Skip to content

TST: Replace deprecated pyarrow.parquet.ParquetDataset #42873

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

Merged
merged 2 commits into from
Aug 4, 2021
Merged

TST: Replace deprecated pyarrow.parquet.ParquetDataset #42873

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
da84da6
TST: Replace deprecated pyarrow.parquet.ParquetDataset
rhshadrach Aug 3, 2021
87cd505
Keep previous method for pyarrow < 5.0
rhshadrach Aug 3, 2021
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
2 changes: 2 additions & 0 deletions pandas/compat/pyarrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,10 @@
pa_version_under2p0 = _palv < Version("2.0.0")
pa_version_under3p0 = _palv < Version("3.0.0")
pa_version_under4p0 = _palv < Version("4.0.0")
pa_version_under5p0 = _palv < Version("5.0.0")
except ImportError:
pa_version_under1p0 = True
pa_version_under2p0 = True
pa_version_under3p0 = True
pa_version_under4p0 = True
pa_version_under5p0 = True
36 changes: 26 additions & 10 deletions pandas/tests/io/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
from pandas.compat.pyarrow import (
pa_version_under1p0,
pa_version_under2p0,
pa_version_under5p0,
)
import pandas.util._test_decorators as td

Expand Down Expand Up @@ -222,6 +223,29 @@ def compare(repeat):
compare(repeat)


def check_partition_names(path, expected):
"""Check partitions of a parquet file are as expected.

Parameters
----------
path: str
Path of the dataset.
expected: iterable of str
Expected partition names.
"""
if pa_version_under5p0:
import pyarrow.parquet as pq

dataset = pq.ParquetDataset(path, validate_schema=False)
assert len(dataset.partitions.partition_names) == len(expected)
assert dataset.partitions.partition_names == set(expected)
else:
import pyarrow.dataset as ds

dataset = ds.dataset(path, partitioning="hive")
assert dataset.partitioning.schema.names == expected


def test_invalid_engine(df_compat):
msg = "engine must be one of 'pyarrow', 'fastparquet'"
with pytest.raises(ValueError, match=msg):
Expand Down Expand Up @@ -743,11 +767,7 @@ def test_partition_cols_supported(self, pa, df_full):
df = df_full
with tm.ensure_clean_dir() as path:
df.to_parquet(path, partition_cols=partition_cols, compression=None)
import pyarrow.parquet as pq

dataset = pq.ParquetDataset(path, validate_schema=False)
assert len(dataset.partitions.partition_names) == 2
assert dataset.partitions.partition_names == set(partition_cols)
check_partition_names(path, partition_cols)
assert read_parquet(path).shape == df.shape

def test_partition_cols_string(self, pa, df_full):
Expand All @@ -757,11 +777,7 @@ def test_partition_cols_string(self, pa, df_full):
df = df_full
with tm.ensure_clean_dir() as path:
df.to_parquet(path, partition_cols=partition_cols, compression=None)
import pyarrow.parquet as pq

dataset = pq.ParquetDataset(path, validate_schema=False)
assert len(dataset.partitions.partition_names) == 1
assert dataset.partitions.partition_names == set(partition_cols_list)
check_partition_names(path, partition_cols_list)
assert read_parquet(path).shape == df.shape

@pytest.mark.parametrize("path_type", [str, pathlib.Path])
Expand Down