String dtype: more informative repr (keeping brief __str__)

Author: jorisvandenbossche

pandas/core/arrays/string_.py

@@ -198,11 +198,8 @@ def __init__(
         self._na_value = na_value
 
     def __repr__(self) -> str:
-        if self._na_value is libmissing.NA:
-            return f"{self.name}[{self.storage}]"
-        else:
-            # TODO add more informative repr
-            return self.name
+        storage = "" if self.storage == "pyarrow" else "storage='python', "
+        return f"<StringDtype({storage}na_value={self._na_value})>"
 
     def __eq__(self, other: object) -> bool:
         # we need to override the base class __eq__ because na_value (NA or NaN)

pandas/tests/arrays/string_/test_string.py

@@ -103,6 +103,18 @@ def test_repr(dtype):
     assert repr(df.A.array) == expected
 
 
+def test_dtype_repr(dtype):
+    if dtype.storage == "pyarrow":
+        if dtype.na_value is pd.NA:
+            assert repr(dtype) == "<StringDtype(na_value=<NA>)>"
+        else:
+            assert repr(dtype) == "<StringDtype(na_value=nan)>"
+    elif dtype.na_value is pd.NA:
+        assert repr(dtype) == "<StringDtype(storage='python', na_value=<NA>)>"
+    else:
+        assert repr(dtype) == "<StringDtype(storage='python', na_value=nan)>"
+
+
 def test_none_to_nan(cls, dtype):
     a = cls._from_sequence(["a", None, "b"], dtype=dtype)
     assert a[1] is not None