Fix Up Typing in GroupBy (#26089)

Author: WillAyd

doc/source/whatsnew/v0.25.0.rst

@@ -218,6 +218,7 @@ Other API Changes
 - :meth:`Timestamp.strptime` will now rise a ``NotImplementedError`` (:issue:`25016`)
 - Comparing :class:`Timestamp` with unsupported objects now returns :py:obj:`NotImplemented` instead of raising ``TypeError``. This implies that unsupported rich comparisons are delegated to the other object, and are now consistent with Python 3 behavior for ``datetime`` objects (:issue:`24011`)
 - Bug in :meth:`DatetimeIndex.snap` which didn't preserving the ``name`` of the input :class:`Index` (:issue:`25575`)
+- The ``arg`` argument in :meth:`pandas.core.groupby.DataFrameGroupBy.agg` has been renamed to ``func`` (:issue:`26089`)
 
 .. _whatsnew_0250.deprecations:
 

mypy.ini

@@ -59,15 +59,6 @@ ignore_errors=True
 [mypy-pandas.core.config_init]
 ignore_errors=True
 
-[mypy-pandas.core.groupby.generic]
-ignore_errors=True
-
-[mypy-pandas.core.groupby.groupby]
-ignore_errors=True
-
-[mypy-pandas.core.groupby.ops]
-ignore_errors=True
-
 [mypy-pandas.core.indexes.base]
 ignore_errors=True
 

pandas/core/groupby/generic.py

@@ -144,25 +144,25 @@ def _cython_agg_blocks(self, how, alt=None, numeric_only=True,
 
         return new_items, new_blocks
 
-    def aggregate(self, arg, *args, **kwargs):
+    def aggregate(self, func, *args, **kwargs):
 
         _level = kwargs.pop('_level', None)
-        result, how = self._aggregate(arg, _level=_level, *args, **kwargs)
+        result, how = self._aggregate(func, _level=_level, *args, **kwargs)
         if how is None:
             return result
 
         if result is None:
 
             # grouper specific aggregations
             if self.grouper.nkeys > 1:
-                return self._python_agg_general(arg, *args, **kwargs)
+                return self._python_agg_general(func, *args, **kwargs)
             else:
 
                 # try to treat as if we are passing a list
                 try:
                     assert not args and not kwargs
                     result = self._aggregate_multiple_funcs(
-                        [arg], _level=_level, _axis=self.axis)
+                        [func], _level=_level, _axis=self.axis)
 
                     result.columns = Index(
                         result.columns.levels[0],
@@ -174,7 +174,7 @@ def aggregate(self, arg, *args, **kwargs):
                         # to SparseDataFrame, so we do it here.
                         result = SparseDataFrame(result._data)
                 except Exception:
-                    result = self._aggregate_generic(arg, *args, **kwargs)
+                    result = self._aggregate_generic(func, *args, **kwargs)
 
         if not self.as_index:
             self._insert_inaxis_grouper_inplace(result)

pandas/core/groupby/groupby.py

@@ -12,14 +12,15 @@ class providing the base-class of operations.
 import datetime
 from functools import partial, wraps
 import types
-from typing import Optional, Tuple, Type
+from typing import FrozenSet, Optional, Tuple, Type
 import warnings
 
 import numpy as np
 
 from pandas._config.config import option_context
 
-from pandas._libs import Timestamp, groupby as libgroupby
+from pandas._libs import Timestamp
+import pandas._libs.groupby as libgroupby
 from pandas.compat import set_function_name
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
@@ -325,7 +326,7 @@ def _group_selection_context(groupby):
 
 class _GroupBy(PandasObject, SelectionMixin):
     _group_selection = None
-    _apply_whitelist = frozenset()
+    _apply_whitelist = frozenset()  # type: FrozenSet[str]
 
     def __init__(self, obj, keys=None, axis=0, level=None,
                  grouper=None, exclusions=None, selection=None, as_index=True,

pandas/core/groupby/ops.py

@@ -10,7 +10,9 @@
 
 import numpy as np
 
-from pandas._libs import NaT, groupby as libgroupby, iNaT, lib, reduction
+from pandas._libs import NaT, iNaT, lib
+import pandas._libs.groupby as libgroupby
+import pandas._libs.reduction as reduction
 from pandas.compat import lzip
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import cache_readonly