fix unit tests (by allowing features to be "None", as before)

Author: janvanrijn

openml/datasets/dataset.py

@@ -74,16 +74,18 @@ def __init__(self, dataset_id=None, name=None, version=None, description=None,
         self.update_comment = update_comment
         self.md5_cheksum = md5_checksum
         self.data_file = data_file
-        self.features = {}
-
-        for idx, xmlfeature in enumerate(features['oml:feature']):
-            feature = OpenMLDataFeature(int(xmlfeature['oml:index']),
-                                        xmlfeature['oml:name'],
-                                        xmlfeature['oml:data_type'],
-                                        None, #todo add nominal values (currently not in database)
-                                        int(xmlfeature['oml:number_of_missing_values']))
-            assert idx == feature.index, "Data features not provided in right order"
-            self.features[feature.index] = feature
+        self.features = None
+
+        if features is not None:
+            self.features = {}
+            for idx, xmlfeature in enumerate(features['oml:feature']):
+                feature = OpenMLDataFeature(int(xmlfeature['oml:index']),
+                                            xmlfeature['oml:name'],
+                                            xmlfeature['oml:data_type'],
+                                            None, #todo add nominal values (currently not in database)
+                                            int(xmlfeature['oml:number_of_missing_values']))
+                assert idx == feature.index, "Data features not provided in right order"
+                self.features[feature.index] = feature
 
 
         if data_file is not None:

tests/test_datasets/test_dataset_functions.py

@@ -48,7 +48,7 @@ def test__get_cached_dataset(self, ):
         features = _get_cached_dataset_features(2)
         self.assertIsInstance(dataset, OpenMLDataset)
         self.assertTrue(len(dataset.features) > 0)
-        self.assertTrue(len(dataset.features) == len(features))
+        self.assertTrue(len(dataset.features) == len(features['oml:feature']))
 
     def test_get_chached_dataset_description(self):
         openml.config.set_cache_directory(self.static_cache_dir)