Add test and patch to fix bug GH8868 (groupby sort categorical).

Author: David Cottrell

doc/source/whatsnew/v0.16.0.txt

@@ -307,3 +307,4 @@ Bug Fixes
 - Bug in ``read_csv`` with buffer overflows with certain malformed input files (:issue:`9205`)
 - Bug in groupby MultiIndex with missing pair (:issue:`9049`, :issue:`9344`)
 - Fixed bug in ``Series.groupby`` where grouping on ``MultiIndex`` levels would ignore the sort argument (:issue:`9444`)
+- Fix bug in ``DataFrame.Groupby`` where sort=False is ignored in case of Categorical columns. (:issue:`8868`)

pandas/core/groupby.py

@@ -1925,6 +1925,9 @@ def __init__(self, index, grouper=None, obj=None, name=None, level=None,
 
             # a passed Categorical
             elif isinstance(self.grouper, Categorical):
+                # fix bug #GH8868 sort=False being ignored in categorical groupby
+                if not self.sort:
+                    self.grouper = self.grouper.reorder_categories(self.grouper.unique())
                 self._labels = self.grouper.codes
                 self._group_index = self.grouper.categories
                 if self.name is None:

pandas/tests/test_groupby.py

@@ -3265,6 +3265,30 @@ def test_no_dummy_key_names(self):
                                   self.df['B'].values]).sum()
         self.assertEqual(result.index.names, (None, None))
 
+    def test_groupby_sort_categorical(self):
+        # dataframe groupby sort was being ignored # GH 8868
+        df = DataFrame([['(7.5, 10]', 10, 10],
+                        ['(7.5, 10]', 8, 20],
+                        ['(2.5, 5]', 5, 30],
+                        ['(5, 7.5]', 6, 40],
+                        ['(2.5, 5]', 4, 50],
+                        ['(0, 2.5]', 1, 60],
+                        ['(5, 7.5]', 7, 70]], columns=['range', 'foo', 'bar'])
+        df['range'] = Categorical(df['range'])
+        index = Index(['(0, 2.5]', '(2.5, 5]', '(5, 7.5]', '(7.5, 10]'], dtype='object')
+        index.name = 'range'
+        result_sort = DataFrame([[1, 60], [5, 30], [6, 40], [10, 10]], columns=['foo', 'bar'])
+        result_sort.index = index
+        index = Index(['(7.5, 10]', '(2.5, 5]', '(5, 7.5]', '(0, 2.5]'], dtype='object')
+        index.name = 'range'
+        result_nosort = DataFrame([[10, 10], [5, 30], [6, 40], [1, 60]], index=index, columns=['foo', 'bar'])
+        result_nosort.index = index
+
+        col = 'range'
+        assert_frame_equal(result_sort, df.groupby(col, sort=True).first())
+        assert_frame_equal(result_nosort, df.groupby(col, sort=False).first())
+
+
     def test_groupby_sort_multiindex_series(self):
         # series multiindex groupby sort argument was not being passed through _compress_group_index
         # GH 9444