API: Remove kwargs from GroupBy (#29511)

Author: topper-123

pandas/core/generic.py

@@ -7830,7 +7830,6 @@ def groupby(
         group_keys=True,
         squeeze=False,
         observed=False,
-        **kwargs
     ):
         """
         Group DataFrame or Series using a mapper or by a Series of columns.
@@ -7876,10 +7875,6 @@ def groupby(
 
             .. versionadded:: 0.23.0
 
-        **kwargs
-            Optional, only accepts keyword argument 'mutated' and is passed
-            to groupby.
-
         Returns
         -------
         DataFrameGroupBy or SeriesGroupBy
@@ -7941,12 +7936,13 @@ def groupby(
         Captive      210.0
         Wild         185.0
         """
-        from pandas.core.groupby.groupby import groupby
+        from pandas.core.groupby.groupby import get_groupby
 
         if level is None and by is None:
             raise TypeError("You have to supply one of 'by' and 'level'")
         axis = self._get_axis_number(axis)
-        return groupby(
+
+        return get_groupby(
             self,
             by=by,
             axis=axis,
@@ -7956,7 +7952,6 @@ def groupby(
             group_keys=group_keys,
             squeeze=squeeze,
             observed=observed,
-            **kwargs
         )
 
     def asfreq(self, freq, method=None, how=None, normalize=False, fill_value=None):

pandas/core/groupby/generic.py

@@ -62,7 +62,7 @@
     GroupBy,
     _apply_docs,
     _transform_template,
-    groupby,
+    get_groupby,
 )
 from pandas.core.index import Index, MultiIndex, _all_indexes_same
 import pandas.core.indexes.base as ibase
@@ -996,7 +996,7 @@ def _cython_agg_blocks(
                     #  reductions; see GH#28949
                     obj = obj.iloc[:, 0]
 
-                s = groupby(obj, self.grouper)
+                s = get_groupby(obj, self.grouper)
                 try:
                     result = s.aggregate(lambda x: alt(x, axis=self.axis))
                 except TypeError:

pandas/core/groupby/groupby.py

@@ -26,7 +26,6 @@ class providing the base-class of operations.
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
 from pandas.util._decorators import Appender, Substitution, cache_readonly
-from pandas.util._validators import validate_kwargs
 
 from pandas.core.dtypes.cast import maybe_downcast_to_dtype
 from pandas.core.dtypes.common import (
@@ -349,12 +348,12 @@ def __init__(
         grouper=None,
         exclusions=None,
         selection=None,
-        as_index=True,
-        sort=True,
-        group_keys=True,
-        squeeze=False,
-        observed=False,
-        **kwargs
+        as_index: bool = True,
+        sort: bool = True,
+        group_keys: bool = True,
+        squeeze: bool = False,
+        observed: bool = False,
+        mutated: bool = False,
     ):
 
         self._selection = selection
@@ -376,7 +375,7 @@ def __init__(
         self.group_keys = group_keys
         self.squeeze = squeeze
         self.observed = observed
-        self.mutated = kwargs.pop("mutated", False)
+        self.mutated = mutated
 
         if grouper is None:
             from pandas.core.groupby.grouper import get_grouper
@@ -396,9 +395,6 @@ def __init__(
         self.grouper = grouper
         self.exclusions = set(exclusions) if exclusions else set()
 
-        # we accept no other args
-        validate_kwargs("group", kwargs, {})
-
     def __len__(self) -> int:
         return len(self.groups)
 
@@ -2482,7 +2478,22 @@ def _reindex_output(self, output):
 
 
 @Appender(GroupBy.__doc__)
-def groupby(obj: NDFrame, by, **kwds):
+def get_groupby(
+    obj: NDFrame,
+    by=None,
+    axis: int = 0,
+    level=None,
+    grouper=None,
+    exclusions=None,
+    selection=None,
+    as_index: bool = True,
+    sort: bool = True,
+    group_keys: bool = True,
+    squeeze: bool = False,
+    observed: bool = False,
+    mutated: bool = False,
+):
+
     if isinstance(obj, Series):
         from pandas.core.groupby.generic import SeriesGroupBy
 
@@ -2496,4 +2507,18 @@ def groupby(obj: NDFrame, by, **kwds):
     else:
         raise TypeError("invalid type: {obj}".format(obj=obj))
 
-    return klass(obj, by, **kwds)
+    return klass(
+        obj=obj,
+        keys=by,
+        axis=axis,
+        level=level,
+        grouper=grouper,
+        exclusions=exclusions,
+        selection=selection,
+        as_index=as_index,
+        sort=sort,
+        group_keys=group_keys,
+        squeeze=squeeze,
+        observed=observed,
+        mutated=mutated,
+    )

pandas/core/resample.py

@@ -21,7 +21,7 @@
 from pandas.core.generic import _shared_docs
 from pandas.core.groupby.base import GroupByMixin
 from pandas.core.groupby.generic import SeriesGroupBy
-from pandas.core.groupby.groupby import GroupBy, _GroupBy, _pipe_template, groupby
+from pandas.core.groupby.groupby import GroupBy, _GroupBy, _pipe_template, get_groupby
 from pandas.core.groupby.grouper import Grouper
 from pandas.core.groupby.ops import BinGrouper
 from pandas.core.indexes.datetimes import DatetimeIndex, date_range
@@ -334,7 +334,7 @@ def _gotitem(self, key, ndim, subset=None):
         grouper = self.grouper
         if subset is None:
             subset = self.obj
-        grouped = groupby(subset, by=None, grouper=grouper, axis=self.axis)
+        grouped = get_groupby(subset, by=None, grouper=grouper, axis=self.axis)
 
         # try the key selection
         try:
@@ -353,7 +353,7 @@ def _groupby_and_aggregate(self, how, grouper=None, *args, **kwargs):
 
         obj = self._selected_obj
 
-        grouped = groupby(obj, by=None, grouper=grouper, axis=self.axis)
+        grouped = get_groupby(obj, by=None, grouper=grouper, axis=self.axis)
 
         try:
             if isinstance(obj, ABCDataFrame) and callable(how):

pandas/tests/window/test_grouper.py

@@ -3,6 +3,7 @@
 
 import pandas as pd
 from pandas import DataFrame, Series
+from pandas.core.groupby.groupby import get_groupby
 import pandas.util.testing as tm
 
 
@@ -13,18 +14,18 @@ def setup_method(self, method):
 
     def test_mutated(self):
 
-        msg = r"group\(\) got an unexpected keyword argument 'foo'"
+        msg = r"groupby\(\) got an unexpected keyword argument 'foo'"
         with pytest.raises(TypeError, match=msg):
             self.frame.groupby("A", foo=1)
 
         g = self.frame.groupby("A")
         assert not g.mutated
-        g = self.frame.groupby("A", mutated=True)
+        g = get_groupby(self.frame, by="A", mutated=True)
         assert g.mutated
 
     def test_getitem(self):
         g = self.frame.groupby("A")
-        g_mutated = self.frame.groupby("A", mutated=True)
+        g_mutated = get_groupby(self.frame, by="A", mutated=True)
 
         expected = g_mutated.B.apply(lambda x: x.rolling(2).mean())
 
@@ -45,7 +46,7 @@ def test_getitem_multiple(self):
         # GH 13174
         g = self.frame.groupby("A")
         r = g.rolling(2)
-        g_mutated = self.frame.groupby("A", mutated=True)
+        g_mutated = get_groupby(self.frame, by="A", mutated=True)
         expected = g_mutated.B.apply(lambda x: x.rolling(2).count())
 
         result = r.B.count()