BUG: GH25871 -- adapt test_groupby_levels_and_columns

This test had an adjustment for column order when 'observed=True' is set. This hid the fact that, with that parameter set, the data columns were not actually reordered -- it was just the column group labels (analogous to index labels in pandas-dev#25871), leaving the data columns in place and out of sync. (This was not visible as the data consisted only of ones).

I've made the test more sensitive (unsyncing of data columns will be caught now) and removed the special case for 'observed=True'. As there are no unobserved categories in this case, the result should not be influenced by this parameter.

Author: kpflugshaupt

pandas/tests/groupby/test_grouping.py

@@ -253,28 +253,27 @@ def test_groupby_levels_and_columns(self):
         tm.assert_frame_equal(by_levels, by_columns)
 
     def test_groupby_categorical_index_and_columns(self, observed):
-        # GH18432
+        # GH18432, adapted for GH25871
         columns = ['A', 'B', 'A', 'B']
         categories = ['B', 'A']
-        data = np.ones((5, 4), int)
+        data = np.array([[1, 2, 1, 2],
+                         [1, 2, 1, 2],
+                         [1, 2, 1, 2],
+                         [1, 2, 1, 2],
+                         [1, 2, 1, 2]], int)
         cat_columns = CategoricalIndex(columns,
                                        categories=categories,
                                        ordered=True)
         df = DataFrame(data=data, columns=cat_columns)
         result = df.groupby(axis=1, level=0, observed=observed).sum()
-        expected_data = 2 * np.ones((5, 2), int)
-
-        if observed:
-            # if we are not-observed we undergo a reindex
-            # so need to adjust the output as our expected sets us up
-            # to be non-observed
-            expected_columns = CategoricalIndex(['A', 'B'],
-                                                categories=categories,
-                                                ordered=True)
-        else:
-            expected_columns = CategoricalIndex(categories,
-                                                categories=categories,
-                                                ordered=True)
+        expected_data = np.array([[4, 2],
+                                  [4, 2],
+                                  [4, 2],
+                                  [4, 2],
+                                  [4, 2]], int)
+        expected_columns = CategoricalIndex(categories,
+                                            categories=categories,
+                                            ordered=True)
         expected = DataFrame(data=expected_data, columns=expected_columns)
         assert_frame_equal(result, expected)