diff --git "a/app.py" "b/app.py" --- "a/app.py" +++ "b/app.py" @@ -1,13 +1,13 @@ -# HUGING_FACE_V3.2.0.py (整合 Bert_predict 和 XGBoost 版本 - 新特徵版本) +# HUGING_FACE_V3.1.3.py (整合 Bert_predict 和 XGBoost 版本) # 系統套件 import os from datetime import datetime, timedelta -import google.generativeai as genai +import google.generativeai as genai import pandas as pd import numpy as np import yfinance as yf -from dash import Dash, dcc, html, callback, Input, Output, State +from dash import Dash, dcc, html, callback import dash import plotly.express as px import plotly.graph_objects as go @@ -16,8 +16,6 @@ import re from bs4 import BeautifulSoup import requests import time # 引用 time 模組以處理時間戳 -import warnings -warnings.filterwarnings('ignore') # ========================= 引用外部模組 START ========================= # 引用您組員的預測器程式 @@ -26,505 +24,12 @@ from Bert_predict import BertPredictor # 引用新的模型預測器 from model_predictor import XGBoostModel # ========================== 引用外部模組 END ========================== -# ========================= 新增：交易回測模組 START ========================= -class TradingBacktester: - def __init__(self, initial_capital=1000000, max_position_ratio=0.8, batch_ratio=0.2): - """ - 初始化交易回測器 - - Args: - initial_capital: 初始資金 (預設100萬) - max_position_ratio: 最大持倉比例 (預設80%) - batch_ratio: 每次分批交易比例 (預設20%) - """ - self.initial_capital = initial_capital - self.max_position_ratio = max_position_ratio - self.batch_ratio = batch_ratio - - # 交易記錄 - self.trades = [] - self.portfolio_value = [] - self.positions = [] - self.cash_history = [] - - # 策略參數 - self.trend_threshold = 0.5 # 趨勢判斷閾值 (0.5%) - self.min_trend_days = 3 # 最少連續趨勢天數 - - def get_trend_signal(self, predictions): - """ - 根據預測結果判斷趨勢信號 - - Args: - predictions: dict包含1,5,10,20日預測結果 - - Returns: - signal: 1(買進), -1(賣出), 0(持有) - strength: 信號強度 (0-1) - """ - # 提取預測漲跌幅 - pred_1d = predictions.get('1d', 0) - pred_5d = predictions.get('5d', 0) - pred_10d = predictions.get('10d', 0) - pred_20d = predictions.get('20d', 0) - - # 計算趨勢分數 - trend_score = 0 - total_weight = 0 - - # 權重設計：近期權重較高 - weights = {'1d': 0.4, '5d': 0.3, '10d': 0.2, '20d': 0.1} - - for period, pred in [('1d', pred_1d), ('5d', pred_5d), ('10d', pred_10d), ('20d', pred_20d)]: - if abs(pred) > self.trend_threshold: - trend_score += np.sign(pred) * weights[period] - total_weight += weights[period] - - # 正規化趨勢分數 - if total_weight > 0: - trend_score = trend_score / total_weight - - # 判斷信號強度 - strength = abs(trend_score) - - # 決定交易信號 - if trend_score > 0.3: # 明顯上漲趨勢 - return 1, strength - elif trend_score < -0.3: # 明顯下跌趨勢 - return -1, strength - else: # 盤整或趨勢不明 - return 0, strength - - def calculate_position_size(self, signal, strength, current_cash, current_price, current_position): - """ - 計算交易部位大小 - - Args: - signal: 交易信號 - strength: 信號強度 - current_cash: 當前現金 - current_price: 當前價格 - current_position: 當前持股數量 - - Returns: - shares_to_trade: 交易股數 (正數買入，負數賣出) - """ - max_position_value = self.initial_capital * self.max_position_ratio - max_shares = int(max_position_value / current_price) - - if signal == 1: # 買進信號 - # 計算可買進的最大股數 - available_cash = current_cash * self.batch_ratio * strength - max_buy_shares = int(available_cash / current_price) - - # 確保不超過最大持倉限制 - remaining_capacity = max_shares - current_position - shares_to_buy = min(max_buy_shares, remaining_capacity) - - return max(0, shares_to_buy) - - elif signal == -1: # 賣出信號 - # 計算要賣出的股數 - sell_ratio = self.batch_ratio * strength - shares_to_sell = int(current_position * sell_ratio) - - return -min(shares_to_sell, current_position) - - return 0 - - def simulate_predictions(self, data, predictor_func): - """ - 模擬歷史預測結果 - - 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 = {} - - # 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 - predictions = {} - for days in [1, 5, 10, 20]: - pred_result = predictor_func(historical_data, days) - if pred_result: - 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): - """ - 執行回測 - - Args: - stock_data: 股價資料 - predictor_func: 預測函數 - start_date: 回測開始日期 - end_date: 回測結束日期 - - Returns: - results: 回測結果字典 - """ - # 重置交易記錄 - self.trades = [] - self.portfolio_value = [] - self.positions = [] - self.cash_history = [] - - # 設定回測期間 - if start_date: - stock_data = stock_data[stock_data.index >= start_date] - if end_date: - stock_data = stock_data[stock_data.index <= end_date] - - if len(stock_data) < 100: - raise ValueError("資料不足，無法進行回測") - - print("開始生成歷史預測...") - predictions_history = self.simulate_predictions(stock_data, predictor_func) - - # 初始化 - current_cash = self.initial_capital - current_position = 0 - - print("開始執行回測...") - - # 逐日回測 - for date in stock_data.index: - if date not in predictions_history: - continue - - current_price = stock_data.loc[date, 'Close'] - predictions = predictions_history[date] - - # 獲取交易信號 - signal, strength = self.get_trend_signal(predictions) - - # 計算交易量 - shares_to_trade = self.calculate_position_size( - signal, strength, current_cash, current_price, current_position - ) - - # 執行交易 - if shares_to_trade != 0: - trade_value = shares_to_trade * current_price - - # 更新現金和持倉 - current_cash -= trade_value - current_position += shares_to_trade - - # 記錄交易 - self.trades.append({ - 'date': date, - 'signal': signal, - 'shares': shares_to_trade, - 'price': current_price, - 'value': trade_value, - 'strength': strength, - 'predictions': predictions.copy() - }) - - # 計算投資組合價值 - portfolio_val = current_cash + current_position * current_price - - # 記錄每日狀態 - self.portfolio_value.append({ - 'date': date, - 'portfolio_value': portfolio_val, - 'cash': current_cash, - 'position_value': current_position * current_price, - 'position_shares': current_position, - 'price': current_price - }) - - # 計算績效指標 - results = self._calculate_performance_metrics(stock_data) - - print(f"回測完成！總交易次數: {len(self.trades)}") - return results - - def _calculate_performance_metrics(self, stock_data): - """計算績效指標""" - if not self.portfolio_value: - return {} - - portfolio_df = pd.DataFrame(self.portfolio_value) - portfolio_df.set_index('date', inplace=True) - - # 基本績效 - final_value = portfolio_df['portfolio_value'].iloc[-1] - total_return = (final_value / self.initial_capital - 1) * 100 - - # 基準比較（買入持有策略） - initial_price = stock_data['Close'].iloc[0] - final_price = stock_data['Close'].iloc[-1] - benchmark_return = (final_price / initial_price - 1) * 100 - - # 計算波動率 - portfolio_returns = portfolio_df['portfolio_value'].pct_change().dropna() - annual_volatility = portfolio_returns.std() * np.sqrt(252) * 100 - - # 最大回撤 - rolling_max = portfolio_df['portfolio_value'].expanding().max() - drawdown = (portfolio_df['portfolio_value'] - rolling_max) / rolling_max - max_drawdown = drawdown.min() * 100 - - # 夏普比率 (假設無風險利率為2%) - risk_free_rate = 0.02 - excess_return = total_return/100 - risk_free_rate - sharpe_ratio = excess_return / (annual_volatility/100) if annual_volatility > 0 else 0 - - # 交易統計 - trades_df = pd.DataFrame(self.trades) if self.trades else pd.DataFrame() - buy_trades = len(trades_df[trades_df['signal'] == 1]) if not trades_df.empty else 0 - sell_trades = len(trades_df[trades_df['signal'] == -1]) if not trades_df.empty else 0 - - results = { - 'final_value': final_value, - 'total_return': total_return, - 'benchmark_return': benchmark_return, - 'excess_return': total_return - benchmark_return, - 'annual_volatility': annual_volatility, - 'max_drawdown': max_drawdown, - 'sharpe_ratio': sharpe_ratio, - 'total_trades': len(self.trades), - 'buy_trades': buy_trades, - 'sell_trades': sell_trades, - 'win_rate': self._calculate_win_rate(), - 'portfolio_df': portfolio_df, - 'trades_df': trades_df, - 'initial_capital': self.initial_capital - } - - return results - - def _calculate_win_rate(self): - """計算勝率""" - if len(self.trades) < 2: - return 0 - - # 簡化的勝率計算：檢查每筆交易後的價格變化 - winning_trades = 0 - total_closed_trades = 0 - - for i in range(len(self.trades) - 1): - current_trade = self.trades[i] - next_trade = self.trades[i + 1] - - if current_trade['signal'] == 1: # 買入交易 - price_change = (next_trade['price'] - current_trade['price']) / current_trade['price'] - if price_change > 0: - winning_trades += 1 - total_closed_trades += 1 - - return (winning_trades / total_closed_trades * 100) if total_closed_trades > 0 else 0 - - def create_backtest_chart(self, results, stock_data): - """創建回測結果圖表""" - if 'portfolio_df' not in results: - return go.Figure() - - portfolio_df = results['portfolio_df'] - trades_df = results['trades_df'] - - # 創建子圖 - fig = make_subplots( - rows=3, cols=1, - shared_xaxes=True, - vertical_spacing=0.05, - row_heights=[0.5, 0.25, 0.25], - subplot_titles=('投資組合價值 vs 基準', '持倉變化', '交易信號') - ) - - # 第一個子圖：投資組合價值對比 - fig.add_trace( - go.Scatter( - x=portfolio_df.index, - y=portfolio_df['portfolio_value'], - mode='lines', - name='投資組合價值', - line=dict(color='blue', width=2) - ), - row=1, col=1 - ) - - # 基準線（買入持有） - benchmark_values = [] - initial_shares = self.initial_capital / stock_data['Close'].iloc[0] - for date in portfolio_df.index: - if date in stock_data.index: - benchmark_val = initial_shares * stock_data.loc[date, 'Close'] - benchmark_values.append(benchmark_val) - else: - benchmark_values.append(np.nan) - - fig.add_trace( - go.Scatter( - x=portfolio_df.index, - y=benchmark_values, - mode='lines', - name='買入持有基準', - line=dict(color='gray', width=2, dash='dash') - ), - row=1, col=1 - ) - - # 第二個子圖：持倉變化 - fig.add_trace( - go.Scatter( - x=portfolio_df.index, - y=portfolio_df['position_shares'], - mode='lines', - name='持股數量', - line=dict(color='green', width=2) - ), - row=2, col=1 - ) - - # 第三個子圖：價格和交易信號 - # 先畫價格線 - price_data = stock_data.reindex(portfolio_df.index, method='ffill') - fig.add_trace( - go.Scatter( - x=portfolio_df.index, - y=price_data['Close'], - mode='lines', - name='股價', - line=dict(color='black', width=1) - ), - row=3, col=1 - ) - - # 添加交易點 - if not trades_df.empty: - buy_trades = trades_df[trades_df['signal'] == 1] - sell_trades = trades_df[trades_df['signal'] == -1] - - if not buy_trades.empty: - fig.add_trace( - go.Scatter( - x=buy_trades['date'], - y=buy_trades['price'], - mode='markers', - name='買入', - marker=dict(color='red', size=8, symbol='triangle-up') - ), - row=3, col=1 - ) - - if not sell_trades.empty: - fig.add_trace( - go.Scatter( - x=sell_trades['date'], - y=sell_trades['price'], - mode='markers', - name='賣出', - marker=dict(color='green', size=8, symbol='triangle-down') - ), - row=3, col=1 - ) - - # 更新布局 - fig.update_layout( - title=f"交易策略回測結果", - height=800, - showlegend=True, - xaxis3_title="日期" - ) - - fig.update_yaxes(title_text="價值 (TWD)", row=1, col=1) - fig.update_yaxes(title_text="股數", row=2, col=1) - fig.update_yaxes(title_text="股價 (TWD)", row=3, col=1) - - return fig - - -def create_backtest_summary_card(results): - """創建回測摘要卡片""" - if not results: - return html.Div("回測結果為空", style={'color': 'red'}) - - # 決定績效顏色 - return_color = 'red' if results['total_return'] > 0 else 'green' - excess_color = 'red' if results['excess_return'] > 0 else 'green' - - return html.Div([ - html.Div([ - html.H4("交易策略回測摘要", style={'color': '#2C3E50', 'margin-bottom': '20px'}), - - # 核心績效指標 - html.Div([ - html.Div([ - html.H5("總報酬率", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['total_return']:+.2f}%", - style={'margin': '5px 0', 'color': return_color, 'font-weight': 'bold'}) - ], className="metric-item"), - - html.Div([ - html.H5("vs 買入持有", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['excess_return']:+.2f}%", - style={'margin': '5px 0', 'color': excess_color, 'font-weight': 'bold'}) - ], className="metric-item"), - - html.Div([ - html.H5("夏普比率", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['sharpe_ratio']:.2f}", - style={'margin': '5px 0', 'color': '#3498DB', 'font-weight': 'bold'}) - ], className="metric-item"), - - html.Div([ - html.H5("最大回撤", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['max_drawdown']:.2f}%", - style={'margin': '5px 0', 'color': '#E74C3C', 'font-weight': 'bold'}) - ], className="metric-item") - ], style={'display': 'flex', 'justify-content': 'space-around', 'margin-bottom': '20px'}), - - # 詳細統計 - html.Hr(), - html.Table([ - html.Tr([html.Td("最終投資組合價值"), html.Td(f"${results['final_value']:,.0f}")]), - html.Tr([html.Td("初始資金"), html.Td(f"${results.get('initial_capital', 1000000):,.0f}")]), - html.Tr([html.Td("年化波動率"), html.Td(f"{results['annual_volatility']:.2f}%")]), - html.Tr([html.Td("總交易次數"), html.Td(f"{results['total_trades']}")]), - html.Tr([html.Td("買入次數"), html.Td(f"{results['buy_trades']}")]), - html.Tr([html.Td("賣出次數"), html.Td(f"{results['sell_trades']}")]), - html.Tr([html.Td("交易勝率"), html.Td(f"{results['win_rate']:.1f}%")]) - ], style={'width': '100%', 'margin-top': '10px'}) - - ]) - ], style={ - 'padding': '25px', - 'background': 'white', - 'border-radius': '12px', - 'box-shadow': '0 4px 20px rgba(0,0,0,0.08)', - 'border': '1px solid #e9ecef', - 'margin-bottom': '20px' - }) -# ========================= 新增：交易回測模組 END ========================= -# ========================== 引用外部模組 END ========================== # ========================= 全域設定 START ========================= # 【【【模型切換���關】】】 # False: 使用簡易統計模型 (預設) # True: 使用 model_predictor.py 中的進階 XGBoost 模型 +# *** 注意：請務必設定為 True 才能啟用您的 XGBoost 模型 *** USE_ADVANCED_MODEL = True # ========================= CACHE 設定 START ========================= @@ -535,499 +40,216 @@ CACHE_DURATION_SECONDS = 8 * 60 * 60 # ========================== CACHE 設定 END ========================== # ========================== 全域設定 END ========================== -# 台股代號對應表 (移除台指期，因為它現在是獨立個塊) +# 台股代號對應表 (此處省略，與原檔案相同) TAIWAN_STOCKS = { - '元大台灣50': '0050.TW', - '台積電': '2330.TW', - '聯發科': '2454.TW', - '鴻海': '2317.TW', - '台達電': '2308.TW', - '廣達': '2382.TW', - '富邦金': '2881.TW', - '中信金': '2891.TW', - '國泰金': '2882.TW', - '聯電': '2303.TW', - '中華電': '2412.TW', - '玉山金': '2884.TW', - '兆豐金': '2886.TW', - '日月光投控': '3711.TW', - '華碩': '2357.TW', - '統一': '1216.TW', - '元大金': '2885.TW', - '智邦': '2345.TW', - '緯創': '3231.TW', - '華邦': '3034.TW', - '第一金': '2892.TW', - '瑞昱': '2379.TW', - '緯穎': '6669.TW', - '永豐金': '2890.TW', - '合庫金': '5880.TW', - '臺南金': '2880.TW', - '台光電': '2383.TW', - '世芯-KY': '3661.TW', - '奇鋐': '3017.TW', - '凱基金': '2883.TW', - '大立光': '3008.TW', - '長榮': '2603.TW', - '光寶科': '2301.TW', - '中鋼': '2002.TW', - '中租-KY': '5871.TW', - '國巨': '2327.TW', - '台新金': '2887.TW', - '上海商銀': '5876.TW', - '台泥': '1101.TW', - '台灣大': '3045.TW', - '和碩': '4938.TW', - '遠傳': '4904.TW', - '和泰車': '2207.TW', - '研華': '2395.TW', - '台塑': '1301.TW', - '統一超': '2912.TW', - '藥華藥': '6446.TW', - '南亞': '1303.TW', - '陽明': '2609.TW', - '謝海': '2615.TW', - '台塑化': '6505.TW', - '慧洋-KY': '2637.TW', - '上銀': '2049.TW', - '南亞科': '2408.TW', - '旺宏': '2337.TW', - '譜瑞-KY': '4966.TWO', - '貿聯-KY': '3665.TW', - '驊訊': '6870.TWO', - '穩懋': '3105.TWO', - '金居': '8358.TWO', - '緯軟': '4953.TWO', - '宏捷科': '8086.TWO', - '漢磊': '3707.TWO', - '茂矽': '2342.TW', - '騰雲': '6870.TWO', - '順德': '2351.TW', - '明泰': '3380.TW', + '元大台灣50': '0050.TW', '台積電': '2330.TW', '聯發科': '2454.TW', '鴻海': '2317.TW', + '台達電': '2308.TW', '廣達': '2382.TW', '富邦金': '2881.TW', '中信金': '2891.TW', + '國泰金': '2882.TW', '聯電': '2303.TW', '中華電': '2412.TW', '玉山金': '2884.TW', + '兆豐金': '2886.TW', '日月光投控': '3711.TW', '華碩': '2357.TW', '統一': '1216.TW', + '元大金': '2885.TW', '智邦': '2345.TW', '緯創': '3231.TW', '聯詠': '3034.TW', + '第一金': '2892.TW', '瑞昱': '2379.TW', '緯穎': '6669.TWO', '永豐金': '2890.TW', + '合庫金': '5880.TW', '華南金': '2880.TW', '台光電': '2383.TW', '世芯-KY': '3661.TWO', + '奇鋐': '3017.TW', '凱基金': '2883.TW', '大立光': '3008.TW', '長榮': '2603.TW', + '光寶科': '2301.TW', '中鋼': '2002.TW', '中租-KY': '5871.TW', '國巨': '2327.TW', + '台新金': '2887.TW', '上海商銀': '5876.TW', '台泥': '1101.TW', '台灣大': '3045.TW', + '和碩': '4938.TW', '遠傳': '4904.TW', '和泰車': '2207.TW', '研華': '2395.TW', + '台塑': '1301.TW', '統一超': '2912.TW', '藥華藥': '6446.TWO', '南亞': '1303.TW', + '陽明': '2609.TW', '萬海': '2615.TW', '台塑化': '6505.TW', '慧洋-KY': '2637.TW', + '上銀': '2049.TW', '南亞科': '2408.TW', '旺宏': '2337.TW', '譜瑞-KY': '4966.TWO', + '貿聯-KY': '3665.TW', '驊訊': '6870.TWO', '穩懋': '3105.TWO' } -# 產業分類 +# 產業分類 (此處省略，與原檔案相同) INDUSTRY_MAPPING = { - '0050.TW': 'ETF', - '2330.TW': '半導體', - '2454.TW': '半導體', - '2317.TW': '電子組件', - '2308.TW': '電子', - '2382.TW': '電子', - '2881.TW': '金融', - '2891.TW': '金融', - '2882.TW': '金融', - '2303.TW': '半導體', - '2412.TW': '電信', - '2884.TW': '金融', - '2886.TW': '金融', - '3711.TW': '半導體', - '2357.TW': '電子', - '1216.TW': '食品', - '2885.TW': '金融', - '2345.TW': '網通設備', - '3231.TW': '電子', - '3034.TW': '半導體', - '2892.TW': '金融', - '2379.TW': '半導體', - '6669.TW': '電子', - '2890.TW': '金融', - '5880.TW': '金融', - '2880.TW': '金融', - '2383.TW': '電子', - '3661.TW': '半導體', - '3017.TW': '電子', - '2883.TW': '金融', - '3008.TW': '光學', - '2603.TW': '航運', - '2301.TW': '電子', - '2002.TW': '鋼鐵', - '5871.TW': '金融', - '2327.TW': '電子被動元件', - '2887.TW': '金融', - '5876.TW': '金融', - '1101.TW': '營建', - '3045.TW': '電信', - '4938.TW': '電子', - '4904.TW': '電信', - '2207.TW': '汽車', - '2395.TW': '電腦周邊', - '1301.TW': '塑膠', - '2912.TW': '百貨', - '6446.TW': '生技', - '1303.TW': '塑膠', - '2609.TW': '航運', - '2615.TW': '航運', - '6505.TW': '塑膠', - '2637.TW': '散裝航運', - '2049.TW': '工具機', - '2408.TW': 'DRAM', - '2337.TW': 'NFLSH', - '4966.TWO': '高速傳輸', - '3665.TW': '連接器', - '6870.TWO': '軟體整合', - '3105.TWO': 'PA功率', - '8358.TWO': '銅箔', - '4953.TWO': '軟體', - '8086.TWO': 'PA功率', - '3707.TWO': '矽晶圓', - '2342.TW': '矽晶圓', - '2351.TW': '導線架', - '6870.TWO': '軟體整合', - '3380.TW': '網通' - + '0050.TW': 'ETF', '2330.TW': '半導體', '2454.TW': '半導體', '2317.TW': '電子組件', + '2308.TW': '電子', '2382.TW': '電子', '2881.TW': '金融', '2891.TW': '金融', '2882.TW': '金融', + '2303.TW': '半導體', '2412.TW': '電信', '2884.TW': '金融', '2886.TW': '金融', '3711.TW': '半導體', + '2357.TW': '電子', '1216.TW': '食品', '2885.TW': '金融', '2345.TW': '網通設備', '3231.TW': '電子', + '3034.TW': '半導體', '2892.TW': '金融', '2379.TW': '半導體', '6669.TWO': '電子', '2890.TW': '金融', + '5880.TW': '金融', '2880.TW': '金融', '2383.TW': '電子', '3661.TWO': '半導體', '3017.TW': '電子', + '2883.TW': '金融', '3008.TW': '光學', '2603.TW': '航運', '2301.TW': '電子', '2002.TW': '鋼鐵', + '5871.TW': '金融', '2327.TW': '電子被動元件', '2887.TW': '金融', '5876.TW': '金融', '1101.TW': '營建', + '3045.TW': '電信', '4938.TW': '電子', '4904.TW': '電信', '2207.TW': '汽車', '2395.TW': '電腦周邊', + '1301.TW': '塑膠', '2912.TW': '百貨', '6446.TWO': '生技', '1303.TW': '塑膠', '2609.TW': '航運', + '2615.TW': '航運', '6505.TW': '塑膠', '2637.TW': '散裝航運', '2049.TW': '工具機', '2408.TW': 'DRAM', + '2337.TW': 'NFLSH', '4966.TWO': '高速傳輸', '3665.TW': '連接器', '6870.TWO': '軟體整合', '3105.TWO': 'PA功率' } -# ========================= 風險管理模組 START ========================= -class RiskAnalyzer: - def __init__(self): - self.risk_free_rate = 0.01 # 假設無風險利率為1% +# 模型的特徵欄位順序 (與訓練腳本完全一致) +MODEL_FEATURE_COLUMNS = [ + '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' +] - def calculate_var(self, returns, confidence_level=0.05): - """計算風險價值 (Value at Risk)""" - if returns is None or len(returns) < 30: - return None - return np.percentile(returns.dropna(), confidence_level * 100) +def get_stock_data(symbol, period='2y'): + """獲取股票資料""" + try: + # 確保下載足夠的數據來計算所有指標 + start_date = (datetime.now() - timedelta(days=730)).strftime('%Y-%m-%d') + data = yf.download(symbol, start=start_date, progress=False) + if data.empty: + print(f"警告: {symbol} 數據為空。") + return pd.DataFrame() + # 欄位名稱統一為大寫開頭，以利後續處理 + data.columns = [col.capitalize() for col in data.columns] + return data + except Exception as e: + print(f"獲取 {symbol} 數據時發生錯誤: {e}") + return pd.DataFrame() - def calculate_sharpe_ratio(self, returns): - """計算夏普比率""" - if returns is None or returns.std() == 0: - return 0 - excess_returns = returns - self.risk_free_rate / 252 - return excess_returns.mean() / excess_returns.std() * np.sqrt(252) - def calculate_max_drawdown(self, prices): - """計算最大回撤""" - if prices is None or prices.empty: - return None - # 使用 pct_change() 計算每日報酬率，並加 1 - daily_returns = prices.pct_change() + 1 - # 計算累積乘積，填充 NA 值為 1 - cumulative = daily_returns.cumprod().fillna(1) - rolling_max = cumulative.expanding().max() - drawdown = (cumulative - rolling_max) / rolling_max - return drawdown.min() +def create_new_features(df, dji_df, sox_df): + """ + 【【核心修正】】 + 創建與訓練腳本完全一致的新技術指標特徵。 + """ + # 確保索引是 datetime 格式 + df.index = pd.to_datetime(df.index) + dji_df.index = pd.to_datetime(dji_df.index) + sox_df.index = pd.to_datetime(sox_df.index) - def calculate_beta(self, stock_returns, market_returns): - """計算貝塔值""" - if stock_returns is None or market_returns is None or len(stock_returns) != len(market_returns) or len( - stock_returns) < 30: - return None - - # 合併並去除NA值以對齊數據 - combined = pd.DataFrame({'stock': stock_returns, 'market': market_returns}).dropna() - if len(combined) < 30: - return None + # 重新命名欄位以符合訓練腳本 + df = df.rename(columns={'Close': 'close', 'Volume': 'volume'}) - covariance = np.cov(combined['stock'], combined['market'])[0][1] - market_variance = np.var(combined['market']) - return covariance / market_variance if market_variance != 0 else 0 -# ========================== 風險管理模組 END ========================== + # 1. return_t-1 — 前一日報酬率 + df['return_t-1'] = df['close'].pct_change() -def get_stock_data(symbol, period='1y'): - """獲取股票資料""" - try: - stock = yf.Ticker(symbol) - data = stock.history(period=period) - if data.empty and symbol == 'TXF=F': - stock = yf.Ticker('0050.TW') - data = stock.history(period=period) - if data.empty: - stock = yf.Ticker('^TWII') - data = stock.history(period=period) - return data - except: - return pd.DataFrame() + # 2. return_t-5 — 過去 5 日累積報酬率 + df['return_t-5'] = (df['close'] / df['close'].shift(5) - 1) -def get_us_market_data(): - """獲取美股指數數據""" - try: - indices = { - 'DJI': '^DJI', # 道瓊指數 - 'NAS': '^IXIC', # 那斯達克 - 'SOX': '^SOX', # 費城半導體 - 'S&P_500': '^GSPC', # S&P 500 - 'TSM_ADR': 'TSM' # 台積電ADR - } - - market_data = {} - for name, symbol in indices.items(): - try: - data = yf.Ticker(symbol).history(period='5d') - if not data.empty: - market_data[name] = data['Close'].iloc[-1] - else: - market_data[name] = 0 - except: - market_data[name] = 0 - - return market_data - except Exception as e: - print(f"獲取美股數據時發生錯誤: {e}") - return {'DJI': 0, 'NAS': 0, 'SOX': 0, 'S&P_500': 0, 'TSM_ADR': 0} + # 3. MA5_close — 5 日移動平均價 + df['MA5_close'] = df['close'].rolling(window=5).mean() -def get_exchange_rate(): - """獲取台幣匯率 (USD/TWD)""" - try: - data = yf.Ticker('USDTWD=X').history(period='5d') - if not data.empty: - return data['Close'].iloc[-1] - else: - return 31.5 # 預設值 - except: - return 31.5 + # 4. volatility_5d — 5 日報酬標準差（短期波動） + 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() + df['volume_ratio_5d'] = df['volume'] / df['volume_5d_avg'] + + # 6. MACD_diff — MACD - signal + exp1 = df['close'].ewm(span=12, adjust=False).mean() + exp2 = df['close'].ewm(span=26, adjust=False).mean() + macd_line = exp1 - exp2 + signal_line = macd_line.ewm(span=9, adjust=False).mean() + df['MACD_diff'] = macd_line - signal_line + df['MACDvol'] = (macd_line - signal_line) # 訓練腳本中使用 MACD Histogram 作為 MACDvol + + # 7. dji_return_t-1 & 8. sox_return_t-1 + dji_df['dji_return_t-1'] = dji_df['Close'].pct_change() + sox_df['sox_return_t-1'] = sox_df['Close'].pct_change() + # 合併美股數據 + df = df.merge(dji_df[['dji_return_t-1']], left_index=True, right_index=True, how='left') + df = df.merge(sox_df[['sox_return_t-1']], left_index=True, right_index=True, how='left') + + # 9. NEWS (由外部傳入，此處先設為0) + df['NEWS'] = 0 + + # 10. RSI_14 + 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)) + + # 11. ADX + high_minus_low = df['High'] - df['Low'] + high_minus_close_prev = abs(df['High'] - df['close'].shift(1)) + low_minus_close_prev = abs(df['Low'] - df['close'].shift(1)) + tr = pd.concat([high_minus_low, high_minus_close_prev, low_minus_close_prev], axis=1).max(axis=1) + atr = tr.rolling(window=14).mean() + up_move = df['High'] - df['High'].shift(1) + down_move = df['Low'].shift(1) - df['Low'] + plus_dm = ((up_move > down_move) & (up_move > 0)) * up_move + minus_dm = ((down_move > up_move) & (down_move > 0)) * down_move + plus_di = 100 * (plus_dm.ewm(alpha=1/14, min_periods=0, adjust=False).mean() / atr) + minus_di = 100 * (minus_dm.ewm(alpha=1/14, min_periods=0, adjust=False).mean() / atr) + dx = 100 * (abs(plus_di - minus_di) / (plus_di + minus_di)) + df['ADX'] = dx.ewm(alpha=1/14, min_periods=0, adjust=False).mean() + + # 12. volume_weighted_return + df['volume_weighted_return'] = abs(df['return_t-1']) * df['volume'] + + # 處理 NaN 值 + df.fillna(method='ffill', inplace=True) + df.fillna(0, inplace=True) + + return df def simple_statistical_predict(data, predict_days=5): - """【備用模型】簡化的統計預測模型 - 更新為輸出漲幅百分比格式。""" - if len(data) < 60: - return None - + """【備用模型】簡化的統計預測模型。""" + if len(data) < 60: + return {'predicted_price': data['Close'].iloc[-1], 'change_pct': 0, 'confidence': 0.5} prices = data['Close'].values - current_price = prices[-1] - + # ... (其餘邏輯與原檔案相同) ma_short = np.mean(prices[-5:]) ma_medium = np.mean(prices[-20:]) ma_long = np.mean(prices[-60:]) recent_trend = np.polyfit(range(20), prices[-20:], 1)[0] volatility = np.std(prices[-20:]) / np.mean(prices[-20:]) - base_change = recent_trend * predict_days trend_factor = 1.0 + (0.02 if ma_short > ma_medium > ma_long else -0.02 if ma_short < ma_medium < ma_long else 0) noise_factor = np.random.normal(1, volatility * 0.1) - predicted_price = current_price * trend_factor + base_change + (current_price * noise_factor * 0.01) - - # 【重要更新】計算漲幅百分比 - change_pct = ((predicted_price - current_price) / current_price) * 100 - + predicted_price = prices[-1] * trend_factor + base_change + (prices[-1] * noise_factor * 0.01) + change_pct = ((predicted_price - prices[-1]) / prices[-1]) * 100 return { - 'predicted_price': predicted_price, - 'change_pct': change_pct, # 現在這個值是真正的漲幅百分比 + 'predicted_price': predicted_price, + 'change_pct': change_pct, 'confidence': max(0.6, 1 - volatility * 2) } -def calculate_new_features(df): - """ - 計算新的技術指標特徵 - 針對新特徵需求 - """ - if df.empty: - return df - - # 1. 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 - 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. 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） - df['volatility_5d'] = df['return_t-1'].rolling(window=5).std() - - # 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 - 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 - - # 移除輔助欄位 - if 'volume_5d_avg' in df.columns: - df = df.drop('volume_5d_avg', axis=1) - - return df - def advanced_xgboost_predict(predict_days=5): """ - 【進階模型】使用 XGBoost 模型進行預測 - 新特徵版本 - 【重要更新】現在輸出漲幅百分比而非絕對價格 + 【進階模型】使用 XGBoost 模型進行預測 """ try: - print(f"開始使用 XGBoost 模型進行 {predict_days} 天預測（漲幅百分比版本）...") - + print(f"開始使用 XGBoost 模型進行 {predict_days} 天預測...") + # 初始化 XGBoost 模型 xgb_model = XGBoostModel() - - # 獲取台指期數據 (作為主要標的) - taiex_data = get_stock_data('^TWII', '2y') - if taiex_data.empty or len(taiex_data) < 60: - print("台指期數據不足，無法進行XGBoost預測") - return None - - # 計算技術指標（包含舊的指標） - taiex_data = calculate_technical_indicators(taiex_data) - - # 計算新特徵 - taiex_data = calculate_new_features(taiex_data) - - # 獲取美股指數數據來計算外部指標 - us_market_data = get_us_market_data() - - # 獲取新聞情緒分數 - try: - if predictor is not None: - sentiment_score_raw = predictor.get_news_index() - if sentiment_score_raw is None: - sentiment_score_raw = 0 - else: - sentiment_score_raw = 0 - except: - sentiment_score_raw = 0 - - # 準備特徵數據 (使用最新的數據點) - latest_data = taiex_data.iloc[-1] - - # 取得昨日收盤價 - 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', - ] - - # 添加美股指標（如果有數據的話） - dji_return = 0 - sox_return = 0 - - # 嘗試獲取美股前一日報酬率 - try: - dji_data = get_stock_data('^DJI', '5d') - if not dji_data.empty and len(dji_data) >= 2: - dji_return = (dji_data['Close'].iloc[-1] / dji_data['Close'].iloc[-2] - 1) - except: - pass - - try: - sox_data = get_stock_data('^SOX', '5d') - if not sox_data.empty and len(sox_data) >= 2: - sox_return = (sox_data['Close'].iloc[-1] / sox_data['Close'].iloc[-2] - 1) - except: - pass - - # 檢查並處理 NaN 值，建立特徵狀態記錄 - feature_status = {} - features_list = [] - 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 - - 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'} - - feature_names.append(feature) - # 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' - } + # 獲取主要標的、道瓊、費半的歷史數據 + taiex_data = get_stock_data('^TWII') + dji_data = get_stock_data('^DJI') + sox_data = get_stock_data('^SOX') - # 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' - } + if taiex_data.empty or dji_data.empty or sox_data.empty or len(taiex_data) < 60: + print("主要或美股指數數據不足，無法進行XGBoost預測") + return None - # 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') + # 創建特徵 + processed_data = create_new_features(taiex_data, dji_data, sox_data) - # 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) - - # 詳細的資料驗證日誌 - print("=" * 60) - print("XGBoost 模型輸入特徵檢查報告 (漲幅百分比版本)") - print("=" * 60) - - print(f"總特徵數量: {len(features_list)} 個") - print(f"新聞情緒分數: {sentiment_score_raw:.6f}") - - # 特徵詳細狀態 - print("\n特徵狀態詳情:") - 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+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)) - total_features = len(feature_status) - completeness = (real_features / total_features) * 100 if total_features > 0 else 0 - - print(f"\n特徵完整性:") - print(f" 實際計算特徵: {real_features}/{total_features} ({completeness:.1f}%)") - if completeness < 70: - print(" 警告: 超過30%的特徵使用預設值，可能影響預測準確性") - else: - print(" 特徵完整性良好") - - # 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+1:2d}] {name:18s}: {value:12.6f}") + # 獲取新聞情緒分數 + news_score = 0 + if predictor is not None: + try: + news_score = predictor.get_news_index() + if news_score is None: + news_score = 0 + except Exception as e: + print(f"獲取新聞分數失敗: {e}") + news_score = 0 - print("=" * 60) + # 將最新的新聞分數更新到最後一筆數據 + processed_data['NEWS'].iloc[-1] = news_score + + # 準備特徵 DataFrame (只取最後一筆，並確保欄位順序正確) + latest_features = processed_data.iloc[-1:][MODEL_FEATURE_COLUMNS] + + print("準備送入模型的特徵數據 (最後一筆):") + print(latest_features.to_string()) # 進行預測 - predictions = xgb_model.predict('xgboost_model', input_df) + predictions = xgb_model.predict('xgboost_model', latest_features) - # 【重要更新】處理新的漲幅百分比輸出格式 + # 根據預測天數選擇對應的預測值 pred_mapping = { - 1: 'Change_pct_t1_pred', # 1天後漲幅% - 5: 'Change_pct_t5_pred', # 5天後漲幅% - 10: 'Change_pct_t10_pred', # 10天後漲幅% - 20: 'Change_pct_t20_pred' # 20天後漲幅% + 1: 'Change_pct_t1_pred', + 5: 'Change_pct_t5_pred', + 10: 'Change_pct_t10_pred', + 20: 'Change_pct_t20_pred' } # 找到最接近的預測天數 @@ -1035,34 +257,29 @@ def advanced_xgboost_predict(predict_days=5): closest_day = min(available_days, key=lambda x: abs(x - predict_days)) pred_key = pred_mapping[closest_day] - # 【關鍵修改】現在直接取得漲幅百分比 - predicted_change_pct = predictions[pred_key] - - # 【新增】為了兼容性，計算預測價格（僅供參考） - current_price = latest_data['Close'] - predicted_price = current_price * (1 + predicted_change_pct / 100) + change_pct = predictions[pred_key] + current_price = taiex_data['Close'].iloc[-1] + predicted_price = current_price * (1 + change_pct / 100) print(f"XGBoost 預測完成:") - print(f"- 預測天數: {predict_days} (使用 {closest_day} 天模型)") - print(f"- 當前價格: {current_price:.2f}") - print(f"- 預測漲幅: {predicted_change_pct:+.2f}%") - print(f"- 預測價格: {predicted_price:.2f} (參考)") - print(f"- 使用特徵數: {len(features_list)} 個") - print(f"- 特徵完整性: {completeness:.1f}%") + print(f"- 預測天期: {predict_days} 天 (使用 {closest_day} 天模型)") + print(f"- 當前指數: {current_price:.2f}") + print(f"- 預測漲跌幅: {change_pct:+.2f}%") + print(f"- 預測指數: {predicted_price:.2f}") return { - 'predicted_price': predicted_price, # 為了兼容現有代碼 - 'change_pct': predicted_change_pct, # 【新增】直接的漲幅百分比 - 'confidence': max(0.6, min(0.85, completeness / 100)) # 根據特徵完整性調整信心度 + 'predicted_price': predicted_price, + 'change_pct': change_pct, + 'confidence': 0.85 # XGBoost 模型的信心度 (可調整) } except Exception as e: - print(f"XGBoost 預測時發生錯誤: {e}") + print(f"XGBoost 預測時發生嚴重錯誤: {e}") import traceback traceback.print_exc() return None -def get_prediction(data, predict_days=5): +def get_prediction(predict_days=5): """ 【【模型預測控制器】】 根據 USE_ADVANCED_MODEL 的設定，呼叫對應的預測模型。 @@ -1078,48 +295,42 @@ def get_prediction(data, predict_days=5): # 預設或降級時執行簡易模型 print(f"模式: 簡易統計模型 | 預測天期: {predict_days}天") + data = get_stock_data('^TWII', '2y') return simple_statistical_predict(data, predict_days) def calculate_technical_indicators(df): - """計算技術指標""" + """計算用於繪圖的技術指標""" if df.empty: return df - # 移動平均線 df['MA5'] = df['Close'].rolling(window=5).mean() df['MA20'] = df['Close'].rolling(window=20).mean() - # 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() + exp1 = df['Close'].ewm(span=12, adjust=False).mean() + exp2 = df['Close'].ewm(span=26, adjust=False).mean() df['MACD'] = exp1 - exp2 - df['MACD_Signal'] = df['MACD'].ewm(span=9).mean() + df['MACD_Signal'] = df['MACD'].ewm(span=9, adjust=False).mean() df['MACD_Histogram'] = df['MACD'] - df['MACD_Signal'] - # 布林通道 df['BB_Middle'] = df['Close'].rolling(window=20).mean() bb_std = df['Close'].rolling(window=20).std() df['BB_Upper'] = df['BB_Middle'] + (bb_std * 2) df['BB_Lower'] = df['BB_Middle'] - (bb_std * 2) - # 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() - + df['K'] = rsv.ewm(com=2, adjust=False).mean() + df['D'] = df['K'].ewm(com=2, adjust=False).mean() # 威廉指標 low_min_14 = df['Low'].rolling(window=14).min() high_max_14 = df['High'].rolling(window=14).max() df['Williams_R'] = -100 * (high_max_14 - df['Close']) / (high_max_14 - low_min_14) - # DMI 指標 df['up_move'] = df['High'] - df['High'].shift(1) df['down_move'] = df['Low'].shift(1) - df['Low'] @@ -1130,11 +341,12 @@ def calculate_technical_indicators(df): 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 +# 其餘輔助函式 (get_business_climate_data, get_pmi_data, generate_gemini_analysis, etc.) +# 與原檔案相同，此處省略以保持簡潔 def calculate_volume_profile(df, num_bins=50): - if df.empty or 'High' not in df.columns or 'Low' not in df.columns or 'Volume' not in df.columns: + if df.empty or 'High' not in df.columns or 'Low' not in df.columns or 'Volume' not in df.columns: return None, None, None all_prices = np.concatenate([df['High'].values, df['Low'].values]) min_price, max_price = all_prices.min(), all_prices.max() @@ -1144,7 +356,6 @@ def calculate_volume_profile(df, num_bins=50): hist, bin_edges = np.histogram(df_vol_profile['Price_Indicator'], bins=num_bins, range=(min_price, max_price), weights=df_vol_profile['Volume']) price_centers = (bin_edges[:-1] + bin_edges[1:]) / 2 return bin_edges, hist, price_centers - def get_business_climate_data(): try: if not os.path.exists('business_climate.csv'): return pd.DataFrame() @@ -1158,7 +369,6 @@ def get_business_climate_data(): except Exception as e: print(f"無法獲取景氣燈號資料: {str(e)}") return pd.DataFrame() - def get_pmi_data(): try: if not os.path.exists('taiwan_pmi.csv'): return pd.DataFrame() @@ -1173,25 +383,18 @@ def get_pmi_data(): except Exception as e: print(f"無法獲取 PMI 資料: {str(e)}") return pd.DataFrame() - def generate_gemini_analysis(stock_name, stock_symbol, period, data): - """ - 使用 Gemini API 生成基本面和市場展望分析。 - """ api_key = os.getenv("GEMINI_API_KEY") if not api_key: return "無法讀取 GEMINI API 金鑰", "請在系統環境變數中設定您的金鑰" - try: genai.configure(api_key=api_key) model = genai.GenerativeModel('gemini-1.5-flash') - price_change = ((data['Close'].iloc[-1] - data['Close'].iloc[0]) / data['Close'].iloc[0]) * 100 rsi_current = data['RSI'].iloc[-1] macd_current = data['MACD'].iloc[-1] macd_signal_current = data['MACD_Signal'].iloc[-1] industry = INDUSTRY_MAPPING.get(stock_symbol, '綜合') - prompt = f""" 請扮演一位專業、資深的台灣股市金融分析師。 我將提供一檔台股的即時技術指標數據，請你基於這些數據，結合你對這家公司、其所在產業以及當前市場趨勢的理解，為我生成一段專業的「基本面分析」和一段「市場展望與投資建議」。 @@ -1206,13 +409,12 @@ def generate_gemini_analysis(stock_name, stock_symbol, period, data): **你的任務:** 1. **基本面分析 (約 150 字):** - 　　 - 回覆前都先搜尋資料。 - 評論這家公司的產業地位、近期營運亮點或挑戰。 - 提及任何可能影響其基本面的關鍵因素 (例如：財報、法說會、政策、供應鏈變化等)。 - 請用專業、客觀的語氣撰寫。 2. **市場展望與投資建議 (約 150 字):** - - 基於上述所有資訊，提供對該��票的短期和中期市場展望(例如:是否有沉重賣壓，或是換手發生)。 + - 基於上述所有資訊，提供對該股票的短期和中期市場展望。 - 提出具體的投資建議，例如：適合何種類型的投資人、潛在的風險點。 - 請直接提供分析內容，不要包含任何問候語。 @@ -1220,7 +422,6 @@ def generate_gemini_analysis(stock_name, stock_symbol, period, data): 請嚴格按照以下格式回傳，使用"$$"作為兩個段落之間的分隔符： [基本面分析內容]$$[市場展望與投資建議內容] """ - response = model.generate_content(prompt) parts = response.text.split('$$') if len(parts) == 2: @@ -1228,13 +429,33 @@ def generate_gemini_analysis(stock_name, stock_symbol, period, data): market_outlook = parts[1].strip() return dcc.Markdown(fundamental_analysis), dcc.Markdown(market_outlook) else: - # Fallback for unexpected response format return dcc.Markdown("無法解析 Gemini 回應，請稍後再試。"), dcc.Markdown(response.text) - except Exception as e: error_message = f"呼叫 Gemini API 時發生錯誤: {str(e)}" print(error_message) return dcc.Markdown(error_message), dcc.Markdown("請檢查後台日誌或 API 金鑰設定") +def summarize_news_with_gemini(news_list: list) -> str: + api_key = os.getenv("GEMINI_API_KEY") + if not api_key: + return "錯誤：找不到 GEMINI_API_KEY。請在 Hugging Face Secrets 中設定。" + try: + genai.configure(api_key=api_key) + model = genai.GenerativeModel('gemini-1.5-flash') + formatted_news = "\n".join([f"- {news}" for news in news_list]) + prompt = f""" + 請扮演一位專業的金融市場分析師。 + 以下是幾則最新的英文財經新聞標題，請將它們整合成一段簡潔、流暢、約 200 字的繁體中文市場動態摘要，與利多哪些產業，利空哪些產業。 + 提供3段重點， + 請專注於可能影響市場情緒和股價的關鍵資訊，並直接提供摘要內容，不要包含任何額外的問候語或說明。 + + 英文新聞標題如下： + {formatted_news} + """ + response = model.generate_content(prompt) + return response.text + except Exception as e: + print(f"呼叫 Gemini API 時發生錯誤: {e}") + return f"無法生成新聞摘要，請稍後再試。錯誤訊息：{e}" # 建立 Dash 應用程式 app = dash.Dash(__name__, suppress_callback_exceptions=True) @@ -1248,14 +469,11 @@ except Exception as e: print(f"錯誤：新聞情緒分析模型初始化失敗 - {e}") predictor = None -# 應用程式佈局 -# 完整的 app.layout +# 應用程式佈局 (與原檔案相同，此處省略) app.layout = html.Div([ html.H1("台股分析儀表板", style={'text-align': 'center', 'margin-bottom': '30px'}), - - # AI助手與XGboost機器學習預測區塊 html.Div([ - html.H2("AI助手與XGboost機器學習預測 - 加權指數", style={'text-align': 'center','color': '#FFCC22','margin-bottom': '25px'}), + html.H2("🤖 AI深度學習預測 - 台指期指數", style={'text-align': 'center','color': '#FFCC22','margin-bottom': '25px'}), html.Div([ html.Div([ html.Label("預測期間:", style={'font-weight': 'bold', 'color': '#FFCC22'}), @@ -1270,39 +488,26 @@ app.layout = html.Div([ ]), html.Div([dcc.Graph(id='taiex-prediction-chart')], style={'margin-top': '20px'}) ], style={'background': 'linear-gradient(135deg, #667eea 0%, #764ba2 100%)','padding': '25px','border-radius': '15px','box-shadow': '0 8px 25px rgba(0,0,0,0.15)','color': 'white','margin-bottom': '40px'}), - - # 市場情緒與新聞分析區塊 - html.Div([ - html.Div([ - html.H4("市場情緒指標", style={'color': '#8E44AD'}), - html.Div(id='sentiment-gauge') - ], style={'width': '48%', 'display': 'inline-block', 'vertical-align': 'top'}), - html.Div([ - html.H4("關鍵新聞摘要", style={'color': '#27AE60'}), - html.Div(id='news-summary', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','max-height': '200px','overflow-y': 'auto'}) - ], style={'width': '48%', 'display': 'inline-block', 'margin-left': '4%', 'vertical-align': 'top'}) - ], style={'margin-top': '30px','padding': '20px','background': 'white','border-radius': '10px','box-shadow': '0 2px 10px rgba(0,0,0,0.1)'}), - - # 分析師觀點與市場解讀區塊 html.Div([ - html.H3("分析師觀點與市場解讀", style={'color': '#2E86AB', 'margin-bottom': '20px'}), + html.H3("📰 市場情緒與新聞分析", style={'color': '#E74C3C', 'margin-bottom': '20px'}), html.Div([ html.Div([ - html.H4("技術面分析", style={'color': '#A23B72', 'margin-bottom': '15px'}), - html.Div(id='technical-analysis-text', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','border-left': '4px solid #A23B72','min-height': '150px','font-size': '14px','line-height': '1.6'}) - ], style={'width': '48%', 'display': 'inline-block', 'vertical-align': 'top'}), + html.H4("市場情緒指標", style={'color': '#8E44AD'}), + html.Div(id='sentiment-gauge') + ], style={'width': '48%', 'display': 'inline-block'}), html.Div([ - html.H4("基本面分析 (AI 生成)", style={'color': '#F18F01', 'margin-bottom': '15px'}), - html.Div(id='fundamental-analysis-text', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','border-left': '4px solid #F18F01','min-height': '150px','font-size': '14px','line-height': '1.6'}) - ], style={'width': '48%', 'display': 'inline-block', 'margin-left': '4%', 'vertical-align': 'top'}) - ]), + html.H4("關鍵新聞摘要", style={'color': '#27AE60'}), + html.Div(id='news-summary', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','max-height': '200px','overflow-y': 'auto'}) + ], style={'width': '48%', 'display': 'inline-block', 'margin-left': '4%'}) + ]) + ], style={'margin-top': '30px','padding': '20px','background': 'white','border-radius': '10px','box-shadow': '0 2px 10px rgba(0,0,0,0.1)'}), + html.Div([ + html.H3("景氣燈號與 PMI 分析"), html.Div([ - html.H4("市場展望與投資建議 (AI 生成)", style={'color': '#C73E1D', 'margin-bottom': '15px', 'margin-top': '25px'}), - html.Div(id='market-outlook-text', style={'background': 'linear-gradient(135deg, #667eea 0%, #764ba2 100%)','color': 'white','padding': '20px','border-radius': '10px','min-height': '100px','font-size': '15px','line-height': '1.7','box-shadow': '0 4px 15px rgba(0,0,0,0.1)'}) + html.Div([dcc.Graph(id='business-climate-chart')], style={'width': '48%', 'display': 'inline-block'}), + html.Div([dcc.Graph(id='pmi-chart')], style={'width': '48%', 'display': 'inline-block', 'margin-left': '2%'}) ]) - ], style={'margin-top': '30px','padding': '25px','background': 'white','border-radius': '12px','box-shadow': '0 4px 20px rgba(0,0,0,0.08)','border': '1px solid #e9ecef'}), - - # 股票選擇與設定區塊 + ], style={'margin-top': '30px'}), html.Div([ html.Div([ html.Label("選擇股票:"), @@ -1319,16 +524,10 @@ app.layout = html.Div([ dcc.Dropdown(id='chart-type', options=[{'label': '線圖', 'value': 'line'},{'label': '蠟燭圖', 'value': 'candlestick'}], value='candlestick', style={'margin-bottom': '10px'}) ], style={'width': '30%', 'display': 'inline-block', 'margin-left': '5%', 'vertical-align': 'top'}) ], style={'margin-bottom': '30px'}), - - # 股票資訊卡片 html.Div(id='stock-info-cards', style={'margin-bottom': '30px'}), - - # 價格圖表 html.Div([html.Div([dcc.Graph(id='price-chart')], style={'width': '100%', 'display': 'inline-block', 'vertical-align': 'top'})]), - - # 進階技術指標分析區塊 html.Div([ - html.H3("進階技術指標分析", style={'margin-bottom': '20px'}), + html.H3("📊 進階技術指標分析", style={'margin-bottom': '20px'}), html.Div([ html.Label("選擇技術指標:", style={'font-weight': 'bold', 'margin-right': '10px'}), dcc.Dropdown(id='technical-indicator-selector', @@ -1338,27 +537,27 @@ app.layout = html.Div([ ], style={'margin-bottom': '20px'}), html.Div([dcc.Graph(id='advanced-technical-chart')]) ], style={'margin-top': '20px','padding': '20px','background': 'white','border-radius': '10px','box-shadow': '0 2px 10px rgba(0,0,0,0.1)'}), - - # 成交量圖表 html.Div([dcc.Graph(id='volume-chart')], style={'margin-top': '20px'}), - - # 產業表現分析 html.Div([html.H3("產業表現分析"), dcc.Graph(id='industry-analysis')], style={'margin-top': '30px'}), - - - - # 景氣燈號與PMI分析區塊 html.Div([ - html.H3("景氣燈號與 PMI 分析"), + html.H3("📊 分析師觀點與市場解讀", style={'color': '#2E86AB', 'margin-bottom': '20px'}), html.Div([ - html.Div([dcc.Graph(id='business-climate-chart')], style={'width': '48%', 'display': 'inline-block'}), - html.Div([dcc.Graph(id='pmi-chart')], style={'width': '48%', 'display': 'inline-block', 'margin-left': '2%'}) + html.Div([ + html.H4("📝 技術面分析", style={'color': '#A23B72', 'margin-bottom': '15px'}), + html.Div(id='technical-analysis-text', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','border-left': '4px solid #A23B72','min-height': '150px','font-size': '14px','line-height': '1.6'}) + ], style={'width': '48%', 'display': 'inline-block', 'vertical-align': 'top'}), + html.Div([ + html.H4("📈 基本面分析 (AI 生成)", style={'color': '#F18F01', 'margin-bottom': '15px'}), + html.Div(id='fundamental-analysis-text', style={'background': '#f8f9fa','padding': '15px','border-radius': '8px','border-left': '4px solid #F18F01','min-height': '150px','font-size': '14px','line-height': '1.6'}) + ], style={'width': '48%', 'display': 'inline-block', 'margin-left': '4%', 'vertical-align': 'top'}) + ]), + html.Div([ + html.H4("🎯 市場展望與投資建議 (AI 生成)", style={'color': '#C73E1D', 'margin-bottom': '15px', 'margin-top': '25px'}), + html.Div(id='market-outlook-text', style={'background': 'linear-gradient(135deg, #667eea 0%, #764ba2 100%)','color': 'white','padding': '20px','border-radius': '10px','min-height': '100px','font-size': '15px','line-height': '1.7','box-shadow': '0 4px 15px rgba(0,0,0,0.1)'}) ]) - ], style={'margin-top': '30px'}), - - # 多檔股票比較分析區塊 + ], style={'margin-top': '30px','padding': '25px','background': 'white','border-radius': '12px','box-shadow': '0 4px 20px rgba(0,0,0,0.08)','border': '1px solid #e9ecef'}), html.Div([ - html.H3("多檔股票比較分析", style={'margin-bottom': '20px'}), + html.H3("📊 多檔股票比較分析", style={'margin-bottom': '20px'}), html.Div([ html.Div([ html.Label("選擇比較股票（最多5檔）:", style={'font-weight': 'bold'}), @@ -1375,172 +574,61 @@ app.layout = html.Div([ html.Div([html.H4("比較結果", style={'color': '#2E86AB'}), html.Div(id='comparison-table')], style={'width': '33%', 'display': 'inline-block', 'margin-left': '2%', 'vertical-align': 'top'}) ]) ], style={'margin-top': '30px','padding': '20px','background': 'white','border-radius': '10px','box-shadow': '0 2px 10px rgba(0,0,0,0.1)'}), - - # 風險管理與投資組合分析區塊 - html.Div([ - html.H3("風險管理與投資組合分析", style={'margin-bottom': '20px', 'color': '#C0392B'}), - html.Div([ - html.Div([ - html.Label("選擇投資組合股票（最多5檔）:", style={'font-weight': 'bold'}), - dcc.Dropdown( - id='portfolio-stocks', - options=[{'label': name, 'value': symbol} for name, symbol in TAIWAN_STOCKS.items()], - value=['0050.TW', '2330.TW', '2454.TW'], - multi=True - ) - ], style={'width': '60%', 'display': 'inline-block', 'vertical-align': 'top'}), - html.Div([ - html.Label("分析期間:", style={'font-weight': 'bold'}), - dcc.Dropdown( - id='risk-period-dropdown', - options=[ - {'label': '6個月', 'value': '6mo'}, - {'label': '1年', 'value': '1y'}, - {'label': '2年', 'value': '2y'} - ], - value='1y' - ) - ], style={'width': '35%', 'display': 'inline-block', 'margin-left': '5%', 'vertical-align': 'top'}) - ], style={'margin-bottom': '20px'}), - - html.Div(id='risk-metrics-display', style={'margin-bottom': '20px'}), - dcc.Graph(id='risk-analysis-chart') - - ], style={'margin-top': '30px', 'padding': '20px', 'background': 'white', 'border-radius': '10px', 'box-shadow': '0 2px 10px rgba(0,0,0,0.1)'}), - - # 交易回測功能區塊 - html.Div([ - html.H3("AI驅動交易策略回測", style={'margin-bottom': '20px', 'color': '#8E44AD'}), - - # 回測參數設定區 - html.Div([ - html.Div([ - html.Label("選擇回測股票:", style={'font-weight': 'bold'}), - dcc.Dropdown( - id='backtest-stock-dropdown', - options=[{'label': name, 'value': symbol} for name, symbol in TAIWAN_STOCKS.items()], - value='0050.TW' - ) - ], style={'width': '30%', 'display': 'inline-block'}), - - html.Div([ - html.Label("回測期間:", style={'font-weight': 'bold'}), - dcc.Dropdown( - id='backtest-period-dropdown', - options=[ - {'label': '6個月', 'value': '6mo'}, - {'label': '1年', 'value': '1y'}, - {'label': '2年', 'value': '2y'} - ], - value='1y' - ) - ], style={'width': '25%', 'display': 'inline-block', 'margin-left': '3%'}), - - html.Div([ - html.Label("初始資金 (萬元):", style={'font-weight': 'bold'}), - dcc.Input( - id='initial-capital-input', - type='number', - value=100, - min=10, - max=1000, - step=10, - style={'width': '100%', 'padding': '5px'} - ) - ], style={'width': '20%', 'display': 'inline-block', 'margin-left': '3%'}), - - html.Div([ - html.Button( - '開始回測', - id='run-backtest-button', - n_clicks=0, - style={ - 'background': 'linear-gradient(45deg, #667eea 0%, #764ba2 100%)', - 'color': 'white', - 'border': 'none', - 'padding': '10px 20px', - 'border-radius': '5px', - 'font-weight': 'bold', - 'width': '100%', - 'cursor': 'pointer' - } - ) - ], style={'width': '15%', 'display': 'inline-block', 'margin-left': '4%', 'vertical-align': 'bottom'}) - ], style={'margin-bottom': '20px'}), - - # 結果顯示區 - html.Div(id='backtest-progress'), - html.Div(id='backtest-summary-card'), - dcc.Graph(id='backtest-chart'), - html.Div(id='trading-details-table') - - ], style={ - 'margin-top': '30px', - 'padding': '25px', - 'background': 'white', - 'border-radius': '12px', - 'box-shadow': '0 4px 20px rgba(0,0,0,0.08)', - 'border': '1px solid #e9ecef' - }) - ]) - -# 修改台指期預測的回調函數 +# 回調函數區域 @app.callback( - [Output('taiex-prediction-results', 'children'), - Output('taiex-prediction-chart', 'figure')], - [Input('taiex-prediction-period', 'value')] + [dash.dependencies.Output('taiex-prediction-results', 'children'), + dash.dependencies.Output('taiex-prediction-chart', 'figure')], + [dash.dependencies.Input('taiex-prediction-period', 'value')] ) def update_taiex_prediction(predict_days): + # 獲取最新資料用於顯示 data = get_stock_data('^TWII', '2y') if data.empty: return html.Div("無法獲取台指期資料"), {} # === 修改點：統一呼叫 get_prediction 控制器 === - final_prediction = get_prediction(data, predict_days) + # 注意：get_prediction 不再需要傳入 data，它會自己獲取所需數據 + final_prediction = get_prediction(predict_days) if final_prediction is None: return html.Div("資料不足，無法進行預測"), {} - current_price, last_date = data['Close'].iloc[-1], data.index[-1] - # 【重要更新】現在 change_pct 已經是正確的漲幅百分比 + current_price, last_date = data['Close'].iloc[-1], data.index[-1] predicted_price, change_pct, confidence = final_prediction['predicted_price'], final_prediction['change_pct'], final_prediction['confidence'] - # 生成預測路徑（為了圖表顯示） + # 預測路徑的邏輯 prediction_paths = {1: [1], 5: [1, 5], 10: [1, 5, 10], 20: [1, 10, 20], 60: [1, 10, 20, 60]} intervals_to_predict = prediction_paths.get(predict_days, [predict_days]) prediction_dates, prediction_prices = [last_date], [current_price] for days in intervals_to_predict: - interim_prediction = get_prediction(data, days) + interim_prediction = get_prediction(days) if interim_prediction: prediction_dates.append(last_date + timedelta(days=days)) prediction_prices.append(interim_prediction['predicted_price']) - # 後續繪圖邏輯不變，但現在 change_pct 是真正的漲幅百分比 + # 後續繪圖邏輯不變 color, arrow = ('red', '📈') if change_pct >= 0 else ('green', '📉') result_card = html.Div([ html.H4(f"{predict_days}日後預測結果", style={'margin': '0 0 15px 0', 'color': 'white'}), - html.Div([ - html.Span(f"{arrow} ", style={'font-size': '24px'}), - html.Span(f"{change_pct:+.2f}%", style={'font-size': '28px','font-weight': 'bold','color': color}) - ], style={'margin': '10px 0'}), - html.P(f"目前價格: {current_price:.2f}", style={'margin': '5px 0'}), - html.P(f"預測價格: {predicted_price:.2f}", style={'margin': '5px 0'}), - html.P(f"預測漲幅: {change_pct:+.2f}%", style={'margin': '5px 0', 'font-weight': 'bold'}), # 【新增】 + html.Div([html.Span(f"{arrow} ", style={'font-size': '24px'}), html.Span(f"{change_pct:+.2f}%", style={'font-size': '28px','font-weight': 'bold','color': color})], style={'margin': '10px 0'}), + html.P(f"目前指數: {current_price:.2f}", style={'margin': '5px 0'}), + html.P(f"預測指數: {predicted_price:.2f}", style={'margin': '5px 0'}), html.P(f"信心度: {confidence:.1%}", style={'margin': '5px 0', 'font-size': '14px'}) ], style={'background': 'rgba(255,255,255,0.1)','padding': '20px','border-radius': '10px','border': '1px solid rgba(255,255,255,0.2)'}) - # 繪圖部分保持不變 fig = go.Figure() - recent_data = data.tail(30) + recent_data = data.tail(60) # 顯示最近60天歷史數據 fig.add_trace(go.Scatter(x=recent_data.index, y=recent_data['Close'], mode='lines', name='歷史價格', line=dict(color='#FFA726', width=2))) fig.add_trace(go.Scatter(x=prediction_dates, y=prediction_prices, mode='lines+markers', name=f'{predict_days}日預測路徑', line=dict(color=color, width=3, dash='dash'), marker=dict(size=8))) - fig.update_layout(title=f'台指期 {predict_days}日預測走勢 (預測漲幅: {change_pct:+.2f}%)', xaxis_title='日期', yaxis_title='指數點位', height=350, plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font=dict(color='white')) + fig.update_layout(title=f'台指期 {predict_days}日預測走勢', xaxis_title='日期', yaxis_title='指數點位', height=350, plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)', font=dict(color='white')) return result_card, fig +# 其餘回調函數 (update_stock_info, update_price_chart, etc.) +# 與原檔案相同，此處省略以保持簡潔 @app.callback( - Output('stock-info-cards', 'children'), - [Input('stock-dropdown', 'value')] + dash.dependencies.Output('stock-info-cards', 'children'), + [dash.dependencies.Input('stock-dropdown', 'value')] ) def update_stock_info(selected_stock): data = get_stock_data(selected_stock, '5d') @@ -1564,12 +652,11 @@ def update_stock_info(selected_stock): html.P(f"成交量: {data['Volume'].iloc[-1]:,.0f}", style={'margin': '5px 0'}) ], style={'background': 'white','padding': '20px','border-radius': '10px','box-shadow': '0 2px 10px rgba(0,0,0,0.1)','display': 'inline-block'}) ]) - @app.callback( - Output('price-chart', 'figure'), - [Input('stock-dropdown', 'value'), - Input('period-dropdown', 'value'), - Input('chart-type', 'value')] + dash.dependencies.Output('price-chart', 'figure'), + [dash.dependencies.Input('stock-dropdown', 'value'), + dash.dependencies.Input('period-dropdown', 'value'), + dash.dependencies.Input('chart-type', 'value')] ) def update_price_chart(selected_stock, period, chart_type): data = get_stock_data(selected_stock, period) @@ -1588,12 +675,11 @@ def update_price_chart(selected_stock, period, chart_type): fig.add_trace(go.Bar(orientation='h', y=price_centers, x=volume_per_bin, name='Volume Profile', text=[f'{vol/1000:.0f}k' for vol in volume_per_bin], textposition='auto', marker=dict(color='rgba(173, 216, 230, 0.6)', line=dict(color='rgba(30, 144, 255, 0.8)', width=1))), row=1, col=2) fig.update_layout(title_text=f'{stock_name} 股價走勢與成交量分佈', height=500, showlegend=True, xaxis1=dict(title='日期', type='date', rangeslider_visible=False), yaxis1=dict(title='價格 (TWD)'), xaxis2=dict(title='成交量', showticklabels=True), yaxis2=dict(showticklabels=False), bargap=0.05) return fig - @app.callback( - Output('advanced-technical-chart', 'figure'), - [Input('technical-indicator-selector', 'value'), - Input('stock-dropdown', 'value'), - Input('period-dropdown', 'value')] + dash.dependencies.Output('advanced-technical-chart', 'figure'), + [dash.dependencies.Input('technical-indicator-selector', 'value'), + dash.dependencies.Input('stock-dropdown', 'value'), + dash.dependencies.Input('period-dropdown', 'value')] ) def update_advanced_technical_chart(indicator, selected_stock, period): data = get_stock_data(selected_stock, period) @@ -1647,11 +733,10 @@ def update_advanced_technical_chart(indicator, selected_stock, period): fig.add_trace(go.Scatter(x=data_filtered.index, y=data_filtered['ADX'], mode='lines', name='ADX', line=dict(color='blue', width=2, dash='dot')), row=2, col=1) fig.update_layout(title=f'{stock_name} - DMI 動向指標 (14日)', height=500, showlegend=True, yaxis2_range=[0, 100]) return fig - @app.callback( - Output('volume-chart', 'figure'), - [Input('stock-dropdown', 'value'), - Input('period-dropdown', 'value')] + dash.dependencies.Output('volume-chart', 'figure'), + [dash.dependencies.Input('stock-dropdown', 'value'), + dash.dependencies.Input('period-dropdown', 'value')] ) def update_volume_chart(selected_stock, period): data = get_stock_data(selected_stock, period) @@ -1661,10 +746,9 @@ def update_volume_chart(selected_stock, period): fig = go.Figure(go.Bar(x=data.index, y=data['Volume'], marker_color=colors, name='成交量')) fig.update_layout(title=f'{stock_name} 成交量', xaxis_title='日期', yaxis_title='成交量', height=300) return fig - @app.callback( - Output('industry-analysis', 'figure'), - [Input('stock-dropdown', 'value')] + dash.dependencies.Output('industry-analysis', 'figure'), + [dash.dependencies.Input('stock-dropdown', 'value')] ) def update_industry_analysis(selected_stock): performance_data = [] @@ -1678,94 +762,29 @@ def update_industry_analysis(selected_stock): '月報酬率(%)': return_pct, '絕對波動': abs(return_pct) }) - if not performance_data: fig = go.Figure().add_annotation(text="無法計算產業資料", showarrow=False) - fig.update_layout(title="近一月市場表現分析", height=400) + fig.update_layout(title="近一月市場波動最大標的", height=400) return fig - df_performance = pd.DataFrame(performance_data) - - # 分離漲跌幅數據 - gainers = df_performance[df_performance['月報酬率(%)'] > 0].copy() - losers = df_performance[df_performance['月報酬率(%)'] < 0].copy() - - # 按報酬率排序並取前5名 - top_gainers = gainers.sort_values(by='月報酬率(%)', ascending=False).head(5) - top_losers = losers.sort_values(by='月報酬率(%)', ascending=True).head(5) - - # 創建子圖布局 - 1行2列 - fig = make_subplots( - rows=1, cols=2, - specs=[[{"type": "pie"}, {"type": "pie"}]], - subplot_titles=('📈 近一月漲幅排行 Top 5', '📉 近一月跌幅排行 Top 5'), - horizontal_spacing=0.1 + df_top_movers = df_performance.sort_values(by='絕對波動', ascending=False).head(10) + fig = px.pie( + df_top_movers, + values='絕對波動', + names='股票', + title='近一月市場波動最大 Top 10 標的', + hover_data={'月報酬率(%)': ':.2f'} ) - - # 如果有上漲的股票，添加漲幅圓餅圖 - if not top_gainers.empty: - fig.add_trace(go.Pie( - labels=top_gainers['股票'], - values=top_gainers['月報酬率(%)'], - name="漲幅", - textinfo='label+percent', - textposition='inside', - marker=dict(colors=['#FF6B6B', '#FF8E53', '#FF6B9D', '#C44569', '#F8B500']), - hovertemplate="%{label}
漲幅: +%{value:.1f}%", - textfont=dict(size=12) - ), row=1, col=1) - else: - # 如果沒有上漲股票，顯示提示 - fig.add_annotation( - text="本月無上漲股票", - x=0.25, y=0.5, - showarrow=False, - font=dict(size=16, color="gray") - ) - - # 如果有下跌的股票，添加跌幅圓餅圖（使用絕對值） - if not top_losers.empty: - fig.add_trace(go.Pie( - labels=top_losers['股票'], - values=abs(top_losers['月報酬率(%)']), # 使用絕對值讓圓餅圖正常顯示 - name="跌幅", - textinfo='label+percent', - textposition='inside', - marker=dict(colors=['#20BF6B', '#26DE81', '#2BCBBA', '#45AAF2', '#4834D4']), - hovertemplate="%{label}
跌幅: %{customdata:.1f}%", - customdata=top_losers['月報酬率(%)'], # 顯示實際的負值 - textfont=dict(size=12) - ), row=1, col=2) - else: - # 如果沒有下跌股票，顯示提示 - fig.add_annotation( - text="本月無下跌股票", - x=0.75, y=0.5, - showarrow=False, - font=dict(size=16, color="gray") - ) - - # 更新布局 - fig.update_layout( - title_text="近一月市場表現分析 - 漲跌分佈", - height=500, - showlegend=False, - font=dict(size=11), - title_font_size=16, - annotations=[ - dict(text=f"統計範圍：{len(performance_data)}檔股票", - x=0.5, y=-0.1, - showarrow=False, - xanchor="center", - font=dict(size=12, color="gray")) - ] + fig.update_traces( + textposition='inside', + textinfo='percent+label', + hovertemplate="%{label}
月報酬率: %{customdata[0]:.2f}%" ) - + fig.update_layout(height=400, showlegend=False) return fig - @app.callback( - Output('business-climate-chart', 'figure'), - [Input('stock-dropdown', 'value')] + dash.dependencies.Output('business-climate-chart', 'figure'), + [dash.dependencies.Input('stock-dropdown', 'value')] ) def update_business_climate_chart(selected_stock): df = get_business_climate_data() @@ -1786,67 +805,47 @@ def update_business_climate_chart(selected_stock): fig.add_hline(y=17, line_dash="dash", line_color="yellow", annotation_text="黃燈(17)") fig.update_layout(title="台灣景氣燈號走勢", xaxis_title='日期', yaxis_title='燈號分數', height=300, yaxis=dict(range=[0, 40])) return fig - -# ========================= MODIFIED SECTION START (CACHE INTEGRATED) ========================= @app.callback( - [Output('technical-analysis-text', 'children'), - Output('fundamental-analysis-text', 'children'), - Output('market-outlook-text', 'children')], - [Input('stock-dropdown', 'value'), - Input('period-dropdown', 'value')] + [dash.dependencies.Output('technical-analysis-text', 'children'), + dash.dependencies.Output('fundamental-analysis-text', 'children'), + dash.dependencies.Output('market-outlook-text', 'children')], + [dash.dependencies.Input('stock-dropdown', 'value'), + dash.dependencies.Input('period-dropdown', 'value')] ) def update_analysis_text(selected_stock, period): - # 建立快取的唯一鍵值 cache_key = f"{selected_stock}-{period}" current_time = time.time() - - # 1. 檢查快取 if cache_key in ANALYSIS_CACHE: cached_data = ANALYSIS_CACHE[cache_key] if current_time - cached_data['timestamp'] < CACHE_DURATION_SECONDS: print(f"從快取載入分析: {cache_key}") - # 直接回傳快取的內容 return cached_data['technical'], cached_data['fundamental'], cached_data['outlook'] - print(f"重新生成分析: {cache_key}") - # --- 如果快取沒有，才繼續執行以下程式 --- - data = get_stock_data(selected_stock, period) stock_name = [name for name, symbol in TAIWAN_STOCKS.items() if symbol == selected_stock][0] if data.empty or len(data) < 20: return "資料不足，無法分析", "資料不足，無法分析", "資料不足，無法分析" - data = calculate_technical_indicators(data) - - # 2. 技術面分析 price_change = ((data['Close'].iloc[-1] - data['Close'].iloc[0]) / data['Close'].iloc[0]) * 100 rsi_current = data['RSI'].iloc[-1] if not pd.isna(data['RSI'].iloc[-1]) else 50 macd_current = data['MACD'].iloc[-1] if not pd.isna(data['MACD'].iloc[-1]) else 0 macd_signal_current = data['MACD_Signal'].iloc[-1] if not pd.isna(data['MACD_Signal'].iloc[-1]) else 0 - technical_text = html.Div([ html.P([html.Strong("價格趨勢："), f"在最近 {period} 期間內，{stock_name} 股價呈現", html.Span(f"{'上漲' if price_change > 5 else '下跌' if price_change < -5 else '盤整'}", style={'color': 'red' if price_change > 5 else 'green' if price_change < -5 else 'orange', 'font-weight': 'bold'}), f"走勢，累計變動 {price_change:+.1f}%。"]), - html.P([html.Strong("RSI 指標："), f"目前的 RSI 值為 {rsi_current:.1f}，", html.Span("處於超買區(>70)" if rsi_current > 70 else "處於超賣區(<30)" if rsi_current < 30 else "在正常範圍內", style={'color': 'green' if rsi_current > 70 else 'red' if rsi_current < 30 else 'blue', 'font-weight': 'bold'}), "。"]), + html.P([html.Strong("RSI 指標："), f"目前的 RSI 值為 {rsi_current:.1f}，", html.Span("處於超買區(>70)" if rsi_current > 70 else "處於超賣區(<30)" if rsi_current < 30 else "在正常範圍内", style={'color': 'green' if rsi_current > 70 else 'red' if rsi_current < 30 else 'blue', 'font-weight': 'bold'}), "。"]), html.P([html.Strong("MACD 指標："), f"MACD 快線 ({macd_current:.3f}) 目前", html.Span("高於" if macd_current > macd_signal_current else "低於", style={'color': 'red' if macd_current > macd_signal_current else 'green', 'font-weight': 'bold'}), f" Signal 慢線 ({macd_signal_current:.3f})，", f"顯示市場動能偏向{'多頭' if macd_current > macd_signal_current else '空頭'}。"]), ]) - - # 3. 基本面與展望分析 (呼叫 Gemini) fundamental_text, market_outlook_text = generate_gemini_analysis(stock_name, selected_stock, period, data) - - # 4. 將新產生的結果存入快取 ANALYSIS_CACHE[cache_key] = { 'technical': technical_text, 'fundamental': fundamental_text, 'outlook': market_outlook_text, 'timestamp': current_time } - return technical_text, fundamental_text, market_outlook_text -# ========================== MODIFIED SECTION END ========================== - @app.callback( - Output('pmi-chart', 'figure'), - [Input('stock-dropdown', 'value')] + dash.dependencies.Output('pmi-chart', 'figure'), + [dash.dependencies.Input('stock-dropdown', 'value')] ) def update_pmi_chart(selected_stock): df = get_pmi_data() @@ -1860,43 +859,11 @@ def update_pmi_chart(selected_stock): fig.add_hline(y=50, line_dash="dash", line_color="black", annotation_text="榮枯線(50)") fig.update_layout(title="台灣PMI指數走勢", xaxis_title='日期', yaxis_title='PMI指數', height=300, yaxis=dict(range=[35, 60])) return fig - -def summarize_news_with_gemini(news_list: list) -> str: - """ - 使用 Gemini API 將英文新聞標題列表摘要成一段繁體中文。 - """ - api_key = os.getenv("GEMINI_API_KEY") - if not api_key: - return "錯誤：找不到 GEMINI_API_KEY。請在 Hugging Face Secrets 中設定。" - - try: - genai.configure(api_key=api_key) - model = genai.GenerativeModel('gemini-1.5-flash') - - formatted_news = "\n".join([f"- {news}" for news in news_list]) - - prompt = f""" - 請扮演一位專業的金融市場分析師。 - 以下是幾則最新的英文財經新聞標題，請將它們整合成一段簡潔、流暢、約 200 字的繁體中文市場動態摘要，與利多哪些產業，利空哪些產業。 - 提供3段重點， - 請專注於可能影響市場情緒和股價的關鍵資訊，並直接提供摘要內容，不要包含任何���外的問候語或說明。 - - 英文新聞標題如下： - {formatted_news} - """ - - response = model.generate_content(prompt) - return response.text - - except Exception as e: - print(f"呼叫 Gemini API 時發生錯誤: {e}") - return f"無法生成新聞摘要，請稍後再試。錯誤訊息：{e}" - @app.callback( - [Output('comparison-chart', 'figure'), - Output('comparison-table', 'children')], - [Input('comparison-stocks', 'value'), - Input('comparison-period', 'value')] + [dash.dependencies.Output('comparison-chart', 'figure'), + dash.dependencies.Output('comparison-table', 'children')], + [dash.dependencies.Input('comparison-stocks', 'value'), + dash.dependencies.Input('comparison-period', 'value')] ) def update_comparison_analysis(selected_stocks, period): fixed_stock = '0050.TW' @@ -1923,20 +890,17 @@ def update_comparison_analysis(selected_stocks, period): table = html.Table([html.Thead(html.Tr([html.Th("股票"), html.Th("報酬率"), html.Th("波動率"), html.Th("現價")])), html.Tbody(table_rows)], style={'width': '100%'}) return fig, table return fig, html.Div("無可比較資料") - @app.callback( - [Output('sentiment-gauge', 'children'), - Output('news-summary', 'children')], - [Input('stock-dropdown', 'value')] + [dash.dependencies.Output('sentiment-gauge', 'children'), + dash.dependencies.Output('news-summary', 'children')], + [dash.dependencies.Input('stock-dropdown', 'value')] ) def update_sentiment_analysis(selected_stock): if predictor is None: error_fig = go.Figure().add_annotation(text="情緒指標模型載入失敗", showarrow=False) error_fig.update_layout(height=200) return dcc.Graph(figure=error_fig), html.P("新聞分析模型載入失敗，請檢查後台日誌。") - sentiment_score_raw = predictor.get_news_index() - if sentiment_score_raw is not None: sentiment_score_normalized = (sentiment_score_raw + 1) * 50 sentiment_score_normalized = max(0, min(100, sentiment_score_normalized)) @@ -1961,10 +925,8 @@ def update_sentiment_analysis(selected_stock): error_fig = go.Figure().add_annotation(text="今日尚無情緒分數", showarrow=False) error_fig.update_layout(height=200) gauge_content = dcc.Graph(figure=error_fig) - top_news_list = predictor.get_news() news_content = None - if top_news_list and isinstance(top_news_list, list): summary_text = summarize_news_with_gemini(top_news_list) news_content = dcc.Markdown(summary_text, style={ @@ -1975,331 +937,8 @@ def update_sentiment_analysis(selected_stock): news_content = html.P("昨日無重大相關新聞。", style={'text-align': 'center', 'padding-top': '50px'}) else: news_content = html.P("讀取新聞時發生錯誤。", style={'text-align': 'center', 'padding-top': '50px'}) - return gauge_content, news_content - -# ========================= 新增：風險管理模組回調函數 START ========================= -@app.callback( - [Output('risk-metrics-display', 'children'), - Output('risk-analysis-chart', 'figure')], - [Input('portfolio-stocks', 'value'), - Input('risk-period-dropdown', 'value')] -) -def update_risk_analysis(selected_stocks, period): - if not selected_stocks: - return html.Div("請至少選擇一檔股票進行分析。", style={'color': 'red', 'text-align': 'center'}), {} - - selected_stocks = selected_stocks[:5] # 限制最多5檔 - analyzer = RiskAnalyzer() - - # 獲取大盤數據 - market_data = get_stock_data('^TWII', period) - if market_data.empty: - return html.Div("無法獲取大盤數據 (^TWII)，無法計算 Beta 值。", style={'color': 'red'}), {} - market_returns = market_data['Close'].pct_change().dropna() - - all_stock_data = {} - all_returns_data = {} - individual_metrics_cards = [] - - # 計算個股指標 - for stock_symbol in selected_stocks: - stock_data = get_stock_data(stock_symbol, period) - stock_name = next((name for name, symbol in TAIWAN_STOCKS.items() if symbol == stock_symbol), stock_symbol) - - if stock_data.empty or len(stock_data) < 30: - card = html.Div([ - html.H5(f"{stock_name} ({stock_symbol})", style={'margin-bottom': '10px', 'color': '#34495E'}), - html.P("資料不足，無法計算風險指標。") - ], className="metric-card", style={'border-left': '5px solid #E74C3C'}) - individual_metrics_cards.append(card) - continue - - all_stock_data[stock_symbol] = stock_data - stock_returns = stock_data['Close'].pct_change().dropna() - all_returns_data[stock_symbol] = stock_returns - - # 計算指標 - beta = analyzer.calculate_beta(stock_returns, market_returns) - sharpe = analyzer.calculate_sharpe_ratio(stock_returns) - max_dd = analyzer.calculate_max_drawdown(stock_data['Close']) - var_95 = analyzer.calculate_var(stock_returns, 0.05) - - # 建立個股卡片 - card = html.Div([ - html.H5(f"{stock_name} ({stock_symbol})", style={'margin-bottom': '10px', 'color': '#34495E'}), - html.Table([ - html.Tr([html.Td("Beta (與大盤相關性)"), html.Td(f"{beta:.2f}" if beta is not None else "N/A")]), - html.Tr([html.Td("年化夏普比率"), html.Td(f"{sharpe:.2f}" if sharpe is not None else "N/A")]), - html.Tr([html.Td("最大回撤 (MDD)"), html.Td(f"{max_dd:.2%}" if max_dd is not None else "N/A")]), - html.Tr([html.Td("每日 VaR (95%)"), html.Td(f"{var_95:.2%}" if var_95 is not None else "N/A")]), - ]) - ], className="metric-card", style={'border-left': '5px solid #3498DB', 'width': '32%', 'display': 'inline-block', 'margin': '0.5%', 'padding': '15px', 'background': '#f9f9f9', 'border-radius': '5px', 'box-shadow': '0 1px 3px rgba(0,0,0,0.1)'}) - individual_metrics_cards.append(card) - - # 計算投資組合指標 (假設等權重) - if not all_returns_data: - return html.Div(individual_metrics_cards), {} - - returns_df = pd.DataFrame(all_returns_data).dropna() - num_assets = len(returns_df.columns) - weights = np.array([1/num_assets] * num_assets) - portfolio_returns = returns_df.dot(weights) - - portfolio_sharpe = analyzer.calculate_sharpe_ratio(portfolio_returns) - portfolio_volatility = portfolio_returns.std() * np.sqrt(252) - portfolio_var_95 = analyzer.calculate_var(portfolio_returns, 0.05) - portfolio_var_99 = analyzer.calculate_var(portfolio_returns, 0.01) - - # 建立投資組合總結卡片 - portfolio_card = html.Div([ - html.H4("投資組合整體風險 (等權重)", style={'color': '#2C3E50', 'border-bottom': '2px solid #2C3E50', 'padding-bottom': '10px'}), - html.Table([ - html.Tr([html.Td("年化波動率"), html.Td(f"{portfolio_volatility:.2%}" if portfolio_volatility is not None else "N/A")]), - html.Tr([html.Td("年化夏普比率"), html.Td(f"{portfolio_sharpe:.2f}" if portfolio_sharpe is not None else "N/A")]), - html.Tr([html.Td("每日 VaR (95%)"), html.Td(f"{portfolio_var_95:.2%}" if portfolio_var_95 is not None else "N/A")]), - html.Tr([html.Td("每日 VaR (99%)"), html.Td(f"{portfolio_var_99:.2%}" if portfolio_var_99 is not None else "N/A")]), - ], style={'width': '100%', 'marginTop': '10px'}) - ], style={'padding': '20px', 'background': 'linear-gradient(135deg, #a8c0ff 0%, #3f2b96 100%)', 'color': 'white', 'border-radius': '10px', 'margin-bottom': '20px'}) - - # 圖表：報酬分佈與 VaR - fig = go.Figure() - fig.add_trace(go.Histogram(x=portfolio_returns, nbinsx=50, name='日報酬分佈', marker_color='#3498DB')) - - if portfolio_var_95 is not None: - fig.add_vline(x=portfolio_var_95, line_width=2, line_dash="dash", line_color="orange", - annotation_text=f"VaR 95%: {portfolio_var_95:.2%}", annotation_position="top left") - if portfolio_var_99 is not None: - fig.add_vline(x=portfolio_var_99, line_width=2, line_dash="dash", line_color="red", - annotation_text=f"VaR 99%: {portfolio_var_99:.2%}", annotation_position="top right") - - fig.update_layout( - title="投資組合日報酬率分佈與 VaR", - xaxis_title="日報酬率", - yaxis_title="頻率", - height=400 - ) - - # 組合最終顯示內容 - display_content = html.Div([ - portfolio_card, - html.H4("個別資產風險指標", style={'margin-top': '20px', 'color': '#2C3E50'}), - html.Div(individual_metrics_cards) - ]) - - return display_content, fig -# ========================== 新增：風險管理模組回調函數 END ========================== - - -# 新增：回測結果快取 -BACKTEST_CACHE = {} -BACKTEST_CACHE_DURATION = 24 * 60 * 60 # 24小時 - -# 4. 新增以下回調函數（在其他回調函數之後）： - -@app.callback( - [Output('backtest-progress', 'children'), - Output('backtest-summary-card', 'children'), - Output('backtest-chart', 'figure'), - Output('trading-details-table', 'children')], - [Input('run-backtest-button', 'n_clicks')], - [State('backtest-stock-dropdown', 'value'), - State('backtest-period-dropdown', 'value'), - State('initial-capital-input', 'value')] -) -def run_trading_backtest(n_clicks, selected_stock, period, initial_capital_wan): - """執行交易策略回測""" - if n_clicks == 0: - # 初始狀態 - empty_fig = go.Figure() - empty_fig.update_layout( - title="點擊「開始回測」按鈕執行交易策略分析", - height=400 - ) - empty_fig.add_annotation( - text="等待回測開始...", - x=0.5, y=0.5, - showarrow=False, - font=dict(size=16, color="gray") - ) - return ( - html.Div("準備就緒，點擊按鈕開始回���", style={'color': '#3498DB', 'text-align': 'center'}), - html.Div(), - empty_fig, - html.Div() - ) - - try: - # 參數轉換 - initial_capital = initial_capital_wan * 10000 - - # 檢查快取 - cache_key = f"backtest_{selected_stock}_{period}_{initial_capital}" - current_time = time.time() - - if cache_key in BACKTEST_CACHE: - cached_data = BACKTEST_CACHE[cache_key] - if current_time - cached_data['timestamp'] < BACKTEST_CACHE_DURATION: - results = cached_data['results'] - stock_data = cached_data['stock_data'] - backtester = cached_data['backtester'] - - progress_msg = html.Div("✅ 回測完成 (來自快取)", - style={'color': 'green', 'text-align': 'center', 'font-weight': 'bold'}) - summary_card = create_backtest_summary_card(results) - chart = backtester.create_backtest_chart(results, stock_data) - details_table = create_trading_details_table(results.get('trades_df', pd.DataFrame())) - - return progress_msg, summary_card, chart, details_table - - # 獲取資料 - stock_data = get_stock_data(selected_stock, period) - if stock_data.empty or len(stock_data) < 100: - raise ValueError("股票資料不足，無法進行回測") - - # 執行回測 - backtester = TradingBacktester( - initial_capital=initial_capital, - max_position_ratio=0.8, - batch_ratio=0.2 - ) - - results = backtester.run_backtest(stock_data, get_prediction) - - # 快取結果 - BACKTEST_CACHE[cache_key] = { - 'results': results, - 'stock_data': stock_data, - 'backtester': backtester, - 'timestamp': current_time - } - - # 生成輸出 - progress_msg = html.Div( - f"✅ 回測完成！共執行 {results['total_trades']} 筆交易", - style={'color': 'green', 'text-align': 'center', 'font-weight': 'bold'} - ) - - summary_card = create_backtest_summary_card(results) - chart = backtester.create_backtest_chart(results, stock_data) - details_table = create_trading_details_table(results.get('trades_df', pd.DataFrame())) - - return progress_msg, summary_card, chart, details_table - - except Exception as e: - error_fig = go.Figure() - error_fig.add_annotation(text=f"回測執行失敗: {str(e)}", showarrow=False) - error_fig.update_layout(height=400) - - return ( - html.Div(f"錯誤：{str(e)}", style={'color': 'red', 'text-align': 'center'}), - html.Div("回測執行失敗，請檢查參數或稍後再試"), - error_fig, - html.Div() - ) - -# 5. 新增輔助函數： - -def create_backtest_summary_card(results): - """創建回測摘要卡片""" - if not results: - return html.Div("回測結果為空", style={'color': 'red'}) - - return_color = 'red' if results['total_return'] > 0 else 'green' - excess_color = 'red' if results['excess_return'] > 0 else 'green' - - return html.Div([ - html.H4("交易策略回測摘要", style={'color': '#2C3E50', 'margin-bottom': '20px'}), - - # 核心指標 - html.Div([ - html.Div([ - html.H5("總報酬率", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['total_return']:+.2f}%", - style={'margin': '5px 0', 'color': return_color, 'font-weight': 'bold'}) - ], style={'text-align': 'center'}), - - html.Div([ - html.H5("vs 買入持有", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['excess_return']:+.2f}%", - style={'margin': '5px 0', 'color': excess_color, 'font-weight': 'bold'}) - ], style={'text-align': 'center'}), - - html.Div([ - html.H5("夏普比率", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['sharpe_ratio']:.2f}", - style={'margin': '5px 0', 'color': '#3498DB', 'font-weight': 'bold'}) - ], style={'text-align': 'center'}), - - html.Div([ - html.H5("最大回撤", style={'margin': '0', 'color': '#7F8C8D'}), - html.H3(f"{results['max_drawdown']:.2f}%", - style={'margin': '5px 0', 'color': '#E74C3C', 'font-weight': 'bold'}) - ], style={'text-align': 'center'}) - ], style={'display': 'flex', 'justify-content': 'space-around', 'margin-bottom': '20px'}), - - # 詳細統計表格 - html.Hr(), - html.Table([ - html.Tr([html.Td("最終投資組合價值"), html.Td(f"${results['final_value']:,.0f}")]), - html.Tr([html.Td("初始資金"), html.Td(f"${results.get('initial_capital', 1000000):,.0f}")]), - html.Tr([html.Td("年化波動率"), html.Td(f"{results['annual_volatility']:.2f}%")]), - html.Tr([html.Td("總交易次數"), html.Td(f"{results['total_trades']}")]), - html.Tr([html.Td("買入次數"), html.Td(f"{results['buy_trades']}")]), - html.Tr([html.Td("賣出次數"), html.Td(f"{results['sell_trades']}")]), - html.Tr([html.Td("交易勝率"), html.Td(f"{results['win_rate']:.1f}%")]) - ], style={'width': '100%'}) - ], style={ - 'padding': '25px', - 'background': 'white', - 'border-radius': '12px', - 'box-shadow': '0 4px 20px rgba(0,0,0,0.08)', - 'margin-bottom': '20px' - }) - -def create_trading_details_table(trades_df): - """創建交易詳細記錄表格""" - if trades_df.empty: - return html.Div("尚無交易記錄", style={'text-align': 'center', 'color': 'gray'}) - - # 顯示最近20筆交易 - recent_trades = trades_df.tail(20).copy().sort_values('date', ascending=False) - - table_rows = [] - for _, trade in recent_trades.iterrows(): - signal_text = "🔴 買入" if trade['signal'] == 1 else "🟢 賣出" - signal_color = "#E74C3C" if trade['signal'] == 1 else "#27AE60" - - table_rows.append(html.Tr([ - html.Td(trade['date'].strftime('%Y-%m-%d')), - html.Td(signal_text, style={'color': signal_color, 'font-weight': 'bold'}), - html.Td(f"{abs(trade['shares']):,}"), - html.Td(f"${trade['price']:.2f}"), - html.Td(f"${abs(trade['value']):,.0f}"), - html.Td(f"{trade['strength']:.2f}") - ])) - - return html.Div([ - html.P(f"最近 {len(table_rows)} 筆交易記錄", style={'color': '#7F8C8D'}), - html.Table([ - html.Thead(html.Tr([ - html.Th("交易日期", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}), - html.Th("方向", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}), - html.Th("股數", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}), - html.Th("價格", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}), - html.Th("金額", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}), - html.Th("信號強度", style={'background': '#34495E', 'color': 'white', 'padding': '8px'}) - ])), - html.Tbody(table_rows) - ], style={'width': '100%', 'border-collapse': 'collapse'}) - ]) - -# 6. 完整的TradingBacktester類別需要添加到程式開頭 -# (請參考前面提供的完整類別定義) - - - # 主程式執行 if __name__ == '__main__': app.run(host="0.0.0.0", port=7860, debug=False) \ No newline at end of file