def fit_eval_and_log(model, name, filename, params, fit_kwargs=None):
    print(f"\n--- Training Model: {name} ---")
    start_time = time.time()
    model.fit(X_train, y_train, **(fit_kwargs or {}))
    print(f"[Training Info] Model training completed in {time.time() - start_time:.3f} seconds.")

    preds = model.predict(X_test)
    probs = model.predict_proba(X_test)[:, 1] if hasattr(model, "predict_proba") else preds.astype(float)

    metrics = {
        "Accuracy": round(accuracy_score(y_test, preds), 6),
        "Precision": round(precision_score(y_test, preds, zero_division=0), 6),
        "Recall": round(recall_score(y_test, preds, zero_division=0), 6),
        "AUC-ROC": round(roc_auc_score(y_test, probs), 6),
        "AUC-PR": round(average_precision_score(y_test, probs), 6),
    }
    print(f"{name} Test AUC-PR:", metrics["AUC-PR"])

    joblib.dump(model, filename)
    log_experiment_run(name, params, metrics)
    return metrics

# Baseline vs. tuned, run back to back so the comparison is apples to apples
xgb_base = xgb.XGBClassifier(use_label_encoder=False, eval_metric="logloss", random_state=42)
fit_eval_and_log(
    xgb_base, "XGBoost (Baseline)", "xgboost_model.joblib", xgb_base.get_params(),
    fit_kwargs={"eval_set": [(X_train, y_train), (X_test, y_test)], "verbose": 10}
)

xgb_tuned_params = tuned_params.get("xgboost", {
    "n_estimators": 150, "max_depth": 6, "learning_rate": 0.1,
    "subsample": 0.8, "colsample_bytree": 0.8, "random_state": 42
})
xgb_tuned = xgb.XGBClassifier(**xgb_tuned_params, use_label_encoder=False, eval_metric="logloss")
fit_eval_and_log(xgb_tuned, "XGBoost (Tuned)", "xgboost_model_tuned.joblib", xgb_tuned_params)

lgb_base = lgb.LGBMClassifier(random_state=42, verbose=-1)
fit_eval_and_log(lgb_base, "LightGBM (Baseline)", "lightgbm_model.joblib", lgb_base.get_params())