etf/tests/experiments/ab_test_emerging_market.py

"""
A/B测试：添加新兴市场大类的影响
对比：
- A组（对照组）：当前配置（无新兴市场）
- B组（实验组）：添加印度作为新兴市场大类

核心问题：添加新大类是否增加跨类分散、提升绩效
"""

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

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


def create_config_with_india(base_config: dict) -> dict:
    """在基础配置上添加印度市场"""
    config = base_config.copy()
    config['code_list'] = base_config['code_list'].copy()
    
    # 添加印度市场（新大类）
    # YFinance印度指数需要用^NSEI格式
    config['code_list']['^NSEI'] = {
        'name': '印度Nifty50',
        'etf': '164824.SZ',  # 工银瑞信印度市场LOF
        'market': 'EM'  # 新兴市场大类
    }
    
    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()
    
    if result is None or len(result) == 0:
        return None
    
    # 计算指标
    strategy_nav = result['轮动策略净值']
    strategy_ret = result['轮动策略日收益率']
    
    total_return = strategy_nav.iloc[-1] - 1
    days = len(result)
    years = days / 250
    cagr = (strategy_nav.iloc[-1] ** (1/years)) - 1
    excess_ret = strategy_ret.mean() * 250
    vol = strategy_ret.std() * (250 ** 0.5)
    sharpe = excess_ret / vol if vol > 0 else 0
    rolling_max = strategy_nav.cummax()
    drawdown = (strategy_nav - rolling_max) / rolling_max
    max_dd = drawdown.min()
    calmar = cagr / abs(max_dd) if max_dd < 0 else 0
    win_rate = (strategy_ret > 0).sum() / len(strategy_ret)
    
    # 计算调仓次数
    trades = result.get('调仓记录', [])
    rebalance_count = len(trades) if trades else 0
    
    # 统计大类数量
    markets = set()
    for code_info in config['code_list'].values():
        markets.add(code_info.get('market', 'A'))
    
    metrics = {
        'label': label,
        '大类数量': len(markets),
        '累计收益': total_return,
        'CAGR': cagr,
        'Sharpe': sharpe,
        'MaxDD': max_dd,
        'Calmar': calmar,
        '日胜率': win_rate,
        '调仓次数': rebalance_count,
    }
    
    print(f"\n大类数量: {metrics['大类数量']}")
    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%}")
    print(f"调仓次数: {metrics['调仓次数']}")
    
    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':<15} {'A组(无新兴)':<15} {'B组(有印度)':<15} {'差异':<15}")
    print("-" * 60)
    
    metrics_keys = ['大类数量', '累计收益', 'CAGR', 'Sharpe', 'MaxDD', 'Calmar', '日胜率', '调仓次数']
    
    for key in metrics_keys:
        a_val = a_metrics.get(key, 0)
        b_val = b_metrics.get(key, 0)
        
        diff = b_val - a_val
        if key in ['累计收益', 'CAGR', 'MaxDD', '日胜率']:
            a_str = f"{a_val:.2%}"
            b_str = f"{b_val:.2%}"
            diff_str = f"{diff*100:+.2f}%"
        elif key in ['大类数量', '调仓次数']:
            a_str = str(a_val)
            b_str = str(b_val)
            diff_str = f"+{diff}" if diff > 0 else str(diff)
        else:
            a_str = f"{a_val:.2f}"
            b_str = f"{b_val:.2f}"
            diff_str = f"{diff:+.2f}"
        
        print(f"{key:<15} {a_str:<15} {b_str:<15} {diff_str:<15}")
    
    print("-" * 60)
    
    print(f"\n【关键发现】")
    print(f"添加印度新兴市场大类效果：")
    
    if b_metrics['大类数量'] > a_metrics['大类数量']:
        print(f"  ✓ 大类数量增加 {b_metrics['大类数量'] - a_metrics['大类数量']}（跨类分散提升）")
    
    if b_metrics['累计收益'] > a_metrics['累计收益']:
        print(f"  ✓ 累计收益提升 {b_metrics['累计收益'] - a_metrics['累计收益']:.2%}")
        print(f"  → 新大类确实带来收益增益")
    elif b_metrics['累计收益'] < a_metrics['累计收益']:
        print(f"  ✗ 累计收益下降 {a_metrics['累计收益'] - b_metrics['累计收益']:.2%}")
        print(f"  → 印度市场可能动量信号不够强或流动性问题")
    
    if b_metrics['Sharpe'] > a_metrics['Sharpe']:
        print(f"  ✓ Sharpe改善 {b_metrics['Sharpe'] - a_metrics['Sharpe']:.2f}")
    else:
        print(f"  ✗ Sharpe下降 {a_metrics['Sharpe'] - b_metrics['Sharpe']:.2f}")
    
    if b_metrics['调仓次数'] > a_metrics['调仓次数'] * 1.1:
        print(f"  ⚠ 调仓次数增加 {b_metrics['调仓次数'] - a_metrics['调仓次数']}（可能增加切换成本）")
    
    print(f"\n【策略建议】")
    if b_metrics['累计收益'] > a_metrics['累计收益'] and b_metrics['Sharpe'] >= a_metrics['Sharpe'] * 0.95:
        print(f"  建议：添加印度新兴市场大类（跨类分散有效）")
    elif b_metrics['累计收益'] < a_metrics['累计收益'] * 0.95:
        print(f"  建议：暂不添加印度（收益损失较大）")
        print(f"  原因：LOF流动性可能不足、印度动量信号可能较弱")
    else:
        print(f"  建议：进一步测试其他新兴市场标的（如东南亚科技ETF）")


def main():
    """主函数"""
    config_path = Path(__file__).parent.parent.parent / 'config' / 'strategies' / 'rotation.yaml'
    with open(config_path, 'r') as f:
        base_config = yaml.safe_load(f)
    
    # 添加 end_date
    from datetime import datetime
    base_config['end_date'] = datetime.now().strftime('%Y-%m-%d')
    
    print(f"\n{'='*60}")
    print(f"  A/B测试：添加新兴市场大类（印度）")
    print(f"{'='*60}")
    print(f"\n研究问题：")
    print(f"  - 添加印度作为新大类（EM = Emerging Market）")
    print(f"  - 跨类分散是否真正提升")
    print(f"  - 对比001实验（同大类添加），验证新大类添加效果")
    
    # A组：当前配置
    a_metrics = run_backtest(base_config, "A组: 当前配置（无新兴市场）")
    
    # B组：添加印度
    config_with_india = create_config_with_india(base_config)
    b_metrics = run_backtest(config_with_india, "B组: 添加印度新兴市场")
    
    # 对比
    if a_metrics and b_metrics:
        compare_results(a_metrics, b_metrics)
        
        # 保存结果
        results_df = pd.DataFrame([a_metrics, b_metrics])
        results_path = Path(__file__).parent.parent.parent / 'results' / 'ab_test_emerging_market.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()