Added test cases for GH 5677

Author: Jon M. Mease

pandas/tests/test_groupby.py

@@ -491,6 +491,146 @@ def test_grouper_column_and_index(self):
         expected = df_single.reset_index().groupby(['inner', 'B']).mean()
         assert_frame_equal(result, expected)
 
+    def test_grouper_column_and_index_sugar(self):
+        # GH 5677, allow strings passed as the `by` parameter to reference
+        # columns or index levels
+
+        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)
+
+        df_single = df_multi.reset_index('outer')
+
+        # Column and Index on MultiIndex
+        result = df_multi.groupby(['B', 'inner']).mean()
+        expected = df_multi.groupby(['B', pd.Grouper(level='inner')]).mean()
+        assert_frame_equal(result, expected)
+
+        # Index and Column on MultiIndex
+        result = df_multi.groupby(['inner', 'B']).mean()
+        expected = df_multi.groupby([pd.Grouper(level='inner'), 'B']).mean()
+        assert_frame_equal(result, expected)
+
+        # Column and Index on single Index
+        result = df_single.groupby(['B', 'inner']).mean()
+        expected = df_single.groupby(['B', pd.Grouper(level='inner')]).mean()
+        assert_frame_equal(result, expected)
+
+        # Index and Column on single Index
+        result = df_single.groupby(['inner', 'B']).mean()
+        expected = df_single.groupby([pd.Grouper(level='inner'), 'B']).mean()
+        assert_frame_equal(result, expected)
+
+        # Single element list of Index on MultiIndex
+        result = df_multi.groupby(['inner']).mean()
+        expected = df_multi.groupby(pd.Grouper(level='inner')).mean()
+        assert_frame_equal(result, expected)
+
+        # Single element list of Index on single Index
+        result = df_single.groupby(['inner']).mean()
+        expected = df_single.groupby(pd.Grouper(level='inner')).mean()
+        assert_frame_equal(result, expected)
+
+        # Index on MultiIndex
+        result = df_multi.groupby('inner').mean()
+        expected = df_multi.groupby(pd.Grouper(level='inner')).mean()
+        assert_frame_equal(result, expected)
+
+        # Index on single Index
+        result = df_single.groupby('inner').mean()
+        expected = df_single.groupby(pd.Grouper(level='inner')).mean()
+        assert_frame_equal(result, expected)
+
+    def test_grouper_column_takes_precedence_over_level(self):
+        # GH 5677, when a string passed as the `by` parameter
+        # matches a column and an index level the column takes
+        # precedence
+
+        idx = pd.MultiIndex.from_tuples([('a', 1), ('a', 2), ('a', 3),
+                                         ('b', 1), ('b', 2), ('b', 3)])
+        idx.names = ['outer', 'inner']
+        df_multi_both = pd.DataFrame({"A": np.arange(6),
+                                      'B': ['one', 'one', 'two',
+                                            'two', 'one', 'one'],
+                                      'inner': [1, 1, 1, 1, 1, 1]},
+                                     index=idx)
+
+        df_single_both = df_multi_both.reset_index('outer')
+
+        # Group MultiIndex by single key
+        result = df_multi_both.groupby('inner').mean()
+        expected = df_multi_both.groupby(pd.Grouper(key='inner')).mean()
+        assert_frame_equal(result, expected)
+        not_expected = df_multi_both.groupby(pd.Grouper(level='inner')).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group single Index by single key
+        result = df_single_both.groupby('inner').mean()
+        expected = df_single_both.groupby(pd.Grouper(key='inner')).mean()
+        assert_frame_equal(result, expected)
+        not_expected = df_single_both.groupby(pd.Grouper(level='inner')).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group MultiIndex by single key list
+        result = df_multi_both.groupby(['inner']).mean()
+        expected = df_multi_both.groupby(pd.Grouper(key='inner')).mean()
+        assert_frame_equal(result, expected)
+        not_expected = df_multi_both.groupby(pd.Grouper(level='inner')).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group single Index by single key list
+        result = df_single_both.groupby(['inner']).mean()
+        expected = df_single_both.groupby(pd.Grouper(key='inner')).mean()
+        assert_frame_equal(result, expected)
+        not_expected = df_single_both.groupby(pd.Grouper(level='inner')).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group MultiIndex by two keys (1)
+        result = df_multi_both.groupby(['B', 'inner']).mean()
+        expected = df_multi_both.groupby(['B',
+                                          pd.Grouper(key='inner')]).mean()
+        assert_frame_equal(result, expected)
+
+        not_expected = df_multi_both.groupby(['B',
+                                              pd.Grouper(level='inner')
+                                              ]).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group MultiIndex by two keys (2)
+        result = df_multi_both.groupby(['inner', 'B']).mean()
+        expected = df_multi_both.groupby([pd.Grouper(key='inner'),
+                                          'B']).mean()
+        assert_frame_equal(result, expected)
+
+        not_expected = df_multi_both.groupby([pd.Grouper(level='inner'),
+                                              'B']).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group single Index by two keys (1)
+        result = df_single_both.groupby(['B', 'inner']).mean()
+        expected = df_single_both.groupby(['B',
+                                          pd.Grouper(key='inner')]).mean()
+        assert_frame_equal(result, expected)
+
+        not_expected = df_single_both.groupby(['B',
+                                               pd.Grouper(level='inner')
+                                               ]).mean()
+        assert not result.index.equals(not_expected.index)
+
+        # Group single Index by two keys (2)
+        result = df_single_both.groupby(['inner', 'B']).mean()
+        expected = df_single_both.groupby([pd.Grouper(key='inner'),
+                                           'B']).mean()
+        assert_frame_equal(result, expected)
+
+        not_expected = df_single_both.groupby([pd.Grouper(level='inner'),
+                                               'B']).mean()
+        assert not result.index.equals(not_expected.index)
+
     def test_grouper_getting_correct_binner(self):
 
         # GH 10063