Add username

doc/progress.rst

@@ -25,6 +25,7 @@ Changelog
 * ADD #412: The scikit-learn extension populates the short name field for flows.
 * MAINT #726: Update examples to remove deprecation warnings from scikit-learn
 * MAINT #752: Update OpenML-Python to be compatible with sklearn 0.21
+* ADD #790: Add user ID and name to list_evaluations
 
 
 0.9.0

openml/evaluations/evaluation.py

@@ -26,6 +26,10 @@ class OpenMLEvaluation(object):
         The evaluation metric of this item (e.g., accuracy).
     upload_time : str
         The time of evaluation.
+    uploader: int
+        Uploader ID (user ID)
+    upload_name : str
+        Name of the uploader of this evaluation
     value : float
         The value (score) of this evaluation.
     values : List[float]
@@ -35,7 +39,8 @@ class OpenMLEvaluation(object):
         (e.g., in case of precision, auroc, recall)
     """
     def __init__(self, run_id, task_id, setup_id, flow_id, flow_name,
-                 data_id, data_name, function, upload_time, value, values,
+                 data_id, data_name, function, upload_time, uploader: int,
+                 uploader_name: str, value, values,
                  array_data=None):
         self.run_id = run_id
         self.task_id = task_id
@@ -46,6 +51,8 @@ def __init__(self, run_id, task_id, setup_id, flow_id, flow_name,
         self.data_name = data_name
         self.function = function
         self.upload_time = upload_time
+        self.uploader = uploader
+        self.uploader_name = uploader_name
         self.value = value
         self.values = values
         self.array_data = array_data

openml/evaluations/functions.py

@@ -172,6 +172,12 @@ def __list_evaluations(api_call, output_format='object'):
         type(evals_dict['oml:evaluations'])
 
     evals = collections.OrderedDict()
+    uploader_ids = list(set([eval_['oml:uploader'] for eval_ in
+                             evals_dict['oml:evaluations']['oml:evaluation']]))
+    api_users = "user/list/user_id/" + ','.join(uploader_ids)
+    xml_string_user = openml._api_calls._perform_api_call(api_users, 'get')
+    users = xmltodict.parse(xml_string_user, force_list=('oml:user',))
+    user_dict = {user['oml:id']: user['oml:username'] for user in users['oml:users']['oml:user']}
     for eval_ in evals_dict['oml:evaluations']['oml:evaluation']:
         run_id = int(eval_['oml:run_id'])
         value = None
@@ -194,6 +200,8 @@ def __list_evaluations(api_call, output_format='object'):
                                              eval_['oml:data_name'],
                                              eval_['oml:function'],
                                              eval_['oml:upload_time'],
+                                             int(eval_['oml:uploader']),
+                                             user_dict[eval_['oml:uploader']],
                                              value, values, array_data)
         else:
             # for output_format in ['dict', 'dataframe']
@@ -206,6 +214,8 @@ def __list_evaluations(api_call, output_format='object'):
                              'data_name': eval_['oml:data_name'],
                              'function': eval_['oml:function'],
                              'upload_time': eval_['oml:upload_time'],
+                             'uploader': int(eval_['oml:uploader']),
+                             'uploader_name': user_dict[eval_['oml:uploader']],
                              'value': value,
                              'values': values,
                              'array_data': array_data}

tests/test_evaluations/test_evaluation_functions.py

@@ -54,7 +54,9 @@ def test_evaluation_list_filter_uploader_ID_16(self):
 
         uploader_id = 16
         evaluations = openml.evaluations.list_evaluations("predictive_accuracy",
-                                                          uploader=[uploader_id])
+                                                          uploader=[uploader_id],
+                                                          output_format='dataframe')
+        self.assertEqual(evaluations['uploader'].unique(), [uploader_id])
 
         self.assertGreater(len(evaluations), 50)