BUG: Fix bug in GroupBy that ignores group_keys arg for empty datafra… (pandas-dev#60505)

BUG: Fix bug in GroupBy that ignores group_keys arg for empty dataframes/series

Author: snitish

doc/source/whatsnew/v3.0.0.rst

@@ -733,6 +733,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)
 - Bug in :meth:`DataFrameGroupBy.agg` that raises ``AttributeError`` when there is dictionary input and duplicated columns, instead of returning a DataFrame with the aggregation of all duplicate columns. (:issue:`55041`)
+- Bug in :meth:`DataFrameGroupBy.apply` and :meth:`SeriesGroupBy.apply` for empty data frame with ``group_keys=False`` still creating output index using group keys. (:issue:`60471`)
 - Bug in :meth:`DataFrameGroupBy.apply` that was returning a completely empty DataFrame when all return values of ``func`` were ``None`` instead of returning an empty DataFrame with the original columns and dtypes. (:issue:`57775`)
 - Bug in :meth:`DataFrameGroupBy.apply` with ``as_index=False`` that was returning :class:`MultiIndex` instead of returning :class:`Index`. (:issue:`58291`)
 - Bug in :meth:`DataFrameGroupBy.cumsum` and :meth:`DataFrameGroupBy.cumprod` where ``numeric_only`` parameter was passed indirectly through kwargs instead of passing directly. (:issue:`58811`)

pandas/core/groupby/generic.py

@@ -583,6 +583,8 @@ def _wrap_applied_output(
             if is_transform:
                 # GH#47787 see test_group_on_empty_multiindex
                 res_index = data.index
+            elif not self.group_keys:
+                res_index = None
             else:
                 res_index = self._grouper.result_index
 
@@ -1967,6 +1969,8 @@ def _wrap_applied_output(
             if is_transform:
                 # GH#47787 see test_group_on_empty_multiindex
                 res_index = data.index
+            elif not self.group_keys:
+                res_index = None
             else:
                 res_index = self._grouper.result_index
 

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -159,6 +159,7 @@ def test_agg_apply_corner(ts, tsframe):
     tm.assert_frame_equal(grouped.agg("sum"), exp_df)
 
     res = grouped.apply(np.sum, axis=0)
+    exp_df = exp_df.reset_index(drop=True)
     tm.assert_frame_equal(res, exp_df)
 
 

pandas/tests/groupby/test_all_methods.py

@@ -22,7 +22,7 @@
 def test_multiindex_group_all_columns_when_empty(groupby_func):
     # GH 32464
     df = DataFrame({"a": [], "b": [], "c": []}).set_index(["a", "b", "c"])
-    gb = df.groupby(["a", "b", "c"], group_keys=False)
+    gb = df.groupby(["a", "b", "c"], group_keys=True)
     method = getattr(gb, groupby_func)
     args = get_groupby_method_args(groupby_func, df)
     if groupby_func == "corrwith":

pandas/tests/groupby/test_grouping.py

@@ -777,10 +777,21 @@ def test_evaluate_with_empty_groups(self, func, expected):
         # (not testing other agg fns, because they return
         # different index objects.
         df = DataFrame({1: [], 2: []})
-        g = df.groupby(1, group_keys=False)
+        g = df.groupby(1, group_keys=True)
         result = getattr(g[2], func)(lambda x: x)
         tm.assert_series_equal(result, expected)
 
+    def test_groupby_apply_empty_with_group_keys_false(self):
+        # 60471
+        # test apply'ing empty groups with group_keys False
+        # (not testing other agg fns, because they return
+        # different index objects.
+        df = DataFrame({"A": [], "B": [], "C": []})
+        g = df.groupby("A", group_keys=False)
+        result = g.apply(lambda x: x / x.sum(), include_groups=False)
+        expected = DataFrame({"B": [], "C": []}, index=None)
+        tm.assert_frame_equal(result, expected)
+
     def test_groupby_empty(self):
         # https://github.com/pandas-dev/pandas/issues/27190
         s = Series([], name="name", dtype="float64")