[RoleStage] Improved clustering performance

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

@@ -59,9 +59,14 @@ class Clusterer:
 
     def group_by_clusters(self, dataset:List[Dict], labels:List[Any]) -> Dict[Any, List[Dict]]:
         clusters = {}
-        # TODO optimize by iterating through dataset only once
-        for label in labels:
-            clusters[label] = [ds for ds in dataset if ds['cluster_label'] == label]
+
+        for ds in dataset:
+            label = ds['cluster_label']
+
+            if label not in clusters:
+                clusters[label] = []
+
+            clusters[label].append(ds)
         
         return clusters