Merge pull request #6914 from sinhrks/getgroup

BUG: GroupBy.get_group doesnt work with TimeGrouper

Author: jreback

doc/source/release.rst

@@ -410,6 +410,7 @@ Bug Fixes
 - 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`)
+- Bug in ``groupBy.get_group`` created by ``TimeGrouper`` raises ``AttributeError`` (:issue:`6914`)
 - Bug in ``DatetimeIndex.tz_localize`` and ``DatetimeIndex.tz_convert`` affects to NaT (:issue:`5546`)
 - Bug in arithmetic operations affecting to NaT (:issue:`6873`)
 - Bug in ``Series.str.extract`` where the resulting ``Series`` from a single

pandas/core/groupby.py

@@ -2,6 +2,7 @@
 from functools import wraps
 import numpy as np
 import datetime
+import collections
 
 from pandas.compat import(
     zip, builtins, range, long, lrange, lzip,
@@ -1556,6 +1557,17 @@ def apply(self, f, data, axis=0):
 
         return result_keys, result_values, mutated
 
+    @cache_readonly
+    def indices(self):
+        indices = collections.defaultdict(list)
+
+        i = 0
+        for label, bin in zip(self.binlabels, self.bins):
+            if i < bin:
+                indices[label] = list(range(i, bin))
+                i = bin
+        return indices
+
     @cache_readonly
     def ngroups(self):
         return len(self.binlabels)

pandas/tests/test_groupby.py

@@ -3140,6 +3140,55 @@ def test_timegrouper_with_reg_groups(self):
             result2 = df.groupby([pd.TimeGrouper(freq=freq), 'user_id'])['whole_cost'].sum()
             assert_series_equal(result2, expected)
 
+    def test_timegrouper_get_group(self):
+        # GH 6914
+
+        df_original = DataFrame({
+            'Buyer': 'Carl Joe Joe Carl Joe Carl'.split(),
+            'Quantity': [18,3,5,1,9,3],
+            'Date' : [datetime(2013,9,1,13,0), datetime(2013,9,1,13,5),
+                      datetime(2013,10,1,20,0), datetime(2013,10,3,10,0),
+                      datetime(2013,12,2,12,0), datetime(2013,9,2,14,0),]})
+        df_reordered = df_original.sort(columns='Quantity')
+
+        # single grouping
+        expected_list = [df_original.iloc[[0, 1, 5]], df_original.iloc[[2, 3]],
+                         df_original.iloc[[4]]]
+        dt_list = ['2013-09-30', '2013-10-31', '2013-12-31']
+
+        for df in [df_original, df_reordered]:
+            grouped = df.groupby(pd.Grouper(freq='M', key='Date'))
+            for t, expected in zip(dt_list, expected_list):
+                dt = pd.Timestamp(t)
+                result = grouped.get_group(dt)
+                assert_frame_equal(result, expected)
+
+        # multiple grouping
+        expected_list = [df_original.iloc[[1]], df_original.iloc[[3]],
+                         df_original.iloc[[4]]]
+        g_list = [('Joe', '2013-09-30'), ('Carl', '2013-10-31'), ('Joe', '2013-12-31')]
+
+        for df in [df_original, df_reordered]:
+            grouped = df.groupby(['Buyer', pd.Grouper(freq='M', key='Date')])
+            for (b, t), expected in zip(g_list, expected_list):
+                dt = pd.Timestamp(t)
+                result = grouped.get_group((b, dt))
+                assert_frame_equal(result, expected)
+
+        # with index
+        df_original = df_original.set_index('Date')
+        df_reordered = df_original.sort(columns='Quantity')
+
+        expected_list = [df_original.iloc[[0, 1, 5]], df_original.iloc[[2, 3]],
+                         df_original.iloc[[4]]]
+
+        for df in [df_original, df_reordered]:
+            grouped = df.groupby(pd.Grouper(freq='M'))
+            for t, expected in zip(dt_list, expected_list):
+                dt = pd.Timestamp(t)
+                result = grouped.get_group(dt)
+                assert_frame_equal(result, expected)
+
     def test_cumcount(self):
         df = DataFrame([['a'], ['a'], ['a'], ['b'], ['a']], columns=['A'])
         g = df.groupby('A')