Backport PR #32561: Ensure valid Block mutation in SeriesBinGrouper. (#32635)

Co-authored-by: Tom Augspurger <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.0.2.rst

@@ -20,6 +20,7 @@ Fixed regressions
 - Fixed regression in ``groupby(..).rolling(..).apply()`` (``RollingGroupby``) where the ``raw`` parameter was ignored (:issue:`31754`)
 - Fixed regression in :meth:`rolling(..).corr() <pandas.core.window.rolling.Rolling.corr>` when using a time offset (:issue:`31789`)
 - Fixed regression in :meth:`groupby(..).nunique() <pandas.core.groupby.DataFrameGroupBy.nunique>` which was modifying the original values if ``NaN`` values were present (:issue:`31950`)
+- Fixed regression in ``DataFrame.groupby`` raising a ``ValueError`` from an internal operation (:issue:`31802`)
 - Fixed regression where :func:`read_pickle` raised a ``UnicodeDecodeError`` when reading a py27 pickle with :class:`MultiIndex` column (:issue:`31988`).
 - Fixed regression in :class:`DataFrame` arithmetic operations with mis-matched columns (:issue:`31623`)
 - Fixed regression in :meth:`groupby(..).agg() <pandas.core.groupby.GroupBy.agg>` calling a user-provided function an extra time on an empty input (:issue:`31760`)

pandas/_libs/reduction.pyx

@@ -177,6 +177,8 @@ cdef class _BaseGrouper:
             object.__setattr__(cached_ityp, '_index_data', islider.buf)
             cached_ityp._engine.clear_mapping()
             object.__setattr__(cached_typ._data._block, 'values', vslider.buf)
+            object.__setattr__(cached_typ._data._block, 'mgr_locs',
+                               slice(len(vslider.buf)))
             object.__setattr__(cached_typ, '_index', cached_ityp)
             object.__setattr__(cached_typ, 'name', self.name)
 

pandas/tests/groupby/test_bin_groupby.py

@@ -5,6 +5,7 @@
 
 from pandas.core.dtypes.common import ensure_int64
 
+import pandas as pd
 from pandas import Index, Series, isna
 import pandas._testing as tm
 
@@ -51,6 +52,30 @@ def test_series_bin_grouper():
     tm.assert_almost_equal(counts, exp_counts)
 
 
+def assert_block_lengths(x):
+    assert len(x) == len(x._data.blocks[0].mgr_locs)
+    return 0
+
+
+def cumsum_max(x):
+    x.cumsum().max()
+    return 0
+
+
+@pytest.mark.parametrize("func", [cumsum_max, assert_block_lengths])
+def test_mgr_locs_updated(func):
+    # https://github.com/pandas-dev/pandas/issues/31802
+    # Some operations may require creating new blocks, which requires
+    # valid mgr_locs
+    df = pd.DataFrame({"A": ["a", "a", "a"], "B": ["a", "b", "b"], "C": [1, 1, 1]})
+    result = df.groupby(["A", "B"]).agg(func)
+    expected = pd.DataFrame(
+        {"C": [0, 0]},
+        index=pd.MultiIndex.from_product([["a"], ["a", "b"]], names=["A", "B"]),
+    )
+    tm.assert_frame_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "binner,closed,expected",
     [