COMPAT/TST: fix group_info dtype issues, xref #10981

Author: jreback

pandas/core/groupby.py

@@ -1793,13 +1793,13 @@ def indices(self):
     @cache_readonly
     def group_info(self):
         ngroups = self.ngroups
-        obs_group_ids = np.arange(ngroups)
+        obs_group_ids = np.arange(ngroups, dtype='int64')
         rep = np.diff(np.r_[0, self.bins])
 
         if ngroups == len(self.bins):
-            comp_ids = np.repeat(np.arange(ngroups), rep)
+            comp_ids = np.repeat(np.arange(ngroups, dtype='int64'), rep)
         else:
-            comp_ids = np.repeat(np.r_[-1, np.arange(ngroups)], rep)
+            comp_ids = np.repeat(np.r_[-1, np.arange(ngroups, dtype='int64')], rep)
 
         return comp_ids, obs_group_ids, ngroups
 
@@ -2552,8 +2552,8 @@ def nunique(self, dropna=True):
 
         # group boundries are where group ids change
         # unique observations are where sorted values change
-        idx = np.r_[0, 1 + np.nonzero(ids[1:] != ids[:-1])[0]]
-        inc = np.r_[1, val[1:] != val[:-1]]
+        idx = com._ensure_int64(np.r_[0, 1 + np.nonzero(ids[1:] != ids[:-1])[0]])
+        inc = com._ensure_int64(np.r_[1, val[1:] != val[:-1]])
 
         # 1st item of each group is a new unique observation
         mask = isnull(val)

pandas/tseries/tests/test_resample.py

@@ -919,7 +919,7 @@ def test_resample_timegrouper(self):
     def test_resample_group_info(self):  # GH10914
         for n, k in product((10000, 100000), (10, 100, 1000)):
             dr = date_range(start='2015-08-27', periods=n // 10, freq='T')
-            ts = Series(np.random.randint(0, n // k, n),
+            ts = Series(np.random.randint(0, n // k, n).astype('int64'),
                         index=np.random.choice(dr, n))
 
             left = ts.resample('30T', how='nunique')
@@ -1585,7 +1585,7 @@ def test_aggregate_with_nat(self):
         # check TimeGrouper's aggregation is identical as normal groupby
 
         n = 20
-        data = np.random.randn(n, 4)
+        data = np.random.randn(n, 4).astype('int64')
         normal_df = DataFrame(data, columns=['A', 'B', 'C', 'D'])
         normal_df['key'] = [1, 2, np.nan, 4, 5] * 4