This is an automated email from the ASF dual-hosted git repository.
raulcd pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 085493b8ab GH-37853: [Python] Remove test and fixture involving
fastparquet (#50416)
085493b8ab is described below
commit 085493b8ab2ad97d95c03dcaf4dac890dfe5ff19
Author: Raúl Cumplido <[email protected]>
AuthorDate: Thu Jul 9 10:33:27 2026 +0200
GH-37853: [Python] Remove test and fixture involving fastparquet (#50416)
### Rationale for this change
`test_fastparquet_cross_compatibility` is not exercised and when exercised
with latest versions it fails because it's not compatible with pandas 3 and it
won't be as the project is retired, see:
- https://github.com/dask/fastparquet/pull/973
### What changes are included in this PR?
Removal of fixture to mark test as `fastparquet` and remove single test
that still required fastarquet.
### Are these changes tested?
Yes and no. CI is exercised as expected but `fastparquet` tests weren't
exercised on CI in the first place.
### Are there any user-facing changes?
No
* GitHub Issue: #37853
Authored-by: Raúl Cumplido <[email protected]>
Signed-off-by: Raúl Cumplido <[email protected]>
---
python/pyarrow/conftest.py | 8 ------
python/pyarrow/tests/parquet/test_basic.py | 43 ------------------------------
2 files changed, 51 deletions(-)
diff --git a/python/pyarrow/conftest.py b/python/pyarrow/conftest.py
index 9fed75dac3..e2595dc2d9 100644
--- a/python/pyarrow/conftest.py
+++ b/python/pyarrow/conftest.py
@@ -33,7 +33,6 @@ groups = [
'cython',
'dataset',
'hypothesis',
- 'fastparquet',
'flight',
'gandiva',
'gcs',
@@ -69,7 +68,6 @@ defaults = {
'bz2': Codec.is_available('bz2'),
'cython': False,
'dataset': False,
- 'fastparquet': False,
'flight': False,
'gandiva': False,
'gcs': False,
@@ -116,12 +114,6 @@ try:
except ImportError:
pass
-try:
- import fastparquet # noqa
- defaults['fastparquet'] = True
-except ImportError:
- pass
-
try:
import warnings
with warnings.catch_warnings():
diff --git a/python/pyarrow/tests/parquet/test_basic.py
b/python/pyarrow/tests/parquet/test_basic.py
index 01c84b4f35..20e3f51bb6 100644
--- a/python/pyarrow/tests/parquet/test_basic.py
+++ b/python/pyarrow/tests/parquet/test_basic.py
@@ -817,49 +817,6 @@ def test_parquet_file_too_small(tempdir):
pq.read_table(path)
[email protected]
[email protected]
[email protected]("ignore:RangeIndex:FutureWarning")
[email protected]("ignore:tostring:DeprecationWarning:fastparquet")
[email protected]("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(),
