etf/tests/experiments/ab_test_spx.py

"""
A/B测试：添加标普500对轮动策略的影响
对比：
- A组（对照组）：当前11只标的配置
- B组（实验组）：添加标普500后的12只标的配置
"""

import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))

from strategies.rotation.engine import RotationStrategy
import pandas as pd


def create_config_with_spx(base_config: dict) -> dict:
    """在基础配置上添加标普500"""
    config = base_config.copy()
    config['code_list'] = base_config['code_list'].copy()
    
    # 添加标普500（美股大类内）
    config['code_list']['SPX'] = {
        'name': '标普500',
        'etf': '513500.SH',
        'market': 'US'  # 与纳指100同属美股大类
    }
    
    return config


def run_backtest(config: dict, label: str) -> dict:
    """运行回测并返回关键指标"""
    print(f"\n{'='*60}")
    print(f"  {label}")
    print(f"{'='*60}")
    
    strategy = RotationStrategy(config)
    result = strategy.run()  # result 是 DataFrame
    
    if result is None or len(result) == 0:
        return None
    
    # 从 DataFrame 中直接计算指标
    strategy_nav = result['轮动策略净值']
    strategy_ret = result['轮动策略日收益率']
    benchmark_nav = result['基准净值']
    benchmark_ret = result['基准日收益率']
    
    # 累计收益
    total_return = strategy_nav.iloc[-1] - 1
    
    # CAGR (交易日口径)
    days = len(result)
    years = days / 250
    cagr = (strategy_nav.iloc[-1] ** (1/years)) - 1
    
    # Sharpe
    excess_ret = strategy_ret.mean() * 250  # 年化收益
    vol = strategy_ret.std() * (250 ** 0.5)  # 年化波动
    sharpe = excess_ret / vol if vol > 0 else 0
    
    # 最大回撤
    rolling_max = strategy_nav.cummax()
    drawdown = (strategy_nav - rolling_max) / rolling_max
    max_dd = drawdown.min()
    
    # Calmar
    calmar = cagr / abs(max_dd) if max_dd < 0 else 0
    
    # 日胜率
    win_rate = (strategy_ret > 0).sum() / len(strategy_ret)
    
    # 提取关键指标
    metrics = {
        'label': label,
        '标的数': len(config['code_list']),
        '累计收益': total_return,
        'CAGR': cagr,
        'Sharpe': sharpe,
        'MaxDD': max_dd,
        'Calmar': calmar,
        '日胜率': win_rate,
    }
    
    print(f"\n标的池: {len(config['code_list'])}只")
    print(f"累计收益: {metrics['累计收益']:.2%}")
    print(f"CAGR: {metrics['CAGR']:.2%}")
    print(f"Sharpe: {metrics['Sharpe']:.2f}")
    print(f"MaxDD: {metrics['MaxDD']:.2%}")
    print(f"Calmar: {metrics['Calmar']:.2f}")
    print(f"日胜率: {metrics['日胜率']:.2%}")
    
    return metrics


def compare_results(a_metrics: dict, b_metrics: dict):
    """对比两组结果"""
    print(f"\n{'='*60}")
    print(f"  对比结果")
    print(f"{'='*60}")
    
    print(f"\n{'指标':<12} {'A组(无SPX)':<15} {'B组(有SPX)':<15} {'差异':<15}")
    print("-" * 60)
    
    metrics_keys = ['标的数', '累计收益', 'CAGR', 'Sharpe', 'MaxDD', 'Calmar', '日胜率']
    
    for key in metrics_keys:
        a_val = a_metrics.get(key, 0)
        b_val = b_metrics.get(key, 0)
        
        if key == '标的数':
            diff = b_val - a_val
            diff_str = f"+{diff}" if diff > 0 else str(diff)
        else:
            diff = b_val - a_val
            if key in ['累计收益', 'CAGR', 'MaxDD', '日胜率']:
                diff_str = f"{diff*100:+.2f}%"
            else:
                diff_str = f"{diff:+.2f}"
        
        if key in ['累计收益', 'CAGR', 'MaxDD', '日胜率']:
            a_str = f"{a_val:.2%}"
            b_str = f"{b_val:.2%}"
        else:
            a_str = str(a_val)
            b_str = str(b_val)
        
        print(f"{key:<12} {a_str:<15} {b_str:<15} {diff_str:<15}")
    
    print("-" * 60)
    
    # 分析美股大类内部切换情况
    print(f"\n【关键发现】")
    print(f"添加标普500后：")
    print(f"  - 美股大类从1只→2只（纳指100 + 标普500）")
    print(f"  - 类内竞争：纳指100 vs 标普500，得分高者代表美股大类")
    print(f"  - 跨类分散不变：美股大类还是只输出1只冠军进入Top3")
    
    if b_metrics['累计收益'] != a_metrics['累计收益']:
        print(f"  - 累计收益变化：{a_metrics['累计收益']:.2%} → {b_metrics['累计收益']:.2%}")


def main():
    """主函数"""
    import yaml
    
    # 加载基础配置
    config_path = Path(__file__).parent.parent / 'config' / 'strategies' / 'rotation.yaml'
    with open(config_path, 'r') as f:
        base_config = yaml.safe_load(f)
    
    # 添加缺失的 end_date（使用今天日期）
    from datetime import datetime
    base_config['end_date'] = datetime.now().strftime('%Y-%m-%d')
    
    print(f"\n{'='*60}")
    print(f"  A/B测试：添加标普500对diversified模式的影响")
    print(f"{'='*60}")
    print(f"\n测试假设：")
    print(f"  - diversified=true 模式下，每大类只选1只冠军")
    print(f"  - 添加标普500（同属美股大类）不会增加跨类分散")
    print(f"  - 但可能增加类内切换频率和换手率")
    
    # A组：当前配置（11只，无标普500）
    a_metrics = run_backtest(base_config, "A组: 当前配置（11只，无标普500）")
    
    # B组：添加标普500后的配置（12只）
    config_with_spx = create_config_with_spx(base_config)
    b_metrics = run_backtest(config_with_spx, "B组: 添加标普500（12只）")
    
    # 对比结果
    if a_metrics and b_metrics:
        compare_results(a_metrics, b_metrics)
        
        # 保存对比结果
        results_df = pd.DataFrame([a_metrics, b_metrics])
        results_path = Path(__file__).parent.parent / 'results' / 'ab_test_spx.csv'
        results_df.to_csv(results_path, index=False)
        print(f"\n对比结果已保存: {results_path}")


if __name__ == '__main__':
    main()