diff --git a/doc/progress.rst b/doc/progress.rst index 3c2402bd6..493b029e5 100644 --- a/doc/progress.rst +++ b/doc/progress.rst @@ -6,6 +6,11 @@ Changelog ========= +0.14.1 +~~~~~~ + + * FIX: Fallback on downloading ARFF when failing to download parquet from MinIO due to a ServerError. + 0.14.0 ~~~~~~ diff --git a/openml/__version__.py b/openml/__version__.py index d3d65bbac..d44a77ce2 100644 --- a/openml/__version__.py +++ b/openml/__version__.py @@ -3,4 +3,4 @@ # License: BSD 3-Clause # The following line *must* be the last in the module, exactly as formatted: -__version__ = "0.14.0" +__version__ = "0.14.1" diff --git a/openml/datasets/functions.py b/openml/datasets/functions.py index d04ad8812..adbb46c6e 100644 --- a/openml/datasets/functions.py +++ b/openml/datasets/functions.py @@ -7,6 +7,7 @@ from typing import List, Dict, Optional, Union, cast import warnings +import minio.error import numpy as np import arff import pandas as pd @@ -499,6 +500,8 @@ def get_dataset( ) except urllib3.exceptions.MaxRetryError: parquet_file = None + if parquet_file is None and arff_file: + logger.warning("Failed to download parquet, fallback on ARFF.") else: parquet_file = None remove_dataset_cache = False @@ -1095,7 +1098,7 @@ def _get_dataset_parquet( openml._api_calls._download_minio_file( source=cast(str, url), destination=output_file_path ) - except (FileNotFoundError, urllib3.exceptions.MaxRetryError) as e: + except (FileNotFoundError, urllib3.exceptions.MaxRetryError, minio.error.ServerError) as e: logger.warning("Could not download file from %s: %s" % (cast(str, url), e)) return None return output_file_path