20210326公众号

LightGBM调参

1. 经验法:

往两个方向调：

1.提高准确率：max_depth, num_leaves, learning_rate

2.降低过拟合：max_bin, min_data_in_leaf；L1, L2正则化；数据抽样, 列采样

1.使用较小的num_leaves，max_depth和max_bin，降低复杂度。

2.使用min_data_in_leaf和min_sum_hessian_in_leaf，该值越大，模型的学习越保守。

3.设置bagging_freq和bagging_fraction使用bagging。

4.设置feature_fraction进行特征采样。

5.使用lambda_l1,lambda_l2和min_gain_to_split正则化。

2. 贪心调参:

先调整对模型影响最大的参数，再调整对模型影响次大的参数，缺点是容易调成局部最优，需要多次调试。日常调参顺序如下:

① num_leaves, max_depth

② min_data_in_leaf, min_child_weight

③ bagging_freq, bagging_fraction, feature_fraction,

④ reg_lambda, reg_alpha

⑤ min_split_gain

from sklearn.model_selection import cross_val_score
# 调objective
best_obj = dict()
for obj in objective:
    model = LGBMRegressor(objective=obj)
    score = cross_val_score(model, X_train, y_train, cv=5, scoring='f1').mean()
    best_obj[obj] = score

# num_leaves
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 = cross_val_score(model, X_train, y_train, cv=5, scoring='f1').mean()
    best_leaves[leaves] = score

# max_depth
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 = cross_val_score(model, X_train, y_train, cv=5, scoring='f1').mean()
    best_depth[depth] = score

以此类推，按调参顺序依次调整优化，并且可以对每一个最优参数下模型的得分进行可视化。

3. 网格搜索

即穷举搜索，在参数数组里循环遍历，一般大数据集不会用到，因为速度太慢。

from sklearn.model_selection import GridSearchCV

def get_best_cv_params(learning_rate=0.1, n_estimators=581, num_leaves=31, max_depth=-1, bagging_fraction=1.0, feature_fraction=1.0, bagging_freq=0, min_data_in_leaf=20, min_child_weight=0.001, min_split_gain=0, reg_lambda=0, reg_alpha=0, param_grid=None):

    cv_fold = KFold(n_splits=5, shuffle=True, random_state=2021)

    model_lgb = lgb.LGBMClassifier(learning_rate=learning_rate,
                                   n_estimators=n_estimators,
                                   num_leaves=num_leaves,
                                   max_depth=max_depth,
                                   bagging_fraction=bagging_fraction,
                                   feature_fraction=feature_fraction,
                                   bagging_freq=bagging_freq,
                                   min_data_in_leaf=min_data_in_leaf,
                                   min_child_weight=min_child_weight,
                                   min_split_gain=min_split_gain,
                                   reg_lambda=reg_lambda,
                                   reg_alpha=reg_alpha,
                                   n_jobs= 8
                                  )

    f1 = make_scorer(f1_score, average='micro')
    grid_search = GridSearchCV(estimator=model_lgb, 
                               cv=cv_fold,
                               param_grid=param_grid,
                               scoring=f1

                              )
    grid_search.fit(X_train, y_train)

    print('模型当前最优参数为:{}'.format(grid_search.best_params_))
    print('模型当前最优得分为:{}'.format(grid_search.best_score_))

总体思路是先粗调再细调。在一开始调整时，可设置较大的学习率如0.1，先确定树的个数，再依次调整参数，最后设置较小的学习率如0.05，确定最终参数。

lgb_params = {'num_leaves': range(10, 80, 5), 'max_depth': range(3,10,2)}
get_best_cv_params()
#----------------------------------------
lgb_params = {'num_leaves': range(25, 35, 1), 'max_depth': range(5,9,1)}
get_best_cv_params(n_estimators=85)
#----------------------------------------
lgb_params = {'bagging_fraction': [i/10 for i in range(5,10,1)], 
              'feature_fraction': [i/10 for i in range(5,10,1)],
              'bagging_freq': range(0,81,10)}
get_best_cv_params(n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45）
#----------------------------------------
lgb_params = {'reg_lambda': [0,0.001,0.01,0.03,0.08,0.3,0.5], 'reg_alpha': [0,0.001,0.01,0.03,0.08,0.3,0.5]}
get_best_cv_params(n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45, bagging_fraction=0.9, feature_fraction=0.9, bagging_freq=40)
#----------------------------------------
lgb_params = {'min_split_gain': [i/10 for i in range(0,11,1)]}
get_best_cv_params(n_estimators=85, num_leaves=29, max_depth=7, min_data_in_leaf=45, bagging_fraction=0.9, feature_fraction=0.9, bagging_freq=40, min_split_gain=None)
#----------------------------------------
final_params = {
                'boosting_type': 'gbdt',
                'learning_rate': 0.01,
                'num_leaves': 29,
                'max_depth': 7,
                'objective': 'multiclass',
                'num_class': 4,
                'min_data_in_leaf':45,
                'min_child_weight':0.001,
                'bagging_fraction': 0.9,
                'feature_fraction': 0.9,
                'bagging_freq': 40,
                'min_split_gain': 0,
                'reg_lambda':0,
                'reg_alpha':0,
                'nthread': 6
               }

cv_result = lgb.cv(train_set=lgb_train,
                   early_stopping_rounds=20,
                   num_boost_round=5000,
                   nfold=5,
                   stratified=True,
                   shuffle=True,
                   params=final_params,
                   feval=f1_score_vali,
                   seed=0,
                  )

4. 贝叶斯调参

是一种用模型找到目标函数最小值的方法，比网格和随机搜索省时。步骤如下：

① 定义优化函数(rf_cv）

② 建立模型

③ 定义待优化的参数

④ 得到优化结果，并返回要优化的分数指标

from sklearn.model_selection import cross_val_score
#定义优化函数
def rf_cv_lgb(num_leaves, max_depth, bagging_fraction, feature_fraction, bagging_freq, min_data_in_leaf, 
              min_child_weight, min_split_gain, reg_lambda, reg_alpha):

# 建立模型
    model_lgb = lgb.LGBMClassifier(boosting_type='gbdt', objective='multiclass', num_class=4,learning_rate=0.1, n_estimators=5000,num_leaves=int(num_leaves), max_depth=int(max_depth), bagging_fraction=round(bagging_fraction, 2), feature_fraction=round(feature_fraction, 2),bagging_freq=int(bagging_freq), min_data_in_leaf=int(min_data_in_leaf),min_child_weight=min_child_weight)
    f1 = make_scorer(f1_score, average='micro')
    val = cross_val_score(model_lgb, X_train_split, y_train_split, cv=5, scoring=f1).mean()

    return val

from bayes_opt import BayesianOptimization
#定义优化参数
bayes_lgb = BayesianOptimization(
    rf_cv_lgb, 
    {
        'num_leaves':(10, 200),
        'max_depth':(3, 20),
        'bagging_fraction':(0.5, 1.0),
        'feature_fraction':(0.5, 1.0),
        'bagging_freq':(0, 100),
        'min_data_in_leaf':(10,100),
        'min_child_weight':(0, 10),
        'min_split_gain':(0.0, 1.0),
        'reg_alpha':(0.0, 10),
        'reg_lambda':(0.0, 10),
    }
)

#开始优化
bayes_lgb.maximize(n_iter=20)

#显示优化结果
bayes_lgb.max

参数优化完成后，可根据优化后的参数建立新的模型，降低学习率并寻找最优模型迭代次数。

#设置较小的学习率，并通过cv函数确定当前最优的迭代次数
base_params_lgb = {
                    'boosting_type': 'gbdt',
                    'objective': 'multiclass',
                    'num_class': 4,
                    'learning_rate': 0.01,
                    'num_leaves': 138,
                    'max_depth': 11,
                    'min_data_in_leaf': 43,
                    'min_child_weight': 6.5,
                    'bagging_fraction': 0.64,
                    'feature_fraction': 0.93,
                    'bagging_freq': 49,
                    'reg_lambda': 7,
                    'reg_alpha': 0.21,
                    'min_split_gain': 0.288,
                    'nthread': 10,
                    'verbose': -1,
}

cv_result_lgb = lgb.cv(
    train_set=train_matrix,
    early_stopping_rounds=1000, 
    num_boost_round=20000,
    nfold=5,
    stratified=True,
    shuffle=True,
    params=base_params_lgb,
    feval=f1_score_vali,
    seed=0
)
print('迭代次数{}'.format(len(cv_result_lgb['f1_score-mean'])))
print('最终模型的f1为{}'.format(max(cv_result_lgb['f1_score-mean'])))

模型参数确定之后，建立最终模型并对验证集进行验证。