[ArrowStringArray] BUG: fix test_astype_string for Float32Dtype (pandas-dev#40998)

Author: simonjayhawkins

pandas/core/arrays/interval.py

@@ -829,6 +829,7 @@ def astype(self, dtype, copy: bool = True):
         """
         from pandas import Index
         from pandas.core.arrays.string_ import StringDtype
+        from pandas.core.arrays.string_arrow import ArrowStringDtype
 
         if dtype is not None:
             dtype = pandas_dtype(dtype)
@@ -851,7 +852,7 @@ def astype(self, dtype, copy: bool = True):
             return self._shallow_copy(new_left, new_right)
         elif is_categorical_dtype(dtype):
             return Categorical(np.asarray(self), dtype=dtype)
-        elif isinstance(dtype, StringDtype):
+        elif isinstance(dtype, (StringDtype, ArrowStringDtype)):
             return dtype.construct_array_type()._from_sequence(self, copy=False)
 
         # TODO: This try/except will be repeated.

pandas/core/arrays/string_arrow.py

@@ -229,10 +229,21 @@ def _chk_pyarrow_available(cls) -> None:
 
     @classmethod
     def _from_sequence(cls, scalars, dtype: Dtype | None = None, copy: bool = False):
+        from pandas.core.arrays.masked import BaseMaskedArray
+
         cls._chk_pyarrow_available()
-        # convert non-na-likes to str, and nan-likes to ArrowStringDtype.na_value
-        scalars = lib.ensure_string_array(scalars, copy=False)
-        return cls(pa.array(scalars, type=pa.string(), from_pandas=True))
+
+        if isinstance(scalars, BaseMaskedArray):
+            # avoid costly conversion to object dtype in ensure_string_array and
+            # numerical issues with Float32Dtype
+            na_values = scalars._mask
+            result = scalars._data
+            result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
+            return cls(pa.array(result, mask=na_values, type=pa.string()))
+
+        # convert non-na-likes to str
+        result = lib.ensure_string_array(scalars, copy=copy)
+        return cls(pa.array(result, type=pa.string(), from_pandas=True))
 
     @classmethod
     def _from_sequence_of_strings(

pandas/tests/extension/base/casting.py

@@ -43,10 +43,10 @@ def test_astype_str(self, data):
         expected = pd.Series([str(x) for x in data[:5]], dtype=str)
         self.assert_series_equal(result, expected)
 
-    def test_astype_string(self, data):
+    def test_astype_string(self, data, nullable_string_dtype):
         # GH-33465
-        result = pd.Series(data[:5]).astype("string")
-        expected = pd.Series([str(x) for x in data[:5]], dtype="string")
+        result = pd.Series(data[:5]).astype(nullable_string_dtype)
+        expected = pd.Series([str(x) for x in data[:5]], dtype=nullable_string_dtype)
         self.assert_series_equal(result, expected)
 
     def test_to_numpy(self, data):