MoFin/archive/evolution-cleanup-20260821/evolution/lesson_extractor.py

# -*- coding: utf-8 -*-
"""
evolution/lesson_extractor.py — 实盘平仓教训提取（2026-08-15 重写）

旧版病状（见 docs/decisions/2026-08-15-策略自我进化闭环重构.md）：
  - 硬编码 version='v_next4'（已证伪策略）
  - 名为"已平仓交易教训"，实际读的是回测 trades 而非实盘平仓
  - 用 LLM 逐笔分析回测 trades（既贵又假——回测交易没有"教训"可挖）

重写方向（设计文档批准）：
  1. 数据源改实盘：strategy_tracking 已平仓记录（status=hit_tp/hit_sl/expired/manual_close）
  2. 结合当日温区（market_regime）归因
  3. 规则化提取（非 LLM）：命中止盈=盈利规律，止损/超时=亏损教训
  4. 每周一次，跟随 evolution_engine 同跑（周六 22:00）

幂等：按 trade_id 去重（同笔不重复写）；已写过的 lesson_text 跳过。
"""
import sys, os, sqlite3
from datetime import datetime, timedelta

sys.path.insert(0, "/home/hmo/MoFin")

DB = os.environ.get("MOFIN_DB", "/home/hmo/MoFin/data/mofin.db")
LOOKBACK_DAYS = 30   # 提取近30天已平仓

# 状态 → 教训类型映射
STATUS_LESSON = {
    "hit_tp": ("win_pattern", "止盈有效"),
    "hit_sl": ("loss_pattern", "止损生效"),
    "expired": ("loss_pattern", "持有到期未达目标"),
    "manual_close": ("loss_pattern", "人工平仓"),
}

# 平仓原因 → 细化教训
REASON_TEXT = {
    "止盈触发": "触达止盈位落袋",
    "止损触发": "跌破止损位离场",
    "反弹减仓触发": "反弹遇阻减仓",
    "超时退出": "持有超时退出",
}


def get_conn():
    conn = sqlite3.connect(DB)
    conn.row_factory = sqlite3.Row
    return conn


def get_regime_for(conn, date_str, market="a"):
    """取指定日期最近的市场温区"""
    r = conn.execute(
        "SELECT regime FROM market_regime WHERE market=? AND date<=? ORDER BY date DESC LIMIT 1",
        (market, date_str)).fetchone()
    return r["regime"] if r else None


def extract_lessons(days=LOOKBACK_DAYS, verbose=True):
    """提取近 N 天实盘已平仓交易的教训"""
    conn = get_conn()
    since = (datetime.now() - timedelta(days=days)).strftime("%Y-%m-%d")

    rows = conn.execute("""
        SELECT id, code, name, status, closed_at, close_reason, theoretical_pnl,
               actual_pnl, actual_exit_reason
        FROM strategy_tracking
        WHERE status != 'active' AND closed_at >= ?
        ORDER BY closed_at DESC
    """, (since,)).fetchall()
    if not rows:
        if verbose:
            print(f"近{days}天无已平仓记录，跳过", flush=True)
        conn.close()
        return []

    # 统计 + 提取
    stats = {"hit_tp": 0, "hit_sl": 0, "expired": 0, "manual_close": 0}
    lessons = []
    written = 0
    for r in rows:
        status = r["status"]
        stats[status] = stats.get(status, 0) + 1
        # 只对止盈/止损提取（expired/manual_close 噪音大，跳过教训提取但统计）
        if status not in ("hit_tp", "hit_sl"):
            continue
        pnl = r["actual_pnl"] if r["actual_pnl"] is not None else r["theoretical_pnl"]
        if pnl is None:
            continue
        # 幂等：同 trade_id 已写过则跳过
        exist = conn.execute(
            "SELECT 1 FROM strategy_lessons WHERE trade_id=? AND lesson_type=?",
            (r["id"], "win_pattern" if status == "hit_tp" else "loss_pattern")).fetchone()
        if exist:
            continue

        regime = get_regime_for(conn, (r["closed_at"] or "")[:10])
        reason_txt = REASON_TEXT.get(r["close_reason"], r["close_reason"] or "平仓")
        if status == "hit_tp":
            ltype = "win_pattern"
            conf = 0.6 if pnl >= 5 else 0.4
            text = (f"实盘止盈：{r['name']}({r['code']}) {reason_txt}，"
                    f"收益{pnl:+.1f}%" + (f"（{regime}温区）" if regime else ""))
        else:
            ltype = "loss_pattern"
            conf = 0.6 if pnl <= -5 else 0.4
            text = (f"实盘止损：{r['name']}({r['code']}) {reason_txt}，"
                    f"亏损{pnl:+.1f}%" + (f"（{regime}温区）" if regime else ""))
        lessons.append({
            "trade_id": r["id"], "lesson_type": ltype, "lesson_text": text,
            "confidence": conf, "profit_pct": pnl,
        })

    # 写库
    for l in lessons:
        conn.execute("""
            INSERT INTO strategy_lessons (strategy_version, trade_id, lesson_type, lesson_text, confidence, applied)
            VALUES ('live_trades', ?, ?, ?, ?, 0)
        """, (l["trade_id"], l["lesson_type"], l["lesson_text"], l["confidence"]))
        written += 1
    conn.commit()

    # 温区级汇总教训（全部已平仓按温区归因）
    if stats["hit_tp"] + stats["hit_sl"] > 0:
        tp_pnl = sum((r["actual_pnl"] if r["actual_pnl"] is not None else r["theoretical_pnl"] or 0)
                     for r in rows if r["status"] == "hit_tp")
        sl_pnl = sum((r["actual_pnl"] if r["actual_pnl"] is not None else r["theoretical_pnl"] or 0)
                     for r in rows if r["status"] == "hit_sl")
        summary = (f"近{days}天实盘复盘：止盈{stats['hit_tp']}笔(均{round(tp_pnl/max(stats['hit_tp'],1),1)}%)"
                   f" / 止损{stats['hit_sl']}笔(均{round(sl_pnl/max(stats['hit_sl'],1),1)}%)")
        # 汇总教训写一条（幂等：按文本）
        exist_sum = conn.execute(
            "SELECT 1 FROM strategy_lessons WHERE lesson_text=? AND lesson_type='summary'",
            (summary,)).fetchone()
        if not exist_sum:
            conn.execute("""
                INSERT INTO strategy_lessons (strategy_version, trade_id, lesson_type, lesson_text, confidence, applied)
                VALUES ('live_trades', NULL, 'summary', ?, 0.8, 0)
            """, (summary,))
            written += 1
        conn.commit()

    conn.close()
    if verbose:
        print(f"近{days}天已平仓: {stats}，新增教训 {written} 条", flush=True)
        for l in lessons[:5]:
            print(f"  [{l['lesson_type']}] {l['lesson_text']} ({l['confidence']})", flush=True)
    return lessons


if __name__ == "__main__":
    extract_lessons()