FIX-#2463: fixed 'drop' parameter at groupby.aggregation

Signed-off-by: Dmitry Chigarev <dmitry.chigarev@intel.com>

modin/pandas/groupby.py

@@ -28,6 +28,7 @@
 from pandas.core.dtypes.common import is_list_like
 from pandas.core.aggregation import reconstruct_func
 import pandas.core.common as com
+from types import BuiltinFunctionType
 
 from modin.error_message import ErrorMessage
 from modin.utils import _inherit_docstrings, try_cast_to_pandas
@@ -358,6 +359,13 @@ def aggregate(self, func=None, *args, **kwargs):
             # so we throw a different message
             raise NotImplementedError("axis other than 0 is not supported")
 
+        if (
+            callable(func)
+            and isinstance(func, BuiltinFunctionType)
+            and func.__name__ in dir(self)
+        ):
+            func = func.__name__
+
         relabeling_required = False
         if isinstance(func, dict) or func is None:
 
@@ -389,6 +397,12 @@ def _reconstruct_func(func, **kwargs):
                 *args,
                 **kwargs,
             )
+        elif callable(func):
+            return self._apply_agg_function(
+                lambda grp, *args, **kwargs: grp.aggregate(func, *args, **kwargs),
+                *args,
+                **kwargs,
+            )
         elif isinstance(func, str):
             # Using "getattr" here masks possible AttributeError which we throw
             # in __getattr__, so we should call __getattr__ directly instead.
@@ -398,7 +412,6 @@ def _reconstruct_func(func, **kwargs):
 
         result = self._apply_agg_function(
             func,
-            drop=self._as_index,
             *args,
             **kwargs,
         )

modin/pandas/test/test_groupby.py

@@ -151,6 +151,7 @@ def test_mixed_dtypes_groupby(as_index):
             eval_skew(modin_groupby, pandas_groupby)
 
         agg_functions = [
+            lambda df: df.sum(),
             "min",
             min,
             "max",
@@ -358,7 +359,7 @@ def maybe_get_columns(df, by):
         eval_var(modin_groupby, pandas_groupby)
         eval_skew(modin_groupby, pandas_groupby)
 
-    agg_functions = ["min", "max", min, sum]
+    agg_functions = [lambda df: df.sum(), "min", "max", min, sum]
     for func in agg_functions:
         eval_agg(modin_groupby, pandas_groupby, func)
         eval_aggregate(modin_groupby, pandas_groupby, func)
@@ -491,6 +492,7 @@ def test_single_group_row_groupby():
     eval_std(modin_groupby, pandas_groupby)
 
     agg_functions = [
+        lambda df: df.sum(),
         "min",
         "max",
         max,
@@ -613,7 +615,15 @@ def test_large_row_groupby(is_by_category):
     # eval_prod(modin_groupby, pandas_groupby) causes overflows
     eval_std(modin_groupby, pandas_groupby)
 
-    agg_functions = ["min", "max", min, sum, {"A": "sum"}, {"A": "max", "B": "sum", "C": "min"}]
+    agg_functions = [
+        lambda df: df.sum(),
+        "min",
+        "max",
+        min,
+        sum,
+        {"A": "sum"},
+        {"A": "max", "B": "sum", "C": "min"},
+    ]
     for func in agg_functions:
         eval_agg(modin_groupby, pandas_groupby, func)
         eval_aggregate(modin_groupby, pandas_groupby, func)
@@ -870,7 +880,7 @@ def test_series_groupby(by, as_index_series_or_dataframe):
             eval_var(modin_groupby, pandas_groupby)
             eval_skew(modin_groupby, pandas_groupby)
 
-        agg_functions = ["min", "max", max, sum]
+        agg_functions = [lambda df: df.sum(), "min", "max", max, sum]
         for func in agg_functions:
             eval_agg(modin_groupby, pandas_groupby, func)
             eval_aggregate(modin_groupby, pandas_groupby, func)