Skip to content

BUG: value_counts not working correctly on ExtensionArrays #33674

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
May 1, 2020
11 changes: 11 additions & 0 deletions pandas/tests/extension/base/methods.py
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,17 @@ def test_value_counts(self, all_data, dropna):

self.assert_series_equal(result, expected)

def test_value_counts_with_normalize(self, data):
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")
Expand Down
4 changes: 4 additions & 0 deletions pandas/tests/extension/decimal/test_decimal.py
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
4 changes: 4 additions & 0 deletions pandas/tests/extension/json/test_json.py
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand Down
4 changes: 4 additions & 0 deletions pandas/tests/extension/test_numpy.py
Original file line number Diff line number Diff line change
Expand Up @@ -199,6 +199,10 @@ class TestMethods(BaseNumPyTests, base.BaseMethodsTests):
def test_value_counts(self, all_data, dropna):
pass

@pytest.mark.xfail(reason="not working")
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
Expand Down