Merge pull request #8123 from TomAugspurger/groupby-tuple

BUG: fix groupby with tuple bug

Author: Tom Augspurger

doc/source/v0.15.0.txt

@@ -640,6 +640,7 @@ Bug Fixes
 
 
 
-
+- Bug in accessing groups from a ``GroupBy`` when the original grouper
+ was a tuple (:issue:`8121`).
 
 

pandas/core/groupby.py

@@ -431,9 +431,18 @@ def convert(key, s):
  sample = next(iter(self.indices))
  if isinstance(sample, tuple):
  if not isinstance(name, tuple):
- raise ValueError("must supply a tuple to get_group with multiple grouping keys")
+ msg = ("must supply a tuple to get_group with multiple"
+ " grouping keys")
+ raise ValueError(msg)
  if not len(name) == len(sample):
- raise ValueError("must supply a a same-length tuple to get_group with multiple grouping keys")
+ try:
+ # If the original grouper was a tuple
+ return self.indices[name]
+ except KeyError:
+ # turns out it wasn't a tuple
+ msg = ("must supply a a same-length tuple to get_group"
+ " with multiple grouping keys")
+ raise ValueError(msg)
 
  name = tuple([ convert(n, k) for n, k in zip(name,sample) ])
 

pandas/tests/test_groupby.py

@@ -598,6 +598,23 @@ def test_get_group(self):
  self.assertRaises(ValueError, lambda : g.get_group(('foo')))
  self.assertRaises(ValueError, lambda : g.get_group(('foo','bar','baz')))
 
+ def test_get_group_grouped_by_tuple(self):
+ # GH 8121
+ df = DataFrame([[(1,), (1, 2), (1,), (1, 2)]],
+ index=['ids']).T
+ gr = df.groupby('ids')
+ expected = DataFrame({'ids': [(1,), (1,)]}, index=[0, 2])
+ result = gr.get_group((1,))
+ assert_frame_equal(result, expected)
+
+ dt = pd.to_datetime(['2010-01-01', '2010-01-02', '2010-01-01',
+ '2010-01-02'])
+ df = DataFrame({'ids': [(x,) for x in dt]}) 
+ gr = df.groupby('ids')
+ result = gr.get_group(('2010-01-01',))
+ expected = DataFrame({'ids': [(dt[0],), (dt[0],)]}, index=[0, 2])
+ assert_frame_equal(result, expected)
+
  def test_agg_apply_corner(self):
  # nothing to group, all NA
  grouped = self.ts.groupby(self.ts * np.nan)