Update inference.py

inference.py

@@ -1,5 +1,4 @@
 import torch
-from torch.utils.data import DataLoader, TensorDataset
 import json
 import os
 import csv
@@ -9,71 +8,67 @@ import numpy as np
 
 from nets.model import Model
 from Actor.actor import Actor
-from dataloader import VRP_Dataset
 
-# --- تحديد المجلد الآمن ---
+# --- إعداد المسارات ---
 safe_data_dir = "/home/user/data"
 orders_file = os.path.join(safe_data_dir, "orders.csv")
-
-# --- تحميل الإعدادات ---
 params_path = os.path.join(safe_data_dir, 'params_saved.json')
+model_path = os.path.join(safe_data_dir, "model_state_dict.pt")
+txt_results_file = os.path.join(safe_data_dir, "inference_results.txt")
+csv_results_file = os.path.join(safe_data_dir, "inference_results.csv")
+
+# --- التحقق من الملفات ---
 if not os.path.exists(params_path):
     raise FileNotFoundError(f"Settings file not found at {params_path}")
+if not os.path.exists(model_path):
+    raise FileNotFoundError(f"Model not found at {model_path}")
+if not os.path.exists(orders_file):
+    raise FileNotFoundError(f"orders.csv not found at {orders_file}")
 
+# --- تحميل الإعدادات ---
 with open(params_path, 'r') as f:
     params = json.load(f)
 
 device = params['device']
 
 # --- تحميل النموذج ---
-model_path = os.path.join(safe_data_dir, "model_state_dict.pt")
-if not os.path.exists(model_path):
-    raise FileNotFoundError(f"Model not found at {model_path}")
-
 model = Model(
-    input_size = 5,  # تعديل حسب تمثيل البيانات
+    input_size=4,  # استخدام 4 خصائص فقط (lng1, lat1, lng2, lat2)
     embedding_size=params["embedding_size"],
     decoder_input_size=params["decoder_input_size"]
 )
 model.load_state_dict(torch.load(model_path, map_location=device))
 model.eval()
 
-# --- إعداد ملف النتائج ---
-txt_results_file = os.path.join(safe_data_dir, "inference_results.txt")
-csv_results_file = os.path.join(safe_data_dir, "inference_results.csv")
-os.makedirs(safe_data_dir, exist_ok=True)
-
-# --- قراءة ملف CSV ---
-if not os.path.exists(orders_file):
-    raise FileNotFoundError(f"orders.csv not found at {orders_file}")
-
+# --- قراءة بيانات الطلبات ---
 df = pd.read_csv(orders_file)
 
-# --- تجهيز البيانات كـ Tensor ---
+# --- استخراج الإحداثيات ---
 pickup_lng = df['lng'].to_numpy()
 pickup_lat = df['lat'].to_numpy()
 delivery_lng = df['delivery_gps_lng'].to_numpy()
 delivery_lat = df['delivery_gps_lat'].to_numpy()
 
-# دمج البيانات في مصفوفة واحدة (batch_size=1, N, features)
-coords = np.stack([pickup_lng, pickup_lat, delivery_lng, delivery_lat], axis=1)  # shape (N, 4)
+coords = np.stack([pickup_lng, pickup_lat, delivery_lng, delivery_lat], axis=1)
 coords_tensor = torch.tensor(coords, dtype=torch.float32).unsqueeze(0).to(device)
 
-# --- إنشاء Batch مدخل للنموذج ---
+# --- تجهيز Batch ---
 batch = [{"coords": coords_tensor}]
 
-# --- إعداد الممثلين ---
-actor = Actor(model=model,
-              num_movers=params['num_movers'],
-              num_neighbors_encoder=params['num_neighbors_encoder'],
-              num_neighbors_action=params['num_neighbors_action'],
-              device=device,
-              normalize=False)
+# --- تهيئة الممثل والـ NN ---
+actor = Actor(
+    model=model,
+    num_movers=params['num_movers'],
+    num_neighbors_encoder=params['num_neighbors_encoder'],
+    num_neighbors_action=params['num_neighbors_action'],
+    device=device,
+    normalize=False
+)
 
 nn_actor = Actor(model=None, num_movers=1, num_neighbors_action=1, device=device)
 nn_actor.nearest_neighbors()
 
-# --- تشغيل النموذج ---
+# --- تنفيذ الاستدلال ---
 with torch.no_grad():
     actor.greedy_search()
     actor_output = actor(batch)
@@ -85,7 +80,7 @@ with torch.no_grad():
     improvement = (nn_time - total_time) / nn_time * 100
     timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 
-    # --- عرض جزء من البيانات المستخدمة ---
+    # --- عرض ملخص الإدخالات ---
     coords_preview = "\n".join([
         f"Order {i}: P=({lng1:.4f},{lat1:.4f}) → D=({lng2:.4f},{lat2:.4f})"
         for i, (lng1, lat1, lng2, lat2) in enumerate(coords[:5])
@@ -95,7 +90,7 @@ with torch.no_grad():
 
     input_summary = f"📌 Input Orders Preview:\n{coords_preview}"
 
-    # --- نتيجة كاملة للطباعة ---
+    # --- نتيجة مفصلة للطباعة ---
     result_text = (
         "\n===== INFERENCE RESULT =====\n"
         f"Time: {timestamp}\n"
@@ -105,7 +100,7 @@ with torch.no_grad():
     )
     print(result_text)
 
-    # --- واجهة Gradio ---
+    # --- ملخص للواجهة ---
     summary_text = (
         f"🕒 Time: {timestamp}\n"
         f"🚚 Actor Cost: {total_time:.4f} units\n"
@@ -113,8 +108,9 @@ with torch.no_grad():
         f"📈 Improvement: {improvement:.2f}%\n\n"
         f"{input_summary}"
     )
+    print(f"\n🔍 Summary for UI:\n{summary_text}")
 
-    # --- ��فظ إلى CSV ---
+    # --- حفظ النتائج CSV ---
     write_header = not os.path.exists(csv_results_file)
     with open(csv_results_file, 'a', newline='') as csvfile:
         writer = csv.writer(csvfile)
@@ -126,6 +122,3 @@ with torch.no_grad():
     with open(txt_results_file, 'a') as f:
         f.write(result_text)
         f.write("\n=============================\n")
-
-    # --- إخراج للواجهة
-    print(f"\n🔍 Summary for UI:\n{summary_text}")