Backport PR #52850 on branch 2.0.x (REGR: SeriesGroupBy.agg with mult…

…iple categoricals, as_index=False, and a list fails) (#52854)

* REGR: SeriesGroupBy.agg with multiple categoricals, as_index=False, and a list fails (#52850)

(cherry picked from commit 2ac0da4)

* Fixup for 2.0.x

---------

Co-authored-by: Richard Shadrach <45562402+rhshadrach@users.noreply.github.com>

doc/source/whatsnew/v2.0.1.rst

@@ -19,6 +19,7 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.sort_values` not resetting index when :class:`DataFrame` is already sorted and ``ignore_index=True`` (:issue:`52553`)
 - Fixed regression in :meth:`MultiIndex.isin` raising ``TypeError`` for ``Generator`` (:issue:`52568`)
 - Fixed regression in :meth:`Series.describe` showing ``RuntimeWarning`` for extension dtype :class:`Series` with one element (:issue:`52515`)
+- Fixed regression in :meth:`SeriesGroupBy.agg` failing when grouping with categorical data, multiple groupings, ``as_index=False``, and a list of aggregations (:issue:`52760`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_201.bug_fixes:

pandas/core/groupby/generic.py

@@ -241,8 +241,7 @@ def aggregate(self, func=None, *args, engine=None, engine_kwargs=None, **kwargs)
                 assert columns is not None  # for mypy
                 ret.columns = columns
             if not self.as_index:
-                ret = self._insert_inaxis_grouper(ret)
-                ret.index = default_index(len(ret))
+                ret = ret.reset_index()
             return ret
 
         else:
@@ -328,7 +327,6 @@ def _aggregate_multiple_funcs(self, arg, *args, **kwargs) -> DataFrame:
         output = self.obj._constructor_expanddim(indexed_output, index=None)
         output.columns = Index(key.label for key in results)
 
-        output = self._reindex_output(output)
         return output
 
     def _wrap_applied_output(

pandas/tests/groupby/test_categorical.py

@@ -14,6 +14,7 @@
     qcut,
 )
 import pandas._testing as tm
+from pandas.core.groupby.generic import SeriesGroupBy
 from pandas.tests.groupby import get_groupby_method_args
 
 
@@ -2007,3 +2008,50 @@ def test_many_categories(as_index, sort, index_kind, ordered):
         expected = DataFrame({"a": Series(index), "b": data})
 
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("test_series", [True, False])
+@pytest.mark.parametrize("keys", [["a1"], ["a1", "a2"]])
+def test_agg_list(request, as_index, observed, reduction_func, test_series, keys):
+    # GH#52760
+    if test_series and reduction_func == "corrwith":
+        assert not hasattr(SeriesGroupBy, "corrwith")
+        pytest.skip("corrwith not implemented for SeriesGroupBy")
+    elif reduction_func == "corrwith":
+        msg = "GH#32293: attempts to call SeriesGroupBy.corrwith"
+        request.node.add_marker(pytest.mark.xfail(reason=msg))
+    elif (
+        reduction_func == "nunique"
+        and not test_series
+        and len(keys) != 1
+        and not observed
+        and not as_index
+    ):
+        msg = "GH#52848 - raises a ValueError"
+        request.node.add_marker(pytest.mark.xfail(reason=msg))
+
+    df = DataFrame({"a1": [0, 0, 1], "a2": [2, 3, 3], "b": [4, 5, 6]})
+    df = df.astype({"a1": "category", "a2": "category"})
+    if "a2" not in keys:
+        df = df.drop(columns="a2")
+    gb = df.groupby(by=keys, as_index=as_index, observed=observed)
+    if test_series:
+        gb = gb["b"]
+    args = get_groupby_method_args(reduction_func, df)
+
+    result = gb.agg([reduction_func], *args)
+    expected = getattr(gb, reduction_func)(*args)
+
+    if as_index and (test_series or reduction_func == "size"):
+        expected = expected.to_frame(reduction_func)
+    if not test_series:
+        if not as_index:
+            # TODO: GH#52849 - as_index=False is not respected
+            expected = expected.set_index(keys)
+        expected.columns = MultiIndex(
+            levels=[["b"], [reduction_func]], codes=[[0], [0]]
+        )
+    elif not as_index:
+        expected.columns = keys + [reduction_func]
+
+    tm.assert_equal(result, expected)