[ArrowStringArray] fix test_value_counts_na (#41002)

Author: simonjayhawkins

pandas/core/arrays/string_arrow.py

@@ -675,13 +675,18 @@ def value_counts(self, dropna: bool = True) -> Series:
 
         vc = self._data.value_counts()
 
-        # Index cannot hold ExtensionArrays yet
-        index = Index(type(self)(vc.field(0)).astype(object))
+        values = vc.field(0)
+        counts = vc.field(1)
+        if dropna and self._data.null_count > 0:
+            mask = values.is_valid()
+            values = values.filter(mask)
+            counts = counts.filter(mask)
+
         # No missing values so we can adhere to the interface and return a numpy array.
-        counts = np.array(vc.field(1))
+        counts = np.array(counts)
 
-        if dropna and self._data.null_count > 0:
-            raise NotImplementedError("yo")
+        # Index cannot hold ExtensionArrays yet
+        index = Index(type(self)(values)).astype(object)
 
         return Series(counts, index=index).astype("Int64")
 

pandas/tests/arrays/string_/test_string.py

@@ -476,12 +476,7 @@ def test_arrow_roundtrip(dtype, dtype_object):
     assert result.loc[2, "a"] is pd.NA
 
 
-def test_value_counts_na(dtype, request):
-    if dtype == "arrow_string":
-        reason = "TypeError: boolean value of NA is ambiguous"
-        mark = pytest.mark.xfail(reason=reason)
-        request.node.add_marker(mark)
-
+def test_value_counts_na(dtype):
     arr = pd.array(["a", "b", "a", pd.NA], dtype=dtype)
     result = arr.value_counts(dropna=False)
     expected = pd.Series([2, 1, 1], index=["a", "b", pd.NA], dtype="Int64")
@@ -492,12 +487,7 @@ def test_value_counts_na(dtype, request):
     tm.assert_series_equal(result, expected)
 
 
-def test_value_counts_with_normalize(dtype, request):
-    if dtype == "arrow_string":
-        reason = "TypeError: boolean value of NA is ambiguous"
-        mark = pytest.mark.xfail(reason=reason)
-        request.node.add_marker(mark)
-
+def test_value_counts_with_normalize(dtype):
     s = pd.Series(["a", "b", "a", pd.NA], dtype=dtype)
     result = s.value_counts(normalize=True)
     expected = pd.Series([2, 1], index=["a", "b"], dtype="Float64") / 3