Implement any and all for pyarrow numpy strings (#54591)

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: phofl

pandas/core/arrays/string_arrow.py

@@ -554,3 +554,16 @@ def value_counts(self, dropna: bool = True):
         return Series(
             result._values.to_numpy(), index=result.index, name=result.name, copy=False
         )
+
+    def _reduce(
+        self, name: str, *, skipna: bool = True, keepdims: bool = False, **kwargs
+    ):
+        if name in ["any", "all"]:
+            arr = pc.and_kleene(
+                pc.invert(pc.is_null(self._pa_array)), pc.not_equal(self._pa_array, "")
+            )
+            return ArrowExtensionArray(arr)._reduce(
+                name, skipna=skipna, keepdims=keepdims, **kwargs
+            )
+        else:
+            return super()._reduce(name, skipna=skipna, keepdims=keepdims, **kwargs)

pandas/tests/extension/test_string.py

@@ -158,7 +158,11 @@ def test_fillna_no_op_returns_copy(self, data):
 
 class TestReduce(base.BaseReduceTests):
     def _supports_reduction(self, ser: pd.Series, op_name: str) -> bool:
-        return op_name in ["min", "max"]
+        return (
+            op_name in ["min", "max"]
+            or ser.dtype.storage == "pyarrow_numpy"  # type: ignore[union-attr]
+            and op_name in ("any", "all")
+        )
 
 
 class TestMethods(base.BaseMethodsTests):

pandas/tests/reductions/test_reductions.py

@@ -1078,6 +1078,25 @@ def test_any_all_datetimelike(self):
         assert df.any().all()
         assert not df.all().any()
 
+    def test_any_all_pyarrow_string(self):
+        # GH#54591
+        pytest.importorskip("pyarrow")
+        ser = Series(["", "a"], dtype="string[pyarrow_numpy]")
+        assert ser.any()
+        assert not ser.all()
+
+        ser = Series([None, "a"], dtype="string[pyarrow_numpy]")
+        assert ser.any()
+        assert not ser.all()
+
+        ser = Series([None, ""], dtype="string[pyarrow_numpy]")
+        assert not ser.any()
+        assert not ser.all()
+
+        ser = Series(["a", "b"], dtype="string[pyarrow_numpy]")
+        assert ser.any()
+        assert ser.all()
+
     def test_timedelta64_analytics(self):
         # index min/max
         dti = date_range("2012-1-1", periods=3, freq="D")