refactor site info loading and prediction batching for improved clarity and performance

app.py

@@ -58,12 +58,14 @@ try:
 except FileNotFoundError:
     logger.error(f"{target_file} 找不到")
 
-# 載入測站資訊
+# 載入測站資訊（輸入測站，1000+ 個）
 site_info_file = "station/site_info.csv"
 try:
     logger.info(f"載入 {site_info_file}...")
     site_info = pd.read_csv(site_info_file)
-    logger.info(f"{site_info_file} 載入完成")
+    # 只保留唯一的測站（去除重複的分量）
+    site_info = site_info.drop_duplicates(subset=['Station']).reset_index(drop=True)
+    logger.info(f"{site_info_file} 載入完成，共 {len(site_info)} 個測站")
 except FileNotFoundError:
     logger.warning(f"{site_info_file} 找不到")
 
@@ -415,7 +417,7 @@ def calculate_distance(lat1, lon1, lat2, lon2):
 
 
 def select_nearest_stations(st, epicenter_lat, epicenter_lon, n_stations=25):
-    """選擇距離震央最近的 n 個測站"""
+    """從 site_info（1000+ 個輸入測站）中選擇距離震央最近的 n 個測站"""
     station_distances = []
 
     # 計算每個測站到震央的距離
@@ -448,7 +450,7 @@ def select_nearest_stations(st, epicenter_lat, epicenter_lon, n_stations=25):
     station_distances.sort(key=lambda x: x["distance"])
     selected_stations = station_distances[:n_stations]
 
-    logger.info(f"選擇了 {len(selected_stations)} 個最近的測站")
+    logger.info(f"從 {len(station_distances)} 個輸入測站中選擇了最近的 {len(selected_stations)} 個")
     return selected_stations
 
 
@@ -794,30 +796,60 @@ def predict_intensity(event_name, start_time, end_time, epicenter_lon, epicenter
             waveform_padded[i] = waveforms[i]
             station_info_padded[i] = station_info_list[i]
 
-        # 5. 準備目標測站資訊
-        target_list = []
-        target_names = []
-        for target in target_dict[:25]:
-            target_list.append([
-                target["latitude"],
-                target["longitude"],
-                target["elevation"],
-                get_vs30(target["latitude"], target["longitude"], vs30_input)
-            ])
-            target_names.append(target["station"])
-
-        # 6. 組合成 tensor
-        tensor_data = {
-            "waveform": torch.tensor(waveform_padded).unsqueeze(0).double(),
-            "station": torch.tensor(station_info_padded).unsqueeze(0).double(),
-            "target": torch.tensor(target_list).unsqueeze(0).double(),
-        }
-
-        # 7. 執行預測
-        logger.info("執行模型預測...")
-        with torch.no_grad():
-            weight, sigma, mu = model(tensor_data)
-            pga_list = torch.sum(weight * mu, dim=2).cpu().detach().numpy().flatten().tolist()
+        # 5. 準備所有目標測站資訊（分批處理）
+        all_pga_list = []
+        all_target_names = []
+
+        # 計算需要分幾批（每批 25 個測站）
+        batch_size = 25
+        total_targets = len(target_dict)
+        num_batches = (total_targets + batch_size - 1) // batch_size
+
+        logger.info(f"開始分批預測 {total_targets} 個目標測站（共 {num_batches} 批）...")
+
+        for batch_idx in range(num_batches):
+            start_idx = batch_idx * batch_size
+            end_idx = min((batch_idx + 1) * batch_size, total_targets)
+            batch_targets = target_dict[start_idx:end_idx]
+
+            logger.info(f"預測第 {batch_idx + 1}/{num_batches} 批（測站 {start_idx + 1}-{end_idx}）...")
+
+            # 準備這批目標測站資訊
+            target_list = []
+            target_names = []
+            for target in batch_targets:
+                target_list.append([
+                    target["latitude"],
+                    target["longitude"],
+                    target["elevation"],
+                    get_vs30(target["latitude"], target["longitude"], vs30_input)
+                ])
+                target_names.append(target["station"])
+
+            # Padding 到 25 個（如果不足 25 個）
+            target_padded = np.zeros((batch_size, 4))
+            for i in range(len(target_list)):
+                target_padded[i] = target_list[i]
+
+            # 6. 組合成 tensor
+            tensor_data = {
+                "waveform": torch.tensor(waveform_padded).unsqueeze(0).double(),
+                "station": torch.tensor(station_info_padded).unsqueeze(0).double(),
+                "target": torch.tensor(target_padded).unsqueeze(0).double(),
+            }
+
+            # 7. 執行預測
+            with torch.no_grad():
+                weight, sigma, mu = model(tensor_data)
+                batch_pga = torch.sum(weight * mu, dim=2).cpu().detach().numpy().flatten().tolist()
+
+            # 只取實際有資料的部分
+            all_pga_list.extend(batch_pga[:len(target_names)])
+            all_target_names.extend(target_names)
+
+        logger.info(f"完成所有 {len(all_target_names)} 個測站的預測！")
+        pga_list = all_pga_list
+        target_names = all_target_names
 
         # 8. 繪製互動式地圖
         intensity_map = create_intensity_map(pga_list, target_names, epicenter_lat, epicenter_lon)