CLN, TYP use string types in generics

.pre-commit-config.yaml

@@ -150,9 +150,15 @@ repos:
             (?x)
             \#\ type:\ (?!ignore)|
             \#\ type:\s?ignore(?!\[)|
-            \)\ ->\ \"
+
+            # string return type annotation
+            \)\ ->\ \"|
+
+            # string type annotation in generic
+            (Callable|Dict|Iterable|Iterator|List|Mapping|MutableMapping|Sequence|Set|Tuple|Type|Union)\[[^\]]*\".+?\"[^\]]*\]
         language: pygrep
         types: [python]
+        exclude: ^pandas/_typing\.py$
     -   id: np-bool
         name: Check for use of np.bool instead of np.bool_
         entry: np\.bool[^_8]

pandas/core/aggregation.py

@@ -3,6 +3,8 @@
 kwarg aggregations in groupby and DataFrame/Series aggregation
 """
 
+from __future__ import annotations
+
 from collections import defaultdict
 from functools import partial
 from typing import (
@@ -296,7 +298,7 @@ def relabel_result(
     func: Dict[str, List[Union[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.
@@ -323,7 +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

pandas/core/algorithms.py

@@ -567,7 +567,7 @@ def factorize(
     sort: bool = False,
     na_sentinel: Optional[int] = -1,
     size_hint: Optional[int] = None,
-) -> Tuple[np.ndarray, Union[np.ndarray, "Index"]]:
+) -> Tuple[np.ndarray, Union[np.ndarray, Index]]:
     """
     Encode the object as an enumerated type or categorical variable.
 

pandas/core/arrays/boolean.py

@@ -72,7 +72,7 @@ def numpy_dtype(self) -> np.dtype:
         return np.dtype("bool")
 
     @classmethod
-    def construct_array_type(cls) -> Type["BooleanArray"]:
+    def construct_array_type(cls) -> Type[BooleanArray]:
         """
         Return the array type associated with this dtype.
 
@@ -94,7 +94,7 @@ def _is_numeric(self) -> bool:
         return True
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> BooleanArray:
         """
         Construct BooleanArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/categorical.py

@@ -422,7 +422,7 @@ def dtype(self) -> CategoricalDtype:
         return self._dtype
 
     @property
-    def _constructor(self) -> Type["Categorical"]:
+    def _constructor(self) -> Type[Categorical]:
         return Categorical
 
     @classmethod

pandas/core/arrays/floating.py

@@ -47,7 +47,7 @@ def _is_numeric(self) -> bool:
         return True
 
     @classmethod
-    def construct_array_type(cls) -> Type["FloatingArray"]:
+    def construct_array_type(cls) -> Type[FloatingArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/integer.py

@@ -57,7 +57,7 @@ def _is_numeric(self) -> bool:
         return True
 
     @classmethod
-    def construct_array_type(cls) -> Type["IntegerArray"]:
+    def construct_array_type(cls) -> Type[IntegerArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/numeric.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import datetime
 import numbers
 from typing import TYPE_CHECKING, Any, List, Union
@@ -25,7 +27,7 @@
 
 class NumericDtype(BaseMaskedDtype):
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> BaseMaskedArray:
         """
         Construct IntegerArray/FloatingArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/numpy_.py

@@ -89,7 +89,7 @@ def construct_from_string(cls, string: str) -> PandasDtype:
         return cls(dtype)
 
     @classmethod
-    def construct_array_type(cls) -> Type["PandasArray"]:
+    def construct_array_type(cls) -> Type[PandasArray]:
         """
         Return the array type associated with this dtype.
 
@@ -155,7 +155,7 @@ class PandasArray(
     # ------------------------------------------------------------------------
     # Constructors
 
-    def __init__(self, values: Union[np.ndarray, "PandasArray"], copy: bool = False):
+    def __init__(self, values: Union[np.ndarray, PandasArray], copy: bool = False):
         if isinstance(values, type(self)):
             values = values._ndarray
         if not isinstance(values, np.ndarray):

pandas/core/arrays/period.py

@@ -201,7 +201,7 @@ def _simple_new(
 
     @classmethod
     def _from_sequence(
-        cls: Type["PeriodArray"],
+        cls: Type[PeriodArray],
         scalars: Union[Sequence[Optional[Period]], AnyArrayLike],
         *,
         dtype: Optional[Dtype] = None,

pandas/core/arrays/sparse/array.py

@@ -896,7 +896,7 @@ def _take_with_fill(self, indices, fill_value=None) -> np.ndarray:
 
         return taken
 
-    def _take_without_fill(self, indices) -> Union[np.ndarray, "SparseArray"]:
+    def _take_without_fill(self, indices) -> Union[np.ndarray, SparseArray]:
         to_shift = indices < 0
         indices = indices.copy()
 

pandas/core/arrays/sparse/dtype.py

@@ -173,7 +173,7 @@ def __repr__(self) -> str:
         return self.name
 
     @classmethod
-    def construct_array_type(cls) -> Type["SparseArray"]:
+    def construct_array_type(cls) -> Type[SparseArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/string_.py

@@ -71,7 +71,7 @@ def type(self) -> Type[str]:
         return str
 
     @classmethod
-    def construct_array_type(cls) -> Type["StringArray"]:
+    def construct_array_type(cls) -> Type[StringArray]:
         """
         Return the array type associated with this dtype.
 
@@ -85,7 +85,7 @@ def __repr__(self) -> str:
         return "StringDtype"
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> StringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/string_arrow.py

@@ -87,7 +87,7 @@ def type(self) -> Type[str]:
         return str
 
     @classmethod
-    def construct_array_type(cls) -> Type["ArrowStringArray"]:
+    def construct_array_type(cls) -> Type[ArrowStringArray]:
         """
         Return the array type associated with this dtype.
 
@@ -104,7 +104,7 @@ def __repr__(self) -> str:
         return "ArrowStringDtype"
 
     def __from_arrow__(
-        self, array: Union["pa.Array", "pa.ChunkedArray"]
+        self, array: Union[pa.Array, pa.ChunkedArray]
     ) -> ArrowStringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.

pandas/core/computation/ops.py

@@ -2,6 +2,8 @@
 Operator classes for eval.
 """
 
+from __future__ import annotations
+
 from datetime import datetime
 from distutils.version import LooseVersion
 from functools import partial
@@ -203,7 +205,7 @@ class Op:
 
     op: str
 
-    def __init__(self, op: str, operands: Iterable[Union[Term, "Op"]], encoding=None):
+    def __init__(self, op: str, operands: Iterable[Union[Term, Op]], encoding=None):
         self.op = _bool_op_map.get(op, op)
         self.operands = operands
         self.encoding = encoding

pandas/core/describe.py

@@ -164,7 +164,7 @@ def describe_frame(
     return d
 
 
-def reorder_columns(ldesc: Sequence["Series"]) -> List[Hashable]:
+def reorder_columns(ldesc: Sequence[Series]) -> List[Hashable]:
     """Set a convenient order for rows for display."""
     names: List[Hashable] = []
     ldesc_indexes = sorted((x.index for x in ldesc), key=len)

pandas/core/dtypes/base.py

@@ -2,6 +2,8 @@
 Extend pandas with custom array types.
 """
 
+from __future__ import annotations
+
 from typing import TYPE_CHECKING, Any, List, Optional, Tuple, Type, Union
 
 import numpy as np
@@ -186,7 +188,7 @@ def names(self) -> Optional[List[str]]:
         return None
 
     @classmethod
-    def construct_array_type(cls) -> Type["ExtensionArray"]:
+    def construct_array_type(cls) -> Type[ExtensionArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/dtypes/cast.py

@@ -397,7 +397,7 @@ def maybe_cast_result_dtype(dtype: DtypeObj, how: str) -> DtypeObj:
 
 
 def maybe_cast_to_extension_array(
-    cls: Type["ExtensionArray"], obj: ArrayLike, dtype: Optional[ExtensionDtype] = None
+    cls: Type[ExtensionArray], obj: ArrayLike, dtype: Optional[ExtensionDtype] = None
 ) -> ArrayLike:
     """
     Call to `_from_sequence` that returns the object unchanged on Exception.

pandas/core/dtypes/dtypes.py

@@ -59,7 +59,7 @@ class PandasExtensionDtype(ExtensionDtype):
     base = None
     isbuiltin = 0
     isnative = 0
-    _cache: Dict[str_type, "PandasExtensionDtype"] = {}
+    _cache: Dict[str_type, PandasExtensionDtype] = {}
 
     def __str__(self) -> str_type:
         """
@@ -445,7 +445,7 @@ def _hash_categories(categories, ordered: Ordered = True) -> int:
         return np.bitwise_xor.reduce(hashed)
 
     @classmethod
-    def construct_array_type(cls) -> Type["Categorical"]:
+    def construct_array_type(cls) -> Type[Categorical]:
         """
         Return the array type associated with this dtype.
 
@@ -514,7 +514,7 @@ def validate_categories(categories, fastpath: bool = False):
         return categories
 
     def update_dtype(
-        self, dtype: Union[str_type, "CategoricalDtype"]
+        self, dtype: Union[str_type, CategoricalDtype]
     ) -> CategoricalDtype:
         """
         Returns a CategoricalDtype with categories and ordered taken from dtype
@@ -647,7 +647,7 @@ class DatetimeTZDtype(PandasExtensionDtype):
     _match = re.compile(r"(datetime64|M8)\[(?P<unit>.+), (?P<tz>.+)\]")
     _cache: Dict[str_type, PandasExtensionDtype] = {}
 
-    def __init__(self, unit: Union[str_type, "DatetimeTZDtype"] = "ns", tz=None):
+    def __init__(self, unit: Union[str_type, DatetimeTZDtype] = "ns", tz=None):
         if isinstance(unit, DatetimeTZDtype):
             # error: "str" has no attribute "tz"
             unit, tz = unit.unit, unit.tz  # type: ignore[attr-defined]
@@ -694,7 +694,7 @@ def tz(self):
         return self._tz
 
     @classmethod
-    def construct_array_type(cls) -> Type["DatetimeArray"]:
+    def construct_array_type(cls) -> Type[DatetimeArray]:
         """
         Return the array type associated with this dtype.
 
@@ -940,7 +940,7 @@ def is_dtype(cls, dtype: object) -> bool:
         return super().is_dtype(dtype)
 
     @classmethod
-    def construct_array_type(cls) -> Type["PeriodArray"]:
+    def construct_array_type(cls) -> Type[PeriodArray]:
         """
         Return the array type associated with this dtype.
 
@@ -953,7 +953,7 @@ def construct_array_type(cls) -> Type["PeriodArray"]:
         return PeriodArray
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> PeriodArray:
         """
         Construct PeriodArray from pyarrow Array/ChunkedArray.
@@ -1090,7 +1090,7 @@ def subtype(self):
         return self._subtype
 
     @classmethod
-    def construct_array_type(cls) -> Type["IntervalArray"]:
+    def construct_array_type(cls) -> Type[IntervalArray]:
         """
         Return the array type associated with this dtype.
 
@@ -1184,7 +1184,7 @@ def is_dtype(cls, dtype: object) -> bool:
         return super().is_dtype(dtype)
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> IntervalArray:
         """
         Construct IntervalArray from pyarrow Array/ChunkedArray.

pandas/core/frame.py

@@ -9440,8 +9440,8 @@ def resample(
         base: Optional[int] = None,
         on=None,
         level=None,
-        origin: Union[str, "TimestampConvertibleTypes"] = "start_day",
-        offset: Optional["TimedeltaConvertibleTypes"] = None,
+        origin: Union[str, TimestampConvertibleTypes] = "start_day",
+        offset: Optional[TimedeltaConvertibleTypes] = None,
     ) -> Resampler:
         return super().resample(
             rule=rule,

pandas/core/groupby/generic.py

@@ -1690,7 +1690,7 @@ def _wrap_transformed_output(
 
         return result
 
-    def _wrap_agged_blocks(self, blocks: Sequence["Block"], items: Index) -> DataFrame:
+    def _wrap_agged_blocks(self, blocks: Sequence[Block], items: Index) -> DataFrame:
         if not self.as_index:
             index = np.arange(blocks[0].values.shape[-1])
             mgr = BlockManager(blocks, axes=[items, index])

pandas/core/groupby/groupby.py

@@ -1371,7 +1371,7 @@ class GroupBy(BaseGroupBy[FrameOrSeries]):
 
     @final
     @property
-    def _obj_1d_constructor(self) -> Type["Series"]:
+    def _obj_1d_constructor(self) -> Type[Series]:
         # GH28330 preserve subclassed Series/DataFrames
         if isinstance(self.obj, DataFrame):
             return self.obj._constructor_sliced

pandas/core/groupby/grouper.py

@@ -2,6 +2,8 @@
 Provide user facing operators for doing the split part of the
 split-apply-combine paradigm.
 """
+from __future__ import annotations
+
 from typing import Dict, Hashable, List, Optional, Set, Tuple
 import warnings
 
@@ -616,7 +618,7 @@ def get_grouper(
     mutated: bool = False,
     validate: bool = True,
     dropna: bool = True,
-) -> Tuple["ops.BaseGrouper", Set[Hashable], FrameOrSeries]:
+) -> Tuple[ops.BaseGrouper, Set[Hashable], FrameOrSeries]:
     """
     Create and return a BaseGrouper, which is an internal
     mapping of how to create the grouper indexers.

pandas/core/groupby/ops.py

@@ -100,7 +100,7 @@ class BaseGrouper:
     def __init__(
         self,
         axis: Index,
-        groupings: Sequence["grouper.Grouping"],
+        groupings: Sequence[grouper.Grouping],
         sort: bool = True,
         group_keys: bool = True,
         mutated: bool = False,
@@ -119,7 +119,7 @@ def __init__(
         self.dropna = dropna
 
     @property
-    def groupings(self) -> List["grouper.Grouping"]:
+    def groupings(self) -> List[grouper.Grouping]:
         return self._groupings
 
     @property