rok commented on code in PR #48979:
URL: https://github.com/apache/arrow/pull/48979#discussion_r2828567128
##########
python/pyarrow/tests/parquet/test_basic.py:
##########
@@ -759,17 +760,23 @@ def test_fastparquet_cross_compatibility(tempdir):
fp_file = fp.ParquetFile(file_arrow)
df_fp = fp_file.to_pandas()
- tm.assert_frame_equal(df, df_fp)
+ # TODO: once fastparquet supports pandas 3 dtypes revert string and
categorical
+ # tests by removing `check_dtype=False` and `check_categorical=False` so
type
+ # equality is asserted again
+ tm.assert_frame_equal(df, df_fp, check_dtype=False,
check_categorical=False)
# Fastparquet -> arrow
file_fastparquet = str(tempdir / "cross_compat_fastparquet.parquet")
- fp.write(file_fastparquet, df)
+ # fastparquet can't write pandas 3.0 StringDtype
+ df_for_fp = df.copy()
+ df_for_fp['a'] = df_for_fp['a'].astype(object)
+ fp.write(file_fastparquet, df_for_fp)
table_fp = pq.read_pandas(file_fastparquet)
# for fastparquet written file, categoricals comes back as strings
# (no arrow schema in parquet metadata)
- df['f'] = df['f'].astype(object)
- tm.assert_frame_equal(table_fp.to_pandas(), df)
+ tm.assert_frame_equal(table_fp.to_pandas(), df_for_fp, check_dtype=False,
+ check_categorical=False)
Review Comment:
Maybe:
```suggestion
expected_types = {"a": pd.StringDtype(), "f": object}
tm.assert_frame_equal(table_fp.to_pandas(), df.astype(expected_types))
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
