),
+            dtype=series.dtype,
+        )
+    else:
+        expected = Series(
+            data=[np.nan] * 4,
+            index=MultiIndex.from_product(
+                [[81, 82], [np.nan], ["2018-06-01", "2018-07-01"]],
+                names=["a", "b", "c"],
+            ),
+            dtype=series.dtype,
+        )
+
+    tm.assert_series_equal(result, expected)
