Classifier Comparison: GradientBoostingClassifier vs XGBClassifier vs LGBMClassifier vs CatBoostClassifier

snippet.py

from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
# Models
from sklearn.ensemble import GradientBoostingClassifier
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier
from catboost import CatBoostClassifier

# define dataset
X, y = make_classification(n_samples=3000, n_features=20, n_informative=15, n_redundant=5, random_state=1)
print(X[1:5,:])

# evaluate the model
classifiers = {
    "XGBoost": XGBClassifier(),
    "GradientBoostingClassifier": GradientBoostingClassifier(),
    "LGBMClassifier": LGBMClassifier(),
    "CatBoostClassifier": CatBoostClassifier()
}
cv = RepeatedStratifiedKFold(n_splits=5, n_repeats=3, random_state=1)
for name, model in classifiers.items():
    n_scores = cross_val_score(model, X, y, scoring="roc_auc", cv=cv, n_jobs=-1, error_score='raise')
    print(f"{name}\n{mean(n_scores)}, {std(n_scores)}")