fix astype to string

pandas-dev · jreback · Sep 30, 2020 · May 15, 2020 · May 22, 2020 · May 22, 2020
commit ff3b93759c801aaf86a1b6b76eaa6e8cf9b53ee9
diff --git a/pandas/core/arrays/floating.py b/pandas/core/arrays/floating.py
@@ -384,6 +384,7 @@ def astype(self, dtype, copy: bool = True) -> ArrayLike:
         """
         from pandas.core.arrays.boolean import BooleanArray, BooleanDtype
         from pandas.core.arrays.integer import _IntegerDtype, IntegerArray
+        from pandas.core.arrays.string_ import StringDtype, StringArray
 
         dtype = pandas_dtype(dtype)
 
@@ -400,6 +401,8 @@ def astype(self, dtype, copy: bool = True) -> ArrayLike:
         elif isinstance(dtype, BooleanDtype):
             result = self._data.astype("bool", copy=False)
             return BooleanArray(result, mask=self._mask, copy=False)
+        elif isinstance(dtype, StringDtype):
+            return StringArray._from_sequence(self, copy=False)
 
         # coerce
         if is_float_dtype(dtype):

diff --git a/pandas/core/arrays/integer.py b/pandas/core/arrays/integer.py
@@ -447,7 +447,7 @@ def astype(self, dtype, copy: bool = True) -> ArrayLike:
             casting
         """
         from pandas.core.arrays.boolean import BooleanDtype
-        from pandas.core.arrays.floating import  _FloatingDtype
+        from pandas.core.arrays.floating import _FloatingDtype
         from pandas.core.arrays.string_ import StringDtype
 
         dtype = pandas_dtype(dtype)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
@@ -201,14 +201,21 @@ def _from_sequence(cls, scalars, dtype=None, copy=False):
         if dtype:
             assert dtype == "string"
 
-        result = np.asarray(scalars, dtype="object")
-        if copy and result is scalars:
-            result = result.copy()
+        from pandas.core.arrays.masked import BaseMaskedArray
+
+        if isinstance(scalars, BaseMaskedArray):
+            na_values = scalars._mask
+            result = scalars._data
+        else:
+            result = np.asarray(scalars)
+            if copy and result is scalars:
+                result = result.copy()
+
+            # Standardize all missing-like values to NA
+            # TODO: it would be nice to do this in _validate / lib.is_string_array
+            # We are already doing a scan over the values there.
+            na_values = isna(result)
 
-        # Standardize all missing-like values to NA
-        # TODO: it would be nice to do this in _validate / lib.is_string_array
-        # We are already doing a scan over the values there.
-        na_values = isna(result)
         has_nans = na_values.any()
         if has_nans and result is scalars:
             # force a copy now, if we haven't already