-
-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Closed
dask/fastparquet
#802Labels
Description
@martindurant there are failures cropping up in tests. Looks like 0.8.2 just made it to conda-forge an hour or so ago
=================================== FAILURES ===================================
__________________________ test_parquet[fastparquet] ___________________________
[gw1] linux -- Python 3.9.13 /usr/share/miniconda3/envs/test-environment/bin/python
engine = 'fastparquet'
@pytest.mark.network
@pytest.mark.parametrize("engine", ("pyarrow", "fastparquet"))
def test_parquet(engine):
pytest.importorskip("requests", minversion="2.21.0")
dd = pytest.importorskip("dask.dataframe")
pytest.importorskip(engine)
> df = dd.read_parquet(
[
"https://github.com/Parquet/parquet-compatibility/raw/"
"master/parquet-testdata/impala/1.1.1-NONE/"
"nation.impala.parquet"
],
engine=engine,
).compute()
dask/bytes/tests/test_http.py:179:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
dask/dataframe/io/parquet/core.py:471: in read_parquet
read_metadata_result = engine.read_metadata(
dask/dataframe/io/parquet/fastparquet.py:835: in read_metadata
dataset_info = cls._collect_dataset_info(
dask/dataframe/io/parquet/fastparquet.py:469: in _collect_dataset_info
pf = ParquetFile(
/usr/share/miniconda3/envs/test-environment/lib/python3.9/site-packages/fastparquet/api.py:123: in __init__
writer.consolidate_categories(fmd)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
fmd = column_orders: null
created_by: b'impala version 1.2-INTERNAL (build a462ec42e550c75fccbff98c720f37f3ee9d55a3)'
encryp...ent
num_children: null
precision: null
repetition_type: 1
scale: null
type: 6
type_length: null
version: 1
def consolidate_categories(fmd):
> key_value = [k for k in fmd.key_value_metadata
if k.key == b'pandas']
E TypeError: 'NoneType' object is not iterable
/usr/share/miniconda3/envs/test-environment/lib/python3.9/site-packages/fastparquet/writer.py:1331: TypeErrorref: https://github.com/dask/dask/runs/7998537202?check_suite_focus=true
Reactions are currently unavailable