fixed bug in df.aggregate passing non-existent columns

Author: discort

doc/source/whatsnew/v0.23.0.txt

@@ -646,6 +646,7 @@ Groupby/Resample/Rolling
 - Bug in :func:`DataFrame.groupby` where tuples were interpreted as lists of keys rather than as keys (:issue:`17979`, :issue:`18249`)
 - Bug in :func:`DataFrame.transform` where particular aggregation functions were being incorrectly cast to match the dtype(s) of the grouped data (:issue:`19200`)
 - Bug in :func:`DataFrame.groupby` passing the `on=` kwarg, and subsequently using ``.apply()`` (:issue:`17813`)
+- Bug in :func:`DataFrame.aggregate` on non-existant columns (:issue:`16766`)
 
 Sparse
 ^^^^^^

pandas/core/base.py

@@ -371,6 +371,10 @@ def nested_renaming_depr(level=4):
                     else:
                         new_arg[k] = v
 
+                    if isinstance(obj, ABCDataFrame) and k not in obj.columns:
+                        raise ValueError(
+                            "Column '{col}' does not exist!".format(col=k))
+
                     # the keys must be in the columns
                     # for ndim=2, or renamers for ndim=1
 

pandas/tests/test_resample.py

@@ -614,7 +614,7 @@ def f():
                     t[['A']].agg({'A': ['sum', 'std'],
                                   'B': ['mean', 'std']})
 
-            pytest.raises(SpecificationError, f)
+            pytest.raises(ValueError, f)
 
     def test_agg_nested_dicts(self):
 
@@ -659,6 +659,21 @@ def f():
                                 'B': {'rb': ['mean', 'std']}})
             assert_frame_equal(result, expected, check_like=True)
 
+    def test_try_aggregate_non_existing_column(self):
+        # GH 16766
+        data = [
+            {'dt': datetime(2017, 6, 1, 0), 'x': 1.0, 'y': 2.0},
+            {'dt': datetime(2017, 6, 1, 1), 'x': 2.0, 'y': 2.0},
+            {'dt': datetime(2017, 6, 1, 2), 'x': 3.0, 'y': 1.5}
+        ]
+        df = DataFrame(data).set_index('dt')
+
+        # Error as we don't have 'z' column
+        with pytest.raises(ValueError):
+            df.resample('30T').agg({'x': ['mean'],
+                                    'y': ['median'],
+                                    'z': ['sum']})
+
     def test_selection_api_validation(self):
         # GH 13500
         index = date_range(datetime(2005, 1, 1),