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 bug in map_overlap when after creates an empty partition #10639

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix bug in map_overlap when after creates an empty partition #10639

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 3 additions & 1 deletion dask/dataframe/rolling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,8 @@ def overlap_chunk(func, before, after, *args, **kwargs):
after = next_part_length
if after and expansion:
after *= expansion
if after == 0:
return out.iloc[before:None]
return out.iloc[before:-after]


Expand Down Expand Up @@ -342,7 +344,7 @@ def _get_nexts_partitions(df, after):
nexts = []
for i in range(1, df.npartitions):
key = (name_b, i)
dsk[key] = (_head_timedelta, (df_name, i - 0), (df_name, i), after)
dsk[key] = (_head_timedelta, (df_name, i - 1), (df_name, i), after)
nexts.append(key)
nexts.append(None)
else:
Expand Down
14 changes: 14 additions & 0 deletions dask/dataframe/tests/test_rolling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,6 +248,20 @@ def test_map_overlap_provide_meta():
assert_eq(res, sol)


def test_map_overlap_empty_partition_after():
def func(x):
x = x + x.sum()
return x

idx = pd.date_range("2020-01-01", periods=5, freq="D")
pdf = pd.DataFrame(1, index=idx, columns=["a"])
df = dd.from_pandas(pdf, npartitions=2)

result = df.map_overlap(func, before=0, after="1D")
expected = pd.DataFrame([4, 4, 4, 3, 3], index=idx, columns=["a"])
assert_eq(result, expected)


def mad(x):
return np.fabs(x - x.mean()).mean()

Expand Down