CLN: Simplify gathering of results in aggregate (#37227)

Author: rhshadrach

pandas/core/aggregation.py

@@ -31,7 +31,7 @@
 
 from pandas.core.dtypes.cast import is_nested_object
 from pandas.core.dtypes.common import is_dict_like, is_list_like
-from pandas.core.dtypes.generic import ABCDataFrame, ABCSeries
+from pandas.core.dtypes.generic import ABCDataFrame, ABCNDFrame, ABCSeries
 
 from pandas.core.base import DataError, SpecificationError
 import pandas.core.common as com
@@ -621,58 +621,27 @@ def aggregate(obj, arg: AggFuncType, *args, **kwargs):
         # set the final keys
         keys = list(arg.keys())
 
-        # combine results
-
-        def is_any_series() -> bool:
-            # return a boolean if we have *any* nested series
-            return any(isinstance(r, ABCSeries) for r in results.values())
-
-        def is_any_frame() -> bool:
-            # return a boolean if we have *any* nested series
-            return any(isinstance(r, ABCDataFrame) for r in results.values())
-
-        if isinstance(results, list):
-            return concat(results, keys=keys, axis=1, sort=True), True
-
-        elif is_any_frame():
-            # we have a dict of DataFrames
-            # return a MI DataFrame
+        # Avoid making two isinstance calls in all and any below
+        is_ndframe = [isinstance(r, ABCNDFrame) for r in results.values()]
 
+        # combine results
+        if all(is_ndframe):
             keys_to_use = [k for k in keys if not results[k].empty]
             # Have to check, if at least one DataFrame is not empty.
             keys_to_use = keys_to_use if keys_to_use != [] else keys
-            return (
-                concat([results[k] for k in keys_to_use], keys=keys_to_use, axis=1),
-                True,
+            axis = 0 if isinstance(obj, ABCSeries) else 1
+            result = concat({k: results[k] for k in keys_to_use}, axis=axis)
+        elif any(is_ndframe):
+            # There is a mix of NDFrames and scalars
+            raise ValueError(
+                "cannot perform both aggregation "
+                "and transformation operations "
+                "simultaneously"
             )
+        else:
+            from pandas import Series
 
-        elif isinstance(obj, ABCSeries) and is_any_series():
-
-            # we have a dict of Series
-            # return a MI Series
-            try:
-                result = concat(results)
-            except TypeError as err:
-                # we want to give a nice error here if
-                # we have non-same sized objects, so
-                # we don't automatically broadcast
-
-                raise ValueError(
-                    "cannot perform both aggregation "
-                    "and transformation operations "
-                    "simultaneously"
-                ) from err
-
-            return result, True
-
-        # fall thru
-        from pandas import DataFrame, Series
-
-        try:
-            result = DataFrame(results)
-        except ValueError:
             # we have a dict of scalars
-
             # GH 36212 use name only if obj is a series
             if obj.ndim == 1:
                 obj = cast("Series", obj)

pandas/core/dtypes/generic.py

@@ -53,6 +53,7 @@ def _check(cls, inst) -> bool:
     },
 )
 
+ABCNDFrame = create_pandas_abc_type("ABCNDFrame", "_typ", ("series", "dataframe"))
 ABCSeries = create_pandas_abc_type("ABCSeries", "_typ", ("series",))
 ABCDataFrame = create_pandas_abc_type("ABCDataFrame", "_typ", ("dataframe",))
 

pandas/core/frame.py

@@ -7442,9 +7442,9 @@ def _gotitem(
 
     >>> df.agg({'A' : ['sum', 'min'], 'B' : ['min', 'max']})
             A    B
-    max   NaN  8.0
-    min   1.0  2.0
     sum  12.0  NaN
+    min   1.0  2.0
+    max   NaN  8.0
 
     Aggregate different functions over the columns and rename the index of the resulting
     DataFrame.

pandas/tests/frame/apply/test_frame_apply.py

@@ -1254,7 +1254,7 @@ def test_agg_reduce(self, axis, float_frame):
         # dict input with lists with multiple
         func = dict([(name1, ["mean", "sum"]), (name2, ["sum", "max"])])
         result = float_frame.agg(func, axis=axis)
-        expected = DataFrame(
+        expected = pd.concat(
             dict(
                 [
                     (
@@ -1278,7 +1278,8 @@ def test_agg_reduce(self, axis, float_frame):
                         ),
                     ),
                 ]
-            )
+            ),
+            axis=1,
         )
         expected = expected.T if axis in {1, "columns"} else expected
         tm.assert_frame_equal(result, expected)