API: more permissive conversion to StringDtype

Author: topper-123

pandas/core/arrays/base.py

@@ -213,6 +213,29 @@ def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
         """
         raise AbstractMethodError(cls)
 
+    @classmethod
+    def _from_sequence_of_any_type(cls, scalars, dtype=None, copy=False):
+        """
+        Construct a new ExtensionArray from a sequence of unknown types of scalars.
+
+        .. versionadded:: 1.1.0
+
+        Parameters
+        ----------
+        scalars : Sequence
+            Each element can  be an instance of unknown  scalar types.
+        dtype : dtype, optional
+            Construct for this particular dtype. This should be a Dtype
+            compatible with the ExtensionArray.
+        copy : bool, default False
+            If True, copy the underlying data.
+
+        Returns
+        -------
+        ExtensionArray
+        """
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
+
     @classmethod
     def _from_factorized(cls, values, original):
         """

pandas/core/arrays/integer.py

@@ -1,5 +1,5 @@
 import numbers
-from typing import TYPE_CHECKING, Tuple, Type, Union
+from typing import TYPE_CHECKING, Dict, Tuple, Type, Union
 import warnings
 
 import numpy as np
@@ -764,7 +764,7 @@ class UInt64Dtype(_IntegerDtype):
     __doc__ = _dtype_docstring.format(dtype="uint64")
 
 
-_dtypes = {
+_dtypes: Dict[str, _IntegerDtype] = {
     "int8": Int8Dtype(),
     "int16": Int16Dtype(),
     "int32": Int32Dtype(),

pandas/core/arrays/string_.py

@@ -215,6 +215,21 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
     def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
         return cls._from_sequence(strings, dtype=dtype, copy=copy)
 
+    @classmethod
+    def _from_sequence_of_any_type(cls, scalars, dtype=None, copy=False):
+        values = np.asarray(scalars, dtype="object")
+        na_values = isna(values)
+        has_nans = na_values.any()
+        if has_nans and values is scalars:
+            # force a copy now, if we haven't already
+            values = values.copy()
+        # convert to str, then to object to avoid dtype like '<U3', then insert na_value
+        values = np.asarray(values, dtype=str)
+        values = np.asarray(values, dtype="object")
+        if has_nans:
+            values[na_values] = dtype.na_value
+        return cls._from_sequence(values, dtype=dtype, copy=copy)
+
     def __arrow_array__(self, type=None):
         """
         Convert myself into a pyarrow Array.

pandas/core/construction.py

@@ -283,7 +283,7 @@ def array(
 
     if is_extension_array_dtype(dtype):
         cls = cast(ExtensionDtype, dtype).construct_array_type()
-        return cls._from_sequence(data, dtype=dtype, copy=copy)
+        return cls._from_sequence_of_any_type(data, dtype=dtype, copy=copy)
 
     if dtype is None:
         inferred_dtype = lib.infer_dtype(data, skipna=True)
@@ -562,7 +562,7 @@ def _try_cast(
         elif is_extension_array_dtype(dtype):
             # create an extension array from its dtype
             dtype = cast(ExtensionDtype, dtype)
-            array_type = dtype.construct_array_type()._from_sequence
+            array_type = dtype.construct_array_type()._from_sequence_of_any_type
             subarr = array_type(arr, dtype=dtype, copy=copy)
         elif dtype is not None and raise_cast_failure:
             raise

pandas/core/dtypes/cast.py

@@ -924,7 +924,8 @@ def astype_nansafe(arr, dtype, copy: bool = True, skipna: bool = False):
     """
     # dispatch on extension dtype if needed
     if is_extension_array_dtype(dtype):
-        return dtype.construct_array_type()._from_sequence(arr, dtype=dtype, copy=copy)
+        arr_type = dtype.construct_array_type()._from_sequence_of_any_type
+        return arr_type(arr, dtype=dtype, copy=copy)
 
     if not isinstance(dtype, np.dtype):
         dtype = pandas_dtype(dtype)