massive numpy optimization and more tests

backend/src/utils/cluster_manager.py

@@ -12,6 +12,10 @@ from ..utils.get_time_separation import get_distance
 from ..constants import OSM_CACHE_DIR
 
 
+# silence the overpass logger
+logging.getLogger('OSMPythonTools').setLevel(level=logging.CRITICAL)
+
+
 class Cluster(BaseModel):
     """"
     A class representing an interesting area for shopping or sightseeing.
@@ -102,7 +106,6 @@ class ClusterManager:
                 points.append(coords)
 
             self.all_points = np.array(points)
-            self.valid = True
 
             # Apply DBSCAN to find clusters. Choose different settings for different cities.
             if self.cluster_type == 'shopping' and len(self.all_points) > 200 :
@@ -114,12 +117,17 @@ class ClusterManager:
 
             labels = dbscan.fit_predict(self.all_points)
 
-            # Separate clustered points and noise points
-            self.cluster_points = self.all_points[labels != -1]
-            self.cluster_labels = labels[labels != -1]
+            # Check that there are at least 2 different clusters
+            if len(set(labels)) > 2 :
+                self.logger.debug(f"Found {len(set(labels))} different clusters.")
+                # Separate clustered points and noise points
+                self.cluster_points = self.all_points[labels != -1]
+                self.cluster_labels = labels[labels != -1]
+                self.filter_clusters()      # ValueError here sometimes. I dont know why. # Filter the clusters to keep only the largest ones.
+                self.valid = True
 
-            # filter the clusters to keep only the largest ones
-            self.filter_clusters()        
+            else : 
+                self.valid = False      
 
 
     def generate_clusters(self) -> list[Landmark]: