changed order of flow creation / run execution (first, after, serialize flow, then run task, then publish flow)

removed _ensure_flow_exists function (trivial and unused)

Author: janvanrijn

openml/flows/flow.py

@@ -340,26 +340,6 @@ def publish(self):
         self.flow_id = int(xmltodict.parse(return_value)['oml:upload_flow']['oml:id'])
         return self
 
-    def _ensure_flow_exists(self):
-        """ Checks if a flow exists for the given model and possibly creates it.
-
-        If the given flow exists on the server, the flow-id will simply
-        be returned. Otherwise it will be uploaded to the server.
-
-        Returns
-        -------
-        flow_id : int
-            Flow id on the server.
-        """
-        _, flow_id = _check_flow_exists(self.name, self.external_version)
-        # TODO add numpy and scipy version!
-
-        if int(flow_id) == -1:
-            flow = self.publish()
-            return int(flow.flow_id)
-
-        return int(flow_id)
-
 
 def _check_flow_exists(name, version):
     """Retrieves the flow id of the flow uniquely identified by name+version.

openml/runs/functions.py

@@ -4,6 +4,7 @@
 import xmltodict
 import numpy as np
 import warnings
+import openml
 from sklearn.model_selection._search import BaseSearchCV
 
 from build.lib.openml.exceptions import PyOpenMLError
@@ -44,14 +45,13 @@ def run_task(task, model):
     # adds quite a lot of functionality which is better suited in other places!
     # TODO why doesn't this accept a flow as input? - this would make this more flexible!
     flow = sklearn_to_flow(model)
-    flow_id = flow._ensure_flow_exists()
-    if flow_id < 0:
-        print("No flow")
-        return 0, 2
-    config.logger.info(flow_id)
 
-    if config.avoid_duplicate_runs:
-        # TODO: would be nice if flow._ensure_flow_exists already handled this
+    # returns flow id if the flow exists on the server, -1 otherwise
+    _, flow_id = openml.flows._check_flow_exists(flow.name, flow.external_version)
+
+    # 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 config.avoid_duplicate_runs and flow_id > 0:
         flow = get_flow(flow_id)
         setup_id = setup_exists(flow, model)
         ids = _run_exists(task.task_id, setup_id)
@@ -75,6 +75,14 @@ def run_task(task, model):
         run.error_message = str(message)
         warnings.warn("Run terminated with error: %s" %run.error_message)
 
+    if flow_id < 0:
+        flow.publish()
+    config.logger.info(flow_id)
+
+    # attach the flow to the run
+    run.flow_id = flow_id
+
+
     return run
 
 def _run_exists(task_id, setup_id):