Upload 4 files

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 stock_lstm_model_v2.keras filter=lfs diff=lfs merge=lfs -text
 9CE6ABB0E688BCE5A5B3E69920220912-20250909.xlsx filter=lfs diff=lfs merge=lfs -text
 期末專案輸入資料20220912-20250909.xlsx filter=lfs diff=lfs merge=lfs -text
+taiwan_stock_predictor.keras filter=lfs diff=lfs merge=lfs -text

model_predictor.py

@@ -1,152 +1,572 @@
-# model_predictor.py
-
-import numpy as np
-import pandas as pd
-from tensorflow.keras.models import load_model
-import joblib
-import yfinance as yf
-
-# --- 模型與設定檔 (未來訓練好後，請將檔案放在同目錄下) ---
-MODEL_FILE = 'stock_predictor_model.h5'
-SCALER_X_FILE = 'scaler_X.pkl'
-SCALER_Y_FILE = 'scaler_y.pkl'
-LOOKBACK_DAYS = 30 # 必須與訓練時的 LOOKBACK_DAYS 相同
-
-# --- 啟動時載入模型與縮放器 (只會載入一次) ---
-try:
-    model = load_model(MODEL_FILE)
-    scaler_X = joblib.load(SCALER_X_FILE)
-    scaler_y = joblib.load(SCALER_Y_FILE)
-    print("進階 LSTM 模型與縮放器載入成功。")
-except Exception as e:
-    print(f"提示：未找到或無法載入進階模型檔案 ({e})。應用將使用簡易統計模型。")
-    model = None
-
-# --- 從 app.py 複製過來的技術指標計算函式 ---
-# 確保資料準備的邏輯一致
-def calculate_technical_indicators(df):
-    """計算技術指標"""
-    if df.empty: return df
-    df['MA5'] = df['Close'].rolling(window=5).mean()
-    df['MA20'] = df['Close'].rolling(window=20).mean()
-    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'] = 100 - (100 / (1 + rs))
-    exp1 = df['Close'].ewm(span=12).mean()
-    exp2 = df['Close'].ewm(span=26).mean()
-    df['MACD'] = exp1 - exp2
-    df['MACD_Signal'] = df['MACD'].ewm(span=9).mean()
-    df['MACD_Histogram'] = df['MACD'] - df['MACD_Signal']
-    low_min = df['Low'].rolling(window=9).min()
-    high_max = df['High'].rolling(window=9).max()
-    rsv = (df['Close'] - low_min) / (high_max - low_min) * 100
-    df['K'] = rsv.ewm(com=2).mean()
-    df['D'] = df['K'].ewm(com=2).mean()
-    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)
-    df['TR'] = np.max([df['High'] - df['Low'], abs(df['High'] - df['Close'].shift(1)), abs(df['Low'] - df['Close'].shift(1))], axis=0)
-    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'] = abs(df['+DI'] - df['-DI']) / (df['+DI'] + df['-DI']) * 100
-    df['ADX'] = df['DX'].ewm(com=13, adjust=False).mean()
-    return df
-
-
-def get_all_features_for_model(period="3y"):
-    """獲取並整合模型需要的所有15個特徵。"""
-    print("正在下載市場數據以準備進階模型輸入...")
-    tickers = {'^TWII': 'TWII', '^SOX': 'SOX', 'TSM': 'TSM_ADR'}
-    data_yf = yf.download(list(tickers.keys()), period=period, auto_adjust=True)
-    
-    twii_data = data_yf.loc[:, ('Open', 'High', 'Low', 'Close', 'Volume')]['TWII'].copy()
-    
-    print("正在計算技術指標...")
-    df_main = calculate_technical_indicators(twii_data)
-    
-    print("正在合併外部市場與檔案數據...")
-    df_main['費城 半導體'] = data_yf['Close']['SOX']
-    df_main['台積電 ADR'] = data_yf['Close']['TSM_ADR']
-    
-    try:
-        df_climate = pd.read_csv('business_climate.csv')
-        df_climate['Date'] = pd.to_datetime(df_climate['Date'].astype(str) + '-01')
-        df_climate = df_climate.set_index('Date').rename(columns={'Index': '景氣燈號'})
-        
-        df_pmi = pd.read_csv('taiwan_pmi.csv')
-        df_pmi['Date'] = pd.to_datetime(df_pmi['DATE'].astype(str) + '-01')
-        df_pmi = df_pmi.set_index('Date').rename(columns={'INDEX': 'PMI'})
-        
-        df_main = pd.merge(df_main, df_climate, left_index=True, right_index=True, how='left')
-        df_main = pd.merge(df_main, df_pmi, left_index=True, right_index=True, how='left')
-    except FileNotFoundError as e:
-        print(f"警告: 找不到檔案 {e.filename}，相關欄位將為空。")
-        df_main['景氣燈號'] = np.nan
-        df_main['PMI'] = np.nan
-
-    df_main.fillna(method='ffill', inplace=True)
-    df_main.dropna(inplace=True)
-
-    df_final = df_main.rename(columns={
-        'Close': '加權指數', 'Volume': '成交量', 'K': 'K線', 'D': 'D線',
-        'MACD_Signal': 'MACD信號線', 'MACD_Histogram': 'MACD柱狀圖'
-    })
-    
-    print("所有特徵整合完畢！")
-    return df_final
-
-
-def advanced_lstm_predict(predict_days: int = 5):
-    """使用訓練好的 LSTM 模型進行預測。"""
-    if model is None:
-        print("進階模型未載入，無法進行預測。")
-        return None
-
-    try:
-        # 1. 獲取並整合所有最新資料
-        all_features_df = get_all_features_for_model()
-        if len(all_features_df) < LOOKBACK_DAYS:
-            print("資料長度不足，無法進行進階預測。")
-            return None
-            
-        # 2. 準備輸入資料
-        FEATURES = [
-            '加權指數', '成交量', '費城 半導體', '台積電 ADR', 'RSI', 'MACD', 
-            'MACD信號線', 'MACD柱狀圖', 'K線', 'D線', '+DI', '-DI', 'ADX', 
-            '景氣燈號', 'PMI'
-        ]
-        
-        last_sequence_df = all_features_df[FEATURES].tail(LOOKBACK_DAYS)
-        
-        if last_sequence_df.isnull().values.any():
-            print("警告：輸入的序列資料中存在缺失值，無法預測。")
-            return None
-            
-        input_scaled = scaler_X.transform(last_sequence_df)
-        input_reshaped = np.reshape(input_scaled, (1, LOOKBACK_DAYS, len(FEATURES)))
-        
-        # 3. 執行預測
-        prediction_scaled = model.predict(input_reshaped)
-        prediction_unscaled = scaler_y.inverse_transform(prediction_scaled)
-        
-        # 4. 處理預測結果
-        target_map = {1: 0, 5: 1, 10: 2}
-        if predict_days not in target_map:
-            predict_days = 5 # 預設值
-            
-        predicted_price = prediction_unscaled[0][target_map[predict_days]]
-        
-        last_price = all_features_df['加權指數'].iloc[-1]
-        change_pct = ((predicted_price - last_price) / last_price) * 100
-        
-        return {
-            'predicted_price': predicted_price,
-            'change_pct': change_pct,
-            'confidence': 0.85 # 可設為固定值
-        }
-    except Exception as e:
-        print(f"執行進階預測時發生錯誤: {e}")
-        return None
+# -*- coding: utf-8 -*-
+"""model_predictor.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1CaAPRdPsp3Jt5tQ3BLVcK19euWZmFme5
+"""
+
+# model_predictor.py
+# 進階LSTM模型預測器，適用於HUGING_FACE_V4.2
+
+import os
+import numpy as np
+import pandas as pd
+import yfinance as yf
+from datetime import datetime, timedelta
+import joblib
+from sklearn.preprocessing import StandardScaler, RobustScaler
+from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
+import warnings
+warnings.filterwarnings('ignore')
+
+# TensorFlow/Keras 相關
+try:
+    import tensorflow as tf
+    from tensorflow.keras.models import Sequential, load_model
+    from tensorflow.keras.layers import LSTM, Dense, Dropout, BatchNormalization, GRU, Bidirectional
+    from tensorflow.keras.optimizers import Adam
+    from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint
+    from tensorflow.keras.regularizers import l1_l2
+    print("TensorFlow 載入成功")
+except ImportError:
+    print("警告：TensorFlow 未安裝，模型將無法正常運作")
+    tf = None
+
+class AdvancedStockPredictor:
+    def __init__(self, model_name='taiwan_stock_predictor'):
+        self.model_name = model_name
+        self.model = None
+        self.scaler_X = RobustScaler()
+        self.scaler_y = StandardScaler()
+        self.sequence_length = 60  # 使用60天的歷史數據
+        self.feature_names = [
+            'volume', 'rate', 'DJI', 'NAS', 'SOX', 'SP500', 'TSM_ADR',
+            'RSI', 'MACD', 'MACDsign', 'MACDvol', 'K', 'D',
+            '+DI', '-DI', 'ADX', 'business_climate', 'PMI'
+        ]
+        self.target_names = ['close_1d', 'close_5d', 'close_10d', 'close_20d', 'close_60d']
+        self.is_trained = False
+
+    def fetch_yfinance_data(self, start_date='2022-09-12', end_date='2025-09-08'):
+        """從 yfinance 獲取所需的市場數據"""
+        print("正在從 yfinance 獲取數據...")
+
+        # 定義股票代碼
+        symbols = {
+            'TAIEX': '^TWII',      # 台股指數
+            'DJI': '^DJI',         # 道瓊工業指數
+            'NAS': '^IXIC',        # 納斯達克
+            'SOX': '^SOX',         # 費城半導體指數
+            'SP500': '^GSPC',      # 標普500
+            'TSM_ADR': 'TSM'       # 台積電ADR
+        }
+
+        data_dict = {}
+
+        for name, symbol in symbols.items():
+            try:
+                stock = yf.Ticker(symbol)
+                hist = stock.history(start=start_date, end=end_date)
+                if not hist.empty:
+                    data_dict[name] = hist
+                    print(f"成功獲取 {name} 數據: {len(hist)} 筆記錄")
+                else:
+                    print(f"警告：無法獲取 {name} 數據")
+            except Exception as e:
+                print(f"錯誤：獲取 {name} 數據時發生錯誤: {e}")
+
+        return data_dict
+
+    def load_economic_data(self):
+        """載入經濟數據檔案"""
+        economic_data = {}
+
+        # 載入景氣燈號
+        try:
+            if os.path.exists('business_climate.csv'):
+                bc_df = pd.read_csv('business_climate.csv')
+                if len(bc_df.columns) >= 2:
+                    bc_df.columns = ['Date', 'business_climate']
+                    # 統一時區處理
+                    bc_df['Date'] = pd.to_datetime(bc_df['Date'], errors='coerce').dt.tz_localize(None)
+                    bc_df = bc_df.dropna(subset=['Date'])
+                    bc_df.set_index('Date', inplace=True)
+                    economic_data['business_climate'] = bc_df
+                    print(f"成功載入景氣燈號數據: {len(bc_df)} 筆記錄")
+        except Exception as e:
+            print(f"載入景氣燈號數據時發生錯誤: {e}")
+
+        # 載入 PMI 數據
+        try:
+            if os.path.exists('taiwan_pmi.csv'):
+                pmi_df = pd.read_csv('taiwan_pmi.csv')
+                if len(pmi_df.columns) >= 2:
+                    pmi_df.columns = ['Date', 'PMI']
+                    # 統一時區處理
+                    pmi_df['Date'] = pd.to_datetime(pmi_df['Date'], errors='coerce').dt.tz_localize(None)
+                    pmi_df = pmi_df.dropna(subset=['Date'])
+                    pmi_df.set_index('Date', inplace=True)
+                    economic_data['PMI'] = pmi_df
+                    print(f"成功載入 PMI 數據: {len(pmi_df)} 筆記錄")
+        except Exception as e:
+            print(f"載入 PMI 數據時發生錯誤: {e}")
+
+        return economic_data
+
+    def calculate_technical_indicators(self, df):
+        """計算技術指標"""
+        if df.empty:
+            return df
+
+        # 確保有足夠的數據計算技術指標
+        if len(df) < 60:
+            return pd.DataFrame()
+
+        try:
+            # 基本指標
+            df['volume'] = df['Volume']
+            df['rate'] = df['Close'].pct_change()
+
+            # 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'] = 100 - (100 / (1 + rs))
+
+            # MACD
+            exp1 = df['Close'].ewm(span=12).mean()
+            exp2 = df['Close'].ewm(span=26).mean()
+            df['MACD'] = exp1 - exp2
+            df['MACDsign'] = df['MACD'].ewm(span=9).mean()
+            df['MACDvol'] = df['MACD'] - df['MACDsign']
+
+            # KD 指標
+            low_min = df['Low'].rolling(window=9).min()
+            high_max = df['High'].rolling(window=9).max()
+            rsv = (df['Close'] - low_min) / (high_max - low_min) * 100
+            df['K'] = rsv.ewm(com=2).mean()
+            df['D'] = df['K'].ewm(com=2).mean()
+
+            # DMI 指標
+            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)
+            df['TR'] = np.max([df['High'] - df['Low'],
+                              abs(df['High'] - df['Close'].shift(1)),
+                              abs(df['Low'] - df['Close'].shift(1))], axis=0)
+
+            df['+DI'] = (df['+DM'].ewm(com=13).mean() / df['TR'].ewm(com=13).mean()) * 100
+            df['-DI'] = (df['-DM'].ewm(com=13).mean() / df['TR'].ewm(com=13).mean()) * 100
+            df['DX'] = abs(df['+DI'] - df['-DI']) / (df['+DI'] + df['-DI']) * 100
+            df['ADX'] = df['DX'].ewm(com=13).mean()
+
+        except Exception as e:
+            print(f"計算技術指標時發生錯誤: {e}")
+            return pd.DataFrame()
+
+        return df
+
+    def prepare_training_data(self):
+        """準備訓練數據"""
+        print("開始準備訓練數據...")
+
+        # 獲取市場數據
+        market_data = self.fetch_yfinance_data()
+        economic_data = self.load_economic_data()
+
+        if 'TAIEX' not in market_data:
+            print("錯誤：無法獲取台股指數數據")
+            return None, None
+
+        # 以台股指數為主要數據
+        main_df = market_data['TAIEX'].copy()
+        # 統一時區處理 - 移除時區資訊
+        main_df.index = main_df.index.tz_localize(None)
+
+        main_df = self.calculate_technical_indicators(main_df)
+
+        if main_df.empty:
+            print("錯誤：技術指標計算失敗")
+            return None, None
+
+        # 合併其他市場數據
+        for name, data in market_data.items():
+            if name != 'TAIEX' and not data.empty:
+                # 統一時區處理
+                data.index = data.index.tz_localize(None)
+
+                # 重新命名欄位以避免衝突
+                if name == 'DJI':
+                    main_df['DJI'] = data['Close'].reindex(main_df.index)
+                elif name == 'NAS':
+                    main_df['NAS'] = data['Close'].reindex(main_df.index)
+                elif name == 'SOX':
+                    main_df['SOX'] = data['Close'].reindex(main_df.index)
+                elif name == 'SP500':
+                    main_df['SP500'] = data['Close'].reindex(main_df.index)
+                elif name == 'TSM_ADR':
+                    main_df['TSM_ADR'] = data['Close'].reindex(main_df.index)
+
+        # 合併經濟數據
+        for name, data in economic_data.items():
+            if name == 'business_climate':
+                main_df['business_climate'] = data['business_climate'].reindex(main_df.index, method='ffill')
+            elif name == 'PMI':
+                main_df['PMI'] = data['PMI'].reindex(main_df.index, method='ffill')
+
+        # 創建未來價格標籤
+        close_prices = main_df['Close']
+        for days in [1, 5, 10, 20, 60]:
+            main_df[f'close_{days}d'] = close_prices.shift(-days)
+
+        # 選擇特徵欄位
+        feature_columns = []
+        for feature in self.feature_names:
+            if feature in main_df.columns:
+                feature_columns.append(feature)
+            else:
+                print(f"警告：特徵 {feature} 不存在，使用預設值 0")
+                main_df[feature] = 0  # 使用預設值
+                feature_columns.append(feature)
+
+        # 移除包含 NaN 的行
+        print(f"處理前數據量: {len(main_df)}")
+        main_df = main_df.dropna()
+        print(f"處理後數據量: {len(main_df)}")
+
+        if len(main_df) < self.sequence_length + 60:  # 需要足夠的數據
+            print("錯誤：數據量不足以進行訓練")
+            return None, None
+
+        # 準備特徵和標籤
+        X = main_df[feature_columns].values
+        y = main_df[self.target_names].values
+
+        print(f"數據準備完成：X shape: {X.shape}, y shape: {y.shape}")
+        return X, y
+
+    def create_sequences(self, X, y):
+        """創建時間序列序列"""
+        X_seq, y_seq = [], []
+
+        for i in range(self.sequence_length, len(X)):
+            X_seq.append(X[i-self.sequence_length:i])
+            y_seq.append(y[i])
+
+        return np.array(X_seq), np.array(y_seq)
+
+    def build_model(self, input_shape, output_shape):
+        """建立進階LSTM模型"""
+        if tf is None:
+            raise ImportError("TensorFlow 未安裝，無法建立模型")
+
+        model = Sequential([
+            # 第一層 Bidirectional LSTM
+            Bidirectional(LSTM(128, return_sequences=True, dropout=0.2, recurrent_dropout=0.2),
+                         input_shape=input_shape),
+            BatchNormalization(),
+
+            # 第二層 LSTM
+            LSTM(64, return_sequences=True, dropout=0.2, recurrent_dropout=0.2),
+            BatchNormalization(),
+
+            # 第三層 LSTM
+            LSTM(32, dropout=0.2, recurrent_dropout=0.2),
+            BatchNormalization(),
+
+            # 全連接層
+            Dense(64, activation='relu', kernel_regularizer=l1_l2(l1=0.01, l2=0.01)),
+            Dropout(0.3),
+
+            Dense(32, activation='relu', kernel_regularizer=l1_l2(l1=0.01, l2=0.01)),
+            Dropout(0.2),
+
+            # 輸出層
+            Dense(output_shape, activation='linear')
+        ])
+
+        # 編譯模型
+        model.compile(
+            optimizer=Adam(learning_rate=0.001),
+            loss='huber',
+            metrics=['mae', 'mse']
+        )
+
+        return model
+
+    def train(self, epochs=100, batch_size=32, validation_split=0.2):
+        """訓練模型"""
+        print("開始訓練模型...")
+
+        # 準備數據
+        X, y = self.prepare_training_data()
+        if X is None or y is None:
+            print("錯誤：無法準備訓練數據")
+            return False
+
+        # 數據標準化
+        X_scaled = self.scaler_X.fit_transform(X)
+        y_scaled = self.scaler_y.fit_transform(y)
+
+        # 創建序列
+        X_seq, y_seq = self.create_sequences(X_scaled, y_scaled)
+
+        if len(X_seq) == 0:
+            print("錯誤：無法創建有效序列")
+            return False
+
+        print(f"訓練數據形狀：X_seq: {X_seq.shape}, y_seq: {y_seq.shape}")
+
+        # 建立模型
+        self.model = self.build_model(
+            input_shape=(X_seq.shape[1], X_seq.shape[2]),
+            output_shape=y_seq.shape[1]
+        )
+
+        print("模型架構：")
+        self.model.summary()
+
+        # 設定回調函數
+        callbacks = [
+            EarlyStopping(patience=15, restore_best_weights=True, monitor='val_loss'),
+            ReduceLROnPlateau(factor=0.5, patience=8, min_lr=0.0001, monitor='val_loss'),
+            ModelCheckpoint(f'{self.model_name}.keras', save_best_only=True, monitor='val_loss')
+        ]
+
+        # 訓練模型
+        history = self.model.fit(
+            X_seq, y_seq,
+            epochs=epochs,
+            batch_size=batch_size,
+            validation_split=validation_split,
+            callbacks=callbacks,
+            verbose=1
+        )
+
+        # 儲存模型和縮放器
+        self.save_model()
+
+        # 評估模型
+        self.evaluate_model(X_seq, y_seq, validation_split)
+
+        self.is_trained = True
+        print("模型訓練完成!")
+        return True
+
+    def evaluate_model(self, X_seq, y_seq, validation_split):
+        """評估模型性能"""
+        print("\n模型評估結果：")
+
+        # 分割數據
+        split_idx = int(len(X_seq) * (1 - validation_split))
+        X_val, y_val = X_seq[split_idx:], y_seq[split_idx:]
+
+        # 預測
+        y_pred = self.model.predict(X_val)
+
+        # 反標準化
+        y_val_orig = self.scaler_y.inverse_transform(y_val)
+        y_pred_orig = self.scaler_y.inverse_transform(y_pred)
+
+        # 計算指標
+        for i, target in enumerate(self.target_names):
+            mae = mean_absolute_error(y_val_orig[:, i], y_pred_orig[:, i])
+            mse = mean_squared_error(y_val_orig[:, i], y_pred_orig[:, i])
+            r2 = r2_score(y_val_orig[:, i], y_pred_orig[:, i])
+            print(f"{target}: MAE={mae:.2f}, MSE={mse:.2f}, R2={r2:.4f}")
+
+    def save_model(self):
+        """儲存模型和縮放器"""
+        try:
+            if self.model is not None:
+                self.model.save(f'{self.model_name}.keras')
+                print(f"模型已儲存: {self.model_name}.keras")
+
+            joblib.dump(self.scaler_X, f'{self.model_name}_scaler_X.pkl')
+            joblib.dump(self.scaler_y, f'{self.model_name}_scaler_y.pkl')
+            print("縮放器已儲存")
+
+        except Exception as e:
+            print(f"儲存模型時發生錯誤: {e}")
+
+    def load_model(self):
+        """載入已訓練的模型"""
+        try:
+            if tf is not None and os.path.exists(f'{self.model_name}.keras'):
+                self.model = load_model(f'{self.model_name}.keras')
+                print("模型載入成功")
+
+            if os.path.exists(f'{self.model_name}_scaler_X.pkl'):
+                self.scaler_X = joblib.load(f'{self.model_name}_scaler_X.pkl')
+                print("X 縮放器載入成功")
+
+            if os.path.exists(f'{self.model_name}_scaler_y.pkl'):
+                self.scaler_y = joblib.load(f'{self.model_name}_scaler_y.pkl')
+                print("y 縮放器載入成功")
+
+            self.is_trained = True
+            return True
+
+        except Exception as e:
+            print(f"載入模型時發生錯誤: {e}")
+            return False
+
+    def predict(self, predict_days=5):
+        """進行預測"""
+        if not self.is_trained and not self.load_model():
+            print("錯誤：模型未訓練且無法載入已訓練的模型")
+            return None
+
+        if self.model is None:
+            print("錯誤：模型未載入")
+            return None
+
+        try:
+            # 獲取最新數據
+            print("正在獲取最新數據進行預測...")
+            market_data = self.fetch_yfinance_data(
+                start_date=(datetime.now() - timedelta(days=120)).strftime('%Y-%m-%d'),
+                end_date=datetime.now().strftime('%Y-%m-%d')
+            )
+            economic_data = self.load_economic_data()
+
+            if 'TAIEX' not in market_data:
+                print("錯誤：無法獲取最新台股數據")
+                return None
+
+            # 處理數據（與訓練時相同的流程）
+            main_df = market_data['TAIEX'].copy()
+            # 統一時區處理
+            main_df.index = main_df.index.tz_localize(None)
+
+            main_df = self.calculate_technical_indicators(main_df)
+
+            if main_df.empty or len(main_df) < self.sequence_length:
+                print("錯誤：數據不足以進行預測")
+                return None
+
+            # 合併其他數據
+            for name, data in market_data.items():
+                if name != 'TAIEX' and not data.empty:
+                    # 統一時區處理
+                    data.index = data.index.tz_localize(None)
+
+                    if name == 'DJI':
+                        main_df['DJI'] = data['Close'].reindex(main_df.index)
+                    elif name == 'NAS':
+                        main_df['NAS'] = data['Close'].reindex(main_df.index)
+                    elif name == 'SOX':
+                        main_df['SOX'] = data['Close'].reindex(main_df.index)
+                    elif name == 'SP500':
+                        main_df['SP500'] = data['Close'].reindex(main_df.index)
+                    elif name == 'TSM_ADR':
+                        main_df['TSM_ADR'] = data['Close'].reindex(main_df.index)
+
+            for name, data in economic_data.items():
+                if name == 'business_climate':
+                    main_df['business_climate'] = data['business_climate'].reindex(main_df.index, method='ffill')
+                elif name == 'PMI':
+                    main_df['PMI'] = data['PMI'].reindex(main_df.index, method='ffill')
+
+            # 填充缺失特徵
+            for feature in self.feature_names:
+                if feature not in main_df.columns:
+                    main_df[feature] = 0
+
+            # 使用 fillna 替代已棄用的 method 參數
+            main_df = main_df.fillna(method='ffill').fillna(0)
+
+            # 準備預測數據
+            X = main_df[self.feature_names].values
+            if len(X) < self.sequence_length:
+                print("錯誤：歷史數據不足")
+                return None
+
+            # 使用最後的sequence_length天數據
+            X_recent = X[-self.sequence_length:]
+            X_scaled = self.scaler_X.transform(X_recent.reshape(1, -1))
+            X_scaled = X_scaled.reshape(1, self.sequence_length, -1)
+
+            # 進行預測
+            y_pred_scaled = self.model.predict(X_scaled)
+            y_pred = self.scaler_y.inverse_transform(y_pred_scaled)
+
+            # 獲取當前價格
+            current_price = main_df['Close'].iloc[-1]
+
+            # 根據預測天數選擇對應的預測值
+            day_mapping = {1: 0, 5: 1, 10: 2, 20: 3, 60: 4}
+
+            if predict_days in day_mapping:
+                predicted_price = y_pred[0][day_mapping[predict_days]]
+                change_pct = ((predicted_price - current_price) / current_price) * 100
+
+                # 計算信心度（簡化版本）
+                confidence = min(0.9, max(0.6, 1 - abs(change_pct) / 100))
+
+                result = {
+                    'predicted_price': float(predicted_price),
+                    'change_pct': float(change_pct),
+                    'confidence': float(confidence),
+                    'current_price': float(current_price),
+                    'prediction_days': predict_days
+                }
+
+                print(f"預測結果：{predict_days}天後價格 = {predicted_price:.2f}, 變化 = {change_pct:+.2f}%")
+                return result
+            else:
+                print(f"不支援的預測天數：{predict_days}")
+                return None
+
+        except Exception as e:
+            print(f"預測時發生錯誤: {e}")
+            return None
+
+# 全域預測器實例
+_predictor = None
+
+def get_predictor():
+    """獲取全域預測器實例"""
+    global _predictor
+    if _predictor is None:
+        _predictor = AdvancedStockPredictor()
+    return _predictor
+
+def advanced_lstm_predict(predict_days=5):
+    """
+    供 HUGING_FACE_V4.2 調用的預測函數
+
+    Args:
+        predict_days (int): 預測天數 (1, 5, 10, 20, 60)
+
+    Returns:
+        dict or None: 預測結果字典，包含 predicted_price, change_pct, confidence
+    """
+    try:
+        predictor = get_predictor()
+        return predictor.predict(predict_days)
+    except Exception as e:
+        print(f"advanced_lstm_predict 錯誤: {e}")
+        return None
+
+def train_model():
+    """
+    訓練模型的主函數
+    """
+    print("開始訓練進階LSTM模型...")
+    predictor = AdvancedStockPredictor()
+
+    if predictor.train(epochs=50, batch_size=16):
+        print("模型訓練成功！")
+        return True
+    else:
+        print("模型訓練失敗！")
+        return False
+
+if __name__ == "__main__":
+    # 直接執行時進行模型訓練
+    train_model()

taiwan_stock_predictor.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07d2fae4191bf2bf62428fdb11f4350198209e9dea796d2e19afc06a496a10b
+size 3088553

taiwan_stock_predictor_scaler_X.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca04b01833f094cd3c49d51169274dcd35442683bf9a5ed504888b0030fcb69
+size 791

taiwan_stock_predictor_scaler_y.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdbf13c4e4ba400326b2611b2620ebc8a5437adc25e89d99c8b9a63dd6ef9fb
+size 719