Merge pull request #711 from openml/fix_695

Function to list all data qualities

Author: PGijsbers

doc/api.rst

@@ -72,6 +72,7 @@ Modules
     get_dataset
     get_datasets
     list_datasets
+    list_qualities
     status_update
 
 :mod:`openml.evaluations`: Evaluation Functions

doc/progress.rst

@@ -6,6 +6,10 @@
 Changelog
 =========
 
+0.10.0
+~~~~~~
+* ADD #695: A function to retrieve all the data quality measures available.
+
 0.9.0
 ~~~~~
 * ADD #560: OpenML-Python can now handle regression tasks as well.

openml/datasets/__init__.py

@@ -6,6 +6,7 @@
     get_datasets,
     list_datasets,
     status_update,
+    list_qualities
 )
 from .dataset import OpenMLDataset
 from .data_feature import OpenMLDataFeature
@@ -20,4 +21,5 @@
     'OpenMLDataset',
     'OpenMLDataFeature',
     'status_update',
+    'list_qualities'
 ]

openml/datasets/functions.py

@@ -165,6 +165,30 @@ def _get_cache_directory(dataset: OpenMLDataset) -> str:
     return _create_cache_directory_for_id(DATASETS_CACHE_DIR_NAME, dataset.dataset_id)
 
 
+def list_qualities() -> List[str]:
+    """ Return list of data qualities available.
+
+    The function performs an API call to retrieve the entire list of
+    data qualities that are computed on the datasets uploaded.
+
+    Returns
+    -------
+    list
+    """
+    api_call = "data/qualities/list"
+    xml_string = openml._api_calls._perform_api_call(api_call, 'get')
+    qualities = xmltodict.parse(xml_string, force_list=('oml:quality'))
+    # Minimalistic check if the XML is useful
+    if 'oml:data_qualities_list' not in qualities:
+        raise ValueError('Error in return XML, does not contain '
+                         '"oml:data_qualities_list"')
+    if not isinstance(qualities['oml:data_qualities_list']['oml:quality'], list):
+        raise TypeError('Error in return XML, does not contain '
+                        '"oml:quality" as a list')
+    qualities = qualities['oml:data_qualities_list']['oml:quality']
+    return qualities
+
+
 def list_datasets(
     offset: Optional[int] = None,
     size: Optional[int] = None,

tests/test_datasets/test_dataset_functions.py

@@ -1190,3 +1190,8 @@ def test_create_dataset_attributes_auto_without_df(self):
                 original_data_url=original_data_url,
                 paper_url=paper_url
             )
+
+    def test_list_qualities(self):
+        qualities = openml.datasets.list_qualities()
+        self.assertEqual(isinstance(qualities, list), True)
+        self.assertEqual(all([isinstance(q, str) for q in qualities]), True)