Implement some reductions for string Series

doc/source/whatsnew/v1.0.2.rst

@@ -28,6 +28,11 @@ Fixed regressions
 Bug fixes
 ~~~~~~~~~
 
+**ExtensionArray**
+
+- Fixed issue where taking the minimum, maximum, or sum of a ``Series`` with ``StringDtype`` type would raise. (:issue:`31746`)
+-
+
 **I/O**
 
 - Using ``pd.NA`` with :meth:`DataFrame.to_json` now correctly outputs a null value instead of an empty object (:issue:`31615`)

pandas/core/arrays/string_.py

@@ -274,7 +274,16 @@ def astype(self, dtype, copy=True):
         return super().astype(dtype, copy)
 
     def _reduce(self, name, skipna=True, **kwargs):
-        raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
+        if name in ["min", "max", "sum"]:
+            na_mask = isna(self)
+            if not na_mask.any():
+                return getattr(self, name)(skipna=False, **kwargs)
+            elif skipna:
+                return getattr(self[~na_mask], name)(skipna=False, **kwargs)
+            else:
+                return libmissing.NA
+        else:
+            raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
 
     def value_counts(self, dropna=False):
         from pandas import value_counts

pandas/tests/arrays/string_/test_string.py

@@ -215,15 +215,13 @@ def test_from_sequence_no_mutate(copy):
 
 
 @pytest.mark.parametrize("skipna", [True, False])
-@pytest.mark.xfail(reason="Not implemented StringArray.sum")
 def test_reduce(skipna):
     arr = pd.Series(["a", "b", "c"], dtype="string")
     result = arr.sum(skipna=skipna)
     assert result == "abc"
 
 
 @pytest.mark.parametrize("skipna", [True, False])
-@pytest.mark.xfail(reason="Not implemented StringArray.sum")
 def test_reduce_missing(skipna):
     arr = pd.Series([None, "a", None, "b", "c", None], dtype="string")
     result = arr.sum(skipna=skipna)
@@ -269,3 +267,26 @@ def test_value_counts_na():
     result = arr.value_counts(dropna=True)
     expected = pd.Series([2, 1], index=["a", "b"], dtype="Int64")
     tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("func", ["min", "max"])
+@pytest.mark.parametrize("skipna", [True, False])
+def test_reduction(func, skipna):
+    s = pd.Series(["x", "y", "z"], dtype="string")
+    result = getattr(s, func)(skipna=skipna)
+    expected = "x" if func == "min" else "z"
+
+    assert result == expected
+
+
+@pytest.mark.parametrize("func", ["min", "max"])
+@pytest.mark.parametrize("skipna", [True, False])
+def test_reduction_with_na(func, skipna):
+    s = pd.Series([pd.NA, "y", "z"], dtype="string")
+    result = getattr(s, func)(skipna=skipna)
+
+    if skipna:
+        expected = "y" if func == "min" else "z"
+        assert result == expected
+    else:
+        assert result is pd.NA

pandas/tests/extension/base/reduce.py

@@ -25,6 +25,13 @@ class BaseNoReduceTests(BaseReduceTests):
 
     @pytest.mark.parametrize("skipna", [True, False])
     def test_reduce_series_numeric(self, data, all_numeric_reductions, skipna):
+        if isinstance(data, pd.arrays.StringArray) and all_numeric_reductions in [
+            "min",
+            "max",
+            "sum",
+        ]:
+            pytest.skip("These reductions are implemented")
+
         op_name = all_numeric_reductions
         s = pd.Series(data)