Backport PR pandas-dev#31668: REGR: Fixed handling of Categorical in cython ops (pandas-dev#31678)

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

Author: meeseeksmachine

doc/source/whatsnew/v1.0.1.rst

@@ -19,6 +19,7 @@ Fixed regressions
 - Fixed regression when indexing a ``Series`` or ``DataFrame`` indexed by ``DatetimeIndex`` with a slice containg a :class:`datetime.date` (:issue:`31501`)
 - Fixed regression in ``DataFrame.__setitem__`` raising an ``AttributeError`` with a :class:`MultiIndex` and a non-monotonic indexer (:issue:`31449`)
 - Fixed regression in :class:`Series` multiplication when multiplying a numeric :class:`Series` with >10000 elements with a timedelta-like scalar (:issue:`31457`)
+- Fixed regression in ``.groupby()`` aggregations with categorical dtype using Cythonized reduction functions (e.g. ``first``) (:issue:`31450`)
 - Fixed regression in :meth:`GroupBy.apply` if called with a function which returned a non-pandas non-scalar object (e.g. a list or numpy array) (:issue:`31441`)
 - Fixed regression in :meth:`DataFrame.groupby` whereby taking the minimum or maximum of a column with period dtype would raise a ``TypeError``. (:issue:`31471`)
 - Fixed regression in :meth:`to_datetime` when parsing non-nanosecond resolution datetimes (:issue:`31491`)

pandas/core/groupby/groupby.py

@@ -1379,7 +1379,9 @@ def f(self, **kwargs):
                 except DataError:
                     pass
                 except NotImplementedError as err:
-                    if "function is not implemented for this dtype" in str(err):
+                    if "function is not implemented for this dtype" in str(
+                        err
+                    ) or "category dtype not supported" in str(err):
                         # raised in _get_cython_function, in some cases can
                         #  be trimmed by implementing cython funcs for more dtypes
                         pass

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -378,6 +378,22 @@ def test_agg_index_has_complex_internals(index):
     tm.assert_frame_equal(result, expected)
 
 
+def test_agg_cython_category_not_implemented_fallback():
+    # https://github.com/pandas-dev/pandas/issues/31450
+    df = pd.DataFrame({"col_num": [1, 1, 2, 3]})
+    df["col_cat"] = df["col_num"].astype("category")
+
+    result = df.groupby("col_num").col_cat.first()
+    expected = pd.Series(
+        [1, 2, 3], index=pd.Index([1, 2, 3], name="col_num"), name="col_cat"
+    )
+    tm.assert_series_equal(result, expected)
+
+    result = df.groupby("col_num").agg({"col_cat": "first"})
+    expected = expected.to_frame()
+    tm.assert_frame_equal(result, expected)
+
+
 class TestNamedAggregationSeries:
     def test_series_named_agg(self):
         df = pd.Series([1, 2, 3, 4])