Merge pull request #6338 from jreback/agg

BUG: Issue with groupby agg with a single function and a a mixed-type frame (GH6337)

Author: jreback

doc/source/release.rst

@@ -91,6 +91,7 @@ Bug Fixes
 - ``HDFStore.select_as_multiple`` handles start and stop the same way as ``select`` (:issue:`6177`)
 - ``HDFStore.select_as_coordinates`` and ``select_column`` works where clauses that result in filters (:issue:`6177`)
 - Regression in join of non_unique_indexes (:issue:`6329`)
+- Issue with groupby ``agg`` with a single function and a a mixed-type frame (:issue:`6337`)
 
 pandas 0.13.1
 -------------

pandas/core/groupby.py

@@ -2123,6 +2123,7 @@ def _aggregate_item_by_item(self, func, *args, **kwargs):
         obj = self._obj_with_exclusions
         result = {}
         cannot_agg = []
+        errors=None
         for item in obj:
             try:
                 data = obj[item]
@@ -2133,11 +2134,19 @@ def _aggregate_item_by_item(self, func, *args, **kwargs):
             except ValueError:
                 cannot_agg.append(item)
                 continue
+            except TypeError as e:
+                cannot_agg.append(item)
+                errors=e
+                continue
 
         result_columns = obj.columns
         if cannot_agg:
             result_columns = result_columns.drop(cannot_agg)
 
+            # GH6337
+            if not len(result_columns) and errors is not None:
+                raise errors
+
         return DataFrame(result, columns=result_columns)
 
     def _decide_output_index(self, output, labels):

pandas/tests/test_groupby.py

@@ -370,6 +370,26 @@ def f(grp):
         e.name = None
         assert_series_equal(result,e)
 
+    def test_agg_api(self):
+
+        # GH 6337
+        # http://stackoverflow.com/questions/21706030/pandas-groupby-agg-function-column-dtype-error
+        # different api for agg when passed custom function with mixed frame
+
+        df = DataFrame({'data1':np.random.randn(5),
+                        'data2':np.random.randn(5),
+                        'key1':['a','a','b','b','a'],
+                        'key2':['one','two','one','two','one']})
+        grouped = df.groupby('key1')
+
+        def peak_to_peak(arr):
+            return arr.max() - arr.min()
+
+        expected = grouped.agg([peak_to_peak])
+        expected.columns=['data1','data2']
+        result = grouped.agg(peak_to_peak)
+        assert_frame_equal(result,expected)
+
     def test_agg_regression1(self):
         grouped = self.tsframe.groupby([lambda x: x.year, lambda x: x.month])
         result = grouped.agg(np.mean)