TYP: make more internal funcs keyword-only (#37688)

Author: jbrockmendel

pandas/core/array_algos/masked_reductions.py

@@ -17,6 +17,7 @@ def _sumprod(
     func: Callable,
     values: np.ndarray,
     mask: np.ndarray,
+    *,
     skipna: bool = True,
     min_count: int = 0,
 ):
@@ -52,19 +53,25 @@ def _sumprod(
             return func(values, where=~mask)
 
 
-def sum(values: np.ndarray, mask: np.ndarray, skipna: bool = True, min_count: int = 0):
+def sum(
+    values: np.ndarray, mask: np.ndarray, *, skipna: bool = True, min_count: int = 0
+):
     return _sumprod(
         np.sum, values=values, mask=mask, skipna=skipna, min_count=min_count
     )
 
 
-def prod(values: np.ndarray, mask: np.ndarray, skipna: bool = True, min_count: int = 0):
+def prod(
+    values: np.ndarray, mask: np.ndarray, *, skipna: bool = True, min_count: int = 0
+):
     return _sumprod(
         np.prod, values=values, mask=mask, skipna=skipna, min_count=min_count
     )
 
 
-def _minmax(func: Callable, values: np.ndarray, mask: np.ndarray, skipna: bool = True):
+def _minmax(
+    func: Callable, values: np.ndarray, mask: np.ndarray, *, skipna: bool = True
+):
     """
     Reduction for 1D masked array.
 
@@ -94,9 +101,9 @@ def _minmax(func: Callable, values: np.ndarray, mask: np.ndarray, skipna: bool =
             return libmissing.NA
 
 
-def min(values: np.ndarray, mask: np.ndarray, skipna: bool = True):
+def min(values: np.ndarray, mask: np.ndarray, *, skipna: bool = True):
     return _minmax(np.min, values=values, mask=mask, skipna=skipna)
 
 
-def max(values: np.ndarray, mask: np.ndarray, skipna: bool = True):
+def max(values: np.ndarray, mask: np.ndarray, *, skipna: bool = True):
     return _minmax(np.max, values=values, mask=mask, skipna=skipna)

pandas/core/arrays/_mixins.py

@@ -54,6 +54,7 @@ def _validate_scalar(self, value):
     def take(
         self: _T,
         indices: Sequence[int],
+        *,
         allow_fill: bool = False,
         fill_value: Any = None,
         axis: int = 0,
@@ -246,7 +247,7 @@ def fillna(self: _T, value=None, method=None, limit=None) -> _T:
     # ------------------------------------------------------------------------
     # Reductions
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         meth = getattr(self, name, None)
         if meth:
             return meth(skipna=skipna, **kwargs)

pandas/core/arrays/base.py

@@ -173,7 +173,7 @@ class ExtensionArray:
     # ------------------------------------------------------------------------
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
         """
         Construct a new ExtensionArray from a sequence of scalars.
 
@@ -195,7 +195,7 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
         raise AbstractMethodError(cls)
 
     @classmethod
-    def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
+    def _from_sequence_of_strings(cls, strings, *, dtype=None, copy=False):
         """
         Construct a new ExtensionArray from a sequence of strings.
 
@@ -922,7 +922,11 @@ def repeat(self, repeats, axis=None):
     # ------------------------------------------------------------------------
 
     def take(
-        self, indices: Sequence[int], allow_fill: bool = False, fill_value: Any = None
+        self,
+        indices: Sequence[int],
+        *,
+        allow_fill: bool = False,
+        fill_value: Any = None,
     ) -> "ExtensionArray":
         """
         Take elements from an array.
@@ -1153,7 +1157,7 @@ def _concat_same_type(
     # of objects
     _can_hold_na = True
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         """
         Return a scalar result of performing the reduction operation.
 

pandas/core/arrays/boolean.py

@@ -273,15 +273,17 @@ def dtype(self) -> BooleanDtype:
         return self._dtype
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy: bool = False) -> "BooleanArray":
+    def _from_sequence(
+        cls, scalars, *, dtype=None, copy: bool = False
+    ) -> "BooleanArray":
         if dtype:
             assert dtype == "boolean"
         values, mask = coerce_to_array(scalars, copy=copy)
         return BooleanArray(values, mask)
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings: List[str], dtype=None, copy: bool = False
+        cls, strings: List[str], *, dtype=None, copy: bool = False
     ) -> "BooleanArray":
         def map_string(s):
             if isna(s):
@@ -294,7 +296,7 @@ def map_string(s):
                 raise ValueError(f"{s} cannot be cast to bool")
 
         scalars = [map_string(x) for x in strings]
-        return cls._from_sequence(scalars, dtype, copy)
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
 
     _HANDLED_TYPES = (np.ndarray, numbers.Number, bool, np.bool_)
 
@@ -682,12 +684,12 @@ def _arith_method(self, other, op):
 
         return self._maybe_mask_result(result, mask, other, op_name)
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
 
         if name in {"any", "all"}:
             return getattr(self, name)(skipna=skipna, **kwargs)
 
-        return super()._reduce(name, skipna, **kwargs)
+        return super()._reduce(name, skipna=skipna, **kwargs)
 
     def _maybe_mask_result(self, result, mask, other, op_name: str):
         """

pandas/core/arrays/categorical.py

@@ -385,7 +385,7 @@ def _constructor(self) -> Type["Categorical"]:
         return Categorical
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
         return Categorical(scalars, dtype=dtype)
 
     def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:

pandas/core/arrays/datetimes.py

@@ -301,7 +301,7 @@ def _simple_new(
         return result
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy: bool = False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy: bool = False):
         return cls._from_sequence_not_strict(scalars, dtype=dtype, copy=copy)
 
     @classmethod

pandas/core/arrays/floating.py

@@ -275,16 +275,18 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
         super().__init__(values, mask, copy=copy)
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy: bool = False) -> "FloatingArray":
+    def _from_sequence(
+        cls, scalars, *, dtype=None, copy: bool = False
+    ) -> "FloatingArray":
         values, mask = coerce_to_array(scalars, dtype=dtype, copy=copy)
         return FloatingArray(values, mask)
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, dtype=None, copy: bool = False
+        cls, strings, *, dtype=None, copy: bool = False
     ) -> "FloatingArray":
         scalars = to_numeric(strings, errors="raise")
-        return cls._from_sequence(scalars, dtype, copy)
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
 
     _HANDLED_TYPES = (np.ndarray, numbers.Number)
 

pandas/core/arrays/integer.py

@@ -358,15 +358,17 @@ def __abs__(self):
         return type(self)(np.abs(self._data), self._mask)
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy: bool = False) -> "IntegerArray":
+    def _from_sequence(
+        cls, scalars, *, dtype=None, copy: bool = False
+    ) -> "IntegerArray":
         return integer_array(scalars, dtype=dtype, copy=copy)
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, dtype=None, copy: bool = False
+        cls, strings, *, dtype=None, copy: bool = False
     ) -> "IntegerArray":
         scalars = to_numeric(strings, errors="raise")
-        return cls._from_sequence(scalars, dtype, copy)
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
 
     _HANDLED_TYPES = (np.ndarray, numbers.Number)
 

pandas/core/arrays/interval.py

@@ -227,7 +227,7 @@ def _simple_new(cls, data, closed="right"):
         return result
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
         return cls(scalars, dtype=dtype, copy=copy)
 
     @classmethod
@@ -788,7 +788,7 @@ def shift(self, periods: int = 1, fill_value: object = None) -> "IntervalArray":
             b = empty
         return self._concat_same_type([a, b])
 
-    def take(self, indices, allow_fill=False, fill_value=None, axis=None, **kwargs):
+    def take(self, indices, *, allow_fill=False, fill_value=None, axis=None, **kwargs):
         """
         Take elements from the IntervalArray.
 

pandas/core/arrays/masked.py

@@ -269,6 +269,7 @@ def _concat_same_type(cls: Type[BaseMaskedArrayT], to_concat) -> BaseMaskedArray
     def take(
         self: BaseMaskedArrayT,
         indexer,
+        *,
         allow_fill: bool = False,
         fill_value: Optional[Scalar] = None,
     ) -> BaseMaskedArrayT:
@@ -357,7 +358,7 @@ def value_counts(self, dropna: bool = True) -> "Series":
 
         return Series(counts, index=index)
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         data = self._data
         mask = self._mask
 

pandas/core/arrays/numpy_.py

@@ -172,7 +172,9 @@ def __init__(self, values: Union[np.ndarray, "PandasArray"], copy: bool = False)
         self._dtype = PandasDtype(values.dtype)
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy: bool = False) -> "PandasArray":
+    def _from_sequence(
+        cls, scalars, *, dtype=None, copy: bool = False
+    ) -> "PandasArray":
         if isinstance(dtype, PandasDtype):
             dtype = dtype._dtype
 

pandas/core/arrays/period.py

@@ -192,6 +192,7 @@ def _simple_new(
     def _from_sequence(
         cls: Type["PeriodArray"],
         scalars: Union[Sequence[Optional[Period]], AnyArrayLike],
+        *,
         dtype: Optional[PeriodDtype] = None,
         copy: bool = False,
     ) -> "PeriodArray":
@@ -214,9 +215,9 @@ def _from_sequence(
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, dtype=None, copy=False
+        cls, strings, *, dtype=None, copy=False
     ) -> "PeriodArray":
-        return cls._from_sequence(strings, dtype, copy)
+        return cls._from_sequence(strings, dtype=dtype, copy=copy)
 
     @classmethod
     def _from_datetime64(cls, data, freq, tz=None) -> "PeriodArray":

pandas/core/arrays/sparse/array.py

@@ -484,7 +484,7 @@ def __setitem__(self, key, value):
         raise TypeError(msg)
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
         return cls(scalars, dtype=dtype)
 
     @classmethod
@@ -809,7 +809,7 @@ def _get_val_at(self, loc):
             val = maybe_box_datetimelike(val, self.sp_values.dtype)
             return val
 
-    def take(self, indices, allow_fill=False, fill_value=None) -> "SparseArray":
+    def take(self, indices, *, allow_fill=False, fill_value=None) -> "SparseArray":
         if is_scalar(indices):
             raise ValueError(f"'indices' must be an array, not a scalar '{indices}'.")
         indices = np.asarray(indices, dtype=np.int32)
@@ -1156,7 +1156,7 @@ def nonzero(self):
     # Reductions
     # ------------------------------------------------------------------------
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         method = getattr(self, name, None)
 
         if method is None:

pandas/core/arrays/string_.py

@@ -198,7 +198,7 @@ def _validate(self):
             )
 
     @classmethod
-    def _from_sequence(cls, scalars, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
         if dtype:
             assert dtype == "string"
 
@@ -226,7 +226,7 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
         return new_string_array
 
     @classmethod
-    def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
+    def _from_sequence_of_strings(cls, strings, *, dtype=None, copy=False):
         return cls._from_sequence(strings, dtype=dtype, copy=copy)
 
     def __arrow_array__(self, type=None):
@@ -295,7 +295,7 @@ def astype(self, dtype, copy=True):
 
         return super().astype(dtype, copy)
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         if name in ["min", "max"]:
             return getattr(self, name)(skipna=skipna)
 

pandas/core/arrays/timedeltas.py

@@ -219,7 +219,7 @@ def _simple_new(
 
     @classmethod
     def _from_sequence(
-        cls, data, dtype=TD64NS_DTYPE, copy: bool = False
+        cls, data, *, dtype=TD64NS_DTYPE, copy: bool = False
     ) -> "TimedeltaArray":
         if dtype:
             _validate_td64_dtype(dtype)

pandas/core/base.py

@@ -785,6 +785,7 @@ def _reduce(
         self,
         op,
         name: str,
+        *,
         axis=0,
         skipna=True,
         numeric_only=None,

pandas/core/frame.py

@@ -8719,6 +8719,7 @@ def _reduce(
         self,
         op,
         name: str,
+        *,
         axis=0,
         skipna=True,
         numeric_only=None,

pandas/core/series.py

@@ -4190,7 +4190,15 @@ def f(x):
             )
 
     def _reduce(
-        self, op, name, axis=0, skipna=True, numeric_only=None, filter_type=None, **kwds
+        self,
+        op,
+        name: str,
+        *,
+        axis=0,
+        skipna=True,
+        numeric_only=None,
+        filter_type=None,
+        **kwds,
     ):
         """
         Perform a reduction operation.

pandas/tests/extension/arrow/arrays.py

@@ -159,7 +159,7 @@ def _concat_same_type(cls, to_concat):
     def __invert__(self):
         return type(self).from_scalars(~self._data.to_pandas())
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
         if skipna:
             arr = self[~self.isna()]
         else:

pandas/tests/extension/decimal/array.py

@@ -178,7 +178,7 @@ def _formatter(self, boxed=False):
     def _concat_same_type(cls, to_concat):
         return cls(np.concatenate([x._data for x in to_concat]))
 
-    def _reduce(self, name: str, skipna: bool = True, **kwargs):
+    def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
 
         if skipna:
             # If we don't have any NAs, we can ignore skipna