commit;

manage-instances.sh

@@ -11,7 +11,8 @@ show_help() {
     echo "  start [实例ID]        启动指定实例或所有实例"
     echo "  stop [实例ID]         停止指定实例或所有实例"
     echo "  restart [实例ID]      重启指定实例或所有实例"
-    echo "  logs [实例ID]         实时查看指定实例的日志 (Ctrl+C 退出)"
+    echo "  logs [实例ID]         查看最新10条日志并实时跟踪新日志"
+    echo "  logs-follow [实例ID]  实时查看指定实例的日志 (Ctrl+C 退出)"
     echo "  status               显示实例状态概览"
     echo "  remove [实例ID]       删除指定实例或所有实例"
     echo "  rebuild [数量]        重新构建镜像并部署指定数量的实例"
@@ -21,7 +22,8 @@ show_help() {
     echo "  $0 list              列出所有实例"
     echo "  $0 start 2           启动实例2"
     echo "  $0 stop all          停止所有实例"
-    echo "  $0 logs 1            查看实例1的日志"
+    echo "  $0 logs 1            查看实例1最新10条日志并实时跟踪"
+    echo "  $0 logs-follow 1     实时跟踪实例1的日志"
     echo "  $0 rebuild 2         重新构建并部署2个实例"
     echo "  $0 update            热更新所有实例的代码"
     exit 1
@@ -68,6 +70,13 @@ restart_instance() {
 
 # 函数：查看实例日志
 view_logs() {
+    echo "显示实例 $1 的最新10条日志，然后实时跟踪新日志 (按 Ctrl+C 退出):"
+    echo "----------------------------------------"
+    docker logs --tail 10 -f stock-app-$1
+}
+
+# 函数：实时查看实例日志
+view_logs_follow() {
     echo "正在实时显示实例 $1 的日志 (按 Ctrl+C 退出):"
     echo "----------------------------------------"
     docker logs -f stock-app-$1
@@ -187,6 +196,13 @@ case "$1" in
         fi
         view_logs $2
         ;;
+    logs-follow)
+        if [ "$#" -lt 2 ]; then
+            echo "错误: 缺少实例ID参数"
+            show_help
+        fi
+        view_logs_follow $2
+        ;;
     status)
         show_status
         ;;

src/QMT/strategy.py

@@ -245,7 +245,7 @@ def create_buy_strategy_callback(xt_trader, acc, buy_amount, logger):
                     
                     # 检查是否有在途订单（Redis）
                     if is_stock_pending_order(stock_code):
-                        logger.info(f"{stock_code} 有在途订单，跳过买入")
+                        # logger.info(f"{stock_code} 有在途订单，跳过买入")
                         continue
 
                     # 集合竞价时段：只观察，不下单
@@ -339,7 +339,7 @@ def create_sell_strategy_callback(xt_trader, acc, logger):
                     
                     # 检查是否有在途订单
                     if is_stock_pending_order(stock_code):
-                        logger.info(f"{stock_code} 有在途订单，跳过卖出")
+                        # logger.info(f"{stock_code} 有在途订单，跳过卖出")
                         continue
 
                     # 集合竞价时段：只观察，不下单

src/app.py

@@ -3404,6 +3404,74 @@ def analyze_valuation_indicator():
             "message": f"估值指标分析失败: {str(e)}"
         }), 500
 
+
+@app.route('/api/overlap/analysis', methods=['GET'])
+def analyze_stock_overlap():
+    """分析股票重叠度和滞涨情况
+    GET参数:
+    - stock_code: 股票代码 (例如: 300661.SZ)
+    - days: 分析天数，默认3个交易日
+    
+    返回格式:
+    {
+        "status": "success",
+        "data": {
+            "target_stock": "300661.SZ",
+            "target_stock_name": "圣邦股份",
+            "analysis_date": "2025-09-28 15:30:42",
+            "analysis_period_days": 3,
+            "industries": [...],
+            "concepts": [...],
+            "overlap_threshold": 5,
+            "top5_stocks": [...],
+            "lag_analysis": {...}
+        }
+    }
+    """
+    try:
+        # 获取参数
+        stock_code = request.args.get('stock_code')
+        days = int(request.args.get('days', 3))
+        
+        if not stock_code:
+            return jsonify({
+                "status": "error",
+                "message": "缺少必需参数: stock_code"
+            }), 400
+        
+        # 导入重叠度分析器
+        from src.quantitative_analysis.overlap_analyzer import OverlapAnalyzer
+        
+        # 创建分析器实例
+        analyzer = OverlapAnalyzer()
+        
+        try:
+            # 执行分析
+            result = analyzer.analyze_stock_overlap(stock_code, days)
+            
+            if 'error' in result:
+                return jsonify({
+                    "status": "error",
+                    "message": result['error']
+                }), 500
+            
+            return jsonify({
+                "status": "success",
+                "data": result
+            })
+            
+        finally:
+            # 关闭数据库连接
+            analyzer.close_connection()
+            
+    except Exception as e:
+        logger.error(f"重叠度分析失败: {str(e)}")
+        return jsonify({
+            "status": "error",
+            "message": f"重叠度分析失败: {str(e)}"
+        }), 500
+
+
 if __name__ == '__main__':
 
     # 启动Web服务器

src/quantitative_analysis/average_distance_factor.py

@@ -289,10 +289,10 @@ def main():
     analyzer = AverageDistanceFactor(db_url)
     
     # 示例1: 分析特定行业
-    # result = analyzer.analyze_industry(industry_name="旅游")
+    result = analyzer.analyze_industry(industry_name="军工电子")
     
     # 示例2: 分析特定概念
-    result = analyzer.analyze_industry(concept_name="人形机器人")
+    # result = analyzer.analyze_industry(concept_name="固态电池")
     
     # 示例3: 查看可用的行业列表
     # industries = analyzer.get_available_industries()

src/quantitative_analysis/overlap_analyzer.py

@@ -0,0 +1,668 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+行业重叠度和概念重叠度分析工具
+用于分析某股票与相似股票的重叠度，识别滞涨投资机会
+"""
+
+import sys
+import os
+import logging
+from typing import Dict, List, Optional, Tuple
+from pathlib import Path
+from sqlalchemy import create_engine, text
+import pandas as pd
+from datetime import datetime, timedelta
+
+# 添加项目根路径到Python路径
+project_root = Path(__file__).parent.parent.parent
+sys.path.append(str(project_root))
+
+# 导入配置
+try:
+    from src.valuation_analysis.config import DB_URL
+except ImportError:
+    # 如果上面的导入失败，尝试直接导入
+    import importlib.util
+    config_path = os.path.join(project_root, 'src', 'valuation_analysis', 'config.py')
+    spec = importlib.util.spec_from_file_location("config", config_path)
+    config_module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(config_module)
+    DB_URL = config_module.DB_URL
+
+# 导入股票代码格式转换工具
+try:
+    from tools.stock_code_formatter import StockCodeFormatter
+except ImportError:
+    # 如果上面的导入失败，尝试直接导入
+    import importlib.util
+    formatter_path = os.path.join(project_root, 'tools', 'stock_code_formatter.py')
+    spec = importlib.util.spec_from_file_location("stock_code_formatter", formatter_path)
+    formatter_module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(formatter_module)
+    StockCodeFormatter = formatter_module.StockCodeFormatter
+
+# 设置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+
+class OverlapAnalyzer:
+    """行业重叠度和概念重叠度分析器"""
+    
+    def __init__(self):
+        """初始化"""
+        # MySQL连接
+        self.mysql_engine = None
+        
+        # 股票代码格式转换器
+        self.code_formatter = StockCodeFormatter()
+        
+        # 重叠度评分权重
+        self.INDUSTRY_WEIGHT = 3  # 行业重叠权重
+        self.CONCEPT_WEIGHT = 1   # 概念重叠权重
+        self.MIN_OVERLAP_SCORE = 5  # 最小重叠分数阈值
+        
+        self.connect_mysql()
+    
+    def connect_mysql(self):
+        """连接MySQL数据库"""
+        try:
+            self.mysql_engine = create_engine(
+                DB_URL,
+                pool_size=5,
+                max_overflow=10,
+                pool_recycle=3600
+            )
+            
+            # 测试连接
+            with self.mysql_engine.connect() as conn:
+                conn.execute(text("SELECT 1"))
+            
+            logger.info("MySQL数据库连接成功")
+            
+        except Exception as e:
+            logger.error(f"MySQL数据库连接失败: {str(e)}")
+            raise
+    
+    def normalize_stock_code(self, stock_code: str) -> str:
+        """
+        标准化股票代码格式，转换为数据库中使用的格式
+        
+        Args:
+            stock_code: 输入的股票代码，支持多种格式
+            
+        Returns:
+            str: 标准化后的股票代码
+        """
+        return self.code_formatter.to_prefix_format(stock_code)
+    
+    def get_stock_industries(self, stock_code: str) -> List[Tuple[str, str]]:
+        """
+        获取股票所属的行业板块
+        
+        Args:
+            stock_code: 股票代码
+            
+        Returns:
+            List[Tuple[str, str]]: [(板块代码, 板块名称)] 列表
+        """
+        try:
+            normalized_code = self.normalize_stock_code(stock_code)
+            
+            query = text("""
+                SELECT DISTINCT bk_code, bk_name
+                FROM gp_hybk 
+                WHERE gp_code = :stock_code
+                AND bk_code IS NOT NULL
+                AND bk_name IS NOT NULL
+            """)
+            
+            with self.mysql_engine.connect() as conn:
+                result = conn.execute(query, {"stock_code": normalized_code}).fetchall()
+                
+            industries = [(str(row[0]), str(row[1])) for row in result]
+            logger.info(f"股票 {stock_code} 找到 {len(industries)} 个行业板块")
+            return industries
+            
+        except Exception as e:
+            logger.error(f"获取股票 {stock_code} 行业板块失败: {str(e)}")
+            return []
+    
+    def get_stock_concepts(self, stock_code: str) -> List[Tuple[str, str]]:
+        """
+        获取股票所属的概念板块
+        
+        Args:
+            stock_code: 股票代码
+            
+        Returns:
+            List[Tuple[str, str]]: [(板块代码, 板块名称)] 列表
+        """
+        try:
+            normalized_code = self.normalize_stock_code(stock_code)
+            
+            query = text("""
+                SELECT DISTINCT bk_code, bk_name
+                FROM gp_gnbk 
+                WHERE gp_code = :stock_code
+                AND bk_code IS NOT NULL
+                AND bk_name IS NOT NULL
+            """)
+            
+            with self.mysql_engine.connect() as conn:
+                result = conn.execute(query, {"stock_code": normalized_code}).fetchall()
+                
+            concepts = [(str(row[0]), str(row[1])) for row in result]
+            logger.info(f"股票 {stock_code} 找到 {len(concepts)} 个概念板块")
+            return concepts
+            
+        except Exception as e:
+            logger.error(f"获取股票 {stock_code} 概念板块失败: {str(e)}")
+            return []
+    
+    def get_similar_stocks_by_industry(self, industries: List[Tuple[str, str]]) -> Dict[str, List[str]]:
+        """
+        根据行业板块获取相似股票
+        
+        Args:
+            industries: 行业板块列表 [(板块代码, 板块名称)]
+            
+        Returns:
+            Dict[str, List[str]]: {板块代码: [股票代码列表]}
+        """
+        try:
+            similar_stocks = {}
+            
+            for bk_code, bk_name in industries:
+                query = text("""
+                    SELECT DISTINCT gp_code
+                    FROM gp_hybk 
+                    WHERE bk_code = :bk_code
+                    AND gp_code IS NOT NULL
+                """)
+                
+                with self.mysql_engine.connect() as conn:
+                    result = conn.execute(query, {"bk_code": bk_code}).fetchall()
+                    
+                stock_codes = [row[0] for row in result if row[0]]
+                similar_stocks[bk_code] = stock_codes
+                logger.info(f"行业板块 {bk_name}({bk_code}) 包含 {len(stock_codes)} 只股票")
+            
+            return similar_stocks
+            
+        except Exception as e:
+            logger.error(f"获取行业相似股票失败: {str(e)}")
+            return {}
+    
+    def get_similar_stocks_by_concept(self, concepts: List[Tuple[str, str]]) -> Dict[str, List[str]]:
+        """
+        根据概念板块获取相似股票
+        
+        Args:
+            concepts: 概念板块列表 [(板块代码, 板块名称)]
+            
+        Returns:
+            Dict[str, List[str]]: {板块代码: [股票代码列表]}
+        """
+        try:
+            similar_stocks = {}
+            
+            for bk_code, bk_name in concepts:
+                query = text("""
+                    SELECT DISTINCT gp_code
+                    FROM gp_gnbk 
+                    WHERE bk_code = :bk_code
+                    AND gp_code IS NOT NULL
+                """)
+                
+                with self.mysql_engine.connect() as conn:
+                    result = conn.execute(query, {"bk_code": bk_code}).fetchall()
+                    
+                stock_codes = [row[0] for row in result if row[0]]
+                similar_stocks[bk_code] = stock_codes
+                logger.info(f"概念板块 {bk_name}({bk_code}) 包含 {len(stock_codes)} 只股票")
+            
+            return similar_stocks
+            
+        except Exception as e:
+            logger.error(f"获取概念相似股票失败: {str(e)}")
+            return {}
+    
+    def calculate_overlap_scores(self, target_stock: str, industry_stocks: Dict[str, List[str]], concept_stocks: Dict[str, List[str]]) -> Dict[str, float]:
+        """
+        计算重叠度分数
+        
+        Args:
+            target_stock: 目标股票代码
+            industry_stocks: 行业相似股票字典 {板块代码: [股票代码列表]}
+            concept_stocks: 概念相似股票字典 {板块代码: [股票代码列表]}
+            
+        Returns:
+            Dict[str, float]: {股票代码: 重叠分数}
+        """
+        try:
+            overlap_scores = {}
+            target_stock_normalized = self.normalize_stock_code(target_stock)
+            
+            # 计算行业重叠分数（每个行业+3分）
+            for bk_code, stock_list in industry_stocks.items():
+                for stock_code in stock_list:
+                    if stock_code == target_stock_normalized:
+                        continue  # 跳过目标股票本身
+                    
+                    if stock_code not in overlap_scores:
+                        overlap_scores[stock_code] = 0
+                    
+                    overlap_scores[stock_code] += self.INDUSTRY_WEIGHT
+            
+            # 计算概念重叠分数（每个概念+1分）
+            for bk_code, stock_list in concept_stocks.items():
+                for stock_code in stock_list:
+                    if stock_code == target_stock_normalized:
+                        continue  # 跳过目标股票本身
+                    
+                    if stock_code not in overlap_scores:
+                        overlap_scores[stock_code] = 0
+                    
+                    overlap_scores[stock_code] += self.CONCEPT_WEIGHT
+            
+            logger.info(f"计算出 {len(overlap_scores)} 只股票的重叠分数")
+            return overlap_scores
+            
+        except Exception as e:
+            logger.error(f"计算重叠分数失败: {str(e)}")
+            return {}
+    
+    def filter_high_overlap_stocks(self, overlap_scores: Dict[str, float]) -> List[Tuple[str, float]]:
+        """
+        筛选高重叠度股票
+        
+        Args:
+            overlap_scores: 重叠分数字典
+            
+        Returns:
+            List[Tuple[str, float]]: [(股票代码, 分数)] 按分数降序排列
+        """
+        try:
+            # 筛选分数大于阈值的股票
+            high_overlap_stocks = [
+                (stock_code, score) for stock_code, score in overlap_scores.items() 
+                if score > self.MIN_OVERLAP_SCORE
+            ]
+            
+            # 按分数降序排列
+            high_overlap_stocks.sort(key=lambda x: x[1], reverse=True)
+            
+            logger.info(f"筛选出 {len(high_overlap_stocks)} 只高重叠度股票（分数>{self.MIN_OVERLAP_SCORE}）")
+            return high_overlap_stocks
+            
+        except Exception as e:
+            logger.error(f"筛选高重叠度股票失败: {str(e)}")
+            return []
+    
+    def get_recent_price_changes(self, stock_codes: List[str], days: int = 3) -> Dict[str, Dict]:
+        """
+        获取股票的近期涨跌幅（默认近3个交易日）
+        
+        Args:
+            stock_codes: 股票代码列表
+            days: 统计天数，默认3个交易日
+            
+        Returns:
+            Dict[str, Dict]: {股票代码: {price_change, change_pct, latest_price}}
+        """
+        try:
+            price_changes = {}
+            
+            for stock_code in stock_codes:
+                # 获取最近N个交易日的价格数据
+                query = text("""
+                    SELECT close, percent, timestamp
+                    FROM gp_day_data 
+                    WHERE symbol = :stock_code 
+                    ORDER BY timestamp DESC 
+                    LIMIT :days
+                """)
+                
+                with self.mysql_engine.connect() as conn:
+                    result = conn.execute(query, {"stock_code": stock_code, "days": days}).fetchall()
+                
+                if len(result) >= 2:  # 至少需要2个交易日的数据
+                    # 最新价格（第一个）
+                    latest_price = float(result[0][0]) if result[0][0] else None
+                    latest_change_pct = float(result[0][1]) if result[0][1] else None
+                    
+                    # N天前价格（最后一个）
+                    historical_price = float(result[-1][0]) if result[-1][0] else None
+                    
+                    if latest_price and historical_price:
+                        price_change = latest_price - historical_price
+                        change_pct = (price_change / historical_price) * 100
+                        
+                        price_changes[stock_code] = {
+                            'latest_price': latest_price,
+                            'price_change': price_change,
+                            'change_pct': change_pct,
+                            'latest_change_pct': latest_change_pct,
+                            'trading_days': len(result)
+                        }
+            
+            logger.info(f"获取到 {len(price_changes)} 只股票的近{days}个交易日涨跌幅数据")
+            return price_changes
+            
+        except Exception as e:
+            logger.error(f"获取近期涨跌幅失败: {str(e)}")
+            return {}
+    
+    def analyze_lag_performance(self, target_change: Dict, top5_stocks: List[Tuple[str, float]], similar_changes: Dict[str, Dict]) -> Dict:
+        """
+        分析目标股票的滞涨情况（基于近3个交易日）
+        
+        Args:
+            target_change: 目标股票涨跌幅数据
+            top5_stocks: 重叠度最高的5只股票 [(股票代码, 重叠分数)]
+            similar_changes: 相似股票涨跌幅数据
+            
+        Returns:
+            Dict: 滞涨分析结果
+        """
+        try:
+            if not target_change or 'change_pct' not in target_change:
+                logger.warning("目标股票涨跌幅数据不完整，无法进行滞涨分析")
+                return {
+                    'target_lag_vs_top5': None,
+                    'target_lag_vs_top1': None,
+                    'top5_avg_change': None,
+                    'top1_change': None
+                }
+            
+            target_change_pct = target_change['change_pct']
+            
+            # 获取前5只股票的有效涨跌幅数据
+            top5_changes = []
+            for stock_code, _ in top5_stocks:
+                if stock_code in similar_changes and 'change_pct' in similar_changes[stock_code]:
+                    change_pct = similar_changes[stock_code]['change_pct']
+                    if change_pct is not None:
+                        top5_changes.append(change_pct)
+            
+            if len(top5_changes) < 1:
+                logger.warning("没有有效的前5只股票涨跌幅数据")
+                return {
+                    'target_lag_vs_top5': None,
+                    'target_lag_vs_top1': None,
+                    'top5_avg_change': None,
+                    'top1_change': None
+                }
+            
+            # 计算前5只股票的平均涨幅
+            top5_avg_change = sum(top5_changes) / len(top5_changes)
+            
+            # 获取重叠度最高的1只股票涨幅
+            top1_change = top5_changes[0] if top5_changes else None
+            
+            # 计算滞涨分数
+            lag_vs_top5 = target_change_pct - top5_avg_change if top5_avg_change is not None else None
+            lag_vs_top1 = target_change_pct - top1_change if top1_change is not None else None
+            
+            # 滞涨等级判断
+            def get_lag_level(lag_score):
+                if lag_score is None:
+                    return "无数据"
+                elif lag_score < -8:
+                    return "严重滞涨"
+                elif lag_score < -4:
+                    return "明显滞涨"
+                elif lag_score < -1.5:
+                    return "轻微滞涨"
+                elif lag_score > 4:
+                    return "跑赢同行"
+                elif lag_score > 1.5:
+                    return "略胜同行"
+                else:
+                    return "正常水平"
+            result = {
+                'target_lag_vs_top5': {
+                    'lag_score': lag_vs_top5,
+                    'lag_level': get_lag_level(lag_vs_top5),
+                    'target_change_pct': target_change_pct,
+                    'top5_avg_change': top5_avg_change
+                },
+                'target_lag_vs_top1': {
+                    'lag_score': lag_vs_top1,
+                    'lag_level': get_lag_level(lag_vs_top1),
+                    'target_change_pct': target_change_pct,
+                    'top1_change': top1_change
+                },
+                'top5_avg_change': top5_avg_change,
+                'top1_change': top1_change
+            }
+            
+            logger.info(f"滞涨分析完成 - 目标股票: {target_change_pct:.2f}%, 前5平均: {top5_avg_change:.2f}%, 最高1只: {top1_change:.2f}%")
+            return result
+            
+        except Exception as e:
+            logger.error(f"滞涨分析失败: {str(e)}")
+            return {
+                'target_lag_vs_top5': None,
+                'target_lag_vs_top1': None,
+                'top5_avg_change': None,
+                'top1_change': None
+            }
+    
+    def get_stock_name(self, stock_code: str) -> Optional[str]:
+        """
+        获取股票名称
+        
+        Args:
+            stock_code: 股票代码
+            
+        Returns:
+            str: 股票名称
+        """
+        try:
+            normalized_code = self.normalize_stock_code(stock_code)
+            
+            query = text("""
+                SELECT gp_name
+                FROM gp_code_all 
+                WHERE gp_code = :stock_code
+                LIMIT 1
+            """)
+            
+            with self.mysql_engine.connect() as conn:
+                result = conn.execute(query, {"stock_code": normalized_code}).fetchone()
+                
+            if result and result[0]:
+                return result[0]
+            else:
+                return None
+                
+        except Exception as e:
+            logger.error(f"获取股票名称失败 {stock_code}: {str(e)}")
+            return None
+    
+    def analyze_stock_overlap(self, stock_code: str, days: int = 20) -> Dict:
+        """
+        分析股票重叠度的主函数
+        
+        Args:
+            stock_code: 目标股票代码
+            days: 统计涨跌幅的天数
+            
+        Returns:
+            Dict: 分析结果
+        """
+        try:
+            logger.info(f"开始分析股票 {stock_code} 的重叠度")
+            
+            # 1. 获取目标股票的行业和概念板块
+            industries = self.get_stock_industries(stock_code)
+            concepts = self.get_stock_concepts(stock_code)
+            
+            if not industries and not concepts:
+                logger.warning(f"股票 {stock_code} 没有找到行业或概念板块数据")
+                return {
+                    'target_stock': stock_code,
+                    'error': '未找到行业或概念板块数据'
+                }
+            
+            # 2. 获取相似股票
+            industry_stocks = self.get_similar_stocks_by_industry(industries)
+            concept_stocks = self.get_similar_stocks_by_concept(concepts)
+            
+            # 3. 计算重叠分数
+            overlap_scores = self.calculate_overlap_scores(stock_code, industry_stocks, concept_stocks)
+            
+            # 4. 筛选高重叠度股票
+            high_overlap_stocks = self.filter_high_overlap_stocks(overlap_scores)
+            
+            if not high_overlap_stocks:
+                logger.info(f"股票 {stock_code} 没有找到高重叠度股票（分数>{self.MIN_OVERLAP_SCORE}）")
+                return {
+                    'target_stock': stock_code,
+                    'similar_stocks_count': 0,
+                    'message': f'没有找到重叠度超过{self.MIN_OVERLAP_SCORE}分的股票'
+                }
+            
+            # 5. 获取前5只重叠度最高的股票
+            top5_stocks = high_overlap_stocks[:5]  # 取前5只
+            top5_stock_codes = [stock[0] for stock in top5_stocks]
+            all_stock_codes = [self.normalize_stock_code(stock_code)] + top5_stock_codes
+            
+            price_changes = self.get_recent_price_changes(all_stock_codes, days)
+            
+            # 6. 滞涨分析
+            target_change = price_changes.get(self.normalize_stock_code(stock_code))
+            similar_changes = {code: data for code, data in price_changes.items() 
+                             if code != self.normalize_stock_code(stock_code)}
+            
+            lag_analysis = self.analyze_lag_performance(target_change, top5_stocks, similar_changes)
+            
+            # 7. 组装前5只股票结果
+            top5_results = []
+            for similar_stock, overlap_score in top5_stocks:
+                stock_name = self.get_stock_name(similar_stock)
+                price_data = price_changes.get(similar_stock, {})
+                
+                top5_results.append({
+                    'stock_code': similar_stock,
+                    'stock_name': stock_name,
+                    'overlap_score': overlap_score,
+                    'latest_price': price_data.get('latest_price'),
+                    'price_change': price_data.get('price_change'),
+                    'change_pct': price_data.get('change_pct')
+                })
+            
+            return {
+                'target_stock': stock_code,
+                'target_stock_name': self.get_stock_name(stock_code),
+                'target_price_data': target_change,
+                'analysis_date': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
+                'analysis_period_days': days,
+                'industries': [{'code': code, 'name': name} for code, name in industries],
+                'concepts': [{'code': code, 'name': name} for code, name in concepts],
+                'overlap_threshold': self.MIN_OVERLAP_SCORE,
+                'top5_stocks': top5_results,
+                'lag_analysis': lag_analysis
+            }
+            
+        except Exception as e:
+            logger.error(f"分析股票重叠度失败 {stock_code}: {str(e)}")
+            return {
+                'target_stock': stock_code,
+                'error': str(e)
+            }
+    
+    def close_connection(self):
+        """关闭数据库连接"""
+        try:
+            if self.mysql_engine:
+                self.mysql_engine.dispose()
+                logger.info("MySQL连接已关闭")
+        except Exception as e:
+            logger.error(f"关闭MySQL连接失败: {str(e)}")
+
+
+def main():
+    """主函数 - 示例用法"""
+    analyzer = None
+    try:
+        # 创建分析器实例
+        analyzer = OverlapAnalyzer()
+        
+        # 示例：分析某只股票的重叠度
+        stock_code = "300661.SZ"  # 圣邦股份
+        
+        print(f"=== 股票重叠度分析：{stock_code} ===")
+        
+        # 执行分析
+        result = analyzer.analyze_stock_overlap(stock_code, days=3)
+        
+        if 'error' in result:
+            print(f"分析失败: {result['error']}")
+            return
+        
+        # 输出结果
+        print(f"\n目标股票: {result['target_stock_name']} ({result['target_stock']})")
+        print(f"分析日期: {result['analysis_date']}")
+        print(f"统计周期: {result['analysis_period_days']}天")
+        
+        if 'target_price_data' in result and result['target_price_data']:
+            target_data = result['target_price_data']
+            print(f"目标股票涨跌幅: {target_data.get('change_pct', 0):.2f}%")
+        
+        print(f"\n行业板块: {len(result['industries'])}个")
+        for industry in result['industries'][:3]:  # 显示前3个
+            print(f"  - {industry['name']} ({industry['code']})")
+        
+        print(f"\n概念板块: {len(result['concepts'])}个")
+        for concept in result['concepts'][:3]:  # 显示前3个
+            print(f"  - {concept['name']} ({concept['code']})")
+        
+        print(f"\n重叠度最高的5只股票:")
+        print("-" * 80)
+        print(f"{'股票代码':<12} {'股票名称':<15} {'重叠分数':<8} {'最新价格':<10} {'涨跌幅':<10}")
+        print("-" * 80)
+        
+        for stock in result['top5_stocks']:
+            print(f"{stock['stock_code']:<12} "
+                  f"{stock['stock_name'] or '未知':<15} "
+                  f"{stock['overlap_score']:<8.1f} "
+                  f"{stock['latest_price'] or 0:<10.2f} "
+                  f"{stock['change_pct'] or 0:<10.2f}%")
+        
+        # 显示滞涨分析结果
+        lag_analysis = result.get('lag_analysis', {})
+        if lag_analysis:
+            print(f"\n滞涨分析结果:")
+            print("-" * 50)
+            
+            # vs 前5平均
+            vs_top5 = lag_analysis.get('target_lag_vs_top5', {})
+            if vs_top5:
+                print(f"vs 前5平均: {vs_top5.get('lag_score', 0):.2f}% ({vs_top5.get('lag_level', '未知')})")
+                print(f"  目标股票: {vs_top5.get('target_change_pct', 0):.2f}%")
+                print(f"  前5平均: {vs_top5.get('top5_avg_change', 0):.2f}%")
+            
+            # vs 最高1只
+            vs_top1 = lag_analysis.get('target_lag_vs_top1', {})
+            if vs_top1:
+                print(f"vs 最高1只: {vs_top1.get('lag_score', 0):.2f}% ({vs_top1.get('lag_level', '未知')})")
+                print(f"  目标股票: {vs_top1.get('target_change_pct', 0):.2f}%")
+                print(f"  最高1只: {vs_top1.get('top1_change', 0):.2f}%")
+        
+    except Exception as e:
+        logger.error(f"程序执行失败: {str(e)}")
+    finally:
+        if analyzer:
+            analyzer.close_connection()
+
+
+if __name__ == "__main__":
+    main()

src/quantitative_analysis/tech_fundamental_factor_strategy.py

@@ -713,6 +713,28 @@ def main():
                 print(f"  最高总分: {df['total_score'].max():.2f}")
                 print(f"  最低总分: {df['total_score'].min():.2f}")
         
+        # 生成成长+成熟合并的简表（仅三列：股票代码、总分、排名）
+        combined_parts = []
+        for stage, df in results.items():
+            if isinstance(df, pd.DataFrame) and not df.empty:
+                if 'stock_code' in df.columns and 'total_score' in df.columns:
+                    combined_parts.append(df[['stock_code', 'total_score']].copy())
+        
+        if combined_parts:
+            combined_df = pd.concat(combined_parts, ignore_index=True)
+            # 去除总分为空的数据
+            combined_df = combined_df.dropna(subset=['total_score'])
+            # 按总分降序并重新排名
+            combined_df = combined_df.sort_values('total_score', ascending=False).reset_index(drop=True)
+            combined_df['rank'] = range(1, len(combined_df) + 1)
+            # 保存文件
+            combined_file = f"tech_fundamental_factor_all_{datetime.now().strftime('%Y%m%d_%H%M')}.csv"
+            combined_df.to_csv(combined_file, index=False, encoding='utf-8-sig')
+            print(f"\n=== 合并结果（成长+成熟） ===")
+            print(f"总股票数量: {len(combined_df)}")
+            print(combined_df.head(10).to_string(index=False))
+            print(f"\n合并简表已保存到: {combined_file}")
+        
         print(f"\n=== 策略运行完成 ===")
         
     except Exception as e:

src/quantitative_analysis/tech_fundamental_factor_strategy_v2.py

@@ -0,0 +1,757 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+是固态电池、人形机器人、通信设备、算力租赁四个赛道的筛选。
+结合个股历史基本面，以及个股波动情况，这里波动指标是一个波动越大，分数越高的指标
+v2并不是科技主题选股！！！！！！--这里就是入口--请执行这个文件！
+整合企业生命周期、财务指标和平均距离因子分析
+"""
+
+import sys
+import pandas as pd
+import numpy as np
+import logging
+from typing import Dict, List, Tuple
+from pathlib import Path
+from sqlalchemy import create_engine, text
+from datetime import datetime
+import math
+
+# 添加项目根路径到Python路径
+project_root = Path(__file__).parent.parent.parent
+sys.path.append(str(project_root))
+
+# 导入依赖的工具类
+from src.quantitative_analysis.company_lifecycle_factor import CompanyLifecycleFactor
+from src.quantitative_analysis.financial_indicator_analyzer import FinancialIndicatorAnalyzer
+from src.quantitative_analysis.average_distance_factor import AverageDistanceFactor
+from src.valuation_analysis.config import MONGO_CONFIG2, DB_URL
+
+# 设置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+
+class TechFundamentalFactorStrategy:
+    """科技主题基本面因子选股策略"""
+    
+    def __init__(self):
+        """初始化策略"""
+        self.lifecycle_calculator = CompanyLifecycleFactor()
+        self.financial_analyzer = FinancialIndicatorAnalyzer()
+        self.distance_calculator = AverageDistanceFactor(DB_URL)
+        
+        # MySQL连接
+        self.mysql_engine = create_engine(
+            DB_URL,
+            pool_size=5,
+            max_overflow=10,
+            pool_recycle=3600
+        )
+        
+        # 科技概念板块列表
+        self.tech_concepts = [
+            "固态电池", "人形机器人", "通信设备", "算力租赁"
+        ]
+        logger.info("科技主题基本面因子选股策略初始化完成")
+    
+    def get_tech_stocks(self) -> pd.DataFrame:
+        """
+        获取科技概念板块的股票列表
+        
+        Returns:
+            pd.DataFrame: 包含股票代码和名称的DataFrame
+        """
+        try:
+            # 构建查询条件
+            concepts_str = "', '".join(self.tech_concepts)
+            query = text(f"""
+                SELECT DISTINCT gp_code as stock_code, gp_name as stock_name, bk_name as concept_name
+                FROM gp_gnbk 
+                WHERE bk_name IN ('{concepts_str}')
+                UNION
+                SELECT DISTINCT gp_code as stock_code, gp_name as stock_name, bk_name as concept_name
+                FROM gp_hybk
+                WHERE bk_name = '通信设备'
+                ORDER BY stock_code
+            """)
+
+            with self.mysql_engine.connect() as conn:
+                df = pd.read_sql(query, conn)
+            
+            logger.info(f"获取到 {len(df)} 只科技概念股票")
+            return df
+            
+        except Exception as e:
+            logger.error(f"获取科技概念股票失败: {str(e)}")
+            return pd.DataFrame()
+    
+    def filter_by_lifecycle(self, stock_codes: List[str], year: int = 2024) -> Dict[str, List[str]]:
+        """
+        根据企业生命周期筛选股票
+        
+        Args:
+            stock_codes: 股票代码列表
+            year: 分析年份
+            
+        Returns:
+            Dict: 包含成长期和成熟期股票的字典
+        """
+        try:
+            logger.info(f"开始分析 {len(stock_codes)} 只股票的企业生命周期")
+            
+            # 批量计算生命周期
+            lifecycle_df = self.lifecycle_calculator.batch_calculate_lifecycle_factors(stock_codes, year)
+            
+            # 筛选目标阶段的股票
+            # 引入期(1)和成长期(2)合并为成长期，成熟期(3)保持不变
+            growth_stage_stocks = lifecycle_df[
+                lifecycle_df['stage_id'].isin([1, 2])
+            ]['stock_code'].tolist()
+            
+            mature_stage_stocks = lifecycle_df[
+                lifecycle_df['stage_id'] == 3
+            ]['stock_code'].tolist()
+            
+            result = {
+                'growth': growth_stage_stocks,
+                'mature': mature_stage_stocks
+            }
+            
+            logger.info(f"成长期股票: {len(growth_stage_stocks)} 只")
+            logger.info(f"成熟期股票: {len(mature_stage_stocks)} 只")
+            
+            return result
+            
+        except Exception as e:
+            logger.error(f"生命周期筛选失败: {str(e)}")
+            return {'growth': [], 'mature': []}
+    
+    def calculate_distance_factors(self, growth_stocks: List[str], mature_stocks: List[str]) -> Tuple[pd.DataFrame, pd.DataFrame]:
+        """
+        分别计算成长期和成熟期股票的平均距离因子
+        
+        Args:
+            growth_stocks: 成长期股票列表
+            mature_stocks: 成熟期股票列表
+            
+        Returns:
+            Tuple: (成长期距离因子DataFrame, 成熟期距离因子DataFrame)
+        """
+        try:
+            growth_distance_df = pd.DataFrame()
+            mature_distance_df = pd.DataFrame()
+            
+            # 计算成长期股票距离因子
+            if growth_stocks:
+                logger.info(f"计算 {len(growth_stocks)} 只成长期股票的距离因子")
+                growth_data = self.distance_calculator.get_stock_data(growth_stocks)
+                if not growth_data.empty:
+                    growth_indicators = self.distance_calculator.calculate_technical_indicators(growth_data)
+                    growth_distance_df = self.distance_calculator.calculate_distance_factor(growth_indicators)
+            
+            # 计算成熟期股票距离因子
+            if mature_stocks:
+                logger.info(f"计算 {len(mature_stocks)} 只成熟期股票的距离因子")
+                mature_data = self.distance_calculator.get_stock_data(mature_stocks)
+                if not mature_data.empty:
+                    mature_indicators = self.distance_calculator.calculate_technical_indicators(mature_data)
+                    mature_distance_df = self.distance_calculator.calculate_distance_factor(mature_indicators)
+            
+            return growth_distance_df, mature_distance_df
+            
+        except Exception as e:
+            logger.error(f"计算距离因子失败: {str(e)}")
+            return pd.DataFrame(), pd.DataFrame()
+    
+    def calculate_common_factors(self, stock_codes: List[str]) -> pd.DataFrame:
+        """
+        计算通用因子
+        
+        Args:
+            stock_codes: 股票代码列表
+            
+        Returns:
+            pd.DataFrame: 包含通用因子的DataFrame
+        """
+        try:
+            logger.info(f"计算 {len(stock_codes)} 只股票的通用因子")
+            
+            results = []
+            latest_date = "2025-06-30"  # 最新季度数据
+            annual_date = "2024-12-31"  # 年报数据
+            
+            for stock_code in stock_codes:
+                try:
+
+                    factor_data = {'stock_code': stock_code}
+                    
+                    # 1. 毛利率（使用最新数据）
+                    gross_margin = self.financial_analyzer.analyze_gross_profit_margin(stock_code, latest_date)
+                    factor_data['gross_profit_margin'] = gross_margin
+                    
+                    # 2. 成长能力指标
+                    growth_capability = self.financial_analyzer.analyze_growth_capability(stock_code)
+                    if growth_capability is not None:
+                        # 成长能力越高越好，使用sigmoid函数映射到0-1
+                        growth_score = 1 / (1 + math.exp(-growth_capability))
+                    else:
+                        growth_score = 0.5  # 默认中性评分
+                    factor_data['growth_score'] = growth_score
+                    
+                    # 3. 前五大供应商占比（使用年报数据）
+                    supplier_conc = self.financial_analyzer.analyze_supplier_concentration(stock_code, annual_date)
+                    factor_data['supplier_concentration'] = supplier_conc
+
+                    # 4. 前五大客户占比（使用年报数据）
+                    customer_conc = self.financial_analyzer.analyze_customer_concentration(stock_code, annual_date)
+                    factor_data['customer_concentration'] = customer_conc
+                    
+                    results.append(factor_data)
+                    
+                except Exception as e:
+                    logger.warning(f"计算股票 {stock_code} 通用因子失败: {str(e)}")
+                    continue
+            
+            df = pd.DataFrame(results)
+            logger.info(f"成功计算 {len(df)} 只股票的通用因子")
+            return df
+            
+        except Exception as e:
+            logger.error(f"计算通用因子失败: {str(e)}")
+            return pd.DataFrame()
+    
+    def calculate_growth_specific_factors(self, stock_codes: List[str]) -> pd.DataFrame:
+        """
+        计算成长期特色因子
+        
+        Args:
+            stock_codes: 成长期股票代码列表
+            
+        Returns:
+            pd.DataFrame: 包含成长期特色因子的DataFrame
+        """
+        try:
+            logger.info(f"计算 {len(stock_codes)} 只成长期股票的特色因子")
+            
+            results = []
+            latest_date = "2025-06-30"  # 使用最新数据
+            annual_date = "2024-12-31"  # 使用年度数据
+
+            for stock_code in stock_codes:
+                try:
+
+                    factor_data = {'stock_code': stock_code}
+                    
+                    # 1. 管理费用率（使用最新数据）
+                    admin_ratio = self.financial_analyzer.analyze_admin_expense_ratio(stock_code, latest_date)
+                    factor_data['admin_expense_ratio'] = admin_ratio
+                    
+                    # 2. 研发费用折旧摊销占比（使用年度数据）
+                    # financial_data = self.financial_analyzer.get_financial_data(stock_code, latest_date)
+                    financial_data = self.financial_analyzer.get_financial_data(stock_code, annual_date)
+                    if financial_data:
+                        intangible_amortize = financial_data.get('cash_flow_statement', {}).get('IA_AMORTIZE', 0)
+                        rd_expense = financial_data.get('profit_statement', {}).get('RESEARCH_EXPENSE', 0)
+                        
+                        if rd_expense and rd_expense != 0:
+                            rd_amortize_ratio = intangible_amortize / rd_expense if intangible_amortize else 0
+                        else:
+                            rd_amortize_ratio = None  # 使用None而不是0，避免这些股票获得最高分
+                        
+                        factor_data['rd_amortize_ratio'] = rd_amortize_ratio
+                    else:
+                        factor_data['rd_amortize_ratio'] = None
+                    
+                    # 3. 资产负债率（使用最新数据）
+                    asset_liability_ratio = self.financial_analyzer.analyze_asset_liability_ratio(stock_code, latest_date)
+                    factor_data['asset_liability_ratio'] = asset_liability_ratio
+                    
+                    results.append(factor_data)
+                    
+                except Exception as e:
+                    logger.warning(f"计算股票 {stock_code} 成长期特色因子失败: {str(e)}")
+                    continue
+            
+            df = pd.DataFrame(results)
+            logger.info(f"成功计算 {len(df)} 只成长期股票的特色因子")
+            return df
+            
+        except Exception as e:
+            logger.error(f"计算成长期特色因子失败: {str(e)}")
+            return pd.DataFrame()
+    
+    def calculate_mature_specific_factors(self, stock_codes: List[str]) -> pd.DataFrame:
+        """
+        计算成熟期特色因子
+        
+        Args:
+            stock_codes: 成熟期股票代码列表
+            
+        Returns:
+            pd.DataFrame: 包含成熟期特色因子的DataFrame
+        """
+        try:
+            logger.info(f"计算 {len(stock_codes)} 只成熟期股票的特色因子")
+            
+            latest_date = "2025-06-30"  # 使用最新数据
+            
+            # 在循环外获取全A股PB和ROE数据，避免重复查询
+            logger.info("获取全A股PB数据...")
+            all_pb_data = self.financial_analyzer.get_all_stocks_pb_data()
+            
+            logger.info("获取全A股ROE数据...")
+            all_roe_data = self.financial_analyzer.get_all_stocks_roe_data(latest_date)
+            
+            results = []
+            
+            for stock_code in stock_codes:
+                try:
+                    factor_data = {'stock_code': stock_code}
+                    
+                    # 1. 应收账款周转率（使用最新数据）
+                    formatted_stock_code = self.financial_analyzer.code_formatter.to_dot_format(stock_code)
+                    financial_data = self.financial_analyzer.get_financial_data(formatted_stock_code, latest_date)
+                    if financial_data:
+                        revenue = financial_data.get('profit_statement', {}).get('OPERATE_INCOME', 0)
+                        accounts_rece = financial_data.get('balance_sheet', {}).get('ACCOUNTS_RECE', 0)
+                        
+                        if accounts_rece and accounts_rece != 0:
+                            turnover_ratio = revenue / accounts_rece if revenue else 0
+                        else:
+                            turnover_ratio = None  # 使用None而不是0
+                        
+                        factor_data['accounts_receivable_turnover'] = turnover_ratio
+                    else:
+                        factor_data['accounts_receivable_turnover'] = None
+                    
+                    # 2. 研发强度（使用最新数据）
+                    rd_intensity = self.financial_analyzer.analyze_rd_expense_ratio(stock_code, latest_date)
+                    factor_data['rd_intensity'] = rd_intensity
+                    
+                    # 3. PB-ROE排名因子：使用预获取的全A股数据
+                    if all_pb_data and all_roe_data:
+                        pb_roe_rank_factor = self.financial_analyzer.calculate_pb_roe_rank_factor(
+                            stock_code, all_pb_data, all_roe_data
+                        )
+                        factor_data['pb_roe_rank_factor'] = pb_roe_rank_factor
+                    else:
+                        factor_data['pb_roe_rank_factor'] = None
+                    
+                    results.append(factor_data)
+                    
+                except Exception as e:
+                    logger.warning(f"计算股票 {stock_code} 成熟期特色因子失败: {str(e)}")
+                    continue
+            
+            df = pd.DataFrame(results)
+            logger.info(f"成功计算 {len(df)} 只成熟期股票的特色因子")
+            return df
+            
+        except Exception as e:
+            logger.error(f"计算成熟期特色因子失败: {str(e)}")
+            return pd.DataFrame()
+    
+    def run_strategy(self, year: int = 2024) -> Dict[str, pd.DataFrame]:
+        """
+        运行完整的选股策略
+        
+        Args:
+            year: 分析年份
+            
+        Returns:
+            Dict: 包含成长期和成熟期股票分析结果的字典
+        """
+        try:
+            logger.info("开始运行科技主题基本面因子选股策略")
+            
+            # 1. 获取科技概念股票
+            tech_stocks_df = self.get_tech_stocks()
+            if tech_stocks_df.empty:
+                logger.error("未获取到科技概念股票")
+                return {}
+            
+            stock_codes = tech_stocks_df['stock_code'].unique().tolist()
+            logger.info(f"共获取到 {len(stock_codes)} 只科技概念股票")
+            
+            # 2. 按企业生命周期筛选
+            lifecycle_result = self.filter_by_lifecycle(stock_codes, year)
+            growth_stocks = lifecycle_result['growth']
+            mature_stocks = lifecycle_result['mature']
+            
+            if not growth_stocks and not mature_stocks:
+                logger.warning("未找到符合条件的成长期或成熟期股票")
+                return {}
+            
+            # 3. 计算平均距离因子
+            growth_distance_df, mature_distance_df = self.calculate_distance_factors(growth_stocks, mature_stocks)
+            
+            # 4. 计算通用因子
+            all_qualified_stocks = growth_stocks + mature_stocks
+            common_factors_df = self.calculate_common_factors(all_qualified_stocks)
+            
+            # 5. 计算特色因子
+            growth_specific_df = self.calculate_growth_specific_factors(growth_stocks) if growth_stocks else pd.DataFrame()
+            mature_specific_df = self.calculate_mature_specific_factors(mature_stocks) if mature_stocks else pd.DataFrame()
+            
+            # 6. 合并结果并计算分数
+            result = {}
+            
+            # 处理成长期股票
+            if not growth_specific_df.empty:
+                # 成长期结果合并
+                growth_result = growth_specific_df.copy()
+                
+                # 合并距离因子
+                if not growth_distance_df.empty:
+                    growth_result = growth_result.merge(
+                        growth_distance_df[['symbol', 'avg_distance_factor']], 
+                        left_on='stock_code', right_on='symbol', how='left'
+                    ).drop('symbol', axis=1)
+                
+                # 合并通用因子
+                if not common_factors_df.empty:
+                    growth_result = growth_result.merge(
+                        common_factors_df, on='stock_code', how='left'
+                    )
+                
+                # 计算因子分数
+                growth_result = self.calculate_factor_scores(growth_result, 'growth')
+                
+                # 计算总分并排序
+                growth_result = self.calculate_total_score(growth_result, 'growth')
+                
+                result['growth'] = growth_result
+                logger.info(f"成长期结果: {len(growth_result)} 只股票")
+            
+            # 处理成熟期股票
+            if not mature_specific_df.empty:
+                # 成熟期结果合并
+                mature_result = mature_specific_df.copy()
+                
+                # 合并距离因子
+                if not mature_distance_df.empty:
+                    mature_result = mature_result.merge(
+                        mature_distance_df[['symbol', 'avg_distance_factor']], 
+                        left_on='stock_code', right_on='symbol', how='left'
+                    ).drop('symbol', axis=1)
+                
+                # 合并通用因子
+                if not common_factors_df.empty:
+                    mature_result = mature_result.merge(
+                        common_factors_df, on='stock_code', how='left'
+                    )
+                
+                # 计算因子分数
+                mature_result = self.calculate_factor_scores(mature_result, 'mature')
+                
+                # 计算总分并排序
+                mature_result = self.calculate_total_score(mature_result, 'mature')
+                
+                result['mature'] = mature_result
+                logger.info(f"成熟期结果: {len(mature_result)} 只股票")
+            
+            logger.info("科技主题基本面因子选股策略运行完成")
+            return result
+            
+        except Exception as e:
+            logger.error(f"策略运行失败: {str(e)}")
+            return {}
+    
+    def calculate_factor_scores(self, df: pd.DataFrame, stage: str) -> pd.DataFrame:
+        """
+        计算单因子打分（0-100分位数）
+        
+        Args:
+            df: 包含因子数据的DataFrame
+            stage: 阶段类型 ('growth' 或 'mature')
+            
+        Returns:
+            pd.DataFrame: 包含因子分数的DataFrame
+        """
+        try:
+            if df.empty:
+                return df
+            
+            df_scored = df.copy()
+            
+            # 定义因子方向（正向为True，负向为False）
+            factor_directions = {
+                # 通用因子
+                'gross_profit_margin': True,  # 毛利率_环比增量 - 正向
+                'growth_score': True,       # 成长能力 - 正向
+                'supplier_concentration': False,  # 前5大供应商金额占比合计 - 负向
+                'customer_concentration': False,  # 前5大客户收入金额占比合计 - 负向
+                'avg_distance_factor': True,     # 平均距离因子 - 负向
+                
+                # 成长期特色因子
+                'admin_expense_ratio': False,     # 管理费用/营业总收入_环比增量 - 负向
+                'rd_amortize_ratio': False,       # 研发费用折旧摊销占比_环比增量 - 负向
+                'asset_liability_ratio': True,    # 资产负债率 - 正向
+                
+                # 成熟期特色因子
+                'accounts_receivable_turnover': True,  # 应收账款周转率 - 正向
+                'rd_intensity': True,                  # 研发费用直接投入占比_环比增量 - 正向
+                'pb_roe_rank_factor': False            # PB-ROE排名因子 - 负向（越小越好）
+            }
+            
+            # 为每个因子计算分位数分数
+            for column in df.columns:
+                if column == 'stock_code':
+                    continue
+                
+                # 只对有效值进行排名计算
+                values = df_scored[column].dropna()
+                if len(values) <= 1:
+                    # 如果只有一个值或没有值，所有股票都得50分或0分
+                    if len(values) == 1:
+                        df_scored[f'{column}_score'] = df_scored[column].apply(lambda x: 50 if pd.notna(x) else 0)
+                    else:
+                        df_scored[f'{column}_score'] = 0
+                    continue
+                
+                # 根据因子方向确定排序方式
+                is_positive = factor_directions.get(column, True)
+                
+                # 计算排名分数
+                if is_positive:
+                    # 正向因子：值越大分数越高
+                    ranked_values = values.rank(pct=True) * 100
+                else:
+                    # 负向因子：值越小分数越高
+                    ranked_values = (1 - values.rank(pct=True)) * 100
+                
+                # 初始化分数列
+                df_scored[f'{column}_score'] = 0.0
+                
+                # 将分数赋值给对应的行
+                for idx in ranked_values.index:
+                    df_scored.loc[idx, f'{column}_score'] = ranked_values[idx]
+            
+            logger.info(f"完成 {stage} 阶段 {len(df_scored)} 只股票的因子打分")
+            return df_scored
+            
+        except Exception as e:
+            logger.error(f"计算因子分数失败: {str(e)}")
+            import traceback
+            traceback.print_exc()
+            return df
+    
+    def calculate_total_score(self, df: pd.DataFrame, stage: str) -> pd.DataFrame:
+        """
+        计算总分
+        使用公式：总分 = 1/8 * Mean(Si) + Mean(Si)/Std(Si)
+        
+        Args:
+            df: 包含因子分数的DataFrame
+            stage: 阶段类型 ('growth' 或 'mature')
+            
+        Returns:
+            pd.DataFrame: 包含总分的DataFrame
+        """
+        try:
+            if df.empty:
+                return df
+            
+            df_result = df.copy()
+            
+            # 定义因子权重（注意：这里是factor_score而不是factor）
+            if stage == 'growth':
+                factor_weights = {
+                    # 通用因子
+                    'gross_profit_margin_score': 1/8,
+                    'growth_score_score': 1/8,  # 注意这里是growth_score_score
+                    'supplier_concentration_score': 1/8,
+                    'customer_concentration_score': 1/8,
+                    'avg_distance_factor_score': 2/8,
+                    
+                    # 成长期特色因子
+                    'admin_expense_ratio_score': 1/8,
+                    'rd_amortize_ratio_score': 1/8,
+                    'asset_liability_ratio_score': 1/8
+                }
+            else:  # mature
+                factor_weights = {
+                    # 通用因子
+                    'gross_profit_margin_score': 1/8,
+                    'growth_score_score': 1/8,  # 注意这里是growth_score_score
+                    'supplier_concentration_score': 1/8,
+                    'customer_concentration_score': 1/8,
+                    'avg_distance_factor_score': 2/8,
+                    
+                    # 成熟期特色因子
+                    'accounts_receivable_turnover_score': 1/8,
+                    'rd_intensity_score': 1/8,
+                    'pb_roe_rank_factor_score': 1/8
+                }
+            
+            # 计算每只股票的总分
+            total_scores = []
+            
+            for index, row in df_result.iterrows():
+                # 获取该股票的所有因子分数
+                factor_scores = []
+                valid_weights = []
+                
+                for factor, weight in factor_weights.items():
+                    if factor in row and pd.notna(row[factor]) and row[factor] > 0:
+                        factor_scores.append(row[factor])
+                        valid_weights.append(weight)
+                
+                if len(factor_scores) == 0:
+                    total_scores.append(0)
+                    continue
+                
+                factor_scores = np.array(factor_scores)
+                valid_weights = np.array(valid_weights)
+                
+                # 重新标准化权重
+                valid_weights = valid_weights / valid_weights.sum()
+                
+                # 计算加权平均分数
+                mean_score = np.average(factor_scores, weights=valid_weights)
+                
+                # 计算调整项 Mean(Si)/Std(Si)
+                if len(factor_scores) > 1 and np.std(factor_scores) > 0:
+                    adjustment = np.mean(factor_scores) / np.std(factor_scores)
+                else:
+                    adjustment = 0
+                
+                # 计算总分：1/8 * Mean(Si) + Mean(Si)/Std(Si)
+                total_score = (1/8) * mean_score + adjustment
+                total_scores.append(total_score)
+            
+            df_result['total_score'] = total_scores
+            
+            # 按总分降序排列
+            df_result = df_result.sort_values('total_score', ascending=False).reset_index(drop=True)
+            df_result['rank'] = range(1, len(df_result) + 1)
+            
+            logger.info(f"完成 {stage} 阶段 {len(df_result)} 只股票的总分计算")
+            return df_result
+            
+        except Exception as e:
+            logger.error(f"计算总分失败: {str(e)}")
+            import traceback
+            traceback.print_exc()
+            return df
+    
+    def close_connections(self):
+        """关闭所有数据库连接"""
+        try:
+            if hasattr(self, 'lifecycle_calculator'):
+                del self.lifecycle_calculator
+            if hasattr(self, 'financial_analyzer'):
+                self.financial_analyzer.close_connection()
+            if hasattr(self, 'distance_calculator'):
+                del self.distance_calculator
+            if hasattr(self, 'mysql_engine'):
+                self.mysql_engine.dispose()
+            logger.info("数据库连接已关闭")
+        except Exception as e:
+            logger.error(f"关闭连接失败: {str(e)}")
+
+
+def main():
+    """主函数 - 科技主题基本面因子选股策略"""
+    strategy = None
+    try:
+        print("=== 科技主题基本面因子选股策略 ===")
+        print("数据说明:")
+        print("- 毛利率、净利润增长率等：使用最新数据 (2025-06-30)")
+        print("- 供应商客户集中度、折旧摊销、研发费用：使用年报数据 (2024-12-31)")
+        print()
+        
+        # 创建策略实例
+        strategy = TechFundamentalFactorStrategy()
+        logger.info("策略实例创建成功")
+        
+        # 运行策略
+        results = strategy.run_strategy(year=2024)
+        
+        # 输出结果
+        if not results:
+            print("未获得分析结果")
+            return
+            
+        for stage, df in results.items():
+            print(f"\n=== {stage.upper()} 阶段股票分析结果 ===")
+            print(f"股票数量: {len(df)}")
+            
+            if not df.empty:
+                # 调试：显示所有列名
+                print(f"数据列: {list(df.columns)}")
+                # 显示前5只股票的关键指标
+                print("\n前5只股票:")
+                display_columns = [
+                    'stock_code', 'gross_profit_margin', 'growth_score', 
+                    'supplier_concentration', 'customer_concentration', 
+                    'total_score', 'rank'
+                ]
+                available_columns = [col for col in display_columns if col in df.columns]
+                print(df[available_columns].head(5).to_string(index=False))
+
+                # 保存完整结果
+                output_file = f"tech_fundamental_factor_{stage}_{datetime.now().strftime('%Y%m%d_%H%M')}.csv"
+                df.to_csv(output_file, index=False, encoding='utf-8-sig')
+                print(f"\n完整结果已保存到: {output_file}")
+                
+                # 显示统计信息
+                print(f"\n统计信息:")
+                print(f"  平均总分: {df['total_score'].mean():.2f}")
+                print(f"  最高总分: {df['total_score'].max():.2f}")
+                print(f"  最低总分: {df['total_score'].min():.2f}")
+        
+        # 生成成长+成熟合并的简表（仅三列：股票代码、总分、排名）
+        combined_parts = []
+        for stage, df in results.items():
+            if isinstance(df, pd.DataFrame) and not df.empty:
+                if 'stock_code' in df.columns and 'total_score' in df.columns:
+                    combined_parts.append(df[['stock_code', 'total_score']].copy())
+        
+        if combined_parts:
+            combined_df = pd.concat(combined_parts, ignore_index=True)
+            # 去除总分为空的数据
+            combined_df = combined_df.dropna(subset=['total_score'])
+            # 按总分降序并重新排名
+            combined_df = combined_df.sort_values('total_score', ascending=False).reset_index(drop=True)
+            combined_df['rank'] = range(1, len(combined_df) + 1)
+            # 追加概念列：获取每个股票所属概念（若多概念则以逗号分隔）
+            try:
+                concept_df = strategy.get_tech_stocks()
+                if not concept_df.empty and 'stock_code' in concept_df.columns and 'concept_name' in concept_df.columns:
+                    concept_map = (
+                        concept_df.groupby('stock_code')['concept_name']
+                        .apply(lambda s: ','.join(sorted(set([str(x) for x in s if pd.notna(x)]))))
+                        .to_dict()
+                    )
+                    combined_df['concepts'] = combined_df['stock_code'].map(concept_map)
+                else:
+                    combined_df['concepts'] = None
+            except Exception:
+                combined_df['concepts'] = None
+            # 保存文件
+            combined_file = f"tech_fundamental_factor_all_{datetime.now().strftime('%Y%m%d_%H%M')}.csv"
+            combined_df.to_csv(combined_file, index=False, encoding='utf-8-sig')
+            print(f"\n=== 合并结果（成长+成熟） ===")
+            print(f"总股票数量: {len(combined_df)}")
+            print(combined_df.head(10).to_string(index=False))
+            print(f"\n合并简表已保存到: {combined_file}")
+        
+        print(f"\n=== 策略运行完成 ===")
+        
+    except Exception as e:
+        logger.error(f"程序执行失败: {str(e)}")
+        import traceback
+        traceback.print_exc()
+    finally:
+        if strategy:
+            strategy.close_connections()
+
+
+if __name__ == "__main__":
+    main()

src/quantitative_analysis/us_batch_stock_price_collector.py

@@ -1,3 +1,5 @@
+#美股行业板块导出，从通达信里面打开美股首页，然后栏目里面有个细分行业。点击导出所有栏目即可
+
 import requests
 import pandas as pd
 from datetime import datetime
@@ -291,3 +293,5 @@ if __name__ == '__main__':
     fetch_and_store_us_stock_data_optimized(use_proxy=False)  # 默认不使用代理
 
 
+
+

src/scripts/config.py

@@ -11,7 +11,7 @@ XUEQIU_HEADERS = {
     'Accept-Encoding': 'gzip, deflate, br, zstd',
     'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
     'Client-Version': 'v2.44.75',
-    'Cookie': 'cookiesu=811743062689927; device_id=33fa3c7fca4a65f8f4354e10ed6b7470; smidV2=20250327160437f244626e8b47ca2a7992f30f389e4e790074ae48656a22f10; HMACCOUNT=8B64A2E3C307C8C0; s=c611ttmqlj; xq_is_login=1; u=8493411634; bid=4065a77ca57a69c83405d6e591ab5449_m8r2nhs8; __utma=1.434320573.1747189698.1747189698.1747189698.1; __utmc=1; __utmz=1.1747189698.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); snbim_minify=true; _c_WBKFRo=dsWgHR8i8KGPbIyhFlN51PHOzVuuNytvUAFppfkD; _nb_ioWEgULi=; aliyungf_tc=00c6b999835b16cea9e4a6aab36cca373a0976bf55ee74770d11f421f7119ad8; Hm_lvt_1db88642e346389874251b5a1eded6e3=1757464900; xq_a_token=975ab9f15a4965b9e557b9bc6f33bc1da20a0f49; xqat=975ab9f15a4965b9e557b9bc6f33bc1da20a0f49; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOjg0OTM0MTE2MzQsImlzcyI6InVjIiwiZXhwIjoxNzYwMjU2NzM4LCJjdG0iOjE3NTc2NjQ3Mzg4MjUsImNpZCI6ImQ5ZDBuNEFadXAifQ.TMx4-TjKx96j5h6-EGiRIM2WKtJm1xctZhYidc40Em0pRcr0UBHAKBGl3No5r1BElYa9qnEDgNYI0Zv137Inx-EMPqm5cd1Z_ZjLdWOSLzT9qqBj8zdfuqJwP2nCYvC6KLjd8BvykS0vSFKqwb-r0WhEA3OzbO8teVNsaemdKAhBoIyP3-RQCfRxJ9RLNha1ZMdg66iZvfz_SOsG41y8IA9yyl-FFFJOq4TnAiywY1yO1QIJJhkh8YQqfnDfQQdSIFgJGToU980Lw1dm4aCDY-kvn-t18KjrL_hZJ_UNN65bgZsSsuWf-VQ7wsjjczNrfBYAHdZ6kES0CGo9g8IZZw; xq_r_token=c209224335327f29fc555d9910b43c0df6d52d5a; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1757774901; .thumbcache_f24b8bbe5a5934237bbc0eda20c1b6e7=rJD0qKtipTMjRBkLBVEyXbl0CiVeY7y4AxEZC0Vf6Zkou9cxp0NPsxwSrnOyFyBMr+Ws5/nJDO1NUalRDyAPsA%3D%3D; acw_tc=3ccdc14717578973700474899e2dc1c35b6358f1af81617250f8f00b4cf31c; ssxmod_itna=1-eqGxBDnGKYuxcD4kDRgxYq7ueYKS8DBP01Dp2xQyP08D60DB40Q0qRHhqDylAkiETFN1t42Y5D/KlYeDZDGFdDqx0Ei6FiYHK1ezjCGbKSAQY5P53Niio89NQ7DEQm6fjL1S4K7s5h8KRDo9n4hiDB3DbqDymgY5qxGGA4GwDGoD34DiDDPDb8rDALeD7qDFnenropTDm4GWneGfDDoDYbT3xiUYDDUvbeG2iET4DDN4bIGYZ2G76=r1doBip29xKiTDjqPD/ShUoiuzZKC4icFL2/amAeGyC5GuY6mWHQ77SWcbscAV70i8hx_Bx3rKqB5YGDRYqK8o2xY9iKR0YRDxeEDW0DWnQ8EwhDDiP46iRiGDYZtgrNMhXiY4MQA7bAilP4nPkFGCmqzBqGYesQGQiT3ihKbm5CexbxxD; ssxmod_itna2=1-eqGxBDnGKYuxcD4kDRgxYq7ueYKS8DBP01Dp2xQyP08D60DB40Q0qRHhqDylAkiETFN1t42YeDA4rYnRItORCitz/D3nyGQigbiD',
+    'Cookie': 'cookiesu=811743062689927; device_id=33fa3c7fca4a65f8f4354e10ed6b7470; smidV2=20250327160437f244626e8b47ca2a7992f30f389e4e790074ae48656a22f10; HMACCOUNT=8B64A2E3C307C8C0; s=c611ttmqlj; xq_is_login=1; u=8493411634; bid=4065a77ca57a69c83405d6e591ab5449_m8r2nhs8; __utma=1.434320573.1747189698.1747189698.1747189698.1; __utmc=1; __utmz=1.1747189698.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); snbim_minify=true; _c_WBKFRo=dsWgHR8i8KGPbIyhFlN51PHOzVuuNytvUAFppfkD; _nb_ioWEgULi=; aliyungf_tc=00c6b999835b16cea9e4a6aab36cca373a0976bf55ee74770d11f421f7119ad8; Hm_lvt_1db88642e346389874251b5a1eded6e3=1757464900; xq_a_token=0c9cfffc3d713428b4759d3c4e11fff91b618525; xqat=0c9cfffc3d713428b4759d3c4e11fff91b618525; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOjg0OTM0MTE2MzQsImlzcyI6InVjIiwiZXhwIjoxNzYxNTYzMTU1LCJjdG0iOjE3NTg5NzExNTUyODksImNpZCI6ImQ5ZDBuNEFadXAifQ.KotT161D0bQF-m3HNgQFTknHqUpMUR_KWY7BAjiLKOaQocVghM85sCKUretUK5OpMDXMzGPhzxTWMs4VhGxKUHxHSu3inrbCw7rgGDtK0Lnr_6OXHkEMwDadN37V3AYbxKWaX609pACLK1q2cvRmGg94wAgj9KEqu76gdV4w4tRv4LupUJQgYb6M0GEVe7ejLs2_CdV5PV7j0PSjTtpjaeZWkc9YhW32vOyA6gg3fU9S4BQg7qgciYLI8AxiU-GYgFLyFSK2S7nvAngz8TEhNoQcClKrD4NeqqSj2nA5bh5_5FM8AbdbKGw6K8eIO0wkxCV2iUWBDMz-h160cX0GLw; xq_r_token=e586d0abb8de83a22a5d66be2f908954a50005b2; .thumbcache_f24b8bbe5a5934237bbc0eda20c1b6e7=nGvY6/KwbtfD3HgPBzY+S0khnrVCqr4mPyfsZ27X+GjYcRWS61PMogABu5uvj/LAd4TJsSFQiYwdEepZMxwg3A%3D%3D; ssxmod_itna=1-iqmxyQG=KWqGqwD4qeqY5Lor=G2zDuDBP01DpxYK0CDmxjKideDUDtTxR3R27rQA04D7777mqqeCQ_4D/A0ieDZDGKQDqx0or0KBiBUPehSmRxdW9gTBThssUUo8vG8FV4x9WCL5ZG9emiTjxIx_D0aDmKDUx4x_BAYDeWFDCeDQxirDD4DAmPDFxibDimAb4DdkK8EvUOpIDGrDlKDRchok4GWDiPD76gDl6gpbDDCDiyjKV3Dixiaz3eDBomc41iI4xi3kb8_c8b5Yq4EWi2ID7v3DlPqjdnIKy/M4E3Eps/9=agju40ODG6CofPchOBoFO3o6=rlwIlqrDKpY4Kleiix57xhx_eQDrWD57IpDx54_xmmZ7hpY21Bb0nQi/AO4b3mDrnNDt0=a0q345Bi5Drhl54nmeYnAD_mmD_GWq7h1iGq7YzGxA8DqBD=4nz7xNImYnb47xxD; ssxmod_itna2=1-iqmxyQG=KWqGqwD4qeqY5Lor=G2zDuDBP01DpxYK0CDmxjKideDUDtTxR3R27rQA04D7777mqqeCQ4DW_QRiAwxKA07vi3WDj4pxkh3pfaDlxTMHwkxxRl_UFFyKFmUR1v7kCiqQHALxyxuseYn8Q79bLg08eBKxkZwGFEy8ZxTGW7YkIrrzM=5YCx_Gem5Qg2HvQz9AhR0FvxfOG7AQwzoPjSpGmtApnKdwC4uUuzI6eDo2Bedxmf8L2fgms1KnurZO0K=m0ifvg8yDYb=qs=GimaBFojOsWf01ibDy6ZP5DLpur3mS//PdQPR0PqEEqiKseLxQQ3iKiC3ijQ5zKLELcAULPdKD6Q86ejjQKAk6K3leiePYGxdGpYpDbO3YPKa_x4RPTxTif5T3mOIGa8TCY44Y4hWn1AQq7G1nDQ7GQ7D5BDxzWw8bz3D; is_overseas=0; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1759979780',
     'Referer': 'https://weibo.com/u/7735765253',
     'Sec-Ch-Ua': '"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
     'Sec-Ch-Ua-Mobile': '?0',