From aa413f4d7cd7aebb426d607dd26c6838e355254d Mon Sep 17 00:00:00 2001
From: 21in7 <skawksmsduzo@gmail.com>
Date: Sun, 1 Mar 2026 23:54:13 +0900
Subject: [PATCH] =?UTF-8?q?feat:=20LightGBM=20=EC=9E=84=EA=B3=84=EA=B0=92?=
 =?UTF-8?q?=20=ED=83=90=EC=83=89=EC=9D=84=20=EC=A0=95=EB=B0=80=EB=8F=84=20?=
 =?UTF-8?q?=EC=9A=B0=EC=84=A0(recall>=3D0.15=20=EC=A1=B0=EA=B1=B4=EB=B6=80?=
 =?UTF-8?q?)=EC=9C=BC=EB=A1=9C=20=EB=B3=80=EA=B2=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Made-with: Cursor
---
 scripts/train_model.py | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/scripts/train_model.py b/scripts/train_model.py
index 5850a5b..8d25de2 100644
--- a/scripts/train_model.py
+++ b/scripts/train_model.py
@@ -233,16 +233,26 @@ def train(data_path: str, time_weight_decay: float = 2.0):
 
     val_proba = model.predict_proba(X_val)[:, 1]
     auc = roc_auc_score(y_val, val_proba)
-    # 최적 임계값 탐색 (F1 기준)
-    thresholds = np.arange(0.40, 0.70, 0.05)
-    best_thr, best_f1 = 0.50, 0.0
-    for thr in thresholds:
-        pred = (val_proba >= thr).astype(int)
-        from sklearn.metrics import f1_score
-        f1 = f1_score(y_val, pred, zero_division=0)
-        if f1 > best_f1:
-            best_f1, best_thr = f1, thr
-    print(f"\n검증 AUC: {auc:.4f}  |  최적 임계값: {best_thr:.2f} (F1={best_f1:.3f})")
+
+    # 최적 임계값 탐색: 최소 재현율(0.15) 조건부 정밀도 최대화
+    from sklearn.metrics import precision_recall_curve
+    precisions, recalls, thresholds = precision_recall_curve(y_val, val_proba)
+    # precision_recall_curve의 마지막 원소는 (1.0, 0.0)이므로 제외
+    precisions, recalls = precisions[:-1], recalls[:-1]
+
+    MIN_RECALL = 0.15
+    valid_idx = np.where(recalls >= MIN_RECALL)[0]
+    if len(valid_idx) > 0:
+        best_idx  = valid_idx[np.argmax(precisions[valid_idx])]
+        best_thr  = float(thresholds[best_idx])
+        best_prec = float(precisions[best_idx])
+        best_rec  = float(recalls[best_idx])
+    else:
+        best_thr, best_prec, best_rec = 0.50, 0.0, 0.0
+        print(f"  [경고] recall >= {MIN_RECALL} 조건 만족 임계값 없음 → 기본값 0.50 사용")
+
+    print(f"\n검증 AUC: {auc:.4f}  |  최적 임계값: {best_thr:.4f} "
+          f"(Precision={best_prec:.3f}, Recall={best_rec:.3f})")
     print(classification_report(y_val, (val_proba >= best_thr).astype(int), zero_division=0))
 
     if MODEL_PATH.exists():
@@ -262,6 +272,9 @@ def train(data_path: str, time_weight_decay: float = 2.0):
         "date": datetime.now().isoformat(),
         "backend": "lgbm",
         "auc": round(auc, 4),
+        "best_threshold": round(best_thr, 4),
+        "best_precision": round(best_prec, 3),
+        "best_recall":    round(best_rec, 3),
         "samples": len(dataset),
         "features": len(actual_feature_cols),
         "time_weight_decay": time_weight_decay,