CLN: add typing to dtype arg in selection of files in core/arrays (GH38808) (pandas-dev#38826)

Author: avinashpancham

pandas/_typing.py

@@ -94,8 +94,9 @@
 Axes = Collection
 
 # dtypes
+NpDtype = Union[str, np.dtype]
 Dtype = Union[
-    "ExtensionDtype", str, np.dtype, Type[Union[str, float, int, complex, bool, object]]
+    "ExtensionDtype", NpDtype, Type[Union[str, float, int, complex, bool, object]]
 ]
 # DtypeArg specifies all allowable dtypes in a functions its dtype argument
 DtypeArg = Union[Dtype, Dict[Label, Dtype]]

pandas/core/arrays/base.py

@@ -25,7 +25,7 @@
 import numpy as np
 
 from pandas._libs import lib
-from pandas._typing import ArrayLike, Shape
+from pandas._typing import ArrayLike, Dtype, Shape
 from pandas.compat import set_function_name
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
@@ -189,7 +189,7 @@ class ExtensionArray:
     # ------------------------------------------------------------------------
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype: Optional[Dtype] = None, copy=False):
         """
         Construct a new ExtensionArray from a sequence of scalars.
 
@@ -211,7 +211,9 @@ 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: Optional[Dtype] = None, copy=False
+    ):
         """
         Construct a new ExtensionArray from a sequence of strings.
 
@@ -391,7 +393,10 @@ def __ne__(self, other: Any) -> ArrayLike:
         return ~(self == other)
 
     def to_numpy(
-        self, dtype=None, copy: bool = False, na_value=lib.no_default
+        self,
+        dtype: Optional[Dtype] = None,
+        copy: bool = False,
+        na_value=lib.no_default,
     ) -> np.ndarray:
         """
         Convert to a NumPy ndarray.
@@ -1065,7 +1070,7 @@ def copy(self: ExtensionArrayT) -> ExtensionArrayT:
         """
         raise AbstractMethodError(self)
 
-    def view(self, dtype=None) -> ArrayLike:
+    def view(self, dtype: Optional[Dtype] = None) -> ArrayLike:
         """
         Return a view on the array.
 

pandas/core/arrays/boolean.py

@@ -1,11 +1,11 @@
 import numbers
-from typing import TYPE_CHECKING, List, Tuple, Type, Union
+from typing import TYPE_CHECKING, List, Optional, Tuple, Type, Union
 import warnings
 
 import numpy as np
 
 from pandas._libs import lib, missing as libmissing
-from pandas._typing import ArrayLike
+from pandas._typing import ArrayLike, Dtype
 from pandas.compat.numpy import function as nv
 
 from pandas.core.dtypes.common import (
@@ -273,7 +273,7 @@ def dtype(self) -> BooleanDtype:
 
     @classmethod
     def _from_sequence(
-        cls, scalars, *, dtype=None, copy: bool = False
+        cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
     ) -> "BooleanArray":
         if dtype:
             assert dtype == "boolean"
@@ -282,7 +282,7 @@ def _from_sequence(
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings: List[str], *, dtype=None, copy: bool = False
+        cls, strings: List[str], *, dtype: Optional[Dtype] = None, copy: bool = False
     ) -> "BooleanArray":
         def map_string(s):
             if isna(s):

pandas/core/arrays/categorical.py

@@ -7,6 +7,7 @@
     Dict,
     Hashable,
     List,
+    Optional,
     Sequence,
     Type,
     TypeVar,
@@ -21,7 +22,7 @@
 
 from pandas._libs import NaT, algos as libalgos, hashtable as htable
 from pandas._libs.lib import no_default
-from pandas._typing import ArrayLike, Dtype, Ordered, Scalar
+from pandas._typing import ArrayLike, Dtype, NpDtype, Ordered, Scalar
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import cache_readonly, deprecate_kwarg
 from pandas.util._validators import validate_bool_kwarg, validate_fillna_kwargs
@@ -318,7 +319,7 @@ def __init__(
         values,
         categories=None,
         ordered=None,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
         fastpath=False,
         copy: bool = True,
     ):
@@ -423,7 +424,7 @@ def _constructor(self) -> Type["Categorical"]:
         return Categorical
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype: Optional[Dtype] = None, copy=False):
         return Categorical(scalars, dtype=dtype, copy=copy)
 
     def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:
@@ -558,7 +559,9 @@ def _from_inferred_categories(
         return cls(codes, dtype=dtype, fastpath=True)
 
     @classmethod
-    def from_codes(cls, codes, categories=None, ordered=None, dtype=None):
+    def from_codes(
+        cls, codes, categories=None, ordered=None, dtype: Optional[Dtype] = None
+    ):
         """
         Make a Categorical type from codes and categories or dtype.
 
@@ -1294,7 +1297,7 @@ def _validate_fill_value(self, fill_value):
 
     # -------------------------------------------------------------
 
-    def __array__(self, dtype=None) -> np.ndarray:
+    def __array__(self, dtype: Optional[NpDtype] = None) -> np.ndarray:
         """
         The numpy array interface.
 

pandas/core/arrays/datetimelike.py

@@ -36,7 +36,7 @@
     integer_op_not_supported,
     round_nsint64,
 )
-from pandas._typing import DatetimeLikeScalar, DtypeObj
+from pandas._typing import DatetimeLikeScalar, Dtype, DtypeObj, NpDtype
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError, NullFrequencyError, PerformanceWarning
 from pandas.util._decorators import Appender, Substitution, cache_readonly
@@ -107,15 +107,15 @@ class DatetimeLikeArrayMixin(OpsMixin, NDArrayBackedExtensionArray):
     _recognized_scalars: Tuple[Type, ...]
     _data: np.ndarray
 
-    def __init__(self, data, dtype=None, freq=None, copy=False):
+    def __init__(self, data, dtype: Optional[Dtype] = None, freq=None, copy=False):
         raise AbstractMethodError(self)
 
     @classmethod
     def _simple_new(
         cls: Type[DatetimeLikeArrayT],
         values: np.ndarray,
         freq: Optional[BaseOffset] = None,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
     ) -> DatetimeLikeArrayT:
         raise AbstractMethodError(cls)
 
@@ -265,7 +265,7 @@ def _formatter(self, boxed=False):
     # ----------------------------------------------------------------
     # Array-Like / EA-Interface Methods
 
-    def __array__(self, dtype=None) -> np.ndarray:
+    def __array__(self, dtype: Optional[NpDtype] = None) -> np.ndarray:
         # used for Timedelta/DatetimeArray, overwritten by PeriodArray
         if is_object_dtype(dtype):
             return np.array(list(self), dtype=object)
@@ -383,7 +383,7 @@ def astype(self, dtype, copy=True):
         else:
             return np.asarray(self, dtype=dtype)
 
-    def view(self, dtype=None):
+    def view(self, dtype: Optional[Dtype] = None):
         if dtype is None or dtype is self.dtype:
             return type(self)(self._ndarray, dtype=self.dtype)
         return self._ndarray.view(dtype=dtype)

pandas/core/arrays/integer.py

@@ -5,7 +5,7 @@
 import numpy as np
 
 from pandas._libs import iNaT, lib, missing as libmissing
-from pandas._typing import ArrayLike, DtypeObj
+from pandas._typing import ArrayLike, Dtype, DtypeObj
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import cache_readonly
 
@@ -304,14 +304,14 @@ def __abs__(self):
 
     @classmethod
     def _from_sequence(
-        cls, scalars, *, dtype=None, copy: bool = False
+        cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
     ) -> "IntegerArray":
         values, mask = coerce_to_array(scalars, dtype=dtype, copy=copy)
         return IntegerArray(values, mask)
 
     @classmethod
     def _from_sequence_of_strings(
-        cls, strings, *, dtype=None, copy: bool = False
+        cls, strings, *, dtype: Optional[Dtype] = None, copy: bool = False
     ) -> "IntegerArray":
         scalars = to_numeric(strings, errors="raise")
         return cls._from_sequence(scalars, dtype=dtype, copy=copy)

pandas/core/arrays/period.py

@@ -26,7 +26,7 @@
     get_period_field_arr,
     period_asfreq_arr,
 )
-from pandas._typing import AnyArrayLike
+from pandas._typing import AnyArrayLike, Dtype
 from pandas.util._decorators import cache_readonly, doc
 
 from pandas.core.dtypes.common import (
@@ -198,10 +198,10 @@ def _from_sequence(
         cls: Type["PeriodArray"],
         scalars: Union[Sequence[Optional[Period]], AnyArrayLike],
         *,
-        dtype: Optional[PeriodDtype] = None,
+        dtype: Optional[Dtype] = None,
         copy: bool = False,
     ) -> "PeriodArray":
-        if dtype:
+        if dtype and isinstance(dtype, PeriodDtype):
             freq = dtype.freq
         else:
             freq = None

pandas/core/dtypes/dtypes.py

@@ -22,7 +22,7 @@
 from pandas._libs.interval import Interval
 from pandas._libs.tslibs import NaT, Period, Timestamp, dtypes, timezones, to_offset
 from pandas._libs.tslibs.offsets import BaseOffset
-from pandas._typing import DtypeObj, Ordered
+from pandas._typing import Dtype, DtypeObj, Ordered
 
 from pandas.core.dtypes.base import ExtensionDtype, register_extension_dtype
 from pandas.core.dtypes.generic import ABCCategoricalIndex, ABCIndex
@@ -185,7 +185,7 @@ def _from_values_or_dtype(
         values=None,
         categories=None,
         ordered: Optional[bool] = None,
-        dtype: Optional["CategoricalDtype"] = None,
+        dtype: Optional[Dtype] = None,
     ) -> "CategoricalDtype":
         """
         Construct dtype from the input parameters used in :class:`Categorical`.
@@ -272,7 +272,7 @@ def _from_values_or_dtype(
             # ordered=None.
             dtype = CategoricalDtype(categories, ordered)
 
-        return dtype
+        return cast(CategoricalDtype, dtype)
 
     @classmethod
     def construct_from_string(cls, string: str_type) -> "CategoricalDtype":