Merge pull request #7560 from jreback/groupby_first_perf

PERF: vbench for mixed groupby with datetime (GH7555)

Author: jreback

doc/source/v0.14.1.txt

@@ -144,7 +144,7 @@ Performance
 - Improvements in dtype inference for numeric operations involving yielding performance gains for dtypes: ``int64``, ``timedelta64``, ``datetime64`` (:issue:`7223`)
 - Improvements in Series.transform for significant performance gains (:issue:`6496`)
 - Improvements in DataFrame.transform with ufuncs and built-in grouper functions for signifcant performance gains (:issue:`7383`)
-
+- Regression in groupby aggregation of datetime64 dtypes (:issue:`7555`)
 
 
 

pandas/core/groupby.py

@@ -2332,17 +2332,16 @@ def _cython_agg_blocks(self, how, numeric_only=True):
             data = data.get_numeric_data(copy=False)
 
         for block in data.blocks:
-            values = block.values
 
-            is_numeric = is_numeric_dtype(values.dtype)
+            values = block._try_operate(block.values)
 
-            if is_numeric:
+            if block.is_numeric:
                 values = com.ensure_float(values)
 
             result, _ = self.grouper.aggregate(values, how, axis=agg_axis)
 
             # see if we can cast the block back to the original dtype
-            result = block._try_cast_result(result)
+            result = block._try_coerce_and_cast_result(result)
 
             newb = make_block(result, placement=block.mgr_locs)
             new_blocks.append(newb)

pandas/core/internals.py

@@ -412,6 +412,11 @@ def _try_coerce_result(self, result):
         """ reverse of try_coerce_args """
         return result
 
+    def _try_coerce_and_cast_result(self, result, dtype=None):
+        result = self._try_coerce_result(result)
+        result = self._try_cast_result(result, dtype=dtype)
+        return result
+
     def _try_fill(self, value):
         return value
 
@@ -513,8 +518,7 @@ def setitem(self, indexer, value):
                 dtype, _ = _infer_dtype_from_scalar(value)
             else:
                 dtype = 'infer'
-            values = self._try_coerce_result(values)
-            values = self._try_cast_result(values, dtype)
+            values = self._try_coerce_and_cast_result(values, dtype)
             return [make_block(transf(values),
                                ndim=self.ndim, placement=self.mgr_locs,
                                fastpath=True)]

vb_suite/groupby.py

@@ -244,6 +244,13 @@ def f():
 groupby_last_float32 = Benchmark('data2.groupby(labels).last()', setup,
                                  start_date=datetime(2013, 1, 1))
 
+# with datetimes (GH7555)
+setup = common_setup + """
+df = DataFrame({'a' : date_range('1/1/2011',periods=100000,freq='s'),'b' : range(100000)})
+"""
+
+groupby_mixed_first = Benchmark('df.groupby("b").first()', setup,
+                                 start_date=datetime(2013, 5, 1))
 
 #----------------------------------------------------------------------
 # groupby_indices replacement, chop up Series