ENH: Implement StringArray.min / max

doc/source/whatsnew/v1.1.0.rst

@@ -359,6 +359,7 @@ Strings
 ^^^^^^^
 
 - Bug in the :meth:`~Series.astype` method when converting "string" dtype data to nullable integer dtype (:issue:`32450`).
+- Fixed issue where taking ``min`` or ``max`` of a ``StringArray`` or ``Series`` with ``StringDtype`` type would raise. (:issue:`31746`)
 -
 
 

pandas/core/arrays/string_.py

@@ -4,6 +4,7 @@
 import numpy as np
 
 from pandas._libs import lib, missing as libmissing
+from pandas.compat.numpy import function as nv
 
 from pandas.core.dtypes.base import ExtensionDtype
 from pandas.core.dtypes.common import pandas_dtype
@@ -13,6 +14,7 @@
 
 from pandas import compat
 from pandas.core import ops
+from pandas.core.array_algos import masked_reductions
 from pandas.core.arrays import IntegerArray, PandasArray
 from pandas.core.arrays.integer import _IntegerDtype
 from pandas.core.construction import extract_array
@@ -282,8 +284,25 @@ def astype(self, dtype, copy=True):
         return super().astype(dtype, copy)
 
     def _reduce(self, name, skipna=True, **kwargs):
+        if name in ["min", "max"]:
+            return getattr(self, name)(skipna=skipna)
+
         raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
 
+    def min(self, skipna=True, **kwargs):
+        nv.validate_min((), kwargs)
+        result = masked_reductions.min(
+            values=self.to_numpy(), mask=self.isna(), skipna=skipna
+        )
+        return result
+
+    def max(self, skipna=True, **kwargs):
+        nv.validate_max((), kwargs)
+        result = masked_reductions.max(
+            values=self.to_numpy(), mask=self.isna(), skipna=skipna
+        )
+        return result
+
     def value_counts(self, dropna=False):
         from pandas import value_counts
 

pandas/tests/arrays/string_/test_string.py

@@ -230,6 +230,26 @@ def test_reduce(skipna):
     assert result == "abc"
 
 
+@pytest.mark.parametrize("method", ["min", "max"])
+@pytest.mark.parametrize("skipna", [True, False])
+def test_min_max(method, skipna):
+    arr = pd.Series(["a", "b", "c", None], dtype="string")
+    result = getattr(arr, method)(skipna=skipna)
+    if skipna:
+        expected = "a" if method == "min" else "c"
+        assert result == expected
+    else:
+        assert result is pd.NA
+
+
+@pytest.mark.parametrize("method", ["min", "max"])
+def test_min_max_numpy(method):
+    arr = pd.Series(["a", "b", "c", None], dtype="string")
+    result = getattr(np, method)(arr)
+    expected = "a" if method == "min" else "c"
+    assert result == expected
+
+
 @pytest.mark.parametrize("skipna", [True, False])
 @pytest.mark.xfail(reason="Not implemented StringArray.sum")
 def test_reduce_missing(skipna):

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",
+        ]:
+            # Tested in pandas/tests/arrays/string_/test_string.py
+            pytest.skip("These reductions are implemented")
+
         op_name = all_numeric_reductions
         s = pd.Series(data)