Backport PR #57323 on branch 2.2.x (REGR: Fix regression when grouping over a Series) (#57339)

Backport PR #57323: REGR: Fix regression when grouping over a Series

Co-authored-by: Patrick Hoefler <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v2.2.1.rst

@@ -21,6 +21,7 @@ Fixed regressions
 - Fixed regression in :meth:`.DataFrameGroupBy.idxmin`, :meth:`.DataFrameGroupBy.idxmax`, :meth:`.SeriesGroupBy.idxmin`, :meth:`.SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`.DataFrameGroupBy.idxmin`, :meth:`.DataFrameGroupBy.idxmax`, :meth:`.SeriesGroupBy.idxmin`, :meth:`.SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)
 - Fixed regression in :meth:`CategoricalIndex.difference` raising ``KeyError`` when other contains null values other than NaN (:issue:`57318`)
+- Fixed regression in :meth:`DataFrame.groupby` raising ``ValueError`` when grouping by a :class:`Series` in some cases (:issue:`57276`)
 - Fixed regression in :meth:`DataFrame.loc` raising ``IndexError`` for non-unique, masked dtype indexes where result has more than 10,000 rows (:issue:`57027`)
 - Fixed regression in :meth:`DataFrame.merge` raising ``ValueError`` for certain types of 3rd-party extension arrays (:issue:`57316`)
 - Fixed regression in :meth:`DataFrame.sort_index` not producing a stable sort for a index with duplicates (:issue:`57151`)

pandas/core/internals/managers.py

@@ -12,7 +12,6 @@
     cast,
 )
 import warnings
-import weakref
 
 import numpy as np
 
@@ -282,8 +281,8 @@ def references_same_values(self, mgr: BaseBlockManager, blkno: int) -> bool:
         Checks if two blocks from two different block managers reference the
         same underlying values.
         """
-        ref = weakref.ref(self.blocks[blkno])
-        return ref in mgr.blocks[blkno].refs.referenced_blocks
+        blk = self.blocks[blkno]
+        return any(blk is ref() for ref in mgr.blocks[blkno].refs.referenced_blocks)
 
     def get_dtypes(self) -> npt.NDArray[np.object_]:
         dtypes = np.array([blk.dtype for blk in self.blocks], dtype=object)

pandas/tests/copy_view/test_methods.py

@@ -280,6 +280,17 @@ def test_reset_index_series_drop(using_copy_on_write, index):
     tm.assert_series_equal(ser, ser_orig)
 
 
+def test_groupby_column_index_in_references():
+    df = DataFrame(
+        {"A": ["a", "b", "c", "d"], "B": [1, 2, 3, 4], "C": ["a", "a", "b", "b"]}
+    )
+    df = df.set_index("A")
+    key = df["C"]
+    result = df.groupby(key, observed=True).sum()
+    expected = df.groupby("C", observed=True).sum()
+    tm.assert_frame_equal(result, expected)
+
+
 def test_rename_columns(using_copy_on_write):
     # Case: renaming columns returns a new dataframe
     # + afterwards modifying the result