logger dataset setup

app.py

@@ -4,6 +4,7 @@ import pandas as pd
 import joblib
 from sklearn.cluster import HDBSCAN
 import numpy as np
+import logger_service
 
 # --- 1. 載入模型與歷史資料 (實現動態 Rule 的關鍵) ---
 try:
@@ -35,7 +36,7 @@ USER_DB = {
     "sysadmin": ["1234", "系統管理員", "管理員"]
 }
 
-log_history = []
+log_history = baseline_df.sort_values(by='timestamp', ascending=False).head(20).to_dict('records')
 
 # --- 3. 核心邏輯與真實 HDBSCAN 異常偵測 ---
 def check_anomaly(ip, action, log_time):
@@ -74,6 +75,7 @@ def check_anomaly(ip, action, log_time):
         return "⚠️異常_未知特徵"
 
 def record_log(ip, cookie, account, role, action, status, time_mode, custom_time):
+    global baseline_X, log_history
     # 決定紀錄的時間
     if time_mode == "自訂時間 (模擬過去/未來)" and custom_time.strip() != "":
         log_time = custom_time
@@ -96,6 +98,22 @@ def record_log(ip, cookie, account, role, action, status, time_mode, custom_time
         "action": action,
         "status": status
     }
+
+    try:
+        # 將新行為轉為特徵數值
+        new_hour = pd.to_datetime(log_time).hour
+        new_ip_code = le_ip.transform([ip])[0]
+        new_action_code = le_action.transform([action])[0]
+        new_feature = np.array([[new_hour, new_ip_code, new_action_code]])
+        
+        # 🌟 把新特徵壓入全域矩陣中
+        baseline_X = np.vstack((baseline_X, new_feature))
+    except Exception as e:
+        print(f"⚠️ AI 矩陣更新跳過 (可能是未知特徵): {e}")
+
+    # 呼叫外部 Service 進行存檔與上傳
+    logger_service.push_new_log(new_log)
+
     log_history.insert(0, new_log)
     return pd.DataFrame(log_history)
 

logger_service.py

@@ -0,0 +1,59 @@
+import os
+import pandas as pd
+from huggingface_hub import hf_hub_download, upload_file, login
+
+# --- 配置區 ---
+DATASET_REPO_ID = "My-Project-Team/Digital-Bodyguard-Dataset" 
+CSV_FILENAME = "baseline_logs.csv"
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+if HF_TOKEN:
+    login(token=HF_TOKEN)
+
+def sync_from_hf():
+    """從雲端下載最新的 CSV 並回傳 DataFrame"""
+    try:
+        path = hf_hub_download(
+            repo_id=DATASET_REPO_ID,
+            filename=CSV_FILENAME,
+            repo_type="dataset",
+            token=HF_TOKEN
+        )
+        return pd.read_csv(path)
+    except Exception as e:
+        print(f"⚠️ 無法下載資料，建立新表: {e}")
+        return pd.DataFrame(columns=["timestamp", "ip_address", "cookie_id", "account", "role", "action", "status"])
+
+def upload_to_hf():
+    """將本地的 CSV 檔案同步回雲端"""
+    try:
+        upload_file(
+            path_or_fileobj=CSV_FILENAME,
+            path_in_repo=CSV_FILENAME,
+            repo_id=DATASET_REPO_ID,
+            repo_type="dataset",
+            token=HF_TOKEN,
+            commit_message="System auto-log update"
+        )
+        return True
+    except Exception as e:
+        print(f"❌ 雲端同步失敗: {e}")
+        return False
+
+def push_new_log(new_log_dict):
+    """
+    接收一個字典格式的紀錄，執行：
+    1. 抓取最新雲端資料 2. 合併新紀錄 3. 儲存本地 4. 上傳雲端
+    """
+    # 1. 取得最新資料
+    current_df = sync_from_hf()
+    
+    # 2. 加入新紀錄
+    new_entry = pd.DataFrame([new_log_dict])
+    updated_df = pd.concat([current_df, new_entry], ignore_index=True)
+    
+    # 3. 儲存至本地 (暫存)
+    updated_df.to_csv(CSV_FILENAME, index=False)
+    
+    # 4. 同步回 Dataset
+    return upload_to_hf()