BUG: value_counts not working correctly on ExtensionArrays (pandas-dev#33674)

Author: kotamatsuoka

pandas/tests/extension/base/methods.py

@@ -28,6 +28,18 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
+    def test_value_counts_with_normalize(self, data):
+        # GH 33172
+        data = data[:10].unique()
+        values = np.array(data[~data.isna()])
+
+        result = (
+            pd.Series(data, dtype=data.dtype).value_counts(normalize=True).sort_index()
+        )
+
+        expected = pd.Series([1 / len(values)] * len(values), index=result.index)
+        self.assert_series_equal(result, expected)
+
     def test_count(self, data_missing):
         df = pd.DataFrame({"A": data_missing})
         result = df.count(axis="columns")

pandas/tests/extension/decimal/test_decimal.py

@@ -181,6 +181,10 @@ def test_value_counts(self, all_data, dropna):
 
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(reason="value_counts not implemented yet.")
+    def test_value_counts_with_normalize(self, data):
+        return super().test_value_counts_with_normalize(data)
+
 
 class TestCasting(BaseDecimal, base.BaseCastingTests):
     pass

pandas/tests/extension/json/test_json.py

@@ -193,6 +193,10 @@ class TestMethods(BaseJSON, base.BaseMethodsTests):
     def test_value_counts(self, all_data, dropna):
         pass
 
+    @unhashable
+    def test_value_counts_with_normalize(self, data):
+        pass
+
     @unhashable
     def test_sort_values_frame(self):
         # TODO (EA.factorize): see if _values_for_factorize allows this.

pandas/tests/extension/test_numpy.py

@@ -199,6 +199,10 @@ class TestMethods(BaseNumPyTests, base.BaseMethodsTests):
     def test_value_counts(self, all_data, dropna):
         pass
 
+    @pytest.mark.xfail(reason="not working. will be covered by #32028")
+    def test_value_counts_with_normalize(self, data):
+        return super().test_value_counts_with_normalize(data)
+
     @pytest.mark.skip(reason="Incorrect expected")
     # We have a bool dtype, so the result is an ExtensionArray
     # but expected is not