add default for dtype in init

Author: jbrockmendel

pandas/core/arrays/string_.py

@@ -646,7 +646,11 @@ class StringArray(BaseStringArray, NumpyExtensionArray):  # type: ignore[misc]
     # undo the NumpyExtensionArray hack
     _typ = "extension"
 
-    def __init__(self, values, *, dtype: StringDtype, copy: bool = False) -> None:
+    def __init__(
+        self, values, *, dtype: StringDtype = None, copy: bool = False
+    ) -> None:
+        if dtype is None:
+            dtype = StringDtype()
         values = extract_array(values)
 
         super().__init__(values, copy=copy)
@@ -758,7 +762,7 @@ def _cast_pointwise_result(self, values) -> ArrayLike:
     @classmethod
     def _empty(cls, shape, dtype) -> StringArray:
         values = np.empty(shape, dtype=object)
-        values[:] = libmissing.NA
+        values[:] = dtype.na_value
         return cls(values, dtype=dtype).astype(dtype, copy=False)
 
     def __arrow_array__(self, type=None):

pandas/tests/io/parser/test_upcast.py

@@ -14,7 +14,6 @@
     BooleanArray,
     FloatingArray,
     IntegerArray,
-    StringArray,
 )
 
 
@@ -95,10 +94,7 @@ def test_maybe_upcast_object(val, string_storage):
 
         if string_storage == "python":
             exp_val = "c" if val == "c" else NA
-            dtype = pd.StringDtype()
-            expected = StringArray(
-                np.array(["a", "b", exp_val], dtype=np.object_), dtype=dtype
-            )
+            expected = pd.array(["a", "b", exp_val], dtype=pd.StringDtype())
         else:
             exp_val = "c" if val == "c" else None
             expected = ArrowStringArray(pa.array(["a", "b", exp_val]))

pandas/tests/io/test_orc.py

@@ -12,7 +12,6 @@
 import pandas as pd
 from pandas import read_orc
 import pandas._testing as tm
-from pandas.core.arrays import StringArray
 
 pytest.importorskip("pyarrow.orc")
 
@@ -368,15 +367,9 @@ def test_orc_dtype_backend_numpy_nullable():
 
     expected = pd.DataFrame(
         {
-            "string": StringArray(
-                np.array(["a", "b", "c"], dtype=np.object_), dtype=pd.StringDtype()
-            ),
-            "string_with_nan": StringArray(
-                np.array(["a", pd.NA, "c"], dtype=np.object_), dtype=pd.StringDtype()
-            ),
-            "string_with_none": StringArray(
-                np.array(["a", pd.NA, "c"], dtype=np.object_), dtype=pd.StringDtype()
-            ),
+            "string": pd.array(["a", "b", "c"], dtype=pd.StringDtype()),
+            "string_with_nan": pd.array(["a", pd.NA, "c"], dtype=pd.StringDtype()),
+            "string_with_none": pd.array(["a", pd.NA, "c"], dtype=pd.StringDtype()),
             "int": pd.Series([1, 2, 3], dtype="Int64"),
             "int_with_nan": pd.Series([1, pd.NA, 3], dtype="Int64"),
             "na_only": pd.Series([pd.NA, pd.NA, pd.NA], dtype="Int64"),