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

Test query-planning in gpuCI #11060

Merged
merged 8 commits into from
May 10, 2024
Merged

Test query-planning in gpuCI #11060

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
61d91f7
test legacy and new APIs in gpuCI
rjzamora Apr 22, 2024
63de884
update broken gpu-ci tests for 3.10
rjzamora Apr 22, 2024
0f76817
Merge branch 'main' into gpuci-query-planning
rjzamora Apr 24, 2024
394a00b
roll back fix that is now unnecessary
rjzamora Apr 24, 2024
83c8cb4
Merge branch 'main' into gpuci-query-planning
rjzamora May 2, 2024
3ba474b
only test dask.dataframe with legacy
rjzamora May 9, 2024
2c1005b
Merge remote-tracking branch 'upstream/main' into gpuci-query-planning
rjzamora May 9, 2024
029c2fc
Merge branch 'gpuci-query-planning' of github.com:rjzamora/dask into …
rjzamora May 9, 2024
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
10 changes: 5 additions & 5 deletions continuous_integration/gpuci/build.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,6 @@ cd "$WORKSPACE"
# Determine CUDA release version
export CUDA_REL=${CUDA_VERSION%.*}

# TODO: remove once RAPIDS 24.06 has full support for dask-expr
export DASK_DATAFRAME__QUERY_PLANNING=false

################################################################################
# SETUP - Check environment
################################################################################
Expand Down Expand Up @@ -57,5 +54,8 @@ conda info
conda config --show-sources
conda list --show-channel-urls

rapids-logger "Python py.test for dask"
py.test $WORKSPACE -n 3 -v -m gpu --junitxml="$WORKSPACE/junit-dask.xml" --cov-config="$WORKSPACE/pyproject.toml" --cov=dask --cov-report=xml:"$WORKSPACE/dask-coverage.xml" --cov-report term
rapids-logger "Python py.test for dask (LEGACY)"
DASK_DATAFRAME__QUERY_PLANNING=False py.test $WORKSPACE -n 3 -v -m gpu --junitxml="$WORKSPACE/junit-dask-legacy.xml" --cov-config="$WORKSPACE/pyproject.toml" --cov=dask --cov-report=xml:"$WORKSPACE/dask-coverage-legacy.xml" --cov-report term

rapids-logger "Python py.test for dask (NEW)"
DASK_DATAFRAME__QUERY_PLANNING=True py.test $WORKSPACE -n 3 -v -m gpu --junitxml="$WORKSPACE/junit-dask.xml" --cov-config="$WORKSPACE/pyproject.toml" --cov=dask --cov-report=xml:"$WORKSPACE/dask-coverage.xml" --cov-report term
rjzamora marked this conversation as resolved.
Show resolved Hide resolved
14 changes: 13 additions & 1 deletion dask/dataframe/tests/test_dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5184,7 +5184,19 @@ def test_datetime_loc_open_slicing():
assert_eq(df[0].loc["02.02.2015":], ddf[0].loc["02.02.2015":])


@pytest.mark.parametrize("gpu", [False, pytest.param(True, marks=pytest.mark.gpu)])
@pytest.mark.parametrize(
"gpu",
[
False,
pytest.param(
True,
marks=[
pytest.mark.gpu,
pytest.mark.xfail(DASK_EXPR_ENABLED, reason="not supported"),
rjzamora marked this conversation as resolved.
Show resolved Hide resolved
],
),
],
)
def test_to_datetime(gpu):
xd = pd if not gpu else pytest.importorskip("cudf")

Expand Down
4 changes: 3 additions & 1 deletion dask/dataframe/tests/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3035,7 +3035,9 @@ def test_groupby_apply_cudf(group_keys):
)

assert_eq(res_pd, res_dd)
assert_eq(res_dd, res_dc)
# Pandas and cudf return different `index.name`
# for empty MultiIndex (use `check_names=False`)
assert_eq(res_dd, res_dc, check_names=False)


@pytest.mark.parametrize("sort", [True, False])
Expand Down
13 changes: 12 additions & 1 deletion dask/dataframe/tests/test_multi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1135,7 +1135,18 @@ def test_merge_how_raises():


@pytest.mark.parametrize("parts", [(3, 3), (3, 1), (1, 3)])
@pytest.mark.parametrize("how", ["leftsemi", "leftanti"])
@pytest.mark.parametrize(
"how",
[
"leftsemi",
pytest.param(
"leftanti",
marks=pytest.mark.xfail(
DASK_EXPR_ENABLED, reason="leftanti is not supported yet"
),
),
],
)
@pytest.mark.parametrize(
"engine",
[
Expand Down