"""
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()