remove hardcoded storage

Author: jorisvandenbossche

pandas/core/dtypes/cast.py

@@ -801,7 +801,7 @@ def infer_dtype_from_scalar(val) -> tuple[DtypeObj, Any]:
         if using_string_dtype():
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(storage="pyarrow", na_value=np.nan)
+            dtype = StringDtype(na_value=np.nan)
 
     elif isinstance(val, (np.datetime64, dt.datetime)):
         try:

pandas/core/internals/construction.py

@@ -302,7 +302,7 @@ def ndarray_to_mgr(
             nb = new_block_2d(values, placement=bp, refs=refs)
             block_values = [nb]
     elif dtype is None and values.dtype.kind == "U" and using_string_dtype():
-        dtype = StringDtype(storage="pyarrow", na_value=np.nan)
+        dtype = StringDtype(na_value=np.nan)
 
         obj_columns = list(values)
         block_values = [

pandas/io/_util.py

@@ -34,6 +34,6 @@ def arrow_string_types_mapper() -> Callable:
     pa = import_optional_dependency("pyarrow")
 
     return {
-        pa.string(): pd.StringDtype(storage="pyarrow", na_value=np.nan),
-        pa.large_string(): pd.StringDtype(storage="pyarrow", na_value=np.nan),
+        pa.string(): pd.StringDtype(na_value=np.nan),
+        pa.large_string(): pd.StringDtype(na_value=np.nan),
     }.get

pandas/io/pytables.py

@@ -75,6 +75,7 @@
     PeriodIndex,
     RangeIndex,
     Series,
+    StringDtype,
     TimedeltaIndex,
     concat,
     isna,
@@ -3295,7 +3296,7 @@ def read(
         values = self.read_array("values", start=start, stop=stop)
         result = Series(values, index=index, name=self.name, copy=False)
         if using_string_dtype() and is_string_array(values, skipna=True):
-            result = result.astype("string[pyarrow_numpy]")
+            result = result.astype(StringDtype(na_value=np.nan))
         return result
 
     def write(self, obj, **kwargs) -> None:
@@ -3364,7 +3365,7 @@ def read(
             columns = items[items.get_indexer(blk_items)]
             df = DataFrame(values.T, columns=columns, index=axes[1], copy=False)
             if using_string_dtype() and is_string_array(values, skipna=True):
-                df = df.astype("string[pyarrow_numpy]")
+                df = df.astype(StringDtype(na_value=np.nan))
             dfs.append(df)
 
         if len(dfs) > 0:
@@ -4741,7 +4742,7 @@ def read(
                 values,  # type: ignore[arg-type]
                 skipna=True,
             ):
-                df = df.astype("string[pyarrow_numpy]")
+                df = df.astype(StringDtype(na_value=np.nan))
             frames.append(df)
 
         if len(frames) == 1: