fix unit tests

Author: mfeurer

openml/flows/functions.py

@@ -192,7 +192,9 @@ def assert_flows_equal(flow1, flow2, ignore_parameters_on_older_children=None,
                 if not name in attr2:
                     raise ValueError('Component %s only available in '
                                      'argument2, but not in argument1.' % name)
-                assert_flows_equal(attr1[name], attr2[name], ignore_parameters_on_older_children)
+                assert_flows_equal(attr1[name], attr2[name],
+                                   ignore_parameters_on_older_children,
+                                   ignore_parameters)
 
         else:
             if key == 'parameters':

openml/runs/functions.py

@@ -68,11 +68,9 @@ def run_flow_on_task(task, flow, avoid_duplicate_runs=True, flow_tags=None,
 
     # skips the run if it already exists and the user opts for this in the config file.
     # also, if the flow is not present on the server, the check is not needed.
-    if avoid_duplicate_runs:
-        if flow.flow_id is None:
-            raise ValueError('Cannot check if a run exists if the '
-                             'corresponding flow has not been published yet!')
-        flow_from_server = get_flow(flow.flow_id)
+    flow_id = flow_exists(flow.name, flow.external_version)
+    if avoid_duplicate_runs and flow_id:
+        flow_from_server = get_flow(flow_id)
         setup_id = setup_exists(flow_from_server)
         ids = _run_exists(task.task_id, setup_id)
         if ids:

tests/test_flows/test_flow.py

@@ -147,6 +147,9 @@ def test_publish_flow_with_similar_components(self):
         flow1, sentinel = self._add_sentinel_to_flow_name(flow1, None)
         flow1.publish()
 
+        # In order to assign different upload times to the flows!
+        time.sleep(1)
+
         clf2 = sklearn.ensemble.VotingClassifier(
             [('dt', sklearn.tree.DecisionTreeClassifier(max_depth=2))])
         flow2 = openml.flows.sklearn_to_flow(clf2)

tests/test_runs/test_run_functions.py

@@ -180,18 +180,6 @@ def _check_detailed_evaluations(self, detailed_evaluations, num_repeats, num_fol
                         self.assertGreater(evaluation, 0) # should take at least one millisecond (?)
                         self.assertLess(evaluation, max_time_allowed)
 
-    def test_avoid_duplicate_runs_with_unpublished_flow(self):
-        task_id = 115
-
-        clf = LogisticRegression()
-        flow = sklearn_to_flow(clf)
-        flow, _ = self._add_sentinel_to_flow_name(flow, None)
-        task = openml.tasks.get_task(task_id)
-
-        self.assertRaisesRegexp(ValueError, 'Cannot check if a run exists if the corresponding flow has not been published yet!',
-                                openml.runs.run_flow_on_task, task=task,
-                                flow=flow, avoid_duplicate_runs=True)
-
     def test_run_regression_on_classif_task(self):
         task_id = 115
 

tests/test_setups/__init__.py

@@ -0,0 +1,3 @@
+# Dummy to allow mock classes in the test files to have a version number for
+# their parent module
+__version__ = '0.1'