FIX groupby apply ignores as_index

Author: hayd

doc/source/release.rst

@@ -217,6 +217,7 @@ See :ref:`Internal Refactoring<whatsnew_0130.refactoring>`
     of a duplicate index (:issue:`4359`)
   - In ``to_json``, fix date handling so milliseconds are the default timestamp
     as the docstring says (:issue:`4362`).
+  - ``as_index`` is no longer ignored when doing groupby apply (:issue:`4648`), (:issue:`3417`)
   - JSON NaT handling fixed, NaTs are now serialised to `null` (:issue:`4498`)
   - Fixed JSON handling of escapable characters in JSON object keys (:issue:`4593`)
   - Fixed passing ``keep_default_na=False`` when ``na_values=None`` (:issue:`4318`)

pandas/core/groupby.py

@@ -516,7 +516,7 @@ def _concat_objects(self, keys, values, not_indexed_same=False):
                 result = result.reindex(ax)
             else:
                 result = result.reindex_axis(ax, axis=self.axis)
-        elif self.group_keys:
+        elif self.group_keys and self.as_index:
             group_keys = keys
             group_levels = self.grouper.levels
             group_names = self.grouper.names

pandas/tests/test_groupby.py

@@ -12,7 +12,8 @@
 from pandas.core.groupby import GroupByError, SpecificationError, DataError
 from pandas.core.series import Series
 from pandas.util.testing import (assert_panel_equal, assert_frame_equal,
-                                 assert_series_equal, assert_almost_equal)
+                                 assert_series_equal, assert_almost_equal,
+                                 assert_index_equal)
 from pandas.compat import(
     range, long, lrange, StringIO, lmap, lzip, map, zip, builtins, OrderedDict
 )
@@ -1178,6 +1179,30 @@ def test_groupby_as_index_corner(self):
         self.assertRaises(ValueError, self.df.groupby,
                           lambda x: x.lower(), as_index=False, axis=1)
 
+    def test_groupby_as_index_apply(self):
+        # GH #4648 and #3417
+        df = DataFrame({'item_id': ['b', 'b', 'a', 'c', 'a', 'b'],
+                        'user_id': [1,2,1,1,3,1],
+                        'time': range(6)})
+
+        g_as = df.groupby('user_id', as_index=True)
+        g_not_as = df.groupby('user_id', as_index=False)
+
+        res_as = g_as.head(2).index
+        exp_as = MultiIndex.from_tuples([(1, 0), (1, 2), (2, 1), (3, 4)])
+        assert_index_equal(res_as, exp_as)
+
+        res_not_as = g_not_as.head(2).index
+        exp_not_as = Index([0, 2, 1, 4])
+        assert_index_equal(res_not_as, exp_not_as)
+
+        res_as = g_as.apply(lambda x: x.head(2)).index
+        assert_index_equal(res_not_as, exp_not_as)
+
+        res_not_as = g_not_as.apply(lambda x: x.head(2)).index
+        assert_index_equal(res_not_as, exp_not_as)
+
+
     def test_groupby_multiple_key(self):
         df = tm.makeTimeDataFrame()
         grouped = df.groupby([lambda x: x.year,