Merge pull request #9008 from jreback/grouper

BUG: Bug in using a pd.Grouper(key=...) with no level/axis or level only (GH8795, GH8866)

Author: jreback

doc/source/whatsnew/v0.15.2.txt

@@ -98,6 +98,7 @@ Bug Fixes
 
 - Bug in Timestamp-Timestamp not returning a Timedelta type and datelike-datelike ops with timezones (:issue:`8865`)
 - Made consistent a timezone mismatch exception (either tz operated with None or incompatible timezone), will now return ``TypeError`` rather than ``ValueError`` (a couple of edge cases only), (:issue:`8865`)
+- Bug in using a ``pd.Grouper(key=...)`` with no level/axis or level only (:issue:`8795`, :issue:`8866`)
 - Report a ``TypeError`` when invalid/no paramaters are passed in a groupby (:issue:`8015`)
 - Bug in packaging pandas with ``py2app/cx_Freeze`` (:issue:`8602`, :issue:`8831`)
 - Bug in ``groupby`` signatures that didn't include \*args or \*\*kwargs (:issue:`8733`).

pandas/core/groupby.py

@@ -168,7 +168,7 @@ class Grouper(object):
     freq : string / freqency object, defaults to None
         This will groupby the specified frequency if the target selection (via key or level) is
         a datetime-like object
-    axis : number/name of the axis, defaults to None
+    axis : number/name of the axis, defaults to 0
     sort : boolean, default to False
         whether to sort the resulting labels
 
@@ -198,7 +198,7 @@ def __new__(cls, *args, **kwargs):
             cls = TimeGrouper
         return super(Grouper, cls).__new__(cls)
 
-    def __init__(self, key=None, level=None, freq=None, axis=None, sort=False):
+    def __init__(self, key=None, level=None, freq=None, axis=0, sort=False):
         self.key=key
         self.level=level
         self.freq=freq
@@ -228,6 +228,8 @@ def _get_grouper(self, obj):
         """
 
         self._set_grouper(obj)
+        self.grouper, exclusions, self.obj = _get_grouper(self.obj, [self.key], axis=self.axis,
+                                                          level=self.level, sort=self.sort)
         return self.binner, self.grouper, self.obj
 
     def _set_grouper(self, obj, sort=False):

pandas/tests/test_groupby.py

@@ -373,6 +373,39 @@ def test_grouper_multilevel_freq(self):
                              pd.Grouper(level=1, freq='W')]).sum()
         assert_frame_equal(result, expected)
 
+    def test_grouper_creation_bug(self):
+
+        # GH 8795
+        df = DataFrame({'A':[0,0,1,1,2,2], 'B':[1,2,3,4,5,6]})
+        g = df.groupby('A')
+        expected = g.sum()
+
+        g = df.groupby(pd.Grouper(key='A'))
+        result = g.sum()
+        assert_frame_equal(result, expected)
+
+        result = g.apply(lambda x: x.sum())
+        assert_frame_equal(result, expected)
+
+        g = df.groupby(pd.Grouper(key='A',axis=0))
+        result = g.sum()
+        assert_frame_equal(result, expected)
+
+        # GH8866
+        s = Series(np.arange(8),
+                   index=pd.MultiIndex.from_product([list('ab'),
+                                                     range(2),
+                                                     date_range('20130101',periods=2)],
+                                                    names=['one','two','three']))
+        result = s.groupby(pd.Grouper(level='three',freq='M')).sum()
+        expected = Series([28],index=Index([Timestamp('2013-01-31')],freq='M',name='three'))
+        assert_series_equal(result, expected)
+
+        # just specifying a level breaks
+        result = s.groupby(pd.Grouper(level='one')).sum()
+        expected = s.groupby(level='one').sum()
+        assert_series_equal(result, expected)
+
     def test_grouper_iter(self):
         self.assertEqual(sorted(self.df.groupby('A').grouper), ['bar', 'foo'])