Update app.py

app.py

@@ -133,25 +133,37 @@ class TradingBacktester:
         return 0
     
     def simulate_predictions(self, data, predictor_func):
-        """
-        模擬歷史預測結果
+    """
+    模擬歷史預測結果
+    
+    Args:
+        data: 股價歷史資料
+        predictor_func: 預測函數
         
-        Args:
-            data: 股價歷史資料
-            predictor_func: 預測函數
-            
-        Returns:
-            predictions_history: 歷史預測結果字典
-        """
-        predictions_history = {}
+    Returns:
+        predictions_history: 歷史預測結果字典
+    """
+    predictions_history = {}
+    
+    # 為每個交易日生成預測
+        for i in range(60, len(data)):  # 從第60天開始，確保有足夠歷史資料
+        current_date = data.index[i]
+        historical_data = data.iloc[:i+1].copy()  # 到當前日期的歷史資料
+        
+        # 確保歷史資料有必要的欄位結構 (yfinance格式)
+            if 'Close' not in historical_data.columns and 'close' in historical_data.columns:
+                historical_data['Close'] = historical_data['close']
+            if 'Volume' not in historical_data.columns and 'volume' in historical_data.columns:
+                historical_data['Volume'] = historical_data['volume']
+            if 'High' not in historical_data.columns and 'high' in historical_data.columns:
+                historical_data['High'] = historical_data['high']
+            if 'Low' not in historical_data.columns and 'low' in historical_data.columns:
+                historical_data['Low'] = historical_data['low']
+            if 'Open' not in historical_data.columns and 'open' in historical_data.columns:
+                historical_data['Open'] = historical_data['open']
         
-        # 為每個交易日生成預測
-        for i in range(60, len(data)):  # 從第60天開始，確保有足夠歷史資料，
-            current_date = data.index[i]
-            historical_data = data.iloc[:i+1]  # 到當前日期的歷史資料
-            
             try:
-                # 呼叫預測函數
+                # 呼叫預測函數 - get_prediction會處理特徵計算
                 predictions = {}
                 for days in [1, 5, 10, 20]:
                     pred_result = predictor_func(historical_data, days)
@@ -159,15 +171,15 @@ class TradingBacktester:
                         predictions[f'{days}d'] = pred_result.get('change_pct', 0)
                     else:
                         predictions[f'{days}d'] = 0
-                        
+                    
                 predictions_history[current_date] = predictions
-                
+            
             except Exception as e:
                 # print(f"預測失敗 {current_date}: {e}")
                 predictions_history[current_date] = {
                     '1d': 0, '5d': 0, '10d': 0, '20d': 0
                 }
-                
+            
         return predictions_history
     
     def run_backtest(self, stock_data, predictor_func, start_date=None, end_date=None):
@@ -807,47 +819,98 @@ def simple_statistical_predict(data, predict_days=5):
 
 def calculate_new_features(df):
     """
-    計算新的技術指標特徵 - 針對新特徵需求
+    計算新的技術指標特徵 - 完整對應訓練模型的特徵
     """
     if df.empty:
         return df
     
-    # 1. return_t-1 – 前一日報酬率
+    # 確保基礎欄位存在
+    if 'Close' not in df.columns and 'close' in df.columns:
+        df['Close'] = df['close']
+    if 'Volume' not in df.columns and 'volume' in df.columns:
+        df['Volume'] = df['volume']
+    if 'High' not in df.columns and 'high' in df.columns:
+        df['High'] = df['high']
+    if 'Low' not in df.columns and 'low' in df.columns:
+        df['Low'] = df['low']
+    if 'Open' not in df.columns and 'open' in df.columns:
+        df['Open'] = df['open']
+    
+    # 1. close - 收盤價
+    df['close'] = df['Close']
+    
+    # 2. return_t-1 — 前一日報酬率
     df['return_t-1'] = df['Close'].pct_change()
     
-    # 2. return_t-5 – 過去 5 日累積報酬率
+    # 3. return_t-5 — 過去 5 日累積報酬率
     df['return_t-5'] = (df['Close'] / df['Close'].shift(5) - 1)
     
-    # 3. MA5_close – 5 日移動平均價
+    # 4. MA5_close — 5 日移動平均價
     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()
-    
-    # 5. volatility_5d – 5 日報酬標準差（短期波動）
+    # 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()
     
-    # 6. volume_ratio_5d – 今日成交量 ÷ 5 日均量
+    # 6. volume_ratio_5d — 今日成交量 ÷ 5 日均量
     df['volume_5d_avg'] = df['Volume'].rolling(window=5).mean()
     df['volume_ratio_5d'] = df['Volume'] / df['volume_5d_avg']
     
-    # 7. RSI_14 – 14 日 RSI 指標
+    # 7. MACD_diff — MACD - signal（趨勢強弱）
+    exp1 = df['Close'].ewm(span=12).mean()
+    exp2 = df['Close'].ewm(span=26).mean()
+    macd_line = exp1 - exp2
+    signal_line = macd_line.ewm(span=9).mean()
+    df['MACD_diff'] = macd_line - signal_line
+    
+    # 8. dji_return_t-1 — 前一日道瓊指數報酬率（預設為0，需外部數據）
+    df['dji_return_t-1'] = 0.0
+    
+    # 9. sox_return_t-1 — 前一日費半指數報酬率（預設為0，需外部數據）
+    df['sox_return_t-1'] = 0.0
+    
+    # 10. NEWS — 新聞情緒分數（預設為0，需外部數據）
+    df['NEWS'] = 0.0
+    
+    # 11. MACDvol — MACD柱狀圖
+    df['MACDvol'] = macd_line - signal_line
+    
+    # 12. RSI_14 — 14日RSI
     delta = df['Close'].diff()
     gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
     loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()
     rs = gain / loss
     df['RSI_14'] = 100 - (100 / (1 + rs))
     
-    # 8. MACD_diff – MACD - signal（趨勢強弱）
-    exp1 = df['Close'].ewm(span=12).mean()
-    exp2 = df['Close'].ewm(span=26).mean()
-    macd_line = exp1 - exp2
-    signal_line = macd_line.ewm(span=9).mean()
-    df['MACD_diff'] = macd_line - signal_line
+    # 13. ADX — 平均趨向指標
+    try:
+        df['up_move'] = df['High'] - df['High'].shift(1)
+        df['down_move'] = df['Low'].shift(1) - df['Low']
+        df['+DM'] = np.where((df['up_move'] > df['down_move']) & (df['up_move'] > 0), df['up_move'], 0)
+        df['-DM'] = np.where((df['down_move'] > df['up_move']) & (df['down_move'] > 0), df['down_move'], 0)
+        
+        high_low = df['High'] - df['Low']
+        high_close_prev = np.abs(df['High'] - df['Close'].shift(1))
+        low_close_prev = np.abs(df['Low'] - df['Close'].shift(1))
+        df['TR'] = np.maximum.reduce([high_low, high_close_prev, low_close_prev])
+        
+        df['+DI'] = (df['+DM'].ewm(com=13, adjust=False).mean() / df['TR'].ewm(com=13, adjust=False).mean()) * 100
+        df['-DI'] = (df['-DM'].ewm(com=13, adjust=False).mean() / df['TR'].ewm(com=13, adjust=False).mean()) * 100
+        df['DX'] = np.abs(df['+DI'] - df['-DI']) / (df['+DI'] + df['-DI']) * 100
+        df['ADX'] = df['DX'].ewm(com=13, adjust=False).mean()
+    except:
+        print("警告：ADX計算失敗，使用預設值")
+        df['ADX'] = 25.0  # 預設中性值
+    
+    # 14. volume_weighted_return — 成交量加權報酬率
+    df['volume_weighted_return'] = np.abs(df['return_t-1']) * df['Volume']
     
     # 移除輔助欄位
-    if 'volume_5d_avg' in df.columns:
-        df = df.drop('volume_5d_avg', axis=1)
+    auxiliary_columns = ['volume_5d_avg', 'up_move', 'down_move', '+DM', '-DM', 'TR', '+DI', '-DI', 'DX']
+    df.drop(columns=[col for col in auxiliary_columns if col in df.columns], inplace=True)
+    
+    # 填補 NaN 值
+    df.fillna(method='ffill', inplace=True)
+    df.fillna(0, inplace=True)  # 剩餘的 NaN 用 0 填補
     
     return df
 
@@ -871,8 +934,34 @@ def advanced_xgboost_predict(predict_days=5):
         # 計算技術指標（包含舊的指標）
         taiex_data = calculate_technical_indicators(taiex_data)
         
+        # 計算新特徵
         # 計算新特徵
         taiex_data = calculate_new_features(taiex_data)
+
+        # 確保所有必要特徵都存在且沒有NaN值
+        required_features = [
+            'return_t-1', 'return_t-5', 'MA5_close', 'volatility_5d', 
+            'volume_ratio_5d', 'MACD_diff'
+        ]
+
+        for feature in required_features:
+            if feature not in taiex_data.columns:
+                print(f"警告: 缺少特徵 {feature}，使用默認值")
+                if 'return' in feature:
+                    taiex_data[feature] = 0.0
+                elif 'MA' in feature:
+                    taiex_data[feature] = taiex_data['Close']
+                elif 'volatility' in feature:
+                    taiex_data[feature] = 0.02
+                elif 'volume_ratio' in feature:
+                    taiex_data[feature] = 1.0
+                elif 'MACD' in feature:
+                    taiex_data[feature] = 0.0
+                else:
+                    taiex_data[feature] = 0.0
+
+        # 填補可能的NaN值
+        taiex_data = taiex_data.fillna(method='ffill').fillna(0)
         
         # 獲取美股指數數據來計算外部指標
         us_market_data = get_us_market_data()
@@ -895,14 +984,22 @@ def advanced_xgboost_predict(predict_days=5):
         yesterday_close = latest_data['Close']
 
         # 特徵列表，確保與模型訓練時完全一致
-        new_feature_columns = [
-            'return_t-1',
-            'return_t-5',
-            'MA5_close',
-            'volatility_5d',
-            'volume_ratio_5d',
-            'MACD_diff',
-        ]
+        model_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
+            'MACDvol',                 # MACD柱狀圖
+            'RSI_14',                  # 14日RSI
+            'ADX',                     # ADX指標
+            'volume_weighted_return'   # 成交量加權報酬率
+                ]
         
         # 添加美股指標（如果有數據的話）
         dji_return = 0
@@ -929,25 +1026,241 @@ def advanced_xgboost_predict(predict_days=5):
         feature_names = []
         
         # 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 'MACD' in feature: default_value = 0.0
-                    else: default_value = 0.0
+        for feature in model_feature_columns:
+            if feature in ['dji_return_t-1', 'sox_return_t-1']:
+                # 處理美股指標
+                if feature == 'dji_return_t-1':
+                    features_list.append(dji_return)
+                    feature_status[feature] = {
+                        'value': dji_return, 
+                        'is_real': dji_return != 0, 
+                        'source': 'calculated' if dji_return != 0 else 'default'
+                    }
+                else:  # sox_return_t-1
+                    features_list.append(sox_return)
+                    feature_status[feature] = {
+                        'value': sox_return, 
+                        'is_real': sox_return != 0, 
+                        'source': 'calculated' if sox_return != 0 else 'default'
+                    }
                     
+            elif feature == 'NEWS':
+                # 新聞分數
+                features_list.append(sentiment_score_raw)
+                feature_status[feature] = {
+                    'value': sentiment_score_raw, 
+                    'is_real': True, 
+                    'source': 'calculated'
+                }
+                
+            else:
+                # 其他技術指標特徵
+                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 or feature == 'close': 
+                            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
+                        elif 'RSI' in feature:
+                            default_value = 50.0
+                        elif 'ADX' in feature:
+                            default_value = 25.0
+                        elif 'volume_weighted' 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'
+                        }
+                    else:
+                        features_list.append(value)
+                        feature_status[feature] = {
+                            'value': value, 
+                            'is_real': True, 
+                            'source': 'calculated'
+                        }
+                else:
+                    # 特徵不存在，使用預設值
+                    default_value = 0.0
                     features_list.append(default_value)
-                    feature_status[feature] = {'value': default_value, 'is_real': False, 'source': 'default'}
+                    feature_status[feature] = {
+                        'value': default_value, 
+                        'is_real': False, 
+                        'source': 'missing'
+                    }
+            
+            feature_names.append(feature)
+
+        # 轉換為 DataFrame (XGBoost 模型期望的格式)
+        input_df = pd.DataFrame([features_list], columns=feature_names)for feature in model_feature_columns:
+            if feature in ['dji_return_t-1', 'sox_return_t-1']:
+                # 處理美股指標
+                if feature == 'dji_return_t-1':
+                    features_list.append(dji_return)
+                    feature_status[feature] = {
+                        'value': dji_return, 
+                        'is_real': dji_return != 0, 
+                        'source': 'calculated' if dji_return != 0 else 'default'
+                    }
+                else:  # sox_return_t-1
+                    features_list.append(sox_return)
+                    feature_status[feature] = {
+                        'value': sox_return, 
+                        'is_real': sox_return != 0, 
+                        'source': 'calculated' if sox_return != 0 else 'default'
+                    }
+                    
+            elif feature == 'NEWS':
+                # 新聞分數
+                features_list.append(sentiment_score_raw)
+                feature_status[feature] = {
+                    'value': sentiment_score_raw, 
+                    'is_real': True, 
+                    'source': 'calculated'
+                }
+                
+            else:
+                # 其他技術指標特徵
+                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 or feature == 'close': 
+                            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
+                        elif 'RSI' in feature:
+                            default_value = 50.0
+                        elif 'ADX' in feature:
+                            default_value = 25.0
+                        elif 'volume_weighted' 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'
+                        }
+                    else:
+                        features_list.append(value)
+                        feature_status[feature] = {
+                            'value': value, 
+                            'is_real': True, 
+                            'source': 'calculated'
+                        }
                 else:
-                    features_list.append(value)
-                    feature_status[feature] = {'value': value, 'is_real': True, 'source': 'calculated'}
+                    # 特徵不存在，使用預設值
+                    default_value = 0.0
+                    features_list.append(default_value)
+                    feature_status[feature] = {
+                        'value': default_value, 
+                        'is_real': False, 
+                        'source': 'missing'
+                    }
+            
+            feature_names.append(feature)
+
+        # 轉換為 DataFrame (XGBoost 模型期望的格式)
+        input_df = pd.DataFrame([features_list], columns=feature_names)for feature in model_feature_columns:
+            if feature in ['dji_return_t-1', 'sox_return_t-1']:
+                # 處理美股指標
+                if feature == 'dji_return_t-1':
+                    features_list.append(dji_return)
+                    feature_status[feature] = {
+                        'value': dji_return, 
+                        'is_real': dji_return != 0, 
+                        'source': 'calculated' if dji_return != 0 else 'default'
+                    }
+                else:  # sox_return_t-1
+                    features_list.append(sox_return)
+                    feature_status[feature] = {
+                        'value': sox_return, 
+                        'is_real': sox_return != 0, 
+                        'source': 'calculated' if sox_return != 0 else 'default'
+                    }
+                    
+            elif feature == 'NEWS':
+                # 新聞分數
+                features_list.append(sentiment_score_raw)
+                feature_status[feature] = {
+                    'value': sentiment_score_raw, 
+                    'is_real': True, 
+                    'source': 'calculated'
+                }
                 
-                feature_names.append(feature)
+            else:
+                # 其他技術指標特徵
+                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 or feature == 'close': 
+                            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
+                        elif 'RSI' in feature:
+                            default_value = 50.0
+                        elif 'ADX' in feature:
+                            default_value = 25.0
+                        elif 'volume_weighted' 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'
+                        }
+                    else:
+                        features_list.append(value)
+                        feature_status[feature] = {
+                            'value': value, 
+                            'is_real': True, 
+                            'source': 'calculated'
+                        }
+                else:
+                    # 特徵不存在，使用預設值
+                    default_value = 0.0
+                    features_list.append(default_value)
+                    feature_status[feature] = {
+                        'value': default_value, 
+                        'is_real': False, 
+                        'source': 'missing'
+                    }
+            
+            feature_names.append(feature)
+
+        # 轉換為 DataFrame (XGBoost 模型期望的格式)
+        input_df = pd.DataFrame([features_list], columns=feature_names)
 
         # 按照模型訓練的順序添加剩餘特徵
         # 7. dji_return_t-1