BUG: Lambda function returns KeyError in DataFrameGroupBy.agg

doc/source/whatsnew/v1.0.0.rst

@@ -173,6 +173,7 @@ Groupby/resample/rolling
 -
 -
 - Bug in :meth:`DataFrame.groupby` not offering selection by column name when ``axis=1`` (:issue:`27614`)
+- Bug in :meth:`DataFrameGroupby.agg` not able to use lambdas (:issue:`27519`)
 
 Reshaping
 ^^^^^^^^^

pandas/core/groupby/generic.py

@@ -268,7 +268,9 @@ def aggregate(self, func, *args, **kwargs):
             result.index = np.arange(len(result))
 
         if relabeling:
-            result = result[order]
+
+            # used reordered index of columns
+            result = result.iloc[:, order]
             result.columns = columns
 
         return result._convert(datetime=True)
@@ -1731,8 +1733,8 @@ def _normalize_keyword_aggregation(kwargs):
         The transformed kwargs.
     columns : List[str]
         The user-provided keys.
-    order : List[Tuple[str, str]]
-        Pairs of the input and output column names.
+    order : List[int]
+        List of reordered index of columns.
 
     Examples
     --------
@@ -1752,14 +1754,24 @@ def _normalize_keyword_aggregation(kwargs):
     aggspec = OrderedDict()
     order = []
     columns, pairs = list(zip(*kwargs.items()))
+    reordered_pairs = []
 
     for name, (column, aggfunc) in zip(columns, pairs):
         if column in aggspec:
             aggspec[column].append(aggfunc)
         else:
             aggspec[column] = [aggfunc]
         order.append((column, com.get_callable_name(aggfunc) or aggfunc))
-    return aggspec, columns, order
+
+    # GH 25719, due to aggspec will change the order of assigned columns in aggregation
+    # reordered_pairs will store this reorder and will compare it with order
+    # based on index, it will obtain new order in index
+    for column, aggfuncs in aggspec.items():
+        for aggfunc in aggfuncs:
+            reordered_pairs.append((column, com.get_callable_name(aggfunc) or aggfunc))
+
+    col_idx_order = [reordered_pairs.index(o) for o in order]
+    return aggspec, columns, col_idx_order
 
 
 # TODO: Can't use, because mypy doesn't like us setting __name__

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -560,3 +560,45 @@ def test_with_kwargs(self):
         result = pd.Series([1, 2]).groupby([0, 0]).agg([f1, f2], 0, b=10)
         expected = pd.DataFrame({"<lambda_0>": [13], "<lambda_1>": [30]})
         tm.assert_frame_equal(result, expected)
+
+    def test_agg_lambda(self):
+        # GH 25719
+        df = pd.DataFrame(
+            {
+                "kind": ["cat", "dog", "cat", "dog"],
+                "height": [9.1, 6.0, 9.5, 34.0],
+                "weight": [7.9, 7.5, 9.9, 198.0],
+            }
+        )
+
+        # sort for 35 and earlier
+        columns = ["height_sqr_min", "height_max", "weight_max"]
+        if compat.PY35:
+            columns = ["height_max", "height_sqr_min", "weight_max"]
+        expected = pd.DataFrame(
+            {
+                "height_sqr_min": [82.81, 36.00],
+                "height_max": [9.5, 34.0],
+                "weight_max": [9.9, 198.0],
+            },
+            index=pd.Index(["cat", "dog"], name="kind"),
+            columns=columns,
+        )
+
+        # check pd.NameAgg case
+        result1 = df.groupby(by="kind").agg(
+            height_sqr_min=pd.NamedAgg(
+                column="height", aggfunc=lambda x: np.min(x ** 2)
+            ),
+            height_max=pd.NamedAgg(column="height", aggfunc="max"),
+            weight_max=pd.NamedAgg(column="weight", aggfunc="max"),
+        )
+        tm.assert_frame_equal(result1, expected)
+
+        # check agg('A' = tuple) case
+        result2 = df.groupby(by="kind").agg(
+            height_sqr_min=("height", lambda x: np.min(x ** 2)),
+            height_max=("height", "max"),
+            weight_max=("weight", "max"),
+        )
+        tm.assert_frame_equal(result2, expected)