BUG: Bug in groupby.get_group where a datetlike wasn't always accepted (GH5267)

doc/source/release.rst

@@ -365,6 +365,7 @@ Bug Fixes
   would only replace the first occurrence of a value (:issue:`6689`)
 - Better error message when passing a frequency of 'MS' in ``Period`` construction (GH5332)
 - Bug in `Series.__unicode__` when `max_rows` is `None` and the Series has more than 1000 rows. (:issue:`6863`)
+- Bug in ``groupby.get_group`` where a datetlike wasn't always accepted (:issue:`5267`)
 
 pandas 0.13.1
 -------------

pandas/core/groupby.py

@@ -1,9 +1,11 @@
 import types
 from functools import wraps
 import numpy as np
+import datetime
 
 from pandas.compat import(
-    zip, builtins, range, long, lrange, lzip, OrderedDict, callable
+    zip, builtins, range, long, lrange, lzip,
+    OrderedDict, callable
 )
 from pandas import compat
 
@@ -402,14 +404,32 @@ def indices(self):
         return self.grouper.indices
 
     def _get_index(self, name):
-        """ safe get index """
-        try:
-            return self.indices[name]
-        except:
-            if isinstance(name, Timestamp):
-                name = name.value
-                return self.indices[name]
-            raise
+        """ safe get index, translate keys for datelike to underlying repr """
+
+        def convert(key, s):
+            # possibly convert to they actual key types
+            # in the indices, could be a Timestamp or a np.datetime64
+
+            if isinstance(s, (Timestamp,datetime.datetime)):
+                return Timestamp(key)
+            elif isinstance(s, np.datetime64):
+                return Timestamp(key).asm8
+            return key
+
+        sample = list(self.indices)[0]
+        if isinstance(sample, tuple):
+            if not isinstance(name, tuple):
+                raise ValueError("must supply a tuple to get_group with multiple grouping keys")
+            if not len(name) == len(sample):
+                raise ValueError("must supply a a same-length tuple to get_group with multiple grouping keys")
+
+            name = tuple([ convert(n, k) for n, k in zip(name,sample) ])
+
+        else:
+
+            name = convert(name, sample)
+
+        return self.indices[name]
 
     @property
     def name(self):
@@ -554,7 +574,7 @@ def apply(self, func, *args, **kwargs):
         path. This can lead to unexpected behavior if func has
         side-effects, as they will take effect twice for the first
         group.
-        
+
 
         See also
         --------

pandas/tests/test_groupby.py

@@ -17,7 +17,8 @@
                                  assert_series_equal, assert_almost_equal,
                                  assert_index_equal)
 from pandas.compat import(
-    range, long, lrange, StringIO, lmap, lzip, map, zip, builtins, OrderedDict
+    range, long, lrange, StringIO, lmap, lzip, map,
+    zip, builtins, OrderedDict
 )
 from pandas import compat
 from pandas.core.panel import Panel
@@ -479,6 +480,36 @@ def test_get_group(self):
         expected = wp.reindex(major=[x for x in wp.major_axis if x.month == 1])
         assert_panel_equal(gp, expected)
 
+
+        # GH 5267
+        # be datelike friendly
+        df = DataFrame({'DATE' : pd.to_datetime(['10-Oct-2013', '10-Oct-2013', '10-Oct-2013',
+                                                 '11-Oct-2013', '11-Oct-2013', '11-Oct-2013']),
+                        'label' : ['foo','foo','bar','foo','foo','bar'],
+                        'VAL' : [1,2,3,4,5,6]})
+
+        g = df.groupby('DATE')
+        key = list(g.groups)[0]
+        result1 = g.get_group(key)
+        result2 = g.get_group(Timestamp(key).to_datetime())
+        result3 = g.get_group(str(Timestamp(key)))
+        assert_frame_equal(result1,result2)
+        assert_frame_equal(result1,result3)
+
+        g = df.groupby(['DATE','label'])
+
+        key = list(g.groups)[0]
+        result1 = g.get_group(key)
+        result2 = g.get_group((Timestamp(key[0]).to_datetime(),key[1]))
+        result3 = g.get_group((str(Timestamp(key[0])),key[1]))
+        assert_frame_equal(result1,result2)
+        assert_frame_equal(result1,result3)
+
+        # must pass a same-length tuple with multiple keys
+        self.assertRaises(ValueError, lambda : g.get_group('foo'))
+        self.assertRaises(ValueError, lambda : g.get_group(('foo')))
+        self.assertRaises(ValueError, lambda : g.get_group(('foo','bar','baz')))
+
     def test_agg_apply_corner(self):
         # nothing to group, all NA
         grouped = self.ts.groupby(self.ts * np.nan)