From c196da4902c78056ea43f3ddb38dcb2631233664 Mon Sep 17 00:00:00 2001
From: gahusb <bgg8988@gmail.com>
Date: Sun, 31 May 2026 17:06:00 +0900
Subject: [PATCH] =?UTF-8?q?feat(lotto):=20calibrate=5Fwinner=20+=20backfil?=
 =?UTF-8?q?l=20(=EB=A9=B1=EB=93=B1=C2=B7=EC=B2=AD=ED=81=AC)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 lotto/app/backtest.py           | 43 +++++++++++++++++++++++++++++++++
 lotto/tests/test_backtest_db.py | 25 +++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/lotto/app/backtest.py b/lotto/app/backtest.py
index 0b73392..1aa71e4 100644
--- a/lotto/app/backtest.py
+++ b/lotto/app/backtest.py
@@ -105,6 +105,49 @@ def calibrate_winner_compute(draws, target_draw_no, winning6,
     return {"scores": scores, "percentile": percentile, "cache_draws": len(pit)}
 
 
+MIN_HISTORY = 30  # point-in-time 캐시 최소 회차 (이 미만은 캘리브레이션 skip)
+
+
+def _db():
+    from . import db as _db_mod
+    return _db_mod
+
+
+def calibrate_winner(draw_no: int, sample_m: int = 2000) -> Dict[str, Any]:
+    """DB 진입점: 회차 1개 캘리브레이션 후 저장 (멱등)."""
+    db = _db()
+    draws = db.get_all_draw_numbers()
+    row = db.get_draw(draw_no)
+    if row is None:
+        return {"ok": False, "reason": "no_draw"}
+    pit = point_in_time_draws(draws, draw_no)
+    if len(pit) < MIN_HISTORY:
+        return {"ok": False, "reason": "insufficient_history"}
+    winning6 = [row["n1"], row["n2"], row["n3"], row["n4"], row["n5"], row["n6"]]
+    res = calibrate_winner_compute(draws, draw_no, winning6, sample_m=sample_m)
+    db.save_winner_calibration(
+        draw_no=draw_no, winning=winning6, scores=res["scores"],
+        percentile=res["percentile"], my_pick_avg=None,
+        cache_draws=res["cache_draws"],
+    )
+    return {"ok": True, "draw_no": draw_no, **res}
+
+
+def backfill_calibration(batch: int = 50, sample_m: int = 2000) -> Dict[str, Any]:
+    """미처리 회차만 batch개 캘리브레이션 (멱등·재개 가능)."""
+    db = _db()
+    draws = db.get_all_draw_numbers()
+    done = db.get_calibrated_draw_nos()
+    todo = [d for d, _ in draws if d not in done and d > MIN_HISTORY]
+    todo.sort()
+    n = 0
+    for draw_no in todo[:batch]:
+        r = calibrate_winner(draw_no, sample_m=sample_m)
+        if r.get("ok"):
+            n += 1
+    return {"calibrated": n, "remaining": max(0, len(todo) - batch)}
+
+
 def coverage_tickets(k: int, seed: Optional[int] = None) -> List[List[int]]:
     """greedy 커버리지 — 아직 덜 쓰인 번호를 우선 배치해 번호를 넓게 분산.
     (휠링/보장설계는 향후. 현재는 distinct + 번호 사용 균등화)"""
diff --git a/lotto/tests/test_backtest_db.py b/lotto/tests/test_backtest_db.py
index 00123b7..d3f2b65 100644
--- a/lotto/tests/test_backtest_db.py
+++ b/lotto/tests/test_backtest_db.py
@@ -65,6 +65,31 @@ def test_winner_calibration_upsert(monkeypatch):
     assert row["score_total"] == 2.00
 
 
+def _seed_draws(db, n=40):
+    rows = []
+    import random as _r; _r.seed(2)
+    for i in range(1, n + 1):
+        s = sorted(_r.sample(range(1, 46), 6))
+        rows.append({"drw_no": i, "drw_date": f"2020-01-{(i%28)+1:02d}",
+                     "n1": s[0], "n2": s[1], "n3": s[2], "n4": s[3],
+                     "n5": s[4], "n6": s[5], "bonus": ((s[5] % 45) + 1)})
+    db.upsert_many_draws(rows)
+
+def test_backfill_calibration_idempotent(monkeypatch):
+    db = _fresh_db(monkeypatch)
+    _seed_draws(db, 40)
+    from app import backtest as bt
+    r1 = bt.backfill_calibration(batch=15, sample_m=200)
+    # 첫 회차는 point-in-time 데이터가 빈약 → min_history 이후만 처리
+    done1 = len(db.get_calibrated_draw_nos())
+    assert done1 > 0
+    r2 = bt.backfill_calibration(batch=100, sample_m=200)  # 나머지
+    done2 = len(db.get_calibrated_draw_nos())
+    assert done2 >= done1
+    r3 = bt.backfill_calibration(batch=100, sample_m=200)  # 재실행 → 추가 0
+    assert r3["calibrated"] == 0
+
+
 def test_get_calibrated_draw_nos(monkeypatch):
     """저장된 draw_no 집합이 get_calibrated_draw_nos에 포함되어야 한다."""
     db = _fresh_db(monkeypatch)