Change according to comments

Author: topper-123

doc/source/whatsnew/v1.1.0.rst

@@ -18,19 +18,11 @@ Enhancements
 All dtypes can now be converted to ``StringDtype``
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Previously, declaring or converting to :class:`StringDtype` was in general only possible if the data was already only ``str`` or nan-like.
-For example:
-
-.. code-block:: ipython
-
-    In [1]: pd.Series([1, "abc", np.nan], dtype="string")
-    Out[1]: ValueError: StringArray requires a sequence of strings or pandas.NA
-    In [2]: pd.Series([1, 2, np.nan], dtype="Int64").astype("string")
-    Out[2]: ValueError: StringArray requires a sequence of strings or pandas.NA
-
-This meant that in order to convert arbitrary data to :class:`StringDtype`, you would often have to use ``.astype(str).astype('string')``, which was not intuitive.
+Previously, declaring or converting to :class:`StringDtype` was in general only possible if the data was already only ``str`` or nan-like (:issue:`31204`).
 :class:`StringDtype` now works in all situations where ``astype(str)`` or ``dtype=str`` work:
 
+For example the below now work:
+
 .. ipython:: python
 
    ser = pd.Series([1, "abc", np.nan], dtype="string")

pandas/core/arrays/base.py

@@ -454,7 +454,7 @@ def astype(self, dtype, copy=True):
         from pandas.core.arrays.string_ import StringDtype
 
         dtype = pandas_dtype(dtype)
-        if isinstance(dtype, StringDtype):
+        if isinstance(dtype, StringDtype):  # allow conversion to StringArrays
             return dtype.construct_array_type()._from_sequence(self, copy=False)
 
         return np.array(self, dtype=dtype, copy=copy)

pandas/core/arrays/string_.py

@@ -164,6 +164,11 @@ class StringArray(PandasArray):
     ['1', '1']
     Length: 2, dtype: string
 
+    On the other hand, instantiating StringArrays directly with non-strings will
+    raise an error:
+    >>> pd.arrays.StringArray(np.array([1, 2]))
+    ValueError: StringArray requires a sequence of strings or pandas.NA
+
     For comparison methods, this returns a :class:`pandas.BooleanArray`
 
     >>> pd.array(["a", None, "c"], dtype="string") == "a"
@@ -211,6 +216,7 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
         if has_nans and result is scalars:
             # force a copy now, if we haven't already
             result = result.copy()
+
         # convert to str, then to object to avoid dtype like '<U3', then insert na_value
         result = np.asarray(result, dtype=str)
         result = np.asarray(result, dtype="object")

pandas/core/dtypes/cast.py

@@ -337,9 +337,16 @@ def maybe_cast_to_extension_array(cls: Type["ExtensionArray"], obj, dtype=None):
     -------
     ExtensionArray or obj
     """
+    from pandas.core.arrays.string_ import StringArray
+
     assert isinstance(cls, type), f"must pass a type: {cls}"
     assertion_msg = f"must pass a subclass of ExtensionArray: {cls}"
     assert issubclass(cls, ABCExtensionArray), assertion_msg
+
+    # Everything can be be converted to StringArrays, but we may not want to convert
+    if issubclass(cls, StringArray) and lib.infer_dtype(obj) != "string":
+        return obj
+
     try:
         result = cls._from_sequence(obj, dtype=dtype)
     except Exception:

pandas/core/series.py

@@ -2768,10 +2768,6 @@ def combine(self, other, func, fill_value=None) -> "Series":
         if is_categorical_dtype(self.dtype):
             pass
         elif is_extension_array_dtype(self.dtype):
-            # Everything can be be converted to strings, but we may not want to convert
-            if self.dtype == "string" and lib.infer_dtype(new_values) != "string":
-                return self._constructor(new_values, index=new_index, name=new_name)
-
             # TODO: can we do this for only SparseDtype?
             # The function can return something of any type, so check
             # if the type is compatible with the calling EA.

pandas/tests/extension/decimal/array.py

@@ -136,9 +136,8 @@ def astype(self, dtype, copy=True):
         dtype = pandas_dtype(dtype)
         if isinstance(dtype, type(self.dtype)):
             return type(self)(self._data, context=dtype.context)
-        elif isinstance(dtype, StringDtype):
-            return dtype.construct_array_type()._from_sequence(self, copy=False)
-        return np.asarray(self, dtype=dtype)
+
+        return super().astype(dtype, copy=copy)
 
     def __setitem__(self, key, value):
         if pd.api.types.is_list_like(value):