【模型调参】Lgb调参方法

最新推荐文章于 2023-12-28 14:59:25 发布

Novelin

最新推荐文章于 2023-12-28 14:59:25 发布

阅读量2.8k

点赞数 1

分类专栏：【机器学习模型】

本文链接：https://blog.csdn.net/qq_40860934/article/details/114325023

版权

【机器学习模型】专栏收录该内容

4 篇文章 0 订阅

订阅专栏

首先，调参方法有几种：

贪心算法 https://www.jianshu.com/p/ab89df9759c8
网格调参 https://blog.csdn.net/weixin_43172660/article/details/83032029
贝叶斯调参 https://blog.csdn.net/linxid/article/details/81189154

这里以回归任务、 lgb 模型为例子：

参数集合

objective = ['regression', 'regression_l1', 'mape', 'huber', 'fair']
num_leaves = [3,5,10,15,20,40, 55]
max_depth = [3,5,10,15,20,40, 55]
bagging_fraction = []
feature_fraction = []
drop_rate = []

1 贪心调参

best_obj = dict()
for obj in objective:
    model = LGBMRegressor(objective=obj)
    score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
    best_obj[obj] = score
    
best_leaves = dict()
for leaves in num_leaves:
    model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0], num_leaves=leaves)
    score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
    best_leaves[leaves] = score
    
best_depth = dict()
for depth in max_depth:
    model = LGBMRegressor(objective=min(best_obj.items(), key=lambda x:x[1])[0],
                          num_leaves=min(best_leaves.items(), key=lambda x:x[1])[0],
                          max_depth=depth)
    score = np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))
    best_depth[depth] = score

sns.lineplot(x=['0_initial','1_turning_obj','2_turning_leaves','3_turning_depth'], 
			 y=[0.143 ,min(best_obj.values()), 
			 min(best_leaves.values()), min(best_depth.values())])

2 Grid Search

from sklearn.model_selection import GridSearchCV

parameters = {'objective': objective , 'num_leaves': num_leaves, 'max_depth': max_depth}
model = LGBMRegressor()
clf = GridSearchCV(model, parameters, cv=5)
clf = clf.fit(train_X, train_y)

clf.best_params_
model = LGBMRegressor(objective='regression',
                          num_leaves=55,
                          max_depth=15)

np.mean(cross_val_score(model, X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)))

3 贝叶斯调参

from bayes_opt import BayesianOptimization

def rf_cv(num_leaves, max_depth, subsample, min_child_samples):
    val = cross_val_score(
        LGBMRegressor(objective = 'regression_l1',
            num_leaves=int(num_leaves),
            max_depth=int(max_depth),
            subsample = subsample,
            min_child_samples = int(min_child_samples)
        ),
        X=train_X, y=train_y_ln, verbose=0, cv = 5, scoring=make_scorer(mean_absolute_error)
    ).mean()
    return 1 - val
    
rf_bo = BayesianOptimization(
    rf_cv,
    {
    'num_leaves': (2, 100),
    'max_depth': (2, 100),
    'subsample': (0.1, 1),
    'min_child_samples' : (2, 100)
    }
)

rf_bo.maximize()

1 - rf_bo.max['target']