working clustering on individual locations

src/data-hub/community-detection-microservice/app/configs/swagger.yml

@@ -14,7 +14,7 @@ basePath: "/api"
 paths:
   /debug:
     post:
-      operationId: "debug.echo"
+      operationId: "rest.debug.echo"
       tags:
         - "Echo"
       summary: "Echo function for debugging purposes"
@@ -70,7 +70,7 @@ paths:
             200:
                 description: "Successful operation"
                 schema:
-                  $ref: "#/definitions/Cluster"
+                  $ref: "#/definitions/ClusterValue"
 
   /cluster/cluster.png:
     get:
@@ -97,7 +97,7 @@ paths:
             200:
                 description: "Successful operation"
                 schema:
-                  $ref: "#/definitions/Cluster"
+                  $ref: "#/definitions/ClusterValue"
 
   /agi/cluster/cluster.png:
     get:
@@ -127,10 +127,20 @@ definitions:
         type: "number"
       timestamp:
         type: "number"
-  Cluster:
+  ClusterValue:
     type: "object"
     properties:
       id:
         type: string
         format: uuid
+      cluster_label:
+        type: number
+      latitude:
+        type: number
+      longitude:
+        type: number
+      timestamp:
+        type: number
+      username:
+        type: string
       
\ No newline at end of file

src/data-hub/community-detection-microservice/app/db/agi/agi_repository.py

@@ -12,15 +12,12 @@ class AgiRepository:
         travels = [t for t in travels if t['status'] >= 2]
         for travel in travels:
 
-            locations.append(self.location(travel["id"], travel['startPlace.latitude'], travel['startPlace.longitude'], 0, ''))
-            continue # todo work on locations
-
-            # todo number of complete travels with startlocation and user data
             num_complete_travels = min(len(travel['startedBy']), len(travel['users']))
             for i in range(num_complete_travels):
 
                 cur_location = travel['startedBy'][i]
                 cur_user = travel['users'][i]
+                
                 locations.append(
                     self.location(f'{travel["id"]}-{cur_location["moment"]}',
                             cur_location['coordinate']['latitude'],

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

@@ -17,7 +17,7 @@ class Clusterer:
             labels = self.create_labels(locations)
 
         return self._draw_locations(
-            locations = np.asarray([(l['latitude'], l['longitude']) for l in locations]),
+            locations = self.extract_location_data(locations),
             partition_info = labels
         )
 
@@ -47,7 +47,7 @@ class Clusterer:
         if locations is None or len(locations) == 0:
             return locations # trash in trash out
 
-        locations = np.asarray([(l['latitude'], l['longitude']) for l in locations])
+        locations = self.extract_location_data(locations)
     
         dbsc = DBSCAN(eps = self.epsilon, min_samples = self.min_points)
         dbsc = dbsc.fit(locations)
@@ -78,3 +78,6 @@ class Clusterer:
             clusters[label] = [l for l in locations if l['cluster_label'] == label]
         
         return clusters
+
+    def extract_location_data(self, locations: List[dict]) -> np.ndarray:
+        return np.asarray([(float(l['latitude']), float(l['longitude'])) for l in locations])
\ No newline at end of file