Merge pull request #8434 from jreback/bin_grouper

BUG: Groupby.transform related to BinGrouper and GH8046 (GH8430)

Author: jreback

doc/source/v0.15.0.txt

@@ -880,7 +880,7 @@ Bug Fixes
   when matching block and manager items, when there's only one block there's no ambiguity (:issue:`7794`)
 - Bug in putting a ``PeriodIndex`` into a ``Series`` would convert to ``int64`` dtype, rather than ``object`` of ``Periods`` (:issue:`7932`)
 - Bug in HDFStore iteration when passing a where (:issue:`8014`)
-- Bug in DataFrameGroupby.transform when transforming with a passed non-sorted key (:issue:`8046`)
+- Bug in DataFrameGroupby.transform when transforming with a passed non-sorted key (:issue:`8046`, :issue:`8430`)
 - Bug in repeated timeseries line and area plot may result in ``ValueError`` or incorrect kind (:issue:`7733`)
 - Bug in inference in a MultiIndex with ``datetime.date`` inputs (:issue:`7888`)
 - Bug in ``get`` where an ``IndexError`` would not cause the default value to be returned (:issue:`7725`)

pandas/core/groupby.py

@@ -484,8 +484,7 @@ def _set_result_index_ordered(self, result):
         indices = self.indices
 
         # shortcut of we have an already ordered grouper
-
-        if not Index(self.grouper.group_info[0]).is_monotonic:
+        if not self.grouper.is_monotonic:
             index = Index(np.concatenate([ indices[v] for v in self.grouper.result_index ]))
             result.index = index
             result = result.sort_index()
@@ -1348,6 +1347,11 @@ def groups(self):
             to_groupby = Index(to_groupby)
             return self.axis.groupby(to_groupby.values)
 
+    @cache_readonly
+    def is_monotonic(self):
+        # return if my group orderings are monotonic
+        return Index(self.group_info[0]).is_monotonic
+
     @cache_readonly
     def group_info(self):
         comp_ids, obs_group_ids = self._get_compressed_labels()
@@ -1739,6 +1743,11 @@ def indices(self):
                 i = bin
         return indices
 
+    @cache_readonly
+    def group_info(self):
+        # for compat
+        return self.bins, self.binlabels, self.ngroups
+
     @cache_readonly
     def ngroups(self):
         return len(self.binlabels)

pandas/tests/test_groupby.py

@@ -897,6 +897,11 @@ def demean(arr):
         expected = people.groupby(key).apply(demean).groupby(key).mean()
         assert_frame_equal(result, expected)
 
+        # GH 8430
+        df = tm.makeTimeDataFrame()
+        g = df.groupby(pd.TimeGrouper('M'))
+        g.transform(lambda x: x-1)
+
     def test_transform_fast(self):
 
         df = DataFrame( { 'id' : np.arange( 100000 ) / 3,