Add support of wait_guess_complete for clustering tasks

Author: nicolasservel

dataikuapi/dss/analysis.py

@@ -188,8 +188,9 @@ def create_prediction_ml_task(self,
         return mltask
 
     def create_clustering_ml_task(self,
-                                   ml_backend_type = "PY_MEMORY",
-                                   guess_policy = "KMEANS"):
+                                  ml_backend_type="PY_MEMORY",
+                                  guess_policy="KMEANS",
+                                  wait_guess_complete=True):
 
 
         """Creates a new clustering task in a new visual analysis lab
@@ -205,6 +206,10 @@ def create_clustering_ml_task(self,
 
         :param string ml_backend_type: ML backend to use, one of PY_MEMORY, MLLIB or H2O
         :param string guess_policy: Policy to use for setting the default parameters.  Valid values are: KMEANS and ANOMALY_DETECTION
+        :param boolean wait_guess_complete: if False, the returned ML task will be in 'guessing' state, i.e. analyzing the input dataset to determine feature handling and algorithms.
+                                            You should wait for the guessing to be completed by calling
+                                            ``wait_guess_complete`` on the returned object before doing anything
+                                            else (in particular calling ``train`` or ``get_settings``)
         """
 
         obj = {
@@ -214,7 +219,11 @@ def create_clustering_ml_task(self,
         }
 
         ref = self.client._perform_json("POST", "/projects/%s/lab/%s/models/" % (self.project_key, self.analysis_id), body=obj)
-        return DSSMLTask(self.client, self.project_key, self.analysis_id, ref["mlTaskId"])
+        mltask = DSSMLTask(self.client, self.project_key, self.analysis_id, ref["mlTaskId"])
+
+        if wait_guess_complete:
+            mltask.wait_guess_complete()
+        return mltask
 
     def list_ml_tasks(self):
         """

dataikuapi/dss/dataset.py

@@ -385,8 +385,9 @@ def create_prediction_ml_task(self, target_variable,
              guess_policy = guess_policy, prediction_type = prediction_type, wait_guess_complete = wait_guess_complete)
 
     def create_clustering_ml_task(self, input_dataset,
-                                   ml_backend_type = "PY_MEMORY",
-                                   guess_policy = "KMEANS"):
+                                  ml_backend_type="PY_MEMORY",
+                                  guess_policy="KMEANS",
+                                  wait_guess_complete=True):
         """Creates a new clustering task in a new visual analysis lab
         for a dataset.
 
@@ -400,9 +401,13 @@ def create_clustering_ml_task(self, input_dataset,
 
         :param string ml_backend_type: ML backend to use, one of PY_MEMORY, MLLIB or H2O
         :param string guess_policy: Policy to use for setting the default parameters.  Valid values are: KMEANS and ANOMALY_DETECTION
+        :param boolean wait_guess_complete: if False, the returned ML task will be in 'guessing' state, i.e. analyzing the input dataset to determine feature handling and algorithms.
+                                            You should wait for the guessing to be completed by calling
+                                            ``wait_guess_complete`` on the returned object before doing anything
+                                            else (in particular calling ``train`` or ``get_settings``)
         """
-        return self.project.create_clustering_ml_task(self.dataset_name, 
-            ml_backend_type = ml_backend_type, guess_policy = guess_policy)
+        return self.project.create_clustering_ml_task(self.dataset_name, ml_backend_type=ml_backend_type, guess_policy=guess_policy,
+                                                      wait_guess_complete=wait_guess_complete)
 
     def create_analysis(self):
         """

dataikuapi/dss/project.py

@@ -532,9 +532,9 @@ def create_prediction_ml_task(self, input_dataset, target_variable,
         return ret
 
     def create_clustering_ml_task(self, input_dataset,
-                                   ml_backend_type = "PY_MEMORY",
-                                   guess_policy = "KMEANS"):
-
+                                  ml_backend_type = "PY_MEMORY",
+                                  guess_policy = "KMEANS",
+                                  wait_guess_complete=True):
 
         """Creates a new clustering task in a new visual analysis lab
         for a dataset.
@@ -549,6 +549,10 @@ def create_clustering_ml_task(self, input_dataset,
 
         :param string ml_backend_type: ML backend to use, one of PY_MEMORY, MLLIB or H2O
         :param string guess_policy: Policy to use for setting the default parameters.  Valid values are: KMEANS and ANOMALY_DETECTION
+        :param boolean wait_guess_complete: if False, the returned ML task will be in 'guessing' state, i.e. analyzing the input dataset to determine feature handling and algorithms.
+                                            You should wait for the guessing to be completed by calling
+                                            ``wait_guess_complete`` on the returned object before doing anything
+                                            else (in particular calling ``train`` or ``get_settings``)
         """
 
         obj = {
@@ -559,7 +563,11 @@ def create_clustering_ml_task(self, input_dataset,
         }
 
         ref = self.client._perform_json("POST", "/projects/%s/models/lab/" % self.project_key, body=obj)
-        return DSSMLTask(self.client, self.project_key, ref["analysisId"], ref["mlTaskId"])
+        mltask = DSSMLTask(self.client, self.project_key, ref["analysisId"], ref["mlTaskId"])
+
+        if wait_guess_complete:
+            mltask.wait_guess_complete()
+        return mltask
 
     def list_ml_tasks(self):
         """