REF: make EA reductions, nanops funcs keyword-only (#37541)

* REF: make EA reductions, nanops funcs keyword-only

* whatsnew

Author: jbrockmendel

doc/source/whatsnew/v1.2.0.rst

@@ -545,6 +545,7 @@ ExtensionArray
 - Fixed bug where ``astype()`` with equal dtype and ``copy=False`` would return a new object (:issue:`284881`)
 - Fixed bug when applying a NumPy ufunc with multiple outputs to a :class:`pandas.arrays.IntegerArray` returning None (:issue:`36913`)
 - Fixed an inconsistency in :class:`PeriodArray`'s ``__init__`` signature to those of :class:`DatetimeArray` and :class:`TimedeltaArray` (:issue:`37289`)
+- Reductions for :class:`BooleanArray`, :class:`Categorical`, :class:`DatetimeArray`, :class:`FloatingArray`, :class:`IntegerArray`, :class:`PeriodArray`, :class:`TimedeltaArray`, and :class:`PandasArray` are now keyword-only methods (:issue:`37541`)
 
 Other
 ^^^^^

pandas/core/arrays/boolean.py

@@ -424,7 +424,7 @@ def _values_for_argsort(self) -> np.ndarray:
         data[self._mask] = -1
         return data
 
-    def any(self, skipna: bool = True, **kwargs):
+    def any(self, *, skipna: bool = True, **kwargs):
         """
         Return whether any element is True.
 
@@ -492,7 +492,7 @@ def any(self, skipna: bool = True, **kwargs):
             else:
                 return self.dtype.na_value
 
-    def all(self, skipna: bool = True, **kwargs):
+    def all(self, *, skipna: bool = True, **kwargs):
         """
         Return whether all elements are True.
 

pandas/core/arrays/categorical.py

@@ -1945,7 +1945,7 @@ def _reverse_indexer(self) -> Dict[Hashable, np.ndarray]:
     # Reductions
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         """
         The minimum value of the object.
 
@@ -1981,7 +1981,7 @@ def min(self, skipna=True, **kwargs):
         return self.categories[pointer]
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         """
         The maximum value of the object.
 

pandas/core/arrays/datetimelike.py

@@ -1245,7 +1245,7 @@ def __isub__(self, other):
     # --------------------------------------------------------------
     # Reductions
 
-    def min(self, axis=None, skipna=True, *args, **kwargs):
+    def min(self, *, axis=None, skipna=True, **kwargs):
         """
         Return the minimum value of the Array or minimum along
         an axis.
@@ -1256,7 +1256,7 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
         Index.min : Return the minimum value in an Index.
         Series.min : Return the minimum value in a Series.
         """
-        nv.validate_min(args, kwargs)
+        nv.validate_min((), kwargs)
         nv.validate_minmax_axis(axis, self.ndim)
 
         if is_period_dtype(self.dtype):
@@ -1276,7 +1276,7 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def max(self, axis=None, skipna=True, *args, **kwargs):
+    def max(self, *, axis=None, skipna=True, **kwargs):
         """
         Return the maximum value of the Array or maximum along
         an axis.
@@ -1289,7 +1289,7 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
         """
         # TODO: skipna is broken with max.
         # See https://github.com/pandas-dev/pandas/issues/24265
-        nv.validate_max(args, kwargs)
+        nv.validate_max((), kwargs)
         nv.validate_minmax_axis(axis, self.ndim)
 
         if is_period_dtype(self.dtype):
@@ -1309,7 +1309,7 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def mean(self, skipna=True, axis: Optional[int] = 0):
+    def mean(self, *, skipna=True, axis: Optional[int] = 0):
         """
         Return the mean value of the Array.
 
@@ -1350,8 +1350,8 @@ def mean(self, skipna=True, axis: Optional[int] = 0):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def median(self, axis: Optional[int] = None, skipna: bool = True, *args, **kwargs):
-        nv.validate_median(args, kwargs)
+    def median(self, *, axis: Optional[int] = None, skipna: bool = True, **kwargs):
+        nv.validate_median((), kwargs)
 
         if axis is not None and abs(axis) >= self.ndim:
             raise ValueError("abs(axis) must be less than ndim")

pandas/core/arrays/floating.py

@@ -439,19 +439,19 @@ def _cmp_method(self, other, op):
 
         return BooleanArray(result, mask)
 
-    def sum(self, skipna=True, min_count=0, **kwargs):
+    def sum(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_sum((), kwargs)
         return super()._reduce("sum", skipna=skipna, min_count=min_count)
 
-    def prod(self, skipna=True, min_count=0, **kwargs):
+    def prod(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_prod((), kwargs)
         return super()._reduce("prod", skipna=skipna, min_count=min_count)
 
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         nv.validate_min((), kwargs)
         return super()._reduce("min", skipna=skipna)
 
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         nv.validate_max((), kwargs)
         return super()._reduce("max", skipna=skipna)
 

pandas/core/arrays/integer.py

@@ -603,19 +603,19 @@ def _arith_method(self, other, op):
 
         return self._maybe_mask_result(result, mask, other, op_name)
 
-    def sum(self, skipna=True, min_count=0, **kwargs):
+    def sum(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_sum((), kwargs)
         return super()._reduce("sum", skipna=skipna, min_count=min_count)
 
-    def prod(self, skipna=True, min_count=0, **kwargs):
+    def prod(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_prod((), kwargs)
         return super()._reduce("prod", skipna=skipna, min_count=min_count)
 
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         nv.validate_min((), kwargs)
         return super()._reduce("min", skipna=skipna)
 
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         nv.validate_max((), kwargs)
         return super()._reduce("max", skipna=skipna)
 

pandas/core/arrays/numpy_.py

@@ -271,77 +271,83 @@ def _values_for_factorize(self) -> Tuple[np.ndarray, int]:
     # ------------------------------------------------------------------------
     # Reductions
 
-    def any(self, axis=None, out=None, keepdims=False, skipna=True):
+    def any(self, *, axis=None, out=None, keepdims=False, skipna=True):
         nv.validate_any((), dict(out=out, keepdims=keepdims))
         return nanops.nanany(self._ndarray, axis=axis, skipna=skipna)
 
-    def all(self, axis=None, out=None, keepdims=False, skipna=True):
+    def all(self, *, axis=None, out=None, keepdims=False, skipna=True):
         nv.validate_all((), dict(out=out, keepdims=keepdims))
         return nanops.nanall(self._ndarray, axis=axis, skipna=skipna)
 
-    def min(self, skipna: bool = True, **kwargs) -> Scalar:
+    def min(self, *, skipna: bool = True, **kwargs) -> Scalar:
         nv.validate_min((), kwargs)
         result = masked_reductions.min(
             values=self.to_numpy(), mask=self.isna(), skipna=skipna
         )
         return result
 
-    def max(self, skipna: bool = True, **kwargs) -> Scalar:
+    def max(self, *, skipna: bool = True, **kwargs) -> Scalar:
         nv.validate_max((), kwargs)
         result = masked_reductions.max(
             values=self.to_numpy(), mask=self.isna(), skipna=skipna
         )
         return result
 
-    def sum(self, axis=None, skipna=True, min_count=0, **kwargs) -> Scalar:
+    def sum(self, *, axis=None, skipna=True, min_count=0, **kwargs) -> Scalar:
         nv.validate_sum((), kwargs)
         return nanops.nansum(
             self._ndarray, axis=axis, skipna=skipna, min_count=min_count
         )
 
-    def prod(self, axis=None, skipna=True, min_count=0, **kwargs) -> Scalar:
+    def prod(self, *, axis=None, skipna=True, min_count=0, **kwargs) -> Scalar:
         nv.validate_prod((), kwargs)
         return nanops.nanprod(
             self._ndarray, axis=axis, skipna=skipna, min_count=min_count
         )
 
-    def mean(self, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
+    def mean(self, *, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
         nv.validate_mean((), dict(dtype=dtype, out=out, keepdims=keepdims))
         return nanops.nanmean(self._ndarray, axis=axis, skipna=skipna)
 
     def median(
-        self, axis=None, out=None, overwrite_input=False, keepdims=False, skipna=True
+        self, *, axis=None, out=None, overwrite_input=False, keepdims=False, skipna=True
     ):
         nv.validate_median(
             (), dict(out=out, overwrite_input=overwrite_input, keepdims=keepdims)
         )
         return nanops.nanmedian(self._ndarray, axis=axis, skipna=skipna)
 
-    def std(self, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True):
+    def std(
+        self, *, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True
+    ):
         nv.validate_stat_ddof_func(
             (), dict(dtype=dtype, out=out, keepdims=keepdims), fname="std"
         )
         return nanops.nanstd(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
 
-    def var(self, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True):
+    def var(
+        self, *, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True
+    ):
         nv.validate_stat_ddof_func(
             (), dict(dtype=dtype, out=out, keepdims=keepdims), fname="var"
         )
         return nanops.nanvar(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
 
-    def sem(self, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True):
+    def sem(
+        self, *, axis=None, dtype=None, out=None, ddof=1, keepdims=False, skipna=True
+    ):
         nv.validate_stat_ddof_func(
             (), dict(dtype=dtype, out=out, keepdims=keepdims), fname="sem"
         )
         return nanops.nansem(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
 
-    def kurt(self, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
+    def kurt(self, *, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
         nv.validate_stat_ddof_func(
             (), dict(dtype=dtype, out=out, keepdims=keepdims), fname="kurt"
         )
         return nanops.nankurt(self._ndarray, axis=axis, skipna=skipna)
 
-    def skew(self, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
+    def skew(self, *, axis=None, dtype=None, out=None, keepdims=False, skipna=True):
         nv.validate_stat_ddof_func(
             (), dict(dtype=dtype, out=out, keepdims=keepdims), fname="skew"
         )

pandas/core/arrays/timedeltas.py

@@ -370,6 +370,7 @@ def __iter__(self):
 
     def sum(
         self,
+        *,
         axis=None,
         dtype=None,
         out=None,