API: BooleanArray any/all with NA logic

pandas/core/arrays/boolean.py

@@ -557,6 +557,30 @@ def _values_for_argsort(self) -> np.ndarray:
         data[self._mask] = -1
         return data
 
+    def any(self, skipna=True):
+        # nv.validate_any((), dict(out=out, keepdims=keepdims))
+        valid_values = self._data[~self._mask]
+        if skipna:
+            return valid_values.any()
+        else:
+            result = valid_values.any()
+            if result or len(self) == 0:
+                return result
+            else:
+                return self.dtype.na_value
+
+    def all(self, skipna=True):
+        # nv.validate_any((), dict(out=out, keepdims=keepdims))
+        valid_values = self._data[~self._mask]
+        if skipna:
+            return valid_values.all()
+        else:
+            result = valid_values.all()
+            if not result or len(self) == 0:
+                return result
+            else:
+                return self.dtype.na_value
+
     @classmethod
     def _create_logical_method(cls, op):
         def logical_method(self, other):
@@ -646,6 +670,10 @@ def cmp_method(self, other):
         return set_function_name(cmp_method, name, cls)
 
     def _reduce(self, name, skipna=True, **kwargs):
+
+        if name in {"any", "all"}:
+            return getattr(self, name)(skipna=skipna, **kwargs)
+
         data = self._data
         mask = self._mask
 
@@ -657,12 +685,8 @@ def _reduce(self, name, skipna=True, **kwargs):
         op = getattr(nanops, "nan" + name)
         result = op(data, axis=0, skipna=skipna, mask=mask, **kwargs)
 
-        # if we have a boolean op, don't coerce
-        if name in ["any", "all"]:
-            pass
-
         # if we have numeric op that would result in an int, coerce to int if possible
-        elif name in ["sum", "prod"] and notna(result):
+        if name in ["sum", "prod"] and notna(result):
             int_result = np.int64(result)
             if int_result == result:
                 result = int_result

pandas/tests/arrays/test_boolean.py

@@ -531,6 +531,30 @@ def test_reductions_return_types(dropna, data, all_numeric_reductions):
         assert isinstance(getattr(s, op)(), np.float64)
 
 
+@pytest.mark.parametrize(
+    "values, exp_any, exp_all, exp_any_noskip, exp_all_noskip",
+    [
+        ([True, pd.NA], True, True, True, pd.NA),
+        ([False, pd.NA], False, False, pd.NA, False),
+        ([pd.NA], False, True, pd.NA, pd.NA),
+        ([], False, True, False, True),
+    ],
+)
+def test_any_all(values, exp_any, exp_all, exp_any_noskip, exp_all_noskip):
+    # the methods return numpy scalars
+    exp_any = pd.NA if exp_any is pd.NA else np.bool_(exp_any)
+    exp_all = pd.NA if exp_all is pd.NA else np.bool_(exp_all)
+    exp_any_noskip = pd.NA if exp_any_noskip is pd.NA else np.bool_(exp_any_noskip)
+    exp_all_noskip = pd.NA if exp_all_noskip is pd.NA else np.bool_(exp_all_noskip)
+
+    for con in [pd.array, pd.Series]:
+        a = con(values, dtype="boolean")
+        assert a.any() is exp_any
+        assert a.all() is exp_all
+        assert a.any(skipna=False) is exp_any_noskip
+        assert a.all(skipna=False) is exp_all_noskip
+
+
 # TODO when BooleanArray coerces to object dtype numpy array, need to do conversion
 # manually in the indexing code
 # def test_indexing_boolean_mask():