[RoleStage] Small changes in clustering

src/data-hub/role-stage-discovery-microservice/app/db/repository.py

@@ -79,6 +79,9 @@ class Repository(MongoRepositoryBase):
         entries = super().get_entries(self._clusters_collection, selection={'layer_name': layer_name}, projection={'_id': 0})
         return [Cluster(cluster_dict=e, from_db=True) for e in entries]
     
+    def delete_all_clusters(self):
+        super().drop_collection(self._clusters_collection)
+
 #endregion
 
 #region TimeSlice

src/data-hub/role-stage-discovery-microservice/app/processing/clustering/clusterer.py

@@ -35,7 +35,7 @@ class Clusterer:
         '''Extracts the feature values from the dataset into a np array with same order as original dataset.'''
         extracted_features = []
         for data in dataset:
-            entry = [float(data[feature]) for feature in features]
+            entry = [float(data[feature] if data[feature] is not "" else 0) for feature in features]
             extracted_features.append(entry)
 
         return np.asarray(extracted_features)

src/data-hub/role-stage-discovery-microservice/app/run_clustering.py

@@ -25,8 +25,11 @@ def run_generic_clustering():
             print("skipping")
             continue
 
+        try:
             clusters = run_clustering_for_layer(layer)
             store_generic_clusters(clusters)
+        except Exception as e:
+            print(str(e))
 
 
 def run_clustering_for_layer(layer: Layer) -> List[Cluster]:
@@ -46,4 +49,5 @@ def store_generic_clusters(clusters: List[Cluster]):
 
 
 if __name__ == "__main__":
+    repo.delete_all_clusters()
     run_generic_clustering()