DOC: Add the description for fixing unexpected sort in groupby in wha…

…tsnew note
pandas-dev · Sep 28, 2017 · 9962d61 · 9962d61
1 parent 7b23e65
commit 9962d61
Show file tree

Hide file tree

Showing 4 changed files with 7 additions and 0 deletions.
diff --git a/doc/source/whatsnew/v0.21.0.txt b/doc/source/whatsnew/v0.21.0.txt
@@ -625,6 +625,7 @@ Groupby/Resample/Rolling
 - Bug in ``.rolling(...).apply(...)`` with a ``DataFrame`` with a ``DatetimeIndex``, a ``window`` of a timedelta-convertible and ``min_periods >= 1` (:issue:`15305`)
 - Bug in ``DataFrame.groupby`` where index and column keys were not recognized correctly when the number of keys equaled the number of elements on the groupby axis (:issue:`16859`)
 - Bug in ``groupby.nunique()`` with ``TimeGrouper`` which cannot handle ``NaT`` correctly (:issue:`17575`)
+- Bug in ``DataFrame.groupby`` where a single level selection from a ``MultiIndex`` unexpectedly sorts (:issue:`17537`)
 
 Sparse
 ^^^^^^

diff --git a/pandas/tests/groupby/test_groupby.py b/pandas/tests/groupby/test_groupby.py
@@ -1793,6 +1793,7 @@ def aggfun(ser):
 
     @pytest.mark.parametrize('sort', [True, False])
     def test_groupby_level(self, sort):
+        # GH 17537
         frame = self.mframe
         deleveled = frame.reset_index()
 
@@ -1838,6 +1839,7 @@ def test_groupby_level_index_names(self):
 
     @pytest.mark.parametrize('sort', [True, False])
     def test_groupby_level_with_nas(self, sort):
+        # GH 17537
         index = MultiIndex(levels=[[1, 0], [0, 1, 2, 3]],
                            labels=[[1, 1, 1, 1, 0, 0, 0, 0], [0, 1, 2, 3, 0, 1,
                                                               2, 3]])
@@ -1943,6 +1945,7 @@ def test_groupby_complex(self):
         [False, [0, 0, 0, 1, 1, 2, 2, 3, 3, 3]]
     ])
     def test_level_preserve_order(self, sort, labels):
+        # GH 17537
         grouped = self.mframe.groupby(level=0, sort=sort)
         exp_labels = np.array(labels, np.intp)
         assert_almost_equal(grouped.grouper.labels[0], exp_labels)

diff --git a/pandas/tests/groupby/test_whitelist.py b/pandas/tests/groupby/test_whitelist.py
@@ -183,6 +183,7 @@ def test_regression_whitelist_methods(
         raw_frame, op, level,
         axis, skipna, sort):
     # GH6944
+    # GH 17537
     # explicity test the whitelest methods
 
     if axis == 0:

diff --git a/pandas/tests/test_multilevel.py b/pandas/tests/test_multilevel.py
@@ -1394,6 +1394,7 @@ def test_count(self):
 
     @pytest.mark.parametrize('sort', [True, False])
     def test_series_group_min_max(self, sort):
+        # GH 17537
         for op, level, skipna in cart_product(self.AGG_FUNCTIONS, lrange(2),
                                               [False, True]):
             grouped = self.series.groupby(level=level, sort=sort)
@@ -1407,6 +1408,7 @@ def test_series_group_min_max(self, sort):
 
     @pytest.mark.parametrize('sort', [True, False])
     def test_frame_group_ops(self, sort):
+        # GH 17537
         self.frame.iloc[1, [1, 2]] = np.nan
         self.frame.iloc[7, [0, 1]] = np.nan