BUG: GH12824 fixed apply() returns different result depending on whet…

doc/source/whatsnew/v0.18.2.txt

@@ -149,3 +149,4 @@ Bug Fixes
 - Bug in ``NaT`` - ``Period`` raises ``AttributeError`` (:issue:`13071`)
 - Bug in ``Period`` addition raises ``TypeError`` if ``Period`` is on right hand side (:issue:`13069`)
 - Bug in ``pd.set_eng_float_format()`` that would prevent NaN's from formatting (:issue:`11981`)
+- Bug in ``groupby`` where ``apply`` returns different result depending on whether first result is ``None`` or not (:issue:`12824`)

pandas/core/groupby.py

@@ -806,8 +806,9 @@ def reset_identity(values):
             # reset the identities of the components
             # of the values to prevent aliasing
             for v in values:
-                ax = v._get_axis(self.axis)
-                ax._reset_identity()
+                if v is not None:
+                    ax = v._get_axis(self.axis)
+                    ax._reset_identity()
             return values
 
         if not not_indexed_same:
@@ -3228,7 +3229,21 @@ def _wrap_applied_output(self, keys, values, not_indexed_same=False):
 
         key_names = self.grouper.names
 
-        if isinstance(values[0], DataFrame):
+        # GH12824.
+        def first_non_None_value(values):
+            try:
+                v = next(v for v in values if v is not None)
+            except StopIteration:
+                return None
+            return v
+
+        v = first_non_None_value(values)
+
+        if v is None:
+            # GH9684. If all values are None, then this will throw an error.
+            # We'd prefer it return an empty dataframe.
+            return DataFrame()
+        elif isinstance(v, DataFrame):
             return self._concat_objects(keys, values,
                                         not_indexed_same=not_indexed_same)
         elif self.grouper.groupings is not None:
@@ -3255,21 +3270,15 @@ def _wrap_applied_output(self, keys, values, not_indexed_same=False):
                     key_index = None
 
             # make Nones an empty object
-            if com._count_not_none(*values) != len(values):
-                try:
-                    v = next(v for v in values if v is not None)
-                except StopIteration:
-                    # If all values are None, then this will throw an error.
-                    # We'd prefer it return an empty dataframe.
-                    return DataFrame()
-                if v is None:
-                    return DataFrame()
-                elif isinstance(v, NDFrame):
-                    values = [
-                        x if x is not None else
-                        v._constructor(**v._construct_axes_dict())
-                        for x in values
-                    ]
+            v = first_non_None_value(values)
+            if v is None:
+                return DataFrame()
+            elif isinstance(v, NDFrame):
+                values = [
+                    x if x is not None else
+                    v._constructor(**v._construct_axes_dict())
+                    for x in values
+                ]
 
             v = values[0]
 

pandas/tests/test_groupby.py

@@ -6279,6 +6279,29 @@ def test_func(x):
         expected = DataFrame()
         tm.assert_frame_equal(result, expected)
 
+    def test_groupby_apply_none_first(self):
+        # GH 12824. Tests if apply returns None first.
+        test_df1 = DataFrame({'groups': [1, 1, 1, 2], 'vars': [0, 1, 2, 3]})
+        test_df2 = DataFrame({'groups': [1, 2, 2, 2], 'vars': [0, 1, 2, 3]})
+
+        def test_func(x):
+            if x.shape[0] < 2:
+                return None
+            return x.iloc[[0, -1]]
+
+        result1 = test_df1.groupby('groups').apply(test_func)
+        result2 = test_df2.groupby('groups').apply(test_func)
+        index1 = MultiIndex.from_arrays([[1, 1], [0, 2]],
+                                        names=['groups', None])
+        index2 = MultiIndex.from_arrays([[2, 2], [1, 3]],
+                                        names=['groups', None])
+        expected1 = DataFrame({'groups': [1, 1], 'vars': [0, 2]},
+                              index=index1)
+        expected2 = DataFrame({'groups': [2, 2], 'vars': [1, 3]},
+                              index=index2)
+        tm.assert_frame_equal(result1, expected1)
+        tm.assert_frame_equal(result2, expected2)
+
     def test_first_last_max_min_on_time_data(self):
         # GH 10295
         # Verify that NaT is not in the result of max, min, first and last on