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

Implement string join in cudf-polars #17755

Open
wants to merge 4 commits into
base: branch-25.02
Choose a base branch
from
+25 −4
Open

Implement string join in cudf-polars #17755

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c158750
Use repr formatting for enum
wence- Jan 9, 2025
88fdd58
Implement str.join
wence- Jan 16, 2025
1d8febc
Add test of new functionality
wence- Jan 23, 2025
f72075e
Merge remote-tracking branch 'upstream/branch-25.02' into wence/demo
wence- Jan 23, 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
20 changes: 17 additions & 3 deletions python/cudf_polars/cudf_polars/dsl/expressions/string.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
# SPDX-License-Identifier: Apache-2.0
# TODO: remove need for this
# ruff: noqa: D101
Expand Down Expand Up @@ -111,6 +111,7 @@ def __init__(

def _validate_input(self):
if self.name not in (
StringFunction.Name.ConcatVertical,
StringFunction.Name.Contains,
StringFunction.Name.EndsWith,
StringFunction.Name.Lowercase,
Expand All @@ -124,7 +125,7 @@ def _validate_input(self):
StringFunction.Name.StripCharsEnd,
StringFunction.Name.Uppercase,
):
raise NotImplementedError(f"String function {self.name}")
raise NotImplementedError(f"String function {self.name!r}")
if self.name is StringFunction.Name.Contains:
literal, strict = self.options
if not literal:
Expand Down Expand Up @@ -204,7 +205,20 @@ def do_evaluate(
mapping: Mapping[Expr, Column] | None = None,
) -> Column:
"""Evaluate this expression given a dataframe for context."""
if self.name is StringFunction.Name.Contains:
if self.name is StringFunction.Name.ConcatVertical:
(child,) = self.children
column = child.evaluate(df, context=context, mapping=mapping)
delimiter, ignore_nulls = self.options
if column.obj.null_count() > 0 and not ignore_nulls:
return Column(plc.Column.all_null_like(column.obj, 1))
return Column(
plc.strings.combine.join_strings(
column.obj,
plc.interop.from_arrow(pa.scalar(delimiter, type=pa.string())),
plc.interop.from_arrow(pa.scalar(None, type=pa.string())),
)
)
elif self.name is StringFunction.Name.Contains:
child, arg = self.children
column = child.evaluate(df, context=context, mapping=mapping)

Expand Down
9 changes: 8 additions & 1 deletion python/cudf_polars/tests/expressions/test_stringfunction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
# SPDX-License-Identifier: Apache-2.0
from __future__ import annotations

Expand Down Expand Up @@ -454,3 +454,10 @@ def test_string_to_numeric_invalid(numeric_type):
polars_except=pl.exceptions.InvalidOperationError,
cudf_except=pl.exceptions.ComputeError,
)


@pytest.mark.parametrize("ignore_nulls", [False, True])
@pytest.mark.parametrize("delimiter", ["", "/"])
def test_string_join(ldf, ignore_nulls, delimiter):
q = ldf.select(pl.col("a").str.join(delimiter, ignore_nulls=ignore_nulls))
assert_gpu_result_equal(q)
Loading