Skip to content

REF: Parametrize value_counts tests #28537

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.

Sign up for GitHub

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 2 commits into from
Sep 20, 2019
Merged

REF: Parametrize value_counts tests #28537

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
187eb09
REF: Parametrize value_counts tests
Sep 19, 2019
8ad5c7d
Split out params
Sep 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 17 additions & 18 deletions pandas/tests/groupby/test_value_counts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,29 +52,28 @@ def seed_df(seed_nans, n, m):

@pytest.mark.slow
@pytest.mark.parametrize("df, keys, bins, n, m", binned, ids=ids)
def test_series_groupby_value_counts(df, keys, bins, n, m):
@pytest.mark.parametrize(
"isort, normalize, sort, ascending, dropna", list(product((False, True), repeat=5))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not really a fan of using itertools to generate parametrization. Could you instead write this as:

@pytest.mark.parametrize("isort", [True, False])
@pytest.mark.parametrize("normalize", [True, False])
...

Equivalent at the end of the day but I think clearer and match the rest of the codebase

)
def test_series_groupby_value_counts(
df, keys, bins, n, m, isort, normalize, sort, ascending, dropna
):
def rebuild_index(df):
arr = list(map(df.index.get_level_values, range(df.index.nlevels)))
df.index = MultiIndex.from_arrays(arr, names=df.index.names)
return df

for isort, normalize, sort, ascending, dropna in product((False, True), repeat=5):

kwargs = dict(
normalize=normalize,
sort=sort,
ascending=ascending,
dropna=dropna,
bins=bins,
)
kwargs = dict(
normalize=normalize, sort=sort, ascending=ascending, dropna=dropna, bins=bins
)

gr = df.groupby(keys, sort=isort)
left = gr["3rd"].value_counts(**kwargs)
gr = df.groupby(keys, sort=isort)
left = gr["3rd"].value_counts(**kwargs)

gr = df.groupby(keys, sort=isort)
right = gr["3rd"].apply(Series.value_counts, **kwargs)
right.index.names = right.index.names[:-1] + ["3rd"]
gr = df.groupby(keys, sort=isort)
right = gr["3rd"].apply(Series.value_counts, **kwargs)
right.index.names = right.index.names[:-1] + ["3rd"]

# have to sort on index because of unstable sort on values
left, right = map(rebuild_index, (left, right)) # xref GH9212
tm.assert_series_equal(left.sort_index(), right.sort_index())
# have to sort on index because of unstable sort on values
left, right = map(rebuild_index, (left, right)) # xref GH9212
tm.assert_series_equal(left.sort_index(), right.sort_index())