BUG: Fix groupby.apply() dropping metadata from subclassed DataFrames (#62134) (#62408)

Author: vgnshiyer

doc/source/whatsnew/v3.0.0.rst

@@ -1068,6 +1068,7 @@ Groupby/resample/rolling
 - 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.agg` where applying a user-defined function to an empty DataFrame returned a Series instead of an empty DataFrame. (:issue:`61503`)
 - 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` and :meth:`SeriesGroupBy.apply` not preserving ``_metadata`` attributes from subclassed DataFrames and Series (:issue:`62134`)
 - 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

@@ -621,7 +621,7 @@ def _wrap_applied_output(
             if not self.as_index and not_indexed_same:
                 result = self._insert_inaxis_grouper(result)
                 result.index = default_index(len(result))
-            return result
+            return result.__finalize__(self.obj, method="groupby")
         else:
             # GH #6265 #24880
             result = self.obj._constructor(
@@ -630,7 +630,7 @@ def _wrap_applied_output(
             if not self.as_index:
                 result = self._insert_inaxis_grouper(result)
                 result.index = default_index(len(result))
-            return result
+            return result.__finalize__(self.obj, method="groupby")
 
     __examples_series_doc = dedent(
         """
@@ -2169,7 +2169,7 @@ def _wrap_applied_output_series(
         if not self.as_index:
             result = self._insert_inaxis_grouper(result)
 
-        return result
+        return result.__finalize__(self.obj, method="groupby")
 
     def _cython_transform(
         self,

pandas/core/groupby/groupby.py

@@ -1188,7 +1188,7 @@ def _concat_objects(
         if isinstance(result, Series) and name is not None:
             result.name = name
 
-        return result
+        return result.__finalize__(self.obj, method="groupby")
 
     @final
     def _set_result_index_ordered(

pandas/tests/groupby/test_groupby_subclass.py

@@ -98,6 +98,35 @@ def func2(group):
     tm.assert_series_equal(result, expected)
 
 
+def test_groupby_apply_preserves_metadata():
+    # GH#62134 - Test that apply() preserves metadata when returning DataFrames/Series
+    custom_df = tm.SubclassedDataFrame({"a": [1, 2, 3], "b": [1, 1, 2], "c": [7, 8, 9]})
+    custom_df.testattr = "hello"
+
+    def sum_func(group):
+        assert isinstance(group, tm.SubclassedDataFrame)
+        assert hasattr(group, "testattr")
+        assert group.testattr == "hello"
+        return group.sum()
+
+    result = custom_df.groupby("c").apply(sum_func)
+    assert hasattr(result, "testattr"), "DataFrame apply() should preserve metadata"
+    assert result.testattr == "hello"
+
+    custom_series = tm.SubclassedSeries([1, 2, 3])
+    custom_series.testattr = "hello"
+
+    def sum_series_func(group):
+        assert isinstance(group, tm.SubclassedSeries)
+        assert hasattr(group, "testattr")
+        assert group.testattr == "hello"
+        return group.sum()
+
+    result = custom_series.groupby(custom_df["c"]).apply(sum_series_func)
+    assert hasattr(result, "testattr"), "Series apply() should preserve metadata"
+    assert result.testattr == "hello"
+
+
 @pytest.mark.parametrize("obj", [DataFrame, tm.SubclassedDataFrame])
 def test_groupby_resample_preserves_subclass(obj):
     # GH28330 -- preserve subclass through groupby.resample()