fix unit tests for setup

Author: janvanrijn

openml/runs/run.py

@@ -185,13 +185,19 @@ def get_flow_dict(_flow):
                 flow_map.update(get_flow_dict(_flow.components[subflow]))
             return flow_map
 
-        def extract_parameters(_flow, _param_dict):
+        def extract_parameters(_flow, _param_dict, _main_call=False, main_id=None):
+            # _flow is openml flow object, _param dict maps from flow name to flow id
+            # for the main call, the param dict can be overridden (useful for unit tests / sentinels)
+            # this way, for flows without subflows we do not have to rely on _param_dict
             _params = []
             for _param_name in _flow.parameters:
                 _current = OrderedDict()
                 _current['oml:name'] = _param_name
                 _current['oml:value'] = _flow.parameters[_param_name]
-                _current['oml:component'] = _param_dict[_flow.name]
+                if _main_call:
+                    _current['oml:component'] = main_id
+                else:
+                    _current['oml:component'] = _param_dict[_flow.name]
                 _params.append(_current)
             for _identifier in _flow.components:
                 _params.extend(extract_parameters(_flow.components[_identifier], _param_dict))
@@ -200,7 +206,7 @@ def extract_parameters(_flow, _param_dict):
         flow_dict = get_flow_dict(server_flow)
         local_flow = openml.flows.sklearn_to_flow(model)
 
-        parameters = extract_parameters(local_flow, flow_dict)
+        parameters = extract_parameters(local_flow, flow_dict, True, server_flow.flow_id)
         return parameters
 
 ################################################################################

tests/test_setups/test_setup_functions.py

@@ -32,6 +32,7 @@ class TestRun(TestBase):
     def test_nonexisting_setup_exists(self):
         # first publish a non-existing flow
         sentinel = get_sentinel()
+        # because of the sentinel, we can not use flows that contain subflows
         dectree = DecisionTreeClassifier()
         flow = openml.flows.sklearn_to_flow(dectree)
         flow.name = 'TEST%s%s' % (sentinel, flow.name)
@@ -45,34 +46,32 @@ def test_nonexisting_setup_exists(self):
 
     def test_existing_setup_exists(self):
         # first publish a nonexiting flow
-        bagging = BaggingClassifier(DecisionTreeClassifier(max_depth=5,
-                                                           min_samples_split=3),
-                                    n_estimators=3,
-                                    max_samples=0.5)
-        flow = openml.flows.sklearn_to_flow(bagging)
+
+        # because of the sentinel, we can not use flows that contain subflows
+        classif = DecisionTreeClassifier(max_depth=5,
+                                         min_samples_split=3)
+        flow = openml.flows.sklearn_to_flow(classif)
         flow.name = 'TEST%s%s' % (get_sentinel(), flow.name)
-        flow.components['base_estimator'].name = 'TEST%s%s' % (
-            get_sentinel(), flow.components['base_estimator'].name)
 
         flow = flow.publish()
         flow = openml.flows.get_flow(flow.flow_id)
 
         # although the flow exists, we can be sure there are no
         # setups (yet) as it hasn't been ran
-        setup_id = openml.setups.setup_exists(flow, bagging)
+        setup_id = openml.setups.setup_exists(flow, classif)
         self.assertFalse(setup_id)
 
         # now run the flow on an easy task:
         task = openml.tasks.get_task(115) #diabetes
-        run = openml.runs.run_task(task, bagging)
+        run = openml.runs.run_task(task, classif)
         # spoof flow id, otherwise the sentinel is ignored
         run.flow_id = flow.flow_id
         run = run.publish()
         # download the run, as it contains the right setup id
         run = openml.runs.get_run(run.run_id)
 
         # execute the function we are interested in
-        setup_id = openml.setups.setup_exists(flow, bagging)
+        setup_id = openml.setups.setup_exists(flow, classif)
         self.assertEquals(setup_id, run.setup_id)
 
     def test_setup_get(self):