init commit

dbapp/mainapp/clusters.py

@@ -0,0 +1,31 @@
+from .models import ObjItem
+from sklearn.cluster import DBSCAN, HDBSCAN, KMeans
+import numpy as np
+import matplotlib.pyplot as plt
+
+def get_clusters(coords: list[tuple[float, float]]):    
+    coords = np.radians(coords)
+    lat, lon = coords[:, 0], coords[:, 1]
+    db = DBSCAN(eps=0.06, min_samples=5, algorithm='ball_tree', metric='haversine')
+    # db = HDBSCAN()
+    cluster_labels = db.fit_predict(coords)
+    plt.figure(figsize=(10, 8))
+    unique_labels = set(cluster_labels)
+    colors = plt.cm.tab10(np.linspace(0, 1, len(unique_labels)))
+
+    for label, color in zip(unique_labels, colors):
+        if label == -1:
+            color = 'k'
+            label_name = 'Шум'
+        else:
+            label_name = f'Кластер {label}'
+        
+        mask = cluster_labels == label
+        plt.scatter(lon[mask], lat[mask], c=[color], label=label_name, s=30)
+    
+    plt.xlabel('Долгота')
+    plt.ylabel('Широта')
+    plt.title('Кластеризация геоданных с DBSCAN (метрика Хаверсина)')
+    plt.legend()
+    plt.grid(True)
+    plt.show()