Skip to content

GH-37853: [Python] Remove test and fixture involving fastparquet #50416

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

Open
raulcd wants to merge 1 commit into
base: main
Choose a base branch
from
+0 −51
Open

GH-37853: [Python] Remove test and fixture involving fastparquet #50416

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 0 additions & 8 deletions python/pyarrow/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,6 @@
'cython',
'dataset',
'hypothesis',
'fastparquet',
'flight',
'gandiva',
'gcs',
Expand Down Expand Up @@ -69,7 +68,6 @@
'bz2': Codec.is_available('bz2'),
'cython': False,
'dataset': False,
'fastparquet': False,
'flight': False,
'gandiva': False,
'gcs': False,
Expand Down Expand Up @@ -116,12 +114,6 @@
except ImportError:
pass

try:
import fastparquet # noqa
defaults['fastparquet'] = True
except ImportError:
pass

try:
import warnings
with warnings.catch_warnings():
Expand Down
43 changes: 0 additions & 43 deletions python/pyarrow/tests/parquet/test_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -817,49 +817,6 @@ def test_parquet_file_too_small(tempdir):
pq.read_table(path)


@pytest.mark.pandas
@pytest.mark.fastparquet
@pytest.mark.filterwarnings("ignore:RangeIndex:FutureWarning")
@pytest.mark.filterwarnings("ignore:tostring:DeprecationWarning:fastparquet")
@pytest.mark.filterwarnings("ignore:unclosed file:ResourceWarning")
def test_fastparquet_cross_compatibility(tempdir):
fp = pytest.importorskip('fastparquet')

df = pd.DataFrame(
{
"a": list("abc"),
"b": list(range(1, 4)),
"c": np.arange(4.0, 7.0, dtype="float64"),
"d": [True, False, True],
"e": pd.date_range("20130101", periods=3),
"f": pd.Categorical(["a", "b", "a"]),
# fastparquet writes list as BYTE_ARRAY JSON, so no roundtrip
# "g": [[1, 2], None, [1, 2, 3]],
}
)
table = pa.table(df)

# Arrow -> fastparquet
file_arrow = str(tempdir / "cross_compat_arrow.parquet")
pq.write_table(table, file_arrow, compression=None)

fp_file = fp.ParquetFile(file_arrow)
df_fp = fp_file.to_pandas()
# pandas 3 defaults to StringDtype for strings, fastparquet still returns object
# TODO: remove astype casts once fastparquet supports pandas 3 StringDtype
tm.assert_frame_equal(df_fp, df.astype({"a": object}))

# Fastparquet -> arrow
file_fastparquet = str(tempdir / "cross_compat_fastparquet.parquet")
# fastparquet doesn't support writing pandas 3 StringDtype yet
fp.write(file_fastparquet, df.astype({"a": object}))

table_fp = pq.read_pandas(file_fastparquet)
# for fastparquet written file, categoricals comes back as strings
# (no arrow schema in parquet metadata)
tm.assert_frame_equal(table_fp.to_pandas(), df.astype({"f": object}))


@pytest.mark.parametrize('array_factory', [
lambda: pa.array([0, None] * 10),
lambda: pa.array([0, None] * 10).dictionary_encode(),
Expand Down
Loading