⬆️ UPGRADE: Autoupdate pre-commit config

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.7.4
+    rev: v2.8.0
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
@@ -192,6 +192,6 @@ repos:
         files: ^pandas/
         exclude: ^pandas/tests/
 -   repo: https://github.com/MarcoGorelli/no-string-hints
-    rev: v0.1.6
+    rev: v0.1.7
     hooks:
     -   id: no-string-hints

pandas/_testing/__init__.py

@@ -107,24 +107,24 @@
 _N = 30
 _K = 4
 
-UNSIGNED_INT_DTYPES: List[Dtype] = ["uint8", "uint16", "uint32", "uint64"]
-UNSIGNED_EA_INT_DTYPES: List[Dtype] = ["UInt8", "UInt16", "UInt32", "UInt64"]
-SIGNED_INT_DTYPES: List[Dtype] = [int, "int8", "int16", "int32", "int64"]
-SIGNED_EA_INT_DTYPES: List[Dtype] = ["Int8", "Int16", "Int32", "Int64"]
+UNSIGNED_INT_DTYPES: list[Dtype] = ["uint8", "uint16", "uint32", "uint64"]
+UNSIGNED_EA_INT_DTYPES: list[Dtype] = ["UInt8", "UInt16", "UInt32", "UInt64"]
+SIGNED_INT_DTYPES: list[Dtype] = [int, "int8", "int16", "int32", "int64"]
+SIGNED_EA_INT_DTYPES: list[Dtype] = ["Int8", "Int16", "Int32", "Int64"]
 ALL_INT_DTYPES = UNSIGNED_INT_DTYPES + SIGNED_INT_DTYPES
 ALL_EA_INT_DTYPES = UNSIGNED_EA_INT_DTYPES + SIGNED_EA_INT_DTYPES
 
-FLOAT_DTYPES: List[Dtype] = [float, "float32", "float64"]
-FLOAT_EA_DTYPES: List[Dtype] = ["Float32", "Float64"]
-COMPLEX_DTYPES: List[Dtype] = [complex, "complex64", "complex128"]
-STRING_DTYPES: List[Dtype] = [str, "str", "U"]
+FLOAT_DTYPES: list[Dtype] = [float, "float32", "float64"]
+FLOAT_EA_DTYPES: list[Dtype] = ["Float32", "Float64"]
+COMPLEX_DTYPES: list[Dtype] = [complex, "complex64", "complex128"]
+STRING_DTYPES: list[Dtype] = [str, "str", "U"]
 
-DATETIME64_DTYPES: List[Dtype] = ["datetime64[ns]", "M8[ns]"]
-TIMEDELTA64_DTYPES: List[Dtype] = ["timedelta64[ns]", "m8[ns]"]
+DATETIME64_DTYPES: list[Dtype] = ["datetime64[ns]", "M8[ns]"]
+TIMEDELTA64_DTYPES: list[Dtype] = ["timedelta64[ns]", "m8[ns]"]
 
-BOOL_DTYPES: List[Dtype] = [bool, "bool"]
-BYTES_DTYPES: List[Dtype] = [bytes, "bytes"]
-OBJECT_DTYPES: List[Dtype] = [object, "object"]
+BOOL_DTYPES: list[Dtype] = [bool, "bool"]
+BYTES_DTYPES: list[Dtype] = [bytes, "bytes"]
+OBJECT_DTYPES: list[Dtype] = [object, "object"]
 
 ALL_REAL_DTYPES = FLOAT_DTYPES + ALL_INT_DTYPES
 ALL_NUMPY_DTYPES = (
@@ -417,7 +417,7 @@ def all_timeseries_index_generator(k: int = 10) -> Iterable[Index]:
     ----------
     k: length of each of the index instances
     """
-    make_index_funcs: List[Callable[..., Index]] = [
+    make_index_funcs: list[Callable[..., Index]] = [
         makeDateIndex,
         makePeriodIndex,
         makeTimedeltaIndex,
@@ -865,7 +865,7 @@ def skipna_wrapper(x):
     return skipna_wrapper
 
 
-def convert_rows_list_to_csv_str(rows_list: List[str]):
+def convert_rows_list_to_csv_str(rows_list: list[str]):
     """
     Convert list of CSV rows to single CSV-formatted string for current OS.
 
@@ -885,7 +885,7 @@ def convert_rows_list_to_csv_str(rows_list: List[str]):
     return sep.join(rows_list) + sep
 
 
-def external_error_raised(expected_exception: Type[Exception]) -> ContextManager:
+def external_error_raised(expected_exception: type[Exception]) -> ContextManager:
     """
     Helper function to mark pytest.raises that have an external error message.
 

pandas/compat/pickle_compat.py

@@ -229,7 +229,7 @@ def load_newobj_ex(self):
     pass
 
 
-def load(fh, encoding: Optional[str] = None, is_verbose: bool = False):
+def load(fh, encoding: str | None = None, is_verbose: bool = False):
     """
     Load a pickle, with a provided encoding,
 

pandas/core/aggregation.py

@@ -47,8 +47,8 @@
 
 
 def reconstruct_func(
-    func: Optional[AggFuncType], **kwargs
-) -> Tuple[bool, Optional[AggFuncType], Optional[List[str]], Optional[List[int]]]:
+    func: AggFuncType | None, **kwargs
+) -> tuple[bool, AggFuncType | None, list[str] | None, list[int] | None]:
     """
     This is the internal function to reconstruct func given if there is relabeling
     or not and also normalize the keyword to get new order of columns.
@@ -86,8 +86,8 @@ def reconstruct_func(
     (False, 'min', None, None)
     """
     relabeling = func is None and is_multi_agg_with_relabel(**kwargs)
-    columns: Optional[List[str]] = None
-    order: Optional[List[int]] = None
+    columns: list[str] | None = None
+    order: list[int] | None = None
 
     if not relabeling:
         if isinstance(func, list) and len(func) > len(set(func)):
@@ -134,7 +134,7 @@ def is_multi_agg_with_relabel(**kwargs) -> bool:
     )
 
 
-def normalize_keyword_aggregation(kwargs: dict) -> Tuple[dict, List[str], List[int]]:
+def normalize_keyword_aggregation(kwargs: dict) -> tuple[dict, list[str], list[int]]:
     """
     Normalize user-provided "named aggregation" kwargs.
     Transforms from the new ``Mapping[str, NamedAgg]`` style kwargs
@@ -190,8 +190,8 @@ def normalize_keyword_aggregation(kwargs: dict) -> Tuple[dict, List[str], List[i
 
 
 def _make_unique_kwarg_list(
-    seq: Sequence[Tuple[Any, Any]]
-) -> Sequence[Tuple[Any, Any]]:
+    seq: Sequence[tuple[Any, Any]]
+) -> Sequence[tuple[Any, Any]]:
     """
     Uniquify aggfunc name of the pairs in the order list
 
@@ -295,10 +295,10 @@ def maybe_mangle_lambdas(agg_spec: Any) -> Any:
 
 def relabel_result(
     result: FrameOrSeries,
-    func: Dict[str, List[Union[Callable, str]]],
+    func: dict[str, list[Callable | str]],
     columns: Iterable[Hashable],
     order: Iterable[int],
-) -> Dict[Hashable, Series]:
+) -> dict[Hashable, Series]:
     """
     Internal function to reorder result if relabelling is True for
     dataframe.agg, and return the reordered result in dict.
@@ -325,7 +325,7 @@ def relabel_result(
     reordered_indexes = [
         pair[0] for pair in sorted(zip(columns, order), key=lambda t: t[1])
     ]
-    reordered_result_in_dict: Dict[Hashable, Series] = {}
+    reordered_result_in_dict: dict[Hashable, Series] = {}
     idx = 0
 
     reorder_mask = not isinstance(result, ABCSeries) and len(result.columns) > 1
@@ -369,7 +369,7 @@ def relabel_result(
 
 def validate_func_kwargs(
     kwargs: dict,
-) -> Tuple[List[str], List[Union[str, Callable[..., Any]]]]:
+) -> tuple[list[str], list[str | Callable[..., Any]]]:
     """
     Validates types of user-provided "named aggregation" kwargs.
     `TypeError` is raised if aggfunc is not `str` or callable.
@@ -495,7 +495,7 @@ def transform_dict_like(
         # GH 15931 - deprecation of renaming keys
         raise SpecificationError("nested renamer is not supported")
 
-    results: Dict[Hashable, FrameOrSeriesUnion] = {}
+    results: dict[Hashable, FrameOrSeriesUnion] = {}
     for name, how in func.items():
         colg = obj._gotitem(name, ndim=1)
         try:
@@ -536,7 +536,7 @@ def transform_str_or_callable(
 
 def agg_list_like(
     obj: AggObjType,
-    arg: List[AggFuncTypeBase],
+    arg: list[AggFuncTypeBase],
     _axis: int,
 ) -> FrameOrSeriesUnion:
     """

pandas/core/algorithms.py

@@ -70,15 +70,15 @@
     from pandas import Categorical, DataFrame, Index, Series
     from pandas.core.arrays import DatetimeArray, TimedeltaArray
 
-_shared_docs: Dict[str, str] = {}
+_shared_docs: dict[str, str] = {}
 
 
 # --------------- #
 # dtype access    #
 # --------------- #
 def _ensure_data(
-    values: ArrayLike, dtype: Optional[DtypeObj] = None
-) -> Tuple[np.ndarray, DtypeObj]:
+    values: ArrayLike, dtype: DtypeObj | None = None
+) -> tuple[np.ndarray, DtypeObj]:
     """
     routine to ensure that our data is of the correct
     input dtype for lower-level routines
@@ -495,7 +495,7 @@ def f(c, v):
 
 def factorize_array(
     values: np.ndarray, na_sentinel: int = -1, size_hint=None, na_value=None, mask=None
-) -> Tuple[np.ndarray, np.ndarray]:
+) -> tuple[np.ndarray, np.ndarray]:
     """
     Factorize an array-like to codes and uniques.
 
@@ -558,9 +558,9 @@ def factorize_array(
 def factorize(
     values,
     sort: bool = False,
-    na_sentinel: Optional[int] = -1,
-    size_hint: Optional[int] = None,
-) -> Tuple[np.ndarray, Union[np.ndarray, Index]]:
+    na_sentinel: int | None = -1,
+    size_hint: int | None = None,
+) -> tuple[np.ndarray, np.ndarray | Index]:
     """
     Encode the object as an enumerated type or categorical variable.
 
@@ -2052,7 +2052,7 @@ def safe_sort(
     na_sentinel: int = -1,
     assume_unique: bool = False,
     verify: bool = True,
-) -> Union[np.ndarray, Tuple[np.ndarray, np.ndarray]]:
+) -> np.ndarray | tuple[np.ndarray, np.ndarray]:
     """
     Sort ``values`` and reorder corresponding ``codes``.
 

pandas/core/apply.py

@@ -58,13 +58,13 @@ def frame_apply(
     func: AggFuncType,
     axis: Axis = 0,
     raw: bool = False,
-    result_type: Optional[str] = None,
+    result_type: str | None = None,
     args=None,
     kwds=None,
 ) -> FrameApply:
     """ construct and return a row or column based frame apply object """
     axis = obj._get_axis_number(axis)
-    klass: Type[FrameApply]
+    klass: type[FrameApply]
     if axis == 0:
         klass = FrameRowApply
     elif axis == 1:
@@ -104,7 +104,7 @@ def __init__(
         obj: AggObjType,
         func,
         raw: bool,
-        result_type: Optional[str],
+        result_type: str | None,
         args,
         kwds,
     ):
@@ -144,7 +144,7 @@ def index(self) -> Index:
     def apply(self) -> FrameOrSeriesUnion:
         pass
 
-    def agg(self) -> Tuple[Optional[FrameOrSeriesUnion], Optional[bool]]:
+    def agg(self) -> tuple[FrameOrSeriesUnion | None, bool | None]:
         """
         Provide an implementation for the aggregators.
 
@@ -188,7 +188,7 @@ def agg(self) -> Tuple[Optional[FrameOrSeriesUnion], Optional[bool]]:
         # caller can react
         return result, True
 
-    def maybe_apply_str(self) -> Optional[FrameOrSeriesUnion]:
+    def maybe_apply_str(self) -> FrameOrSeriesUnion | None:
         """
         Compute apply in case of a string.
 
@@ -212,7 +212,7 @@ def maybe_apply_str(self) -> Optional[FrameOrSeriesUnion]:
                 raise ValueError(f"Operation {f} does not support axis=1")
         return self.obj._try_aggregate_string_function(f, *self.args, **self.kwds)
 
-    def maybe_apply_multiple(self) -> Optional[FrameOrSeriesUnion]:
+    def maybe_apply_multiple(self) -> FrameOrSeriesUnion | None:
         """
         Compute apply in case of a list-like or dict-like.
 
@@ -411,7 +411,7 @@ def apply_standard(self):
         # wrap results
         return self.wrap_results(results, res_index)
 
-    def apply_series_generator(self) -> Tuple[ResType, Index]:
+    def apply_series_generator(self) -> tuple[ResType, Index]:
         assert callable(self.f)
 
         series_gen = self.series_generator
@@ -664,11 +664,11 @@ def apply_standard(self) -> FrameOrSeriesUnion:
 
 
 class GroupByApply(Apply):
-    obj: Union[SeriesGroupBy, DataFrameGroupBy]
+    obj: SeriesGroupBy | DataFrameGroupBy
 
     def __init__(
         self,
-        obj: Union[SeriesGroupBy, DataFrameGroupBy],
+        obj: SeriesGroupBy | DataFrameGroupBy,
         func: AggFuncType,
         args,
         kwds,
@@ -690,11 +690,11 @@ def apply(self):
 
 class ResamplerWindowApply(Apply):
     axis = 0
-    obj: Union[Resampler, BaseWindow]
+    obj: Resampler | BaseWindow
 
     def __init__(
         self,
-        obj: Union[Resampler, BaseWindow],
+        obj: Resampler | BaseWindow,
         func: AggFuncType,
         args,
         kwds,

pandas/core/arrays/_mixins.py

@@ -194,7 +194,7 @@ def unique(self: NDArrayBackedExtensionArrayT) -> NDArrayBackedExtensionArrayT:
     @classmethod
     @doc(ExtensionArray._concat_same_type)
     def _concat_same_type(
-        cls: Type[NDArrayBackedExtensionArrayT],
+        cls: type[NDArrayBackedExtensionArrayT],
         to_concat: Sequence[NDArrayBackedExtensionArrayT],
         axis: int = 0,
     ) -> NDArrayBackedExtensionArrayT:
@@ -236,8 +236,8 @@ def _validate_setitem_value(self, value):
         return value
 
     def __getitem__(
-        self: NDArrayBackedExtensionArrayT, key: Union[int, slice, np.ndarray]
-    ) -> Union[NDArrayBackedExtensionArrayT, Any]:
+        self: NDArrayBackedExtensionArrayT, key: int | slice | np.ndarray
+    ) -> NDArrayBackedExtensionArrayT | Any:
         if lib.is_integer(key):
             # fast-path
             result = self._ndarray[key]
@@ -296,7 +296,7 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
             msg = f"'{type(self).__name__}' does not implement reduction '{name}'"
             raise TypeError(msg)
 
-    def _wrap_reduction_result(self, axis: Optional[int], result):
+    def _wrap_reduction_result(self, axis: int | None, result):
         if axis is None or self.ndim == 1:
             return self._box_func(result)
         return self._from_backing_data(result)