preparation for mongodb storage

src/data-hub/community-detection-microservice/app/processing/clusterer.py

@@ -43,6 +43,7 @@ class Clusterer:
             
         return fig
     
+    # TODO refactor for other input
     def create_labels(self, locations:List) -> List:
         if locations is None or len(locations) == 0:
             return locations # trash in trash out
@@ -58,6 +59,7 @@ class Clusterer:
     def extract_location_data(self, locations: List[dict]) -> np.ndarray:
         return np.asarray([(float(l['latitude']), float(l['longitude'])) for l in locations])
 
+    # TODO refactor for other input
     def label_locations(self, locations:List[Dict], labels:List) -> List:
         if locations is None or labels is None:
             return
@@ -84,24 +86,19 @@ class Clusterer:
         return clusters
 
     def cluster_times(self, times:List[Dict]) -> Dict[int, List[Dict]]:
+        times1 = np.asarray([((t['timestamp']), 0) for t in times])
     
-        # times.sort(key=lambda x: x['timestamp'])
-
-        times1 = np.asarray([(float(t['timestamp']), float(0)) for t in times])
-        # print(times)
-    
+        # TODO refactor for other input
         dbsc = DBSCAN(eps = self.epsilon, min_samples = self.min_points)
         dbsc = dbsc.fit(times1)
-        labels = dbsc.labels_
-        print(labels)
+        labels = dbsc.labels_.tolist()
 
         self.label_locations(times, labels)
-        times = [t for t in times if t['cluster_label'] != -1]
-        print(times)
 
-        info = [l for l in labels if l != -1]
-        print(info)
+        clusters = {}
+        for label in labels:
+            clusters[label] = [l for l in times if l['cluster_label'] == label]
         
-        times1 = np.asarray([(float(t['timestamp']), float(0)) for t in times])
-        fig = self._draw_locations(locations=times1, partition_info=info)
-        fig.savefig('img.png')
+        # fig = self._draw_locations(locations=times1, partition_info=labels)
+        # fig.savefig('img.png')
+        return clusters
\ No newline at end of file

src/data-hub/community-detection-microservice/app/run_clustering.py

@@ -10,7 +10,7 @@ from db.repository import Repository
 from processing.clusterer import Clusterer
 
 
-DEBUG = False
+DEBUG = True
 
 repo = Repository()
 
@@ -30,11 +30,16 @@ def run_location_clustering():
 
 
 def run_time_clustering():
+    user_clusterer = Clusterer(epsilon=10**5.8)
+
     all_location_traces = repo.get_agi_locations()
 
-    user_clusterer = Clusterer(epsilon=10**5.8)
+    cluster_result = user_clusterer.cluster_times([l.to_serializable_dict() for l in all_location_traces])
 
-    user_clusterer.cluster_times([l.to_serializable_dict() for l in all_location_traces])
+    clusters = [UserCluster(key, value)
+                for key, value in cluster_result.items()]
+    
+    store_user_clusters(clusters)
 
 
 def store_user_clusters(user_clusters: List[UserCluster]):