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

Preserve Series name in duplicated method. #16655

Merged
merged 2 commits into from
Aug 26, 2024
Merged

Preserve Series name in duplicated method. #16655

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d4c667f
Preserve Series name in duplicated method.
bdice Aug 26, 2024
a005954
Add tests.
bdice Aug 26, 2024
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
4 changes: 3 additions & 1 deletion python/cudf/cudf/core/indexed_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3198,8 +3198,10 @@ def duplicated(self, subset=None, keep="first"):
"""
subset = self._preprocess_subset(subset)

name = None
if isinstance(self, cudf.Series):
columns = [self._column]
name = self.name
else:
columns = [self._data[n] for n in subset]
distinct = libcudf.stream_compaction.distinct_indices(
Expand All @@ -3211,7 +3213,7 @@ def duplicated(self, subset=None, keep="first"):
[as_column(True, length=len(self), dtype=bool)],
bounds_check=False,
)[0]
return cudf.Series._from_column(result, index=self.index)
return cudf.Series._from_column(result, index=self.index, name=name)

@_performance_tracking
def _empty_like(self, keep_index=True) -> Self:
Expand Down
5 changes: 3 additions & 2 deletions python/cudf/cudf/tests/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2115,8 +2115,9 @@ def test_series_hasnans(data):
],
)
@pytest.mark.parametrize("keep", ["first", "last", False])
def test_series_duplicated(data, index, keep):
gs = cudf.Series(data, index=index)
@pytest.mark.parametrize("name", [None, "a"])
def test_series_duplicated(data, index, keep, name):
gs = cudf.Series(data, index=index, name=name)
ps = gs.to_pandas()

assert_eq(gs.duplicated(keep=keep), ps.duplicated(keep=keep))
Expand Down
Loading