CLN: named parameters for GroupBy.(mean|median|var|std) (#31485)

Author: topper-123

doc/source/whatsnew/v1.1.0.rst

@@ -60,6 +60,9 @@ Backwards incompatible API changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 - :meth:`DataFrame.swaplevels` now raises a  ``TypeError`` if the axis is not a :class:`MultiIndex`.
   Previously a ``AttributeError`` was raised (:issue:`31126`)
+- :meth:`DataFrameGroupby.mean` and :meth:`SeriesGroupby.mean` (and similarly for :meth:`~DataFrameGroupby.median`, :meth:`~DataFrameGroupby.std`` and :meth:`~DataFrameGroupby.var``)
+  now raise a  ``TypeError`` if a not-accepted keyword argument is passed into it.
+  Previously a ``UnsupportedFunctionCall`` was raised (``AssertionError`` if ``min_count`` passed into :meth:`~DataFrameGroupby.median``) (:issue:`31485`)
 
 
 .. ---------------------------------------------------------------------------

pandas/core/groupby/groupby.py

@@ -1180,10 +1180,16 @@ def count(self):
 
     @Substitution(name="groupby")
     @Substitution(see_also=_common_see_also)
-    def mean(self, *args, **kwargs):
+    def mean(self, numeric_only: bool = True):
         """
         Compute mean of groups, excluding missing values.
 
+        Parameters
+        ----------
+        numeric_only : bool, default True
+            Include only float, int, boolean columns. If None, will attempt to use
+            everything, then use only numeric data.
+
         Returns
         -------
         pandas.Series or pandas.DataFrame
@@ -1222,33 +1228,40 @@ def mean(self, *args, **kwargs):
         2    4.0
         Name: B, dtype: float64
         """
-        nv.validate_groupby_func("mean", args, kwargs, ["numeric_only"])
         return self._cython_agg_general(
-            "mean", alt=lambda x, axis: Series(x).mean(**kwargs), **kwargs
+            "mean",
+            alt=lambda x, axis: Series(x).mean(numeric_only=numeric_only),
+            numeric_only=numeric_only,
         )
 
     @Substitution(name="groupby")
     @Appender(_common_see_also)
-    def median(self, **kwargs):
+    def median(self, numeric_only=True):
         """
         Compute median of groups, excluding missing values.
 
         For multiple groupings, the result index will be a MultiIndex
 
+        Parameters
+        ----------
+        numeric_only : bool, default True
+            Include only float, int, boolean columns. If None, will attempt to use
+            everything, then use only numeric data.
+
         Returns
         -------
         Series or DataFrame
             Median of values within each group.
         """
         return self._cython_agg_general(
             "median",
-            alt=lambda x, axis: Series(x).median(axis=axis, **kwargs),
-            **kwargs,
+            alt=lambda x, axis: Series(x).median(axis=axis, numeric_only=numeric_only),
+            numeric_only=numeric_only,
         )
 
     @Substitution(name="groupby")
     @Appender(_common_see_also)
-    def std(self, ddof: int = 1, *args, **kwargs):
+    def std(self, ddof: int = 1):
         """
         Compute standard deviation of groups, excluding missing values.
 
@@ -1266,12 +1279,11 @@ def std(self, ddof: int = 1, *args, **kwargs):
         """
 
         # TODO: implement at Cython level?
-        nv.validate_groupby_func("std", args, kwargs)
-        return np.sqrt(self.var(ddof=ddof, **kwargs))
+        return np.sqrt(self.var(ddof=ddof))
 
     @Substitution(name="groupby")
     @Appender(_common_see_also)
-    def var(self, ddof: int = 1, *args, **kwargs):
+    def var(self, ddof: int = 1):
         """
         Compute variance of groups, excluding missing values.
 
@@ -1287,15 +1299,14 @@ def var(self, ddof: int = 1, *args, **kwargs):
         Series or DataFrame
             Variance of values within each group.
         """
-        nv.validate_groupby_func("var", args, kwargs)
         if ddof == 1:
             return self._cython_agg_general(
-                "var", alt=lambda x, axis: Series(x).var(ddof=ddof, **kwargs), **kwargs
+                "var", alt=lambda x, axis: Series(x).var(ddof=ddof)
             )
         else:
-            f = lambda x: x.var(ddof=ddof, **kwargs)
+            func = lambda x: x.var(ddof=ddof)
             with _group_selection_context(self):
-                return self._python_agg_general(f)
+                return self._python_agg_general(func)
 
     @Substitution(name="groupby")
     @Appender(_common_see_also)

pandas/tests/groupby/test_function.py

@@ -671,7 +671,7 @@ def test_nsmallest():
     tm.assert_series_equal(gb.nsmallest(3, keep="last"), e)
 
 
-@pytest.mark.parametrize("func", ["mean", "var", "std", "cumprod", "cumsum"])
+@pytest.mark.parametrize("func", ["cumprod", "cumsum"])
 def test_numpy_compat(func):
     # see gh-12811
     df = pd.DataFrame({"A": [1, 2, 1], "B": [1, 2, 3]})