experiment(rotation): 同大类扩充与纳指vs标普替换对比实验

技术修复： - SOCKS5代理IPv6问题：socks5:// → socks5h:// (hybrid_source.py, yfinance_source.py) 目录整理： - scripts/ → 仅保留策略入口(daily_scheduler, run_rotation, run_cci_screener) - 实验脚本移至 tests/experiments/ - 工具脚本移至 tests/utils/ - 实验记录新增 docs/experiments/ - results/ 添加到 gitignore 实验结果：实验001 - 同大类扩充（添加标普500）： ├─ 累计收益: 1467.35% → 1176.26% (-291%) ├─ CAGR: 48.10% → 43.82% (-4.28%) ├─ 调仓次数: 459 → 501 (+42次) └─ 结论: 添加同大类标的不增加跨类分散，反而侵蚀收益实验002 - 纳指vs标普替换对比： ├─ 累计收益: 1467.35% → 1118.77% (-348%) ├─ CAGR: 48.10% → 42.87% (-5.22%) ├─ Sharpe: 2.21 → 2.08 (-0.13) ├─ MaxDD: -17.33% → -15.14% (+2.18%) └─ 结论: 纳指100优于标普500，成长风格更适合动量策略策略建议： - 保持纳指100作为美股大类代表 - 不添加同大类新标的（避免类内切换成本） - 新增标的应优先考虑新大类（增加跨类分散）
2026-05-06 20:43:38 +08:00
parent a4e8a6050e
commit 6b59855c28
20 changed files with 1086 additions and 2 deletions
--- a/tests/experiments/analyze_negative_scores.py
+++ b/tests/experiments/analyze_negative_scores.py
@@ -0,0 +1,115 @@
+"""
+分析历史 Top 3 标的中存在负分的情况 (正式版)
+"""
+import sys
+import yaml
+import pandas as pd
+import numpy as np
+from pathlib import Path
+from datetime import datetime
+from dotenv import load_dotenv
+
+# 加载环境变量
+load_dotenv()
+
+# 添加项目根目录
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from strategies.rotation.engine import RotationStrategy
+from core.factors.momentum import compute_factors
+
+def load_config(config_path: str) -> dict:
+    with open(config_path, "r", encoding="utf-8") as f:
+        return yaml.safe_load(f)
+
+def analyze_negative_scores():
+    config_path = "config/strategies/rotation.yaml"
+    config = load_config(config_path)
+    
+    # 强制不使用过滤，以获取完整数据
+    config['diversified'] = True
+    config['select_num'] = 3
+    
+    strategy = RotationStrategy(config)
+    
+    # 使用策略内部方法获取数据
+    with strategy.data_source:
+        index_data, etf_data, etf_nav_data, benchmark_data, valid_codes, index_ohlcv_data = strategy.data_source.fetch_all(
+            config['code_list'], 
+            config['benchmark']['code'], 
+            config["start_date"], 
+            datetime.now().strftime('%Y-%m-%d')
+        )
+    
+    # 手动计算因子 (不带过滤)
+    # 注意：为了分析原始得分，我们将 compute_factors 内部调用的过滤函数暂时跳过或分析结果
+    factor_data, valid_codes = compute_factors(
+        index_data, 
+        valid_codes, 
+        n=config["n_days"], 
+        factor_type=config["factor_type"],
+        auto_day=config.get("auto_day", False),
+        index_ohlcv_data=index_ohlcv_data
+    )
+    
+    score_cols = [c for c in factor_data.columns if c.startswith("得分_")]
+    code_config = config['code_list']
+    
+    total_days = len(factor_data)
+    results = []
+    
+    last_top_3 = set()
+    rebalance_count = 0
+    
+    for date, row in factor_data.iterrows():
+        scores = row[score_cols].dropna()
+        if scores.empty: continue
+        
+        # 模拟 diversified 逻辑下的 Top 3 (不带 >0 过滤)
+        cat_best = {}
+        for col_name, s in scores.items():
+            code = col_name.replace("得分_", "")
+            cat = code_config.get(code, {}).get("market", "未知")
+            if cat not in cat_best or s > cat_best[cat][1]:
+                cat_best[cat] = (code, s)
+        
+        sorted_cats = sorted(cat_best.values(), key=lambda x: x[1], reverse=True)
+        top_3_raw = sorted_cats[:3]
+        current_top_3_codes = set(code for code, s in top_3_raw)
+        
+        # 判断是否发生调仓（目标持仓集合发生变化）
+        if current_top_3_codes != last_top_3:
+            rebalance_count += 1
+            # 统计调仓日这 3 只中得分 <= 0 的数量
+            neg_count = sum(1 for code, s in top_3_raw if s <= 0)
+            
+            results.append({
+                "date": date,
+                "neg_count": neg_count,
+                "top_1_score": top_3_raw[0][1],
+                "top_2_score": top_3_raw[1][1] if len(top_3_raw)>1 else np.nan,
+                "top_3_score": top_3_raw[2][1] if len(top_3_raw)>2 else np.nan,
+                "top_1_name": code_config.get(top_3_raw[0][0], {}).get('name')
+            })
+            last_top_3 = current_top_3_codes
+
+    neg_df = pd.DataFrame(results)
+    
+    print(f"\n{'='*60}")
+    print(f"调仓日 (Rebalance Day) Top 3 标的出现负分情况分析")
+    print(f"{'='*60}")
+    print(f"总调仓次数: {rebalance_count}")
+    print(f"涉及负分(<=0)的调仓次数: {len(neg_df[neg_df['neg_count']>0])} ({len(neg_df[neg_df['neg_count']>0])/rebalance_count:.1%})")
+    
+    if not neg_df.empty:
+        print(f"\n调仓日负分详细分布:")
+        print(f"  - 只有 1 只标的为负: {len(neg_df[neg_df['neg_count']==1])} 次")
+        print(f"  - 有 2 只标的为负:   {len(neg_df[neg_df['neg_count']==2])} 次")
+        print(f"  - 全部 3 只标的均为负: {len(neg_df[neg_df['neg_count']==3])} 次")
+        
+        print(f"\n最近 10 次涉及负分的调仓详情:")
+        neg_df['date'] = pd.to_datetime(neg_df['date'])
+        print(neg_df[neg_df['neg_count']>0][['date', 'neg_count', 'top_1_score', 'top_1_name']].tail(10))
+
+if __name__ == "__main__":
+    analyze_negative_scores()