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

Force nightly pyarrow in the upstream build #8993

Merged
merged 8 commits into from May 10, 2022
Merged

Force nightly pyarrow in the upstream build #8993

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
0a872af
CI: force nightly pyarrow in the upstream build
jorisvandenbossche Apr 28, 2022
984b39f
test-upstream
jorisvandenbossche Apr 28, 2022
f5fa063
temporary skip hanging tests [test-upstream]
jorisvandenbossche May 3, 2022
d7be2e9
fix check_compression [test-upstream]
jorisvandenbossche May 3, 2022
626d1dc
remove temp skips [test-upstream]
jorisvandenbossche May 4, 2022
33cced5
[test-upstream]
jorisvandenbossche May 5, 2022
8afb7ea
[test-upstream]
jorisvandenbossche May 6, 2022
0c71371
[test-upstream]
jorisvandenbossche May 9, 2022
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
2 changes: 1 addition & 1 deletion continuous_integration/scripts/install.sh
View file
Open in desktop
Expand Up @@ -7,7 +7,7 @@ set -xe
# python -m pip install --no-deps cityhash

if [[ ${UPSTREAM_DEV} ]]; then
mamba install -y -c arrow-nightlies "pyarrow>5.0"
mamba install -y -c arrow-nightlies "pyarrow>7.0"

# FIXME https://github.com/mamba-org/mamba/issues/412
# mamba uninstall --force numpy pandas fastparquet
Expand Down
15 changes: 15 additions & 0 deletions dask/bytes/tests/test_s3.py
View file
Open in desktop
Expand Up @@ -455,6 +455,9 @@ def test_parquet(s3, engine, s3so, metadata_file):
):
pytest.skip("#7056 - new s3fs not supported before pyarrow 3.0")

if engine == "pyarrow" and lib_version > parse_version("7.0.0"):
pytest.skip("#8993 - parquet dataset with s3 failing on pyarrow master")

url = "s3://%s/test.parquet" % test_bucket_name

data = pd.DataFrame(
Expand Down Expand Up @@ -555,6 +558,12 @@ def test_parquet_append(s3, engine, s3so):
pd = pytest.importorskip("pandas")
np = pytest.importorskip("numpy")

# TEMP
lib = pytest.importorskip(engine)
lib_version = parse_version(lib.__version__)
if engine == "pyarrow" and lib_version > parse_version("7.0.0"):
pytest.skip("#8993 - parquet dataset with s3 failing on pyarrow master")

url = "s3://%s/test.parquet.append" % test_bucket_name

data = pd.DataFrame(
Expand Down Expand Up @@ -609,6 +618,12 @@ def test_parquet_wstoragepars(s3, s3so, engine):
pd = pytest.importorskip("pandas")
np = pytest.importorskip("numpy")

# TEMP
lib = pytest.importorskip(engine)
lib_version = parse_version(lib.__version__)
if engine == "pyarrow" and lib_version > parse_version("7.0.0"):
pytest.skip("#8993 - parquet dataset with s3 failing on pyarrow master")

url = "s3://%s/test.parquet" % test_bucket_name

data = pd.DataFrame({"i32": np.array([0, 5, 2, 5])})
Expand Down
2 changes: 1 addition & 1 deletion dask/dataframe/io/tests/test_parquet.py
View file
Open in desktop
Expand Up @@ -1662,7 +1662,7 @@ def check_compression(engine, filename, compression):
else:
assert md.total_compressed_size != md.total_uncompressed_size
else:
metadata = pa.parquet.ParquetDataset(filename).metadata
metadata = pa.parquet.read_metadata(filename + "/_metadata")
jorisvandenbossche marked this conversation as resolved.
Show resolved Hide resolved
names = metadata.schema.names
for i in range(metadata.num_row_groups):
row_group = metadata.row_group(i)
Expand Down