关于lgb模型参数的问题，可以采用贝叶斯全局优化来调参
import lightgbm as lgb from bayes_opt import BayesianOptimization import warnings warnings.filterwarnings("ignore") from sklearn.datasets import make_classification X, y = make_classification(n_samples=10000,n_features=20,n_classes=2,random_state=2) data = lgb.Dataset(X,y) def lgb_cv(feature_fraction,bagging_fraction,min_data_in_leaf,max_depth,min_split_gain,num_leaves,lambda_l1,lambda_l2,num_iterations=1000): params = {'objective':'binary','num_iterations': num_iterations, 'early_stopping_round':50, 'metric':'l1'} params['feature_fraction'] = max(min(feature_fraction, 1), 0) params['bagging_fraction'] = max(min(bagging_fraction, 1), 0) params["min_data_in_leaf"] = int(round(min_data_in_leaf)) params['max_depth'] = int(round(max_depth)) params['min_split_gain'] = min_split_gain params["num_leaves"] = int(round(num_leaves)) params['lambda_l1'] = max(lambda_l1, 0) params['lambda_l2'] = max(lambda_l2, 0) cv_result = lgb.cv(params, data, nfold=5, seed=2, stratified=True, verbose_eval =50) return -(min(cv_result['l1-mean'])) lgb_bo = BayesianOptimization( lgb_cv, {'feature_fraction': (0.5, 1), 'bagging_fraction': (0.5, 1), 'min_data_in_leaf': (1,100), 'max_depth': (3, 15), 'min_split_gain': (0, 5), 'num_leaves': (16, 128), 'lambda_l1': (0, 100), 'lambda_l2': (0, 100)} ) lgb_bo.maximize(init_points=21,n_iter=90) #init_points表示初始点，n_iter代表迭代次数（即采样数） print (lgb_bo.max)