CatBoost | Gradient Boosting ที่รักคอลัมน์เชิงหมวด

from catboost import CatBoostClassifier, Pool
from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, roc_auc_score

data = fetch_openml(name="credit-g", version=1, as_frame=True)
X = data.data
y = (data.target == "good").astype(int)

cat_cols = X.select_dtypes(include="category").columns.tolist()

X_train, X_valid, y_train, y_valid = train_test_split(
    X, y, test_size=0.2, stratify=y, random_state=42
)

train_pool = Pool(X_train, label=y_train, cat_features=cat_cols)
valid_pool = Pool(X_valid, label=y_valid, cat_features=cat_cols)

model = CatBoostClassifier(
    depth=6,
    iterations=1000,
    learning_rate=0.03,
    loss_function="Logloss",
    eval_metric="AUC",
    random_seed=42,
    early_stopping_rounds=50,
    verbose=100,
)
model.fit(train_pool, eval_set=valid_pool, use_best_model=True)

proba = model.predict_proba(X_valid)[:, 1]
pred = (proba >= 0.5).astype(int)
print("ROC-AUC:", roc_auc_score(y_valid, proba))
print(classification_report(y_valid, pred, digits=3))

importance = model.get_feature_importance(type="PredictionValuesChange")
for name, score in sorted(zip(X.columns, importance), key=lambda x: -x[1])[:10]:
    print(f"{name}: {score:.3f}")

shap_values = model.get_feature_importance(valid_pool, type="ShapValues")