TYP: more return types from ruff

Author: twoertwein

pandas/core/apply.py

@@ -827,7 +827,7 @@ def generate_numba_apply_func(
     def apply_with_numba(self):
         pass
 
-    def validate_values_for_numba(self):
+    def validate_values_for_numba(self) -> None:
         # Validate column dtyps all OK
         for colname, dtype in self.obj.dtypes.items():
             if not is_numeric_dtype(dtype):

pandas/core/array_algos/replace.py

@@ -67,7 +67,7 @@ def compare_or_regex_search(
 
     def _check_comparison_types(
         result: ArrayLike | bool, a: ArrayLike, b: Scalar | Pattern
-    ):
+    ) -> None:
         """
         Raises an error if the two arrays (a,b) cannot be compared.
         Otherwise, returns the comparison result as expected.

pandas/core/arrays/arrow/accessors.py

@@ -39,7 +39,7 @@ def __init__(self, data, validation_msg: str) -> None:
     def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
         pass
 
-    def _validate(self, data):
+    def _validate(self, data) -> None:
         dtype = data.dtype
         if not isinstance(dtype, ArrowDtype):
             # Raise AttributeError so that inspect can handle non-struct Series.

pandas/core/arrays/arrow/extension_types.py

@@ -135,7 +135,7 @@ def to_pandas_dtype(self) -> IntervalDtype:
 """
 
 
-def patch_pyarrow():
+def patch_pyarrow() -> None:
     # starting from pyarrow 14.0.1, it has its own mechanism
     if not pa_version_under14p1:
         return

pandas/core/arrays/categorical.py

@@ -2164,7 +2164,9 @@ def __contains__(self, key) -> bool:
     # ------------------------------------------------------------------
     # Rendering Methods
 
-    def _formatter(self, boxed: bool = False):
+    # error: Return type "None" of "_formatter" incompatible with return
+    # type "Callable[[Any], str | None]" in supertype "ExtensionArray"
+    def _formatter(self, boxed: bool = False) -> None:  # type: ignore[override]
         # Returning None here will cause format_array to do inference.
         return None
 
@@ -2890,7 +2892,7 @@ def __init__(self, data) -> None:
         self._freeze()
 
     @staticmethod
-    def _validate(data):
+    def _validate(data) -> None:
         if not isinstance(data.dtype, CategoricalDtype):
             raise AttributeError("Can only use .cat accessor with a 'category' dtype")
 

pandas/core/arrays/datetimelike.py

@@ -2058,7 +2058,7 @@ def freq(self, value) -> None:
         self._freq = value
 
     @final
-    def _maybe_pin_freq(self, freq, validate_kwds: dict):
+    def _maybe_pin_freq(self, freq, validate_kwds: dict) -> None:
         """
         Constructor helper to pin the appropriate `freq` attribute.  Assumes
         that self._freq is currently set to any freq inferred in
@@ -2092,7 +2092,7 @@ def _maybe_pin_freq(self, freq, validate_kwds: dict):
 
     @final
     @classmethod
-    def _validate_frequency(cls, index, freq: BaseOffset, **kwargs):
+    def _validate_frequency(cls, index, freq: BaseOffset, **kwargs) -> None:
         """
         Validate that a frequency is compatible with the values of a given
         Datetime Array/Index or Timedelta Array/Index

pandas/core/arrays/sparse/accessor.py

@@ -30,7 +30,7 @@ def __init__(self, data=None) -> None:
         self._parent = data
         self._validate(data)
 
-    def _validate(self, data):
+    def _validate(self, data) -> None:
         raise NotImplementedError
 
 
@@ -50,7 +50,7 @@ class SparseAccessor(BaseAccessor, PandasDelegate):
     array([2, 2, 2])
     """
 
-    def _validate(self, data):
+    def _validate(self, data) -> None:
         if not isinstance(data.dtype, SparseDtype):
             raise AttributeError(self._validation_msg)
 
@@ -243,7 +243,7 @@ class SparseFrameAccessor(BaseAccessor, PandasDelegate):
     0.5
     """
 
-    def _validate(self, data):
+    def _validate(self, data) -> None:
         dtypes = data.dtypes
         if not all(isinstance(t, SparseDtype) for t in dtypes):
             raise AttributeError(self._validation_msg)

pandas/core/arrays/sparse/array.py

@@ -1830,7 +1830,9 @@ def __repr__(self) -> str:
         pp_index = printing.pprint_thing(self.sp_index)
         return f"{pp_str}\nFill: {pp_fill}\n{pp_index}"
 
-    def _formatter(self, boxed: bool = False):
+    # error: Return type "None" of "_formatter" incompatible with return
+    # type "Callable[[Any], str | None]" in supertype "ExtensionArray"
+    def _formatter(self, boxed: bool = False) -> None:  # type: ignore[override]
         # Defer to the formatter from the GenericArrayFormatter calling us.
         # This will infer the correct formatter from the dtype of the values.
         return None

pandas/core/arrays/sparse/scipy_sparse.py

@@ -27,7 +27,7 @@
     )
 
 
-def _check_is_partition(parts: Iterable, whole: Iterable):
+def _check_is_partition(parts: Iterable, whole: Iterable) -> None:
     whole = set(whole)
     parts = [set(x) for x in parts]
     if set.intersection(*parts) != set():

pandas/core/arrays/string_.py

@@ -364,7 +364,7 @@ def __init__(self, values, copy: bool = False) -> None:
             self._validate()
         NDArrayBacked.__init__(self, self._ndarray, StringDtype(storage="python"))
 
-    def _validate(self):
+    def _validate(self) -> None:
         """Validate that we only store NA or strings."""
         if len(self._ndarray) and not lib.is_string_array(self._ndarray, skipna=True):
             raise ValueError("StringArray requires a sequence of strings or pandas.NA")

pandas/core/computation/eval.py

@@ -72,7 +72,7 @@ def _check_engine(engine: str | None) -> str:
     return engine
 
 
-def _check_parser(parser: str):
+def _check_parser(parser: str) -> None:
     """
     Make sure a valid parser is passed.
 
@@ -91,7 +91,7 @@ def _check_parser(parser: str):
         )
 
 
-def _check_resolvers(resolvers):
+def _check_resolvers(resolvers) -> None:
     if resolvers is not None:
         for resolver in resolvers:
             if not hasattr(resolver, "__getitem__"):
@@ -102,7 +102,7 @@ def _check_resolvers(resolvers):
                 )
 
 
-def _check_expression(expr):
+def _check_expression(expr) -> None:
     """
     Make sure an expression is not an empty string
 
@@ -149,7 +149,7 @@ def _convert_expression(expr) -> str:
     return s
 
 
-def _check_for_locals(expr: str, stack_level: int, parser: str):
+def _check_for_locals(expr: str, stack_level: int, parser: str) -> None:
     at_top_of_stack = stack_level == 0
     not_pandas_parser = parser != "pandas"
 

pandas/core/computation/ops.py

@@ -491,7 +491,7 @@ def stringify(value):
                 v = v.tz_convert("UTC")
             self.lhs.update(v)
 
-    def _disallow_scalar_only_bool_ops(self):
+    def _disallow_scalar_only_bool_ops(self) -> None:
         rhs = self.rhs
         lhs = self.lhs
 

pandas/core/dtypes/cast.py

@@ -231,7 +231,7 @@ def _maybe_unbox_datetimelike(value: Scalar, dtype: DtypeObj) -> Scalar:
     return value
 
 
-def _disallow_mismatched_datetimelike(value, dtype: DtypeObj):
+def _disallow_mismatched_datetimelike(value, dtype: DtypeObj) -> None:
     """
     numpy allows np.array(dt64values, dtype="timedelta64[ns]") and
     vice-versa, but we do not want to allow this, so we need to

pandas/core/frame.py

@@ -4316,7 +4316,7 @@ def _setitem_array(self, key, value):
             else:
                 self._iset_not_inplace(key, value)
 
-    def _iset_not_inplace(self, key, value):
+    def _iset_not_inplace(self, key, value) -> None:
         # GH#39510 when setting with df[key] = obj with a list-like key and
         #  list-like value, we iterate over those listlikes and set columns
         #  one at a time.  This is different from dispatching to
@@ -4360,7 +4360,7 @@ def igetitem(obj, i: int):
             finally:
                 self.columns = orig_columns
 
-    def _setitem_frame(self, key, value):
+    def _setitem_frame(self, key, value) -> None:
         # support boolean setting with DataFrame input, e.g.
         # df[df > df2] = 0
         if isinstance(key, np.ndarray):

pandas/core/generic.py

@@ -4394,7 +4394,7 @@ def _check_is_chained_assignment_possible(self) -> bool_t:
         return False
 
     @final
-    def _check_setitem_copy(self, t: str = "setting", force: bool_t = False):
+    def _check_setitem_copy(self, t: str = "setting", force: bool_t = False) -> None:
         """
 
         Parameters
@@ -4510,7 +4510,7 @@ def __delitem__(self, key) -> None:
     # Unsorted
 
     @final
-    def _check_inplace_and_allows_duplicate_labels(self, inplace: bool_t):
+    def _check_inplace_and_allows_duplicate_labels(self, inplace: bool_t) -> None:
         if inplace and not self.flags.allows_duplicate_labels:
             raise ValueError(
                 "Cannot specify 'inplace=True' when "

pandas/core/indexes/base.py

@@ -3209,7 +3209,7 @@ def _get_reconciled_name_object(self, other):
         return self
 
     @final
-    def _validate_sort_keyword(self, sort):
+    def _validate_sort_keyword(self, sort) -> None:
         if sort not in [None, False, True]:
             raise ValueError(
                 "The 'sort' keyword only takes the values of "
@@ -6051,7 +6051,7 @@ def argsort(self, *args, **kwargs) -> npt.NDArray[np.intp]:
         #  by RangeIndex, MultIIndex
         return self._data.argsort(*args, **kwargs)
 
-    def _check_indexing_error(self, key):
+    def _check_indexing_error(self, key) -> None:
         if not is_scalar(key):
             # if key is not a scalar, directly raise an error (the code below
             # would convert to numpy arrays and raise later any way) - GH29926

pandas/core/indexes/multi.py

@@ -1571,7 +1571,7 @@ def _format_multi(
     def _get_names(self) -> FrozenList:
         return FrozenList(self._names)
 
-    def _set_names(self, names, *, level=None, validate: bool = True):
+    def _set_names(self, names, *, level=None, validate: bool = True) -> None:
         """
         Set new names on index. Each name has to be a hashable type.
 

pandas/core/indexing.py

@@ -911,7 +911,7 @@ def __setitem__(self, key, value) -> None:
         iloc = self if self.name == "iloc" else self.obj.iloc
         iloc._setitem_with_indexer(indexer, value, self.name)
 
-    def _validate_key(self, key, axis: AxisInt):
+    def _validate_key(self, key, axis: AxisInt) -> None:
         """
         Ensure that key is valid for current indexer.
 
@@ -1225,7 +1225,7 @@ class _LocIndexer(_LocationIndexer):
     # Key Checks
 
     @doc(_LocationIndexer._validate_key)
-    def _validate_key(self, key, axis: Axis):
+    def _validate_key(self, key, axis: Axis) -> None:
         # valid for a collection of labels (we check their presence later)
         # slice of labels (where start-end in labels)
         # slice of integers (only if in the labels)
@@ -1572,7 +1572,7 @@ class _iLocIndexer(_LocationIndexer):
     # -------------------------------------------------------------------
     # Key Checks
 
-    def _validate_key(self, key, axis: AxisInt):
+    def _validate_key(self, key, axis: AxisInt) -> None:
         if com.is_bool_indexer(key):
             if hasattr(key, "index") and isinstance(key.index, Index):
                 if key.index.inferred_type == "integer":
@@ -1783,7 +1783,7 @@ def _get_setitem_indexer(self, key):
 
     # -------------------------------------------------------------------
 
-    def _setitem_with_indexer(self, indexer, value, name: str = "iloc"):
+    def _setitem_with_indexer(self, indexer, value, name: str = "iloc") -> None:
         """
         _setitem_with_indexer is for setting values on a Series/DataFrame
         using positional indexers.
@@ -2038,7 +2038,7 @@ def _setitem_with_indexer_split_path(self, indexer, value, name: str):
             for loc in ilocs:
                 self._setitem_single_column(loc, value, pi)
 
-    def _setitem_with_indexer_2d_value(self, indexer, value):
+    def _setitem_with_indexer_2d_value(self, indexer, value) -> None:
         # We get here with np.ndim(value) == 2, excluding DataFrame,
         #  which goes through _setitem_with_indexer_frame_value
         pi = indexer[0]
@@ -2060,7 +2060,9 @@ def _setitem_with_indexer_2d_value(self, indexer, value):
                 value_col = value_col.tolist()
             self._setitem_single_column(loc, value_col, pi)
 
-    def _setitem_with_indexer_frame_value(self, indexer, value: DataFrame, name: str):
+    def _setitem_with_indexer_frame_value(
+        self, indexer, value: DataFrame, name: str
+    ) -> None:
         ilocs = self._ensure_iterable_column_indexer(indexer[1])
 
         sub_indexer = list(indexer)

pandas/core/internals/base.py

@@ -53,7 +53,7 @@
 
 
 class _AlreadyWarned:
-    def __init__(self):
+    def __init__(self) -> None:
         # This class is used on the manager level to the block level to
         # ensure that we warn only once. The block method can update the
         # warned_already option without returning a value to keep the

pandas/core/internals/managers.py

@@ -1940,13 +1940,15 @@ def _post_setstate(self) -> None:
     def _block(self) -> Block:
         return self.blocks[0]
 
+    # error: Cannot override writeable attribute with read-only property
     @property
-    def _blknos(self):
+    def _blknos(self) -> None:  # type: ignore[override]
         """compat with BlockManager"""
         return None
 
+    # error: Cannot override writeable attribute with read-only property
     @property
-    def _blklocs(self):
+    def _blklocs(self) -> None:  # type: ignore[override]
         """compat with BlockManager"""
         return None
 

pandas/core/ops/array_ops.py

@@ -591,7 +591,7 @@ def maybe_prepare_scalar_for_op(obj, shape: Shape):
 }
 
 
-def _bool_arith_check(op, a: np.ndarray, b):
+def _bool_arith_check(op, a: np.ndarray, b) -> None:
     """
     In contrast to numpy, pandas raises an error for certain operations
     with booleans.

pandas/core/reshape/concat.py

@@ -765,7 +765,7 @@ def _get_concat_axis(self) -> Index:
 
         return concat_axis
 
-    def _maybe_check_integrity(self, concat_index: Index):
+    def _maybe_check_integrity(self, concat_index: Index) -> None:
         if self.verify_integrity:
             if not concat_index.is_unique:
                 overlap = concat_index[concat_index.duplicated()].unique()

pandas/core/reshape/encoding.py

@@ -169,7 +169,7 @@ def get_dummies(
             data_to_encode = data[columns]
 
         # validate prefixes and separator to avoid silently dropping cols
-        def check_len(item, name: str):
+        def check_len(item, name: str) -> None:
             if is_list_like(item):
                 if not len(item) == data_to_encode.shape[1]:
                     len_msg = (

pandas/core/reshape/merge.py

@@ -2091,7 +2091,7 @@ def _maybe_require_matching_dtypes(
     ) -> None:
         # TODO: why do we do this for AsOfMerge but not the others?
 
-        def _check_dtype_match(left: ArrayLike, right: ArrayLike, i: int):
+        def _check_dtype_match(left: ArrayLike, right: ArrayLike, i: int) -> None:
             if left.dtype != right.dtype:
                 if isinstance(left.dtype, CategoricalDtype) and isinstance(
                     right.dtype, CategoricalDtype

pandas/core/reshape/reshape.py

@@ -188,7 +188,7 @@ def _make_sorted_values(self, values: np.ndarray) -> np.ndarray:
             return sorted_values
         return values
 
-    def _make_selectors(self):
+    def _make_selectors(self) -> None:
         new_levels = self.new_index_levels
 
         # make the mask