Spaces:
Sleeping
Sleeping
data clean
Browse files
app.py
CHANGED
|
@@ -62,7 +62,6 @@ try:
|
|
| 62 |
static_file = 'static_train_data.csv'
|
| 63 |
|
| 64 |
# 🛡️【自動隔離防護盾】避免 5 萬筆資料被 logger_service 覆蓋
|
| 65 |
-
# 如果 baseline_logs.csv 存在且超過 500KB (大機率是 5 萬筆資料檔)
|
| 66 |
if os.path.exists('baseline_logs.csv') and os.path.getsize('baseline_logs.csv') > 500000:
|
| 67 |
if not os.path.exists(static_file):
|
| 68 |
shutil.copy('baseline_logs.csv', static_file)
|
|
@@ -115,13 +114,21 @@ try:
|
|
| 115 |
baseline_df['day'] = baseline_df['timestamp'].dt.day
|
| 116 |
baseline_df['hour'] = baseline_df['timestamp'].dt.hour
|
| 117 |
|
| 118 |
-
# 🧠 核心防護:動態擴增 IP 字典
|
| 119 |
clean_ips = baseline_df['clean_ip'].values
|
| 120 |
known_ips = set(le_ip.classes_)
|
| 121 |
unknown_ips = set(clean_ips) - known_ips
|
| 122 |
if unknown_ips:
|
| 123 |
print(f"📖 AI 學習到動態資料庫中的新 IP: {unknown_ips},已自動擴增字典...")
|
| 124 |
le_ip.classes_ = np.append(le_ip.classes_, list(unknown_ips))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
|
| 126 |
# 建立最終的歷史特徵矩陣
|
| 127 |
baseline_X = np.column_stack((
|
|
@@ -129,7 +136,7 @@ try:
|
|
| 129 |
baseline_df['day'].values,
|
| 130 |
baseline_df['hour'].values,
|
| 131 |
le_ip.transform(clean_ips),
|
| 132 |
-
le_action.transform(
|
| 133 |
))
|
| 134 |
|
| 135 |
AI_READY = True
|
|
@@ -404,9 +411,11 @@ def record_log(ip, cookie, account, role, action, status, time_mode, custom_time
|
|
| 404 |
current_time = pd.to_datetime(str(log_time))
|
| 405 |
clean_ip = str(ip).split(" ")[0]
|
| 406 |
|
| 407 |
-
#
|
| 408 |
if clean_ip not in le_ip.classes_:
|
| 409 |
le_ip.classes_ = np.append(le_ip.classes_, clean_ip)
|
|
|
|
|
|
|
| 410 |
|
| 411 |
new_row = np.array([[
|
| 412 |
float(current_time.month), float(current_time.day), float(current_time.hour),
|
|
|
|
| 62 |
static_file = 'static_train_data.csv'
|
| 63 |
|
| 64 |
# 🛡️【自動隔離防護盾】避免 5 萬筆資料被 logger_service 覆蓋
|
|
|
|
| 65 |
if os.path.exists('baseline_logs.csv') and os.path.getsize('baseline_logs.csv') > 500000:
|
| 66 |
if not os.path.exists(static_file):
|
| 67 |
shutil.copy('baseline_logs.csv', static_file)
|
|
|
|
| 114 |
baseline_df['day'] = baseline_df['timestamp'].dt.day
|
| 115 |
baseline_df['hour'] = baseline_df['timestamp'].dt.hour
|
| 116 |
|
| 117 |
+
# 🧠 核心防護 1:動態擴增 IP 字典
|
| 118 |
clean_ips = baseline_df['clean_ip'].values
|
| 119 |
known_ips = set(le_ip.classes_)
|
| 120 |
unknown_ips = set(clean_ips) - known_ips
|
| 121 |
if unknown_ips:
|
| 122 |
print(f"📖 AI 學習到動態資料庫中的新 IP: {unknown_ips},已自動擴增字典...")
|
| 123 |
le_ip.classes_ = np.append(le_ip.classes_, list(unknown_ips))
|
| 124 |
+
|
| 125 |
+
# 🧠 核心防護 2:動態擴增 Action 字典 (解決 login_attempt 等新動作導致崩潰的問題)
|
| 126 |
+
actions = baseline_df['action'].astype(str).values
|
| 127 |
+
known_actions = set(le_action.classes_)
|
| 128 |
+
unknown_actions = set(actions) - known_actions
|
| 129 |
+
if unknown_actions:
|
| 130 |
+
print(f"📖 AI 學習到動態資料庫中的新動作: {unknown_actions},已自動擴增字典...")
|
| 131 |
+
le_action.classes_ = np.append(le_action.classes_, list(unknown_actions))
|
| 132 |
|
| 133 |
# 建立最終的歷史特徵矩陣
|
| 134 |
baseline_X = np.column_stack((
|
|
|
|
| 136 |
baseline_df['day'].values,
|
| 137 |
baseline_df['hour'].values,
|
| 138 |
le_ip.transform(clean_ips),
|
| 139 |
+
le_action.transform(actions)
|
| 140 |
))
|
| 141 |
|
| 142 |
AI_READY = True
|
|
|
|
| 411 |
current_time = pd.to_datetime(str(log_time))
|
| 412 |
clean_ip = str(ip).split(" ")[0]
|
| 413 |
|
| 414 |
+
# 運行時動態擴增未知 IP 與 Action
|
| 415 |
if clean_ip not in le_ip.classes_:
|
| 416 |
le_ip.classes_ = np.append(le_ip.classes_, clean_ip)
|
| 417 |
+
if action not in le_action.classes_:
|
| 418 |
+
le_action.classes_ = np.append(le_action.classes_, action)
|
| 419 |
|
| 420 |
new_row = np.array([[
|
| 421 |
float(current_time.month), float(current_time.day), float(current_time.hour),
|