TST: vbench for #775

Author: wesm

pandas/core/groupby.py

@@ -303,12 +303,20 @@ def mean(self):
 
     def std(self):
         """
-        Compute mean of groups, excluding missing values
+        Compute standard deviation of groups, excluding missing values
 
         For multiple groupings, the result index will be a MultiIndex
         """
         return self._cython_agg_general('std')
 
+    def var(self):
+        """
+        Compute variance of groups, excluding missing values
+
+        For multiple groupings, the result index will be a MultiIndex
+        """
+        return self._cython_agg_general('var')
+
     def size(self):
         """
         Compute group sizes
@@ -595,6 +603,9 @@ def __init__(self, index, grouper=None, name=None, level=None,
                 self._group_index = level_index
                 self.grouper = level_values
         else:
+            if isinstance(self.grouper, (list, tuple)):
+                self.grouper = com._asarray_tuplesafe(self.grouper)
+
             # no level passed
             if not isinstance(self.grouper, np.ndarray):
                 self.grouper = self.index.map(self.grouper)
@@ -1038,7 +1049,7 @@ def aggregate(self, arg, *args, **kwargs):
             for col, func in arg.iteritems():
                 colg = SeriesGroupBy(obj[col], column=col,
                                      groupings=self.groupings)
-                result[col] = colg.agg(func)
+                result[col] = colg.aggregate(func)
 
             result = DataFrame(result)
         elif isinstance(arg, list):

setup.py

@@ -164,9 +164,9 @@
 ]
 
 MAJOR = 0
-MINOR = 7
+MINOR = 8
 MICRO = 0
-ISRELEASED = True
+ISRELEASED = False
 VERSION = '%d.%d.%d' % (MAJOR, MINOR, MICRO)
 QUALIFIER = ''
 

vb_suite/groupby.py

@@ -72,3 +72,22 @@ def f():
     Benchmark('df.groupby(labels).sum()', setup,
               start_date=datetime(2011, 8, 1), logy=True)
 
+#----------------------------------------------------------------------
+# group with different functions per column
+
+setup = common_setup + """
+fac1 = np.array(['A', 'B', 'C'], dtype='O')
+fac2 = np.array(['one', 'two'], dtype='O')
+
+df = DataFrame({'key1': fac1.take(np.random.randint(0, 3, size=100000)),
+                'key2': fac2.take(np.random.randint(0, 2, size=100000)),
+                'value1' : np.random.randn(100000),
+                'value2' : np.random.randn(100000),
+                'value3' : np.random.randn(100000)})
+"""
+
+groupby_multi_different_functions = \
+    Benchmark("""df.groupby(['key1', 'key2']).agg({'value1' : 'mean',
+                                                   'value2' : 'var',
+                                                   'value3' : 'sum'})""",
+              setup, start_date=datetime(2011, 9, 1))