Add typing to core

Author: avinashpancham

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=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

@@ -2,7 +2,7 @@
 from functools import partial
 import operator
 from shutil import get_terminal_size
-from typing import Dict, Hashable, List, Sequence, Type, TypeVar, Union, cast
+from typing import Dict, Hashable, List, Optional, Sequence, Type, TypeVar, Union, cast
 from warnings import warn
 
 import numpy as np
@@ -303,7 +303,7 @@ def __init__(
         values,
         categories=None,
         ordered=None,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
         fastpath=False,
         copy: bool = True,
     ):
@@ -405,7 +405,7 @@ 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:
@@ -540,7 +540,9 @@ 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.
 
@@ -1628,7 +1630,7 @@ def _values_for_rank(self):
             )
         return values
 
-    def view(self, dtype=None):
+    def view(self, dtype: Optional[Dtype] = None):
         if dtype is not None:
             raise NotImplementedError(dtype)
         return self._from_backing_data(self._ndarray)
@@ -2323,7 +2325,7 @@ def replace(self, to_replace, value, inplace: bool = False):
 
     # ------------------------------------------------------------------------
     # String methods interface
-    def _str_map(self, f, na_value=np.nan, dtype=np.dtype(object)):
+    def _str_map(self, f, na_value=np.nan, dtype: Optional[Dtype] = np.dtype(object)):
         # Optimization to apply the callable `f` to the categories once
         # and rebuild the result by `take`ing from the result with the codes.
         # Returns the same type as the object-dtype implementation though.

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
 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[Dtype] = 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/datetimes.py

@@ -22,6 +22,7 @@
     to_offset,
     tzconversion,
 )
+from pandas._typing import Dtype
 from pandas.errors import PerformanceWarning
 
 from pandas.core.dtypes.cast import astype_dt64_to_dt64tz
@@ -216,7 +217,9 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):
     _dtype: Union[np.dtype, DatetimeTZDtype]
     _freq = None
 
-    def __init__(self, values, dtype=DT64NS_DTYPE, freq=None, copy=False):
+    def __init__(
+        self, values, dtype: Optional[Dtype] = DT64NS_DTYPE, freq=None, copy=False
+    ):
         if isinstance(values, (ABCSeries, ABCIndex)):
             values = values._values
 
@@ -290,7 +293,10 @@ def __init__(self, values, dtype=DT64NS_DTYPE, freq=None, copy=False):
 
     @classmethod
     def _simple_new(
-        cls, values, freq: Optional[BaseOffset] = None, dtype=DT64NS_DTYPE
+        cls,
+        values,
+        freq: Optional[BaseOffset] = None,
+        dtype: Optional[Dtype] = DT64NS_DTYPE,
     ) -> "DatetimeArray":
         assert isinstance(values, np.ndarray)
         if values.dtype != DT64NS_DTYPE:
@@ -304,14 +310,16 @@ def _simple_new(
         return result
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype=None, copy: bool = False):
+    def _from_sequence(
+        cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
+    ):
         return cls._from_sequence_not_strict(scalars, dtype=dtype, copy=copy)
 
     @classmethod
     def _from_sequence_not_strict(
         cls,
         data,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
         copy=False,
         tz=None,
         freq=lib.no_default,
@@ -549,7 +557,7 @@ def _resolution_obj(self) -> Resolution:
     # ----------------------------------------------------------------
     # Array-Like / EA-Interface Methods
 
-    def __array__(self, dtype=None) -> np.ndarray:
+    def __array__(self, dtype: Optional[Dtype] = None) -> np.ndarray:
         if dtype is None and self.tz:
             # The default for tz-aware is object, to preserve tz info
             dtype = object
@@ -1861,7 +1869,7 @@ def to_julian_date(self):
     def std(
         self,
         axis=None,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
         out=None,
         ddof: int = 1,
         keepdims: bool = False,
@@ -1884,7 +1892,7 @@ def std(
 
 def sequence_to_dt64ns(
     data,
-    dtype=None,
+    dtype: Optional[Dtype] = None,
     copy=False,
     tz=None,
     dayfirst=False,

pandas/core/arrays/interval.py

@@ -1,7 +1,7 @@
 import operator
 from operator import le, lt
 import textwrap
-from typing import Sequence, Type, TypeVar
+from typing import Optional, Sequence, Type, TypeVar
 
 import numpy as np
 
@@ -14,7 +14,7 @@
     intervals_to_interval_bounds,
 )
 from pandas._libs.missing import NA
-from pandas._typing import ArrayLike
+from pandas._typing import ArrayLike, Dtype
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender
 
@@ -170,7 +170,7 @@ def __new__(
         cls,
         data,
         closed=None,
-        dtype=None,
+        dtype: Optional[Dtype] = None,
         copy: bool = False,
         verify_integrity: bool = True,
     ):
@@ -212,7 +212,13 @@ def __new__(
 
     @classmethod
     def _simple_new(
-        cls, left, right, closed=None, copy=False, dtype=None, verify_integrity=True
+        cls,
+        left,
+        right,
+        closed=None,
+        copy=False,
+        dtype: Optional[Dtype] = None,
+        verify_integrity=True,
     ):
         result = IntervalMixin.__new__(cls)
 
@@ -279,7 +285,7 @@ def _simple_new(
         return result
 
     @classmethod
-    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+    def _from_sequence(cls, scalars, *, dtype: Optional[Dtype] = None, copy=False):
         return cls(scalars, dtype=dtype, copy=copy)
 
     @classmethod
@@ -338,7 +344,9 @@ def _from_factorized(cls, values, original):
             ),
         }
     )
-    def from_breaks(cls, breaks, closed="right", copy=False, dtype=None):
+    def from_breaks(
+        cls, breaks, closed="right", copy=False, dtype: Optional[Dtype] = None
+    ):
         breaks = maybe_convert_platform_interval(breaks)
 
         return cls.from_arrays(breaks[:-1], breaks[1:], closed, copy=copy, dtype=dtype)
@@ -407,7 +415,9 @@ def from_breaks(cls, breaks, closed="right", copy=False, dtype=None):
             ),
         }
     )
-    def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
+    def from_arrays(
+        cls, left, right, closed="right", copy=False, dtype: Optional[Dtype] = None
+    ):
         left = maybe_convert_platform_interval(left)
         right = maybe_convert_platform_interval(right)
 
@@ -464,7 +474,9 @@ def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
             ),
         }
     )
-    def from_tuples(cls, data, closed="right", copy=False, dtype=None):
+    def from_tuples(
+        cls, data, closed="right", copy=False, dtype: Optional[Dtype] = None
+    ):
         if len(data):
             left, right = [], []
         else:

pandas/core/arrays/numpy_.py

@@ -1,11 +1,11 @@
 import numbers
-from typing import Tuple, Type, Union
+from typing import Optional, Tuple, Type, Union
 
 import numpy as np
 from numpy.lib.mixins import NDArrayOperatorsMixin
 
 from pandas._libs import lib
-from pandas._typing import Scalar
+from pandas._typing import Dtype, Scalar
 from pandas.compat.numpy import function as nv
 
 from pandas.core.dtypes.dtypes import ExtensionDtype
@@ -172,7 +172,7 @@ def __init__(self, values: Union[np.ndarray, "PandasArray"], copy: bool = False)
 
     @classmethod
     def _from_sequence(
-        cls, scalars, *, dtype=None, copy: bool = False
+        cls, scalars, *, dtype: Optional[Dtype] = None, copy: bool = False
     ) -> "PandasArray":
         if isinstance(dtype, PandasDtype):
             dtype = dtype._dtype