kis_trader/diag_backtest_4_30.py

"""
4/30 SHORT/SCALP 백테스트 진단 스크립트.

목적:
  1) SHORT 0건의 진짜 원인 — 어느 임계치에서 거래가 발생하는지 sweep
  2) SCALP -90만 trades 의 종목·시각·매매 상세
"""
from __future__ import annotations
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent))

from database import TradeDB
from kis_trader.engine import tail_engine as te
from kis_trader.engine import scalping_engine as se


START = "202604300830"
END   = "202604301600"


def _load_universe(db, sid: str) -> dict:
    """target_candidates_history → {slot_key: [codes]}."""
    rows = db.conn.execute(
        "SELECT slot_key, code FROM target_candidates_history "
        "WHERE strategy_id=%s AND DATE(event_time)='2026-04-30'",
        (sid,),
    ).fetchall()
    history: dict = {}
    for r in rows:
        history.setdefault(r["slot_key"], []).append(r["code"])
    return history


def _load_candles(db, codes, tf: int, min_n: int = 19) -> dict:
    out = {}
    for code in codes:
        rows = db.conn.execute(
            "SELECT candle_time, open, high, low, close, volume FROM ws_candles "
            "WHERE timeframe=%s AND code=%s AND candle_time>=%s AND candle_time<=%s "
            "AND is_confirmed=1 ORDER BY candle_time",
            (tf, code, START, END),
        ).fetchall()
        if len(rows) >= min_n:
            out[code] = [dict(r) for r in rows]
    return out


def _trade_pnl(t):
    """엔진별 trade dict 차이를 흡수해 pnl 추출."""
    if t.get("pnl") is not None:
        return float(t["pnl"])
    try:
        entry = float(t.get("entry") or t.get("buy_price") or 0)
        exit_ = float(t.get("exit") or t.get("sell_price") or 0)
        qty = int(t.get("qty") or 1)
        return (exit_ - entry) * qty
    except Exception:
        return 0.0


def _summary(trades):
    if not trades:
        return "trades=0"
    n = len(trades)
    pnls = [_trade_pnl(t) for t in trades]
    win = sum(1 for p in pnls if p > 0)
    return (f"trades={n} pnl합={sum(pnls):,.0f}원 "
            f"승률={win}/{n}={win/n*100:.0f}% avg={sum(pnls)/n:,.0f}원")


def diag_short(db):
    print("\n" + "=" * 70)
    print("SHORT (꼬리잡기) 4/30 진단")
    print("=" * 70)

    history = _load_universe(db, "SHORT")
    codes = {c for lst in history.values() for c in lst}
    print(f"universe: {len(codes)}종목, {len(history)}슬롯")

    candles = _load_candles(db, codes, tf=3, min_n=19)
    print(f"3분봉 적재: {len(candles)}종목 (RSI 계산 가능)")

    base = te.get_tail_defaults_from_db()
    base["scan_interval_min"] = 1  # SHORT slot 1분 단위

    print()
    print("--- 현재 DB 임계치 ---")
    print(f"  min_drop_rate      = {base['min_drop_rate']*100:.2f}%")
    print(f"  min_recovery_ratio = {base['min_recovery_ratio']*100:.0f}%")
    print(f"  tail_ratio_min     = {base['tail_ratio_min']:.2f}")
    print(f"  tail_pct_min       = {base['tail_pct_min']*100:.2f}%")
    print(f"  max_daily_change   = {base['max_daily_change']:.1f}%")
    print(f"  ma20_max_above     = {base['ma20_max_above']:.1f}%")
    print(f"  rsi_threshold      = {base['rsi_threshold']:.1f}")
    print(f"  max_rec_3m         = {base['max_rec_3m']*100:.0f}%")
    print(f"  high_chase_thr     = {base['high_chase_thr']:.2f}")

    print()
    print("--- 현재 임계치로 백테스트 ---")
    trades = te.run_tail_backtest(candles, dict(base), universe_by_slot=history)
    print(f"  → {_summary(trades)}")

    print()
    print("--- 임계치 단계적 완화 sweep ---")
    sweeps = [
        ("baseline (현재)", {}),
        ("MIN_DROP 1.5% / REC 25%", {"min_drop_rate": 0.015, "min_recovery_ratio": 0.25}),
        ("MIN_DROP 1.0% / REC 20%", {"min_drop_rate": 0.010, "min_recovery_ratio": 0.20}),
        ("MIN_DROP 0.5% / REC 10%", {"min_drop_rate": 0.005, "min_recovery_ratio": 0.10}),
        ("MIN_DROP 0% / REC 0%",    {"min_drop_rate": 0.0,   "min_recovery_ratio": 0.0}),
        ("MA20 ∞ / RSI ∞ + 위 같음", {
            "min_drop_rate": 0.0, "min_recovery_ratio": 0.0,
            "ma20_max_above": 999.0, "rsi_threshold": 999.0,
            "max_daily_change": 999.0, "max_rec_3m": 1.0,
            "high_chase_thr": 999.0,
            "tail_ratio_min": 0.0, "tail_pct_min": 0.0,
        }),
    ]
    for name, ov in sweeps:
        p = dict(base)
        p.update(ov)
        try:
            t = te.run_tail_backtest(candles, p, universe_by_slot=history)
            print(f"  {name:35s} → {_summary(t)}")
        except Exception as e:
            print(f"  {name:35s} → 예외: {e}")


def diag_scalp(db):
    print("\n" + "=" * 70)
    print("SCALP 4/30 진단")
    print("=" * 70)

    history = _load_universe(db, "SCALP")
    codes = {c for lst in history.values() for c in lst}
    print(f"universe: {len(codes)}종목, {len(history)}슬롯")

    # SCALP universe slot 의 분 단위 분포 (5분 정렬 매칭률 보기)
    from collections import Counter
    mins = Counter(int(k[10:12]) for k in history.keys() if len(k) >= 12)
    aligned5 = sum(c for m, c in mins.items() if m % 5 == 0)
    total = sum(mins.values())
    print(f"  slot 5분 정렬 매칭률 (backtest_web 의 scan_interval_min=5 와 매칭): "
          f"{aligned5}/{total} = {aligned5/total*100:.0f}%" if total else "")

    candles = _load_candles(db, codes, tf=1, min_n=10)
    print(f"1분봉 적재: {len(candles)}종목")

    base = se.get_scalping_defaults_from_db()

    # backtest_web SCALP 와 동일하게 scan_interval_min=5 로 1차 시도
    base["scan_interval_min"] = 5
    print()
    print("--- backtest_web 과 동일 (scan_interval_min=5) ---")
    trades5 = se.run_scalping_backtest(candles, dict(base), universe_by_slot=history)
    print(f"  → {_summary(trades5)}")

    # 1분 슬롯과 1:1 매칭 (universe history 1분 키와 일치)
    base["scan_interval_min"] = 1
    print()
    print("--- 보정: scan_interval_min=1 (universe slot 키와 일치) ---")
    trades1 = se.run_scalping_backtest(candles, dict(base), universe_by_slot=history)
    print(f"  → {_summary(trades1)}")

    trades = trades1 if trades1 else trades5
    if trades:
        print()
        print(f"--- trades 상세 (총 {len(trades)}건) ---")
        for t in trades:
            t["pnl"] = _trade_pnl(t)
        trades.sort(key=lambda x: x["pnl"])
        print("  ▼ 손실 큰 5건:")
        for t in trades[:5]:
            print(f"    {t.get('code')} {t.get('buy_time')}→{t.get('sell_time')} "
                  f"매수 {t.get('buy_price'):.0f} → 매도 {t.get('sell_price'):.0f} "
                  f"×{t.get('qty')} pnl={t['pnl']:,.0f} ({t.get('sell_reason')})")
        print("  ▲ 수익 큰 5건:")
        for t in trades[-5:][::-1]:
            print(f"    {t.get('code')} {t.get('buy_time')}→{t.get('sell_time')} "
                  f"매수 {t.get('buy_price'):.0f} → 매도 {t.get('sell_price'):.0f} "
                  f"×{t.get('qty')} pnl={t['pnl']:,.0f} ({t.get('sell_reason')})")
        cnt = Counter(t.get("sell_reason") for t in trades)
        print(f"  sell_reason 분포: {dict(cnt)}")


def main():
    db = TradeDB()
    try:
        diag_short(db)
        diag_scalp(db)
    finally:
        db.close()


if __name__ == "__main__":
    main()