Update app.py

app.py

@@ -257,7 +257,7 @@ def calculate_new_features(df):
     df['MA5_close'] = df['Close'].rolling(window=5).mean()
     
     # 4. MA20_close – 20 日移動平均價  
-    #df['MA20_close'] = df['Close'].rolling(window=20).mean()
+    df['MA20_close'] = df['Close'].rolling(window=20).mean()
     
     # 5. volatility_5d – 5 日報酬標準差（短期波動）
     df['volatility_5d'] = df['return_t-1'].rolling(window=5).std()
@@ -325,19 +325,17 @@ def advanced_xgboost_predict(predict_days=5):
         # 準備特徵數據 (使用最新的數據點)
         latest_data = taiex_data.iloc[-1]
         
-        # 【【【新增功能】】】 取得昨日收盤價
+        # 取得昨日收盤價
         yesterday_close = latest_data['Close']
 
-        # 新特徵列表 - 按照您指定的8個技術指標特徵
+        # 【【【修正】】】特徵列表，確保與模型訓練時完全一致
         new_feature_columns = [
-            '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
-                    # 20 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
-            'RSI_14',           # 14 日 RSI 指標
-            'MACD_diff',        # MACD - signal
+            'return_t-1',
+            'return_t-5',
+            'MA5_close',
+            'volatility_5d',
+            'volume_ratio_5d',
+            'MACD_diff',
         ]
         
         # 添加美股指標（如果有數據的話）
@@ -364,26 +362,18 @@ def advanced_xgboost_predict(predict_days=5):
         features_list = []
         feature_names = []
         
-        # 處理本地計算的特徵
+        # 處理本地計算的技術指標特徵
         for feature in new_feature_columns:
             if feature in latest_data.index:
                 value = latest_data[feature]
                 if pd.isna(value):
                     # 使用合理的預設值
-                    if 'return' in feature:
-                        default_value = 0.0
-                    elif 'MA' in feature:
-                        default_value = latest_data['Close'] if not pd.isna(latest_data['Close']) else 100
-                    elif 'volatility' in feature:
-                        default_value = 0.02
-                    elif 'volume_ratio' in feature:
-                        default_value = 1.0
-                    elif 'RSI' in feature:
-                        default_value = 50.0
-                    elif 'MACD' in feature:
-                        default_value = 0.0
-                    else:
-                        default_value = 0.0
+                    if 'return' in feature: default_value = 0.0
+                    elif 'MA' in feature: default_value = latest_data['Close'] if not pd.isna(latest_data['Close']) else 100
+                    elif 'volatility' in feature: default_value = 0.02
+                    elif 'volume_ratio' in feature: default_value = 1.0
+                    elif 'MACD' in feature: default_value = 0.0
+                    else: default_value = 0.0
                     
                     features_list.append(default_value)
                     feature_status[feature] = {'value': default_value, 'is_real': False, 'source': 'default'}
@@ -392,36 +382,39 @@ def advanced_xgboost_predict(predict_days=5):
                     feature_status[feature] = {'value': value, 'is_real': True, 'source': 'calculated'}
                 
                 feature_names.append(feature)
-        
-        # 【【【新增功能】】】 添加 'close' 和 'NEWS' 特徵
-        # 1. 添加昨日收盤價 ('close')
-        if not pd.isna(yesterday_close):
-            features_list.append(yesterday_close)
-            feature_status['close'] = {'value': yesterday_close, 'is_real': True, 'source': 'calculated'}
-        else:
-            features_list.append(10000) # Fallback value for price
-            feature_status['close'] = {'value': 10000, 'is_real': False, 'source': 'default'}
-        feature_names.append('close')
-
-        # 2. 添加新聞情緒分數 ('NEWS')
-        features_list.append(sentiment_score_raw)
-        feature_status['NEWS'] = {'value': sentiment_score_raw, 'is_real': True, 'source': 'calculated'}
-        feature_names.append('NEWS')
 
-        # 添加美股指標
-        features_list.extend([dji_return, sox_return])
-        feature_names.extend(['dji_return_t-1', 'sox_return_t-1'])
-        
+        # 【【【修正】】】 按照模型訓練的順序添加剩餘特徵
+        # 7. dji_return_t-1
+        features_list.append(dji_return)
+        feature_names.append('dji_return_t-1')
         feature_status['dji_return_t-1'] = {
             'value': dji_return, 
             'is_real': dji_return != 0, 
             'source': 'calculated' if dji_return != 0 else 'default'
         }
+
+        # 8. sox_return_t-1
+        features_list.append(sox_return)
+        feature_names.append('sox_return_t-1')
         feature_status['sox_return_t-1'] = {
             'value': sox_return, 
             'is_real': sox_return != 0, 
             'source': 'calculated' if sox_return != 0 else 'default'
         }
+
+        # 9. close
+        if not pd.isna(yesterday_close):
+            features_list.append(yesterday_close)
+            feature_status['close'] = {'value': yesterday_close, 'is_real': True, 'source': 'calculated'}
+        else:
+            features_list.append(10000) # Fallback value for price
+            feature_status['close'] = {'value': 10000, 'is_real': False, 'source': 'default'}
+        feature_names.append('close')
+
+        # 10. NEWS
+        features_list.append(sentiment_score_raw)
+        feature_status['NEWS'] = {'value': sentiment_score_raw, 'is_real': True, 'source': 'calculated'}
+        feature_names.append('NEWS')
         
         # 轉換為 DataFrame (XGBoost 模型期望的格式)
         input_df = pd.DataFrame([features_list], columns=feature_names)
@@ -439,7 +432,7 @@ def advanced_xgboost_predict(predict_days=5):
         for i, (name, value) in enumerate(zip(feature_names, features_list)):
             status = feature_status.get(name, {})
             status_symbol = "✓正常" if status.get('is_real', False) else "⚠預設值"
-            print(f"  [{i:2d}] {name:18s}: {value:12.6f} ({status_symbol})")
+            print(f"  [{i+1:2d}] {name:18s}: {value:12.6f} ({status_symbol})")
         
         # 統計完整性
         real_features = sum(1 for status in feature_status.values() if status.get('is_real', False))
@@ -456,7 +449,7 @@ def advanced_xgboost_predict(predict_days=5):
         # 顯示完整特徵向量
         print(f"\n完整特徵向量 (共{len(features_list)}個特徵):")
         for i, (name, value) in enumerate(zip(feature_names, features_list)):
-            print(f"  [{i:2d}] {name:18s}: {value:12.6f}")
+            print(f"  [{i+1:2d}] {name:18s}: {value:12.6f}")
         
         print("=" * 60)