Skip to content
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

Jump to bottom

FIX-#2365: Fix Series.value_counts when dropna=False #2366

Merged
merged 1 commit into from
Nov 5, 2020
Merged

FIX-#2365: Fix Series.value_counts when dropna=False #2366

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 11 additions & 8 deletions modin/backends/pandas/query_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -732,18 +732,21 @@ def reduce_func(df, *args, **kwargs):
dropna = kwargs.get("dropna", True)

try:
result = df.squeeze(axis=1).groupby(df.index, sort=False).sum()
result = (
df.squeeze(axis=1)
.groupby(df.index, sort=False, dropna=dropna)
.sum()
)
# This will happen with Arrow buffer read-only errors. We don't want to copy
# all the time, so this will try to fast-path the code first.
except (ValueError):
result = df.copy().squeeze(axis=1).groupby(df.index, sort=False).sum()

if not dropna and np.nan in df.index:
result = result.append(
pandas.Series(
[df.squeeze(axis=1).loc[[np.nan]].sum()], index=[np.nan]
)
result = (
df.copy()
.squeeze(axis=1)
.groupby(df.index, sort=False, dropna=dropna)
.sum()
)

if normalize:
result = result / df.squeeze(axis=1).sum()

Expand Down
20 changes: 20 additions & 0 deletions modin/pandas/test/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3444,6 +3444,26 @@ def sort_index_for_equal_values(result, ascending):
)
df_equals(modin_result, pandas_result)

# from issue #2365
arr = np.random.rand(2 ** 6)
arr[::10] = np.nan
modin_series, pandas_series = create_test_series(arr)
modin_result = modin_series.value_counts(dropna=False, ascending=True)
pandas_result = sort_index_for_equal_values(
pandas_series.value_counts(dropna=False, ascending=True), True
)
if get_current_backend() == "BaseOnPython":
modin_result = sort_index_for_equal_values(modin_result, ascending=True)
df_equals(modin_result, pandas_result)

modin_result = modin_series.value_counts(dropna=False, ascending=False)
pandas_result = sort_index_for_equal_values(
pandas_series.value_counts(dropna=False, ascending=False), False
)
if get_current_backend() == "BaseOnPython":
modin_result = sort_index_for_equal_values(modin_result, ascending=False)
df_equals(modin_result, pandas_result)


@pytest.mark.parametrize("data", test_data_values, ids=test_data_keys)
def test_values(data):
Expand Down