Update model_predictor.py

model_predictor.py

@@ -20,17 +20,22 @@ class XGBoostModel:
         """
         self.model = None
         self.scaler = None
+        # ***FIXED: Updated feature columns to match the training script***
         self.feature_columns = [
-            'close',             # 前一日收盤價  
-            'return_t-1',        # 前一日報酬率
-            'return_t-5',        # 過去 5 日累積報酬率
-            'MA5_close',         # 5 日移動平均價
-            'volatility_5d',     # 5 日報酬標準差
-            'volume_ratio_5d',   # 今日成交量 ÷ 5 日均量
-            'MACD_diff',         # MACD - signal
-            'dji_return_t-1',    # 前一日道瓊指數報酬率
-            'sox_return_t-1',    # 前一日費半指數報酬率
-            'NEWS'               # 新聞情緒分數
+            'close',
+            'return-t-1',
+            'return-t-5',
+            'MA5_close',
+            'volatility_5d',
+            'volume_ratio_5d',
+            'MACD_diff',
+            'dji_return-t-1',
+            'sox_return-t-1',
+            'NEWS',
+            'MACDvol',
+            'RSI_14',
+            'ADX',
+            'volume_weighted_return'
         ]
         
         # 【新增】輸出目標對應表
@@ -122,17 +127,17 @@ class XGBoostModel:
         df['close'] = df['Close']
         df['volume'] = df['Volume']
         
-        # 1. return_t-1 — 前一日報酬率 (***FIXED: Changed hyphen to underscore***)
-        df['return_t_1'] = df['close'].pct_change()
+        # 1. return-t-1 — 前一日報酬率 (***FIXED: Corrected to use hyphen***)
+        df['return-t-1'] = df['close'].pct_change()
         
-        # 2. return_t-5 — 過去 5 日累積報酬率 (***FIXED: Changed hyphen to underscore***)
-        df['return_t_5'] = (df['close'] / df['close'].shift(5) - 1)
+        # 2. return-t-5 — 過去 5 日累積報酬率 (***FIXED: Corrected to use hyphen***)
+        df['return-t-5'] = (df['close'] / df['close'].shift(5) - 1)
         
         # 3. MA5_close — 5 日移動平均價
         df['MA5_close'] = df['close'].rolling(window=5).mean()
         
         # 4. volatility_5d — 5 日報酬標準差
-        df['volatility_5d'] = df['return_t_1'].rolling(window=5).std()
+        df['volatility_5d'] = df['return-t-1'].rolling(window=5).std()
         
         # 5. volume_ratio_5d — 今日成交量 ÷ 5 日均量
         df['volume_5d_avg'] = df['volume'].rolling(window=5).mean()
@@ -146,8 +151,8 @@ class XGBoostModel:
         df['MACD_diff'] = macd_line - signal_line
         
         # 7-8. 美股指數報酬率（需要外部資料，暫設為0）
-        df['dji_return_t-1'] = 0.0
-        df['sox_return_t-1'] = 0.0
+        df['dji_return-t-1'] = 0.0
+        df['sox_return-t-1'] = 0.0
         
         # 9. NEWS — 新聞情緒分數（需要外部資料，暫設為0）
         df['NEWS'] = 0.0
@@ -178,8 +183,8 @@ class XGBoostModel:
         df['DX'] = np.abs(df['+DI'] - df['-DI']) / (df['+DI'] + df['-DI']) * 100
         df['ADX'] = df['DX'].ewm(com=13, adjust=False).mean()
         
-        # 13. volume_weighted_return — 成交量加權報酬率 (***FIXED: Changed hyphen to underscore***)
-        df['volume_weighted_return'] = np.abs(df['return_t_1']) * df['volume']
+        # 13. volume_weighted_return — 成交量加權報酬率
+        df['volume_weighted_return'] = np.abs(df['return-t-1']) * df['volume']
         
         # 清理輔助欄位
         cleanup_columns = ['volume_5d_avg', 'up_move', 'down_move', '+DM', '-DM', 'TR', '+DI', '-DI', 'DX']
@@ -190,6 +195,7 @@ class XGBoostModel:
         df.fillna(0, inplace=True)  # 剩餘的 NaN 用 0 填補
         
         return df
+