Skip to content

Use .plc_column instead of .to_pylibcudf in join, internals methods #20743

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

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
+16 −26
Open

Use .plc_column instead of .to_pylibcudf in join, internals methods #20743

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
a42507e
Use .plc_column in join.py
mroeschke Nov 27, 2025
9d922e3
Use .plc_column in stream_compaction
mroeschke Nov 27, 2025
53ece96
Use .plc_column in sorting.py
mroeschke Nov 27, 2025
c67abd0
Merge remote-tracking branch 'upstream/main' into ref/cudf/join_inter…
mroeschke Dec 1, 2025
047bea3
Merge remote-tracking branch 'upstream/main' into ref/cudf/join_inter…
mroeschke Dec 2, 2025
ba99439
Merge remote-tracking branch 'upstream/main' into ref/cudf/join_inter…
mroeschke Dec 2, 2025
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
12 changes: 6 additions & 6 deletions python/cudf/cudf/core/_internals/sorting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ def is_sorted(
"""
column_order, null_precedence = ordering(ascending, na_position)
return plc.sorting.is_sorted(
plc.Table([col.to_pylibcudf(mode="read") for col in source_columns]),
plc.Table([col.plc_column for col in source_columns]),
column_order,
null_precedence,
)
Expand Down Expand Up @@ -123,7 +123,7 @@ def order_by(
)
return func(
plc.Table(
[col.to_pylibcudf(mode="read") for col in columns_from_table],
[col.plc_column for col in columns_from_table],
),
column_order,
null_precedence,
Expand Down Expand Up @@ -168,8 +168,8 @@ def sort_by_key(
plc.sorting.stable_sort_by_key if stable else plc.sorting.sort_by_key
)
return func(
plc.Table([col.to_pylibcudf(mode="read") for col in values]),
plc.Table([col.to_pylibcudf(mode="read") for col in keys]),
plc.Table([col.plc_column for col in values]),
plc.Table([col.plc_column for col in keys]),
column_order,
null_precedence,
).columns()
Expand Down Expand Up @@ -207,8 +207,8 @@ def search_sorted(
"lower_bound" if side == "left" else "upper_bound",
)
return func(
plc.Table([col.to_pylibcudf(mode="read") for col in source]),
plc.Table([col.to_pylibcudf(mode="read") for col in values]),
plc.Table([col.plc_column for col in source]),
plc.Table([col.plc_column for col in values]),
column_order,
null_precedence,
)
8 changes: 4 additions & 4 deletions python/cudf/cudf/core/_internals/stream_compaction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ def drop_nulls(
keep_threshold = len(keys)

plc_table = plc.stream_compaction.drop_nulls(
plc.Table([col.to_pylibcudf(mode="read") for col in columns]),
plc.Table([col.plc_column for col in columns]),
keys,
keep_threshold,
)
Expand All @@ -73,8 +73,8 @@ def apply_boolean_mask(
columns obtained from applying mask
"""
plc_table = plc.stream_compaction.apply_boolean_mask(
plc.Table([col.to_pylibcudf(mode="read") for col in columns]),
boolean_mask.to_pylibcudf(mode="read"),
plc.Table([col.plc_column for col in columns]),
boolean_mask.plc_column,
)
return plc_table.columns()

Expand Down Expand Up @@ -110,7 +110,7 @@ def drop_duplicates(
raise ValueError('keep must be either "first", "last" or False')

plc_table = plc.stream_compaction.stable_distinct(
plc.Table([col.to_pylibcudf(mode="read") for col in columns]),
plc.Table([col.plc_column for col in columns]),
keys if keys is not None else list(range(len(columns))),
keep_option,
plc.types.NullEquality.EQUAL
Expand Down
22 changes: 6 additions & 16 deletions python/cudf/cudf/core/join/join.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,8 @@ def _joiner(
raise ValueError(f"Invalid join type {how}")

left_rows, right_rows = join_func(
plc.Table([col.to_pylibcudf(mode="read") for col in lhs]),
plc.Table([col.to_pylibcudf(mode="read") for col in rhs]),
plc.Table([col.plc_column for col in lhs]),
plc.Table([col.plc_column for col in rhs]),
plc.types.NullEquality.EQUAL,
)
return (
Expand Down Expand Up @@ -325,18 +325,8 @@ def perform_merge(self) -> DataFrame:

if self.how == "cross":
lib_table = plc.join.cross_join(
plc.Table(
[
col.to_pylibcudf(mode="read")
for col in self.lhs._columns
]
),
plc.Table(
[
col.to_pylibcudf(mode="read")
for col in self.rhs._columns
]
),
plc.Table([col.plc_column for col in self.lhs._columns]),
plc.Table([col.plc_column for col in self.rhs._columns]),
)
columns = lib_table.columns()
left_names, right_names = (
Expand Down Expand Up @@ -689,8 +679,8 @@ def _joiner( # type: ignore[override]

return ColumnBase.from_pylibcudf(
join_func(
plc.Table([col.to_pylibcudf(mode="read") for col in lhs]),
plc.Table([col.to_pylibcudf(mode="read") for col in rhs]),
plc.Table([col.plc_column for col in lhs]),
plc.Table([col.plc_column for col in rhs]),
plc.types.NullEquality.EQUAL,
)
), None
Expand Down
Loading