Allow datasets without qualities to be downloaded. (openml#847)

PGijsbers · web-flow · commit a5b35e618cee · 2019-10-17T19:41:32.000+02:00
* Allow datasets without qualities to be downloaded.

* Remove future tense to bring comply with the character limit

* move downloading qualities back into main try/except

* Write warning message to log if no qualities could be found when getting a dataset.
diff --git a/examples/20_basic/simple_suites_tutorial.py b/examples/20_basic/simple_suites_tutorial.py
@@ -50,7 +50,7 @@
 print(tasks)
 
 ####################################################################################################
-# and iterated over for benchmarking. For speed reasons we'll only iterate over the first three tasks:
+# and iterated over for benchmarking. For speed reasons we only iterate over the first three tasks:
 
 for task_id in tasks[:3]:
     task = openml.tasks.get_task(task_id)
diff --git a/openml/datasets/functions.py b/openml/datasets/functions.py
@@ -1,4 +1,5 @@
 import io
+import logging
 import os
 import re
 from typing import List, Dict, Union, Optional
@@ -28,6 +29,7 @@
 
 
 DATASETS_CACHE_DIR_NAME = 'datasets'
+logger = logging.getLogger(__name__)
 
 ############################################################################
 # Local getters/accessors to the cache directory
@@ -498,10 +500,17 @@ def get_dataset(
         remove_dataset_cache = True
         description = _get_dataset_description(did_cache_dir, dataset_id)
         features = _get_dataset_features(did_cache_dir, dataset_id)
-        qualities = _get_dataset_qualities(did_cache_dir, dataset_id)
 
-        arff_file = _get_dataset_arff(description) if download_data else None
+        try:
+            qualities = _get_dataset_qualities(did_cache_dir, dataset_id)
+        except OpenMLServerException as e:
+            if e.code == 362 and str(e) == 'No qualities found - None':
+                logger.warning("No qualities found for dataset {}".format(dataset_id))
+                qualities = None
+            else:
+                raise
 
+        arff_file = _get_dataset_arff(description) if download_data else None
         remove_dataset_cache = False
     except OpenMLServerException as e:
         # if there was an exception,
