Bug: Grouping by index and column fails on DataFrame with single index (GH14327)

doc/source/whatsnew/v0.19.0.txt

@@ -1584,3 +1584,4 @@ Bug Fixes
 - ``PeridIndex`` can now accept ``list`` and ``array`` which contains ``pd.NaT`` (:issue:`13430`)
 - Bug in ``df.groupby`` where ``.median()`` returns arbitrary values if grouped dataframe contains empty bins (:issue:`13629`)
 - Bug in ``Index.copy()`` where ``name`` parameter was ignored (:issue:`14302`)
+- Bug in ``df.groupby`` causing an ``AttributeError`` when grouping a single index frame by a column and the index (:issue`14327`)

pandas/core/groupby.py

@@ -2201,36 +2201,45 @@ def __init__(self, index, grouper=None, obj=None, name=None, level=None,
                     raise AssertionError('Level %s not in index' % str(level))
                 level = index.names.index(level)
 
-            inds = index.labels[level]
-            level_index = index.levels[level]
-
             if self.name is None:
                 self.name = index.names[level]
 
-            # XXX complete hack
+            if isinstance(index, MultiIndex):
+                inds = index.labels[level]
+                level_index = index.levels[level]
 
-            if grouper is not None:
-                level_values = index.levels[level].take(inds)
-                self.grouper = level_values.map(self.grouper)
-            else:
-                # all levels may not be observed
-                labels, uniques = algos.factorize(inds, sort=True)
+                # XXX complete hack
+
+                if grouper is not None:
+                    level_values = index.levels[level].take(inds)
+                    self.grouper = level_values.map(self.grouper)
+                else:
+                    # all levels may not be observed
+                    labels, uniques = algos.factorize(inds, sort=True)
 
-                if len(uniques) > 0 and uniques[0] == -1:
-                    # handle NAs
-                    mask = inds != -1
-                    ok_labels, uniques = algos.factorize(inds[mask], sort=True)
+                    if len(uniques) > 0 and uniques[0] == -1:
+                        # handle NAs
+                        mask = inds != -1
+                        ok_labels, uniques = algos.factorize(inds[mask],
+                                                             sort=True)
 
-                    labels = np.empty(len(inds), dtype=inds.dtype)
-                    labels[mask] = ok_labels
-                    labels[~mask] = -1
+                        labels = np.empty(len(inds), dtype=inds.dtype)
+                        labels[mask] = ok_labels
+                        labels[~mask] = -1
 
-                if len(uniques) < len(level_index):
-                    level_index = level_index.take(uniques)
+                    if len(uniques) < len(level_index):
+                        level_index = level_index.take(uniques)
+
+                    self._labels = labels
+                    self._group_index = level_index
+                    self.grouper = level_index.take(labels)
+
+            # Single level index passed
+            else:
+                # Use single level index as grouper if none passed
+                if grouper is None:
+                    self.grouper = index
 
-                self._labels = labels
-                self._group_index = level_index
-                self.grouper = level_index.take(labels)
         else:
             if isinstance(self.grouper, (list, tuple)):
                 self.grouper = com._asarray_tuplesafe(self.grouper)

pandas/tests/test_groupby.py

@@ -458,6 +458,28 @@ def test_grouper_creation_bug(self):
         expected = s.groupby(level='one').sum()
         assert_series_equal(result, expected)
 
+    def test_grouper_column_and_index(self):
+        # GH 14327
+
+        # Grouping a multi-index frame by a column and an index level should
+        # be equivalent to resetting the index and grouping by two columns
+        idx = pd.MultiIndex.from_tuples([('a', 1), ('a', 2), ('a', 3),
+                                         ('b', 1), ('b', 2), ('b', 3)])
+        idx.names = ['outer', 'inner']
+        df_multi = pd.DataFrame({"A": np.arange(6),
+                                 'B': ['one', 'one', 'two',
+                                       'two', 'one', 'one']},
+                                index=idx)
+        result = df_multi.groupby(['B', pd.Grouper(level='inner')]).mean()
+        expected = df_multi.reset_index().groupby(['B', 'inner']).mean()
+        assert_frame_equal(result, expected)
+
+        # Grouping a single-index frame by a column and the index should
+        # be equivalent to resetting the index and grouping by two columns
+        df_single = df_multi.reset_index('outer')
+        result = df_single.groupby(['B', pd.Grouper(level='inner')]).mean()
+        assert_frame_equal(result, expected)
+
     def test_grouper_getting_correct_binner(self):
 
         # GH 10063