REF: de-duplicate methods across nullable EA subclasses (#45380)

Author: jbrockmendel

pandas/core/arrays/boolean.py

@@ -324,15 +324,6 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
     def dtype(self) -> BooleanDtype:
         return self._dtype
 
-    @classmethod
-    def _from_sequence(
-        cls, scalars, *, dtype: Dtype | None = None, copy: bool = False
-    ) -> BooleanArray:
-        if dtype:
-            assert dtype == "boolean"
-        values, mask = coerce_to_array(scalars, copy=copy)
-        return BooleanArray(values, mask)
-
     @classmethod
     def _from_sequence_of_strings(
         cls,
@@ -361,8 +352,13 @@ def map_string(s):
 
     _HANDLED_TYPES = (np.ndarray, numbers.Number, bool, np.bool_)
 
-    def _coerce_to_array(self, value) -> tuple[np.ndarray, np.ndarray]:
-        return coerce_to_array(value)
+    @classmethod
+    def _coerce_to_array(
+        cls, value, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        if dtype:
+            assert dtype == "boolean"
+        return coerce_to_array(value, copy=copy)
 
     @overload
     def astype(self, dtype: npt.DTypeLike, copy: bool = ...) -> np.ndarray:

pandas/core/arrays/floating.py

@@ -1,41 +1,26 @@
 from __future__ import annotations
 
-from typing import overload
-
 import numpy as np
 
 from pandas._libs import (
     lib,
     missing as libmissing,
 )
-from pandas._typing import (
-    ArrayLike,
-    AstypeArg,
-    DtypeObj,
-    npt,
-)
+from pandas._typing import DtypeObj
 from pandas.util._decorators import cache_readonly
 
-from pandas.core.dtypes.astype import astype_nansafe
 from pandas.core.dtypes.common import (
     is_bool_dtype,
-    is_datetime64_dtype,
     is_float_dtype,
     is_integer_dtype,
     is_object_dtype,
-    pandas_dtype,
-)
-from pandas.core.dtypes.dtypes import (
-    ExtensionDtype,
-    register_extension_dtype,
 )
+from pandas.core.dtypes.dtypes import register_extension_dtype
 
-from pandas.core.arrays import ExtensionArray
 from pandas.core.arrays.numeric import (
     NumericArray,
     NumericDtype,
 )
-from pandas.core.tools.numeric import to_numeric
 
 
 class FloatingDtype(NumericDtype):
@@ -260,79 +245,10 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
         super().__init__(values, mask, copy=copy)
 
     @classmethod
-    def _from_sequence(
-        cls, scalars, *, dtype=None, copy: bool = False
-    ) -> 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:
-        scalars = to_numeric(strings, errors="raise")
-        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
-
-    def _coerce_to_array(self, value) -> tuple[np.ndarray, np.ndarray]:
-        return coerce_to_array(value, dtype=self.dtype)
-
-    @overload
-    def astype(self, dtype: npt.DTypeLike, copy: bool = ...) -> np.ndarray:
-        ...
-
-    @overload
-    def astype(self, dtype: ExtensionDtype, copy: bool = ...) -> ExtensionArray:
-        ...
-
-    @overload
-    def astype(self, dtype: AstypeArg, copy: bool = ...) -> ArrayLike:
-        ...
-
-    def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
-        """
-        Cast to a NumPy array or ExtensionArray with 'dtype'.
-
-        Parameters
-        ----------
-        dtype : str or dtype
-            Typecode or data-type to which the array is cast.
-        copy : bool, default True
-            Whether to copy the data, even if not necessary. If False,
-            a copy is made only if the old dtype does not match the
-            new dtype.
-
-        Returns
-        -------
-        ndarray or ExtensionArray
-            NumPy ndarray, or BooleanArray, IntegerArray or FloatingArray with
-            'dtype' for its dtype.
-
-        Raises
-        ------
-        TypeError
-            if incompatible type with an FloatingDtype, equivalent of same_kind
-            casting
-        """
-        dtype = pandas_dtype(dtype)
-
-        if isinstance(dtype, ExtensionDtype):
-            return super().astype(dtype, copy=copy)
-
-        # coerce
-        if is_float_dtype(dtype):
-            # In astype, we consider dtype=float to also mean na_value=np.nan
-            kwargs = {"na_value": np.nan}
-        elif is_datetime64_dtype(dtype):
-            # error: Dict entry 0 has incompatible type "str": "datetime64"; expected
-            # "str": "float"
-            kwargs = {"na_value": np.datetime64("NaT")}  # type: ignore[dict-item]
-        else:
-            kwargs = {}
-
-        # error: Argument 2 to "to_numpy" of "BaseMaskedArray" has incompatible
-        # type "**Dict[str, float]"; expected "bool"
-        data = self.to_numpy(dtype=dtype, **kwargs)  # type: ignore[arg-type]
-        return astype_nansafe(data, dtype, copy=False)
+    def _coerce_to_array(
+        cls, value, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        return coerce_to_array(value, dtype=dtype, copy=copy)
 
     def _values_for_argsort(self) -> np.ndarray:
         return self._data

pandas/core/arrays/integer.py

@@ -1,43 +1,28 @@
 from __future__ import annotations
 
-from typing import overload
-
 import numpy as np
 
 from pandas._libs import (
     lib,
     missing as libmissing,
 )
-from pandas._typing import (
-    ArrayLike,
-    AstypeArg,
-    Dtype,
-    DtypeObj,
-    npt,
-)
+from pandas._typing import DtypeObj
 from pandas.util._decorators import cache_readonly
 
-from pandas.core.dtypes.base import (
-    ExtensionDtype,
-    register_extension_dtype,
-)
+from pandas.core.dtypes.base import register_extension_dtype
 from pandas.core.dtypes.common import (
     is_bool_dtype,
-    is_datetime64_dtype,
     is_float_dtype,
     is_integer_dtype,
     is_object_dtype,
     is_string_dtype,
-    pandas_dtype,
 )
 
-from pandas.core.arrays import ExtensionArray
 from pandas.core.arrays.masked import BaseMaskedDtype
 from pandas.core.arrays.numeric import (
     NumericArray,
     NumericDtype,
 )
-from pandas.core.tools.numeric import to_numeric
 
 
 class _IntegerDtype(NumericDtype):
@@ -319,75 +304,10 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
         super().__init__(values, mask, copy=copy)
 
     @classmethod
-    def _from_sequence(
-        cls, scalars, *, dtype: Dtype | None = 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: Dtype | None = None, copy: bool = False
-    ) -> IntegerArray:
-        scalars = to_numeric(strings, errors="raise")
-        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
-
-    def _coerce_to_array(self, value) -> tuple[np.ndarray, np.ndarray]:
-        return coerce_to_array(value, dtype=self.dtype)
-
-    @overload
-    def astype(self, dtype: npt.DTypeLike, copy: bool = ...) -> np.ndarray:
-        ...
-
-    @overload
-    def astype(self, dtype: ExtensionDtype, copy: bool = ...) -> ExtensionArray:
-        ...
-
-    @overload
-    def astype(self, dtype: AstypeArg, copy: bool = ...) -> ArrayLike:
-        ...
-
-    def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
-        """
-        Cast to a NumPy array or ExtensionArray with 'dtype'.
-
-        Parameters
-        ----------
-        dtype : str or dtype
-            Typecode or data-type to which the array is cast.
-        copy : bool, default True
-            Whether to copy the data, even if not necessary. If False,
-            a copy is made only if the old dtype does not match the
-            new dtype.
-
-        Returns
-        -------
-        ndarray or ExtensionArray
-            NumPy ndarray, BooleanArray or IntegerArray with 'dtype' for its dtype.
-
-        Raises
-        ------
-        TypeError
-            if incompatible type with an IntegerDtype, equivalent of same_kind
-            casting
-        """
-        dtype = pandas_dtype(dtype)
-
-        if isinstance(dtype, ExtensionDtype):
-            return super().astype(dtype, copy=copy)
-
-        na_value: float | np.datetime64 | lib.NoDefault
-
-        # coerce
-        if is_float_dtype(dtype):
-            # In astype, we consider dtype=float to also mean na_value=np.nan
-            na_value = np.nan
-        elif is_datetime64_dtype(dtype):
-            na_value = np.datetime64("NaT")
-        else:
-            na_value = lib.no_default
-
-        return self.to_numpy(dtype=dtype, na_value=na_value, copy=False)
+    def _coerce_to_array(
+        cls, value, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        return coerce_to_array(value, dtype=dtype, copy=copy)
 
     def _values_for_argsort(self) -> np.ndarray:
         """

pandas/core/arrays/masked.py

@@ -20,6 +20,7 @@
 from pandas._typing import (
     ArrayLike,
     AstypeArg,
+    DtypeObj,
     NpDtype,
     PositionalIndexer,
     Scalar,
@@ -160,6 +161,13 @@ def __init__(self, values: np.ndarray, mask: np.ndarray, copy: bool = False):
         self._data = values
         self._mask = mask
 
+    @classmethod
+    def _from_sequence(
+        cls: type[BaseMaskedArrayT], scalars, *, dtype=None, copy: bool = False
+    ) -> BaseMaskedArrayT:
+        values, mask = cls._coerce_to_array(scalars, dtype=dtype, copy=copy)
+        return cls(values, mask)
+
     @property
     def dtype(self) -> BaseMaskedDtype:
         raise AbstractMethodError(self)
@@ -219,14 +227,17 @@ def fillna(
             new_values = self.copy()
         return new_values
 
-    def _coerce_to_array(self, values) -> tuple[np.ndarray, np.ndarray]:
-        raise AbstractMethodError(self)
+    @classmethod
+    def _coerce_to_array(
+        cls, values, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        raise AbstractMethodError(cls)
 
     def __setitem__(self, key, value) -> None:
         _is_scalar = is_scalar(value)
         if _is_scalar:
             value = [value]
-        value, mask = self._coerce_to_array(value)
+        value, mask = self._coerce_to_array(value, dtype=self.dtype)
 
         if _is_scalar:
             value = value[0]
@@ -806,7 +817,10 @@ def _quantile(
         except TypeError:
             # GH#42626: not able to safely cast Int64
             # for floating point output
-            out = np.asarray(res, dtype=np.float64)
+            # error: Incompatible types in assignment (expression has type
+            # "ndarray[Any, dtype[floating[_64Bit]]]", variable has type
+            # "BaseMaskedArrayT")
+            out = np.asarray(res, dtype=np.float64)  # type: ignore[assignment]
         return out
 
     def _reduce(self, name: str, *, skipna: bool = True, **kwargs):