remove string return annotations

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -145,11 +145,12 @@ repos:
         language: pygrep
         types_or: [python, cython]
     -   id: unwanted-typing
-        name: Check for use of comment-based annotation syntax and missing error codes
+        name: Check for outdated annotation syntax and missing error codes
         entry: |
             (?x)
             \#\ type:\ (?!ignore)|
-            \#\ type:\s?ignore(?!\[)
+            \#\ type:\s?ignore(?!\[)|
+            \)\ ->\ \"
         language: pygrep
         types: [python]
     -   id: np-bool

pandas/compat/pickle_compat.py

@@ -1,6 +1,7 @@
 """
 Support pre-0.12 series pickle compatibility.
 """
+from __future__ import annotations
 
 import contextlib
 import copy
@@ -64,7 +65,7 @@ class _LoadSparseSeries:
     # https://github.com/python/mypy/issues/1020
     # error: Incompatible return type for "__new__" (returns "Series", but must return
     # a subtype of "_LoadSparseSeries")
-    def __new__(cls) -> "Series":  # type: ignore[misc]
+    def __new__(cls) -> Series:  # type: ignore[misc]
         from pandas import Series
 
         warnings.warn(
@@ -82,7 +83,7 @@ class _LoadSparseFrame:
     # https://github.com/python/mypy/issues/1020
     # error: Incompatible return type for "__new__" (returns "DataFrame", but must
     # return a subtype of "_LoadSparseFrame")
-    def __new__(cls) -> "DataFrame":  # type: ignore[misc]
+    def __new__(cls) -> DataFrame:  # type: ignore[misc]
         from pandas import DataFrame
 
         warnings.warn(

pandas/core/arrays/boolean.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import numbers
 from typing import TYPE_CHECKING, List, Optional, Tuple, Type, Union
 import warnings
@@ -93,7 +95,7 @@ def _is_numeric(self) -> bool:
 
     def __from_arrow__(
         self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
-    ) -> "BooleanArray":
+    ) -> BooleanArray:
         """
         Construct BooleanArray from pyarrow Array/ChunkedArray.
         """
@@ -276,7 +278,7 @@ def dtype(self) -> BooleanDtype:
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
-    ) -> "BooleanArray":
+    ) -> BooleanArray:
         if dtype:
             assert dtype == "boolean"
         values, mask = coerce_to_array(scalars, copy=copy)
@@ -291,7 +293,7 @@ def _from_sequence_of_strings(
         copy: bool = False,
         true_values: Optional[List[str]] = None,
         false_values: Optional[List[str]] = None,
-    ) -> "BooleanArray":
+    ) -> BooleanArray:
         true_values_union = cls._TRUE_VALUES.union(true_values or [])
         false_values_union = cls._FALSE_VALUES.union(false_values or [])
 

pandas/core/arrays/categorical.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from csv import QUOTE_NONNUMERIC
 from functools import partial
 import operator
@@ -740,7 +742,7 @@ def _set_categories(self, categories, fastpath=False):
 
         self._dtype = new_dtype
 
-    def _set_dtype(self, dtype: CategoricalDtype) -> "Categorical":
+    def _set_dtype(self, dtype: CategoricalDtype) -> Categorical:
         """
         Internal method for directly updating the CategoricalDtype
 
@@ -1740,7 +1742,7 @@ def fillna(self, value=None, method=None, limit=None):
     def _ndarray(self) -> np.ndarray:
         return self._codes
 
-    def _from_backing_data(self, arr: np.ndarray) -> "Categorical":
+    def _from_backing_data(self, arr: np.ndarray) -> Categorical:
         return self._constructor(arr, dtype=self.dtype, fastpath=True)
 
     def _box_func(self, i: int):
@@ -2160,7 +2162,7 @@ def _concat_same_type(
 
     # ------------------------------------------------------------------
 
-    def _encode_with_my_categories(self, other: "Categorical") -> "Categorical":
+    def _encode_with_my_categories(self, other: "Categorical") -> Categorical:
         """
         Re-encode another categorical using this Categorical's categories.
 

pandas/core/arrays/datetimes.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from datetime import datetime, time, timedelta, tzinfo
 from typing import Optional, Union, cast
 import warnings
@@ -291,7 +293,7 @@ def __init__(self, values, dtype=DT64NS_DTYPE, freq=None, copy=False):
     @classmethod
     def _simple_new(
         cls, values, freq: Optional[BaseOffset] = None, dtype=DT64NS_DTYPE
-    ) -> "DatetimeArray":
+    ) -> DatetimeArray:
         assert isinstance(values, np.ndarray)
         if values.dtype != DT64NS_DTYPE:
             assert values.dtype == "i8"

pandas/core/arrays/floating.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from typing import List, Optional, Tuple, Type
 import warnings
 
@@ -242,14 +244,14 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype=None, copy: bool = False
-    ) -> "FloatingArray":
+    ) -> 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
-    ) -> "FloatingArray":
+    ) -> FloatingArray:
         scalars = to_numeric(strings, errors="raise")
         return cls._from_sequence(scalars, dtype=dtype, copy=copy)
 

pandas/core/arrays/integer.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from typing import Dict, List, Optional, Tuple, Type
 import warnings
 
@@ -303,14 +305,14 @@ def __abs__(self):
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
-    ) -> "IntegerArray":
+    ) -> IntegerArray:
         values, mask = coerce_to_array(scalars, dtype=dtype, copy=copy)
         return IntegerArray(values, mask)
 
     @classmethod
     def _from_sequence_of_strings(
         cls, strings, *, dtype: Optional[Dtype] = None, copy: bool = False
-    ) -> "IntegerArray":
+    ) -> IntegerArray:
         scalars = to_numeric(strings, errors="raise")
         return cls._from_sequence(scalars, dtype=dtype, copy=copy)
 

pandas/core/arrays/interval.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import operator
 from operator import le, lt
 import textwrap
@@ -861,7 +863,7 @@ def copy(self: IntervalArrayT) -> IntervalArrayT:
     def isna(self) -> np.ndarray:
         return isna(self._left)
 
-    def shift(self, periods: int = 1, fill_value: object = None) -> "IntervalArray":
+    def shift(self, periods: int = 1, fill_value: object = None) -> IntervalArray:
         if not len(self) or periods == 0:
             return self.copy()
 

pandas/core/arrays/masked.py

@@ -346,7 +346,7 @@ def factorize(self, na_sentinel: int = -1) -> Tuple[np.ndarray, ExtensionArray]:
         uniques = type(self)(uniques, np.zeros(len(uniques), dtype=bool))
         return codes, uniques
 
-    def value_counts(self, dropna: bool = True) -> "Series":
+    def value_counts(self, dropna: bool = True) -> Series:
         """
         Returns a Series containing counts of each unique value.
 

pandas/core/arrays/numpy_.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import numbers
 from typing import Optional, Tuple, Type, Union
 
@@ -75,7 +77,7 @@ def _is_boolean(self) -> bool:
         return self.kind == "b"
 
     @classmethod
-    def construct_from_string(cls, string: str) -> "PandasDtype":
+    def construct_from_string(cls, string: str) -> PandasDtype:
         try:
             dtype = np.dtype(string)
         except TypeError as err:
@@ -174,7 +176,7 @@ def __init__(self, values: Union[np.ndarray, "PandasArray"], copy: bool = False)
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
-    ) -> "PandasArray":
+    ) -> PandasArray:
         if isinstance(dtype, PandasDtype):
             dtype = dtype._dtype
 
@@ -184,10 +186,10 @@ def _from_sequence(
         return cls(result)
 
     @classmethod
-    def _from_factorized(cls, values, original) -> "PandasArray":
+    def _from_factorized(cls, values, original) -> PandasArray:
         return cls(values)
 
-    def _from_backing_data(self, arr: np.ndarray) -> "PandasArray":
+    def _from_backing_data(self, arr: np.ndarray) -> PandasArray:
         return type(self)(arr)
 
     # ------------------------------------------------------------------------

pandas/core/arrays/period.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from datetime import timedelta
 import operator
 from typing import Any, Callable, List, Optional, Sequence, Type, Union
@@ -191,7 +193,7 @@ def _simple_new(
         values: np.ndarray,
         freq: Optional[BaseOffset] = None,
         dtype: Optional[Dtype] = None,
-    ) -> "PeriodArray":
+    ) -> PeriodArray:
         # alias for PeriodArray.__init__
         assertion_msg = "Should be numpy array of type i8"
         assert isinstance(values, np.ndarray) and values.dtype == "i8", assertion_msg
@@ -204,7 +206,7 @@ def _from_sequence(
         *,
         dtype: Optional[Dtype] = None,
         copy: bool = False,
-    ) -> "PeriodArray":
+    ) -> PeriodArray:
         if dtype and isinstance(dtype, PeriodDtype):
             freq = dtype.freq
         else:
@@ -225,11 +227,11 @@ def _from_sequence(
     @classmethod
     def _from_sequence_of_strings(
         cls, strings, *, dtype: Optional[Dtype] = None, copy=False
-    ) -> "PeriodArray":
+    ) -> PeriodArray:
         return cls._from_sequence(strings, dtype=dtype, copy=copy)
 
     @classmethod
-    def _from_datetime64(cls, data, freq, tz=None) -> "PeriodArray":
+    def _from_datetime64(cls, data, freq, tz=None) -> PeriodArray:
         """
         Construct a PeriodArray from a datetime64 array
 
@@ -504,7 +506,7 @@ def _box_func(self, x) -> Union[Period, NaTType]:
         return Period._from_ordinal(ordinal=x, freq=self.freq)
 
     @doc(**_shared_doc_kwargs, other="PeriodIndex", other_name="PeriodIndex")
-    def asfreq(self, freq=None, how: str = "E") -> "PeriodArray":
+    def asfreq(self, freq=None, how: str = "E") -> PeriodArray:
         """
         Convert the {klass} to the specified frequency `freq`.
 
@@ -675,7 +677,7 @@ def _sub_period_array(self, other):
 
     def _addsub_int_array(
         self, other: np.ndarray, op: Callable[[Any, Any], Any]
-    ) -> "PeriodArray":
+    ) -> PeriodArray:
         """
         Add or subtract array of integers; equivalent to applying
         `_time_shift` pointwise.

pandas/core/arrays/sparse/array.py

@@ -1,6 +1,8 @@
 """
 SparseArray data structure
 """
+from __future__ import annotations
+
 from collections import abc
 import numbers
 import operator
@@ -812,7 +814,7 @@ 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)
@@ -1403,7 +1405,7 @@ def _arith_method(self, other, op):
                     other = SparseArray(other, fill_value=self.fill_value, dtype=dtype)
                 return _sparse_array_op(self, other, op, op_name)
 
-    def _cmp_method(self, other, op) -> "SparseArray":
+    def _cmp_method(self, other, op) -> SparseArray:
         if not is_scalar(other) and not isinstance(other, type(self)):
             # convert list-like to ndarray
             other = np.asarray(other)
@@ -1431,19 +1433,19 @@ def _cmp_method(self, other, op) -> "SparseArray":
 
     _logical_method = _cmp_method
 
-    def _unary_method(self, op) -> "SparseArray":
+    def _unary_method(self, op) -> SparseArray:
         fill_value = op(np.array(self.fill_value)).item()
         values = op(self.sp_values)
         dtype = SparseDtype(values.dtype, fill_value)
         return type(self)._simple_new(values, self.sp_index, dtype)
 
-    def __pos__(self) -> "SparseArray":
+    def __pos__(self) -> SparseArray:
         return self._unary_method(operator.pos)
 
-    def __neg__(self) -> "SparseArray":
+    def __neg__(self) -> SparseArray:
         return self._unary_method(operator.neg)
 
-    def __invert__(self) -> "SparseArray":
+    def __invert__(self) -> SparseArray:
         return self._unary_method(operator.invert)
 
     # ----------

pandas/core/arrays/sparse/dtype.py

@@ -1,4 +1,5 @@
 """Sparse Dtype"""
+from __future__ import annotations
 
 import re
 from typing import TYPE_CHECKING, Any, List, Optional, Tuple, Type
@@ -185,7 +186,7 @@ def construct_array_type(cls) -> Type["SparseArray"]:
         return SparseArray
 
     @classmethod
-    def construct_from_string(cls, string: str) -> "SparseDtype":
+    def construct_from_string(cls, string: str) -> SparseDtype:
         """
         Construct a SparseDtype from a string form.
 

pandas/core/arrays/string_.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from typing import TYPE_CHECKING, Optional, Type, Union
 
 import numpy as np
@@ -84,7 +86,7 @@ def __repr__(self) -> str:
 
     def __from_arrow__(
         self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
-    ) -> "StringArray":
+    ) -> StringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.
         """

pandas/core/arrays/string_arrow.py

@@ -105,7 +105,7 @@ def __repr__(self) -> str:
 
     def __from_arrow__(
         self, array: Union["pa.Array", "pa.ChunkedArray"]
-    ) -> "ArrowStringArray":
+    ) -> ArrowStringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.
         """
@@ -507,7 +507,7 @@ def __setitem__(self, key: Union[int, np.ndarray], value: Any) -> None:
 
     def take(
         self, indices: Sequence[int], allow_fill: bool = False, fill_value: Any = None
-    ) -> "ExtensionArray":
+    ) -> ExtensionArray:
         """
         Take elements from an array.