name and str() change to "string"

Author: simonjayhawkins

pandas/_testing/asserters.py

@@ -48,6 +48,7 @@
     TimedeltaArray,
 )
 from pandas.core.arrays.datetimelike import DatetimeLikeArrayMixin
+from pandas.core.arrays.string_ import StringDtype
 
 from pandas.io.formats.printing import pprint_thing
 
@@ -638,12 +639,20 @@ def raise_assert_detail(obj, message, left, right, diff=None, index_values=None)
 
     if isinstance(left, np.ndarray):
         left = pprint_thing(left)
-    elif is_categorical_dtype(left) or isinstance(left, PandasDtype):
+    elif (
+        is_categorical_dtype(left)
+        or isinstance(left, PandasDtype)
+        or isinstance(left, StringDtype)
+    ):
         left = repr(left)
 
     if isinstance(right, np.ndarray):
         right = pprint_thing(right)
-    elif is_categorical_dtype(right) or isinstance(right, PandasDtype):
+    elif (
+        is_categorical_dtype(right)
+        or isinstance(right, PandasDtype)
+        or isinstance(right, StringDtype)
+    ):
         right = repr(right)
 
     msg += f"""

pandas/core/arrays/string_.py

@@ -84,6 +84,8 @@ class StringDtype(ExtensionDtype):
     string[python]
     """
 
+    name = "string"
+
     #: StringDtype.na_value uses pandas.NA
     na_value = libmissing.NA
     _metadata = ("storage",)
@@ -102,10 +104,6 @@ def __init__(self, storage=None):
 
         self.storage = storage
 
-    @property
-    def name(self):
-        return f"string[{self.storage}]"
-
     @property
     def type(self) -> type[str]:
         return str
@@ -182,6 +180,9 @@ def construct_array_type(  # type: ignore[override]
             return ArrowStringArray
 
     def __repr__(self):
+        return f"string[{self.storage}]"
+
+    def __str__(self):
         return self.name
 
     def __from_arrow__(
@@ -268,7 +269,7 @@ class StringArray(PandasArray):
     >>> pd.array(['This is', 'some text', None, 'data.'], dtype="string")
     <StringArray>
     ['This is', 'some text', <NA>, 'data.']
-    Length: 4, dtype: string[python]
+    Length: 4, dtype: string
 
     Unlike arrays instantiated with ``dtype="object"``, ``StringArray``
     will convert the values to strings.
@@ -280,7 +281,7 @@ class StringArray(PandasArray):
     >>> pd.array(['1', 1], dtype="string")
     <StringArray>
     ['1', '1']
-    Length: 2, dtype: string[python]
+    Length: 2, dtype: string
 
     However, instantiating StringArrays directly with non-strings will raise an error.
 

pandas/core/arrays/string_arrow.py

@@ -127,7 +127,7 @@ class ArrowStringArray(OpsMixin, ExtensionArray, ObjectStringArrayMixin):
     >>> pd.array(['This is', 'some text', None, 'data.'], dtype="string[pyarrow]")
     <ArrowStringArray>
     ['This is', 'some text', <NA>, 'data.']
-    Length: 4, dtype: string[pyarrow]
+    Length: 4, dtype: string
     """
 
     def __init__(self, values):

pandas/core/construction.py

@@ -239,15 +239,15 @@ def array(
     >>> pd.array(["a", None, "c"])
     <StringArray>
     ['a', <NA>, 'c']
-    Length: 3, dtype: string[python]
+    Length: 3, dtype: string
 
     >>> with pd.option_context("string_storage", "pyarrow"):
     ...     arr = pd.array(["a", None, "c"])
     ...
     >>> arr
     <ArrowStringArray>
     ['a', <NA>, 'c']
-    Length: 3, dtype: string[pyarrow]
+    Length: 3, dtype: string
 
     >>> pd.array([pd.Period('2000', freq="D"), pd.Period("2000", freq="D")])
     <PeriodArray>

pandas/core/generic.py

@@ -6139,12 +6139,12 @@ def convert_dtypes(
         2  3  z   <NA>  <NA>    20  200.0
 
         >>> dfn.dtypes
-        a              Int32
-        b     string[python]
-        c            boolean
-        d     string[python]
-        e              Int64
-        f            Float64
+        a      Int32
+        b     string
+        c    boolean
+        d     string
+        e      Int64
+        f    Float64
         dtype: object
 
         Start with a Series of strings and missing data represented by ``np.nan``.
@@ -6162,7 +6162,7 @@ def convert_dtypes(
         0       a
         1       b
         2    <NA>
-        dtype: string[python]
+        dtype: string
         """
         if self.ndim == 1:
             return self._convert_dtypes(

pandas/core/strings/accessor.py

@@ -3080,7 +3080,7 @@ def _result_dtype(arr):
     from pandas.core.arrays.string_ import StringDtype
 
     if isinstance(arr.dtype, StringDtype):
-        return arr.dtype.name
+        return arr.dtype
     else:
         return object
 

pandas/tests/arrays/string_/test_string.py

@@ -32,15 +32,11 @@ def test_repr(dtype):
     expected = "      A\n0     a\n1  <NA>\n2     b"
     assert repr(df) == expected
 
-    expected = (
-        f"0       a\n1    <NA>\n2       b\nName: A, dtype: string[{dtype.storage}]"
-    )
+    expected = "0       a\n1    <NA>\n2       b\nName: A, dtype: string"
     assert repr(df.A) == expected
 
     arr_name = "ArrowStringArray" if dtype.storage == "pyarrow" else "StringArray"
-    expected = (
-        f"<{arr_name}>\n['a', <NA>, 'b']\nLength: 3, dtype: string[{dtype.storage}]"
-    )
+    expected = f"<{arr_name}>\n['a', <NA>, 'b']\nLength: 3, dtype: string"
     assert repr(df.A.array) == expected
 
 

pandas/tests/extension/test_string.py

@@ -94,7 +94,9 @@ def data_for_grouping(dtype, chunked):
 
 
 class TestDtype(base.BaseDtypeTests):
-    pass
+    def test_eq_with_str(self, dtype):
+        assert dtype == f"string[{dtype.storage}]"
+        super().test_eq_with_str(dtype)
 
 
 class TestInterface(base.BaseInterfaceTests):
@@ -106,7 +108,9 @@ def test_view(self, data, request):
 
 
 class TestConstructors(base.BaseConstructorsTests):
-    pass
+    def test_from_dtype(self, data):
+        # base test uses string representation of dtype
+        pass
 
 
 class TestReshaping(base.BaseReshapingTests):