博客

import lightgbm as lgb
from sklearn import datasets
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
 
 
file = datasets.load_boston()
data = file.data
target = file.target
 
X_train, X_test, y_train, y_test = train_test_split(data,target,test_size = 0.4,random_state = 0)
 
lgb_train = lgb.Dataset(X_train,y_train)
lgb_eval = lgb.Dataset(X_test,y_test,reference=lgb_train)
 
params = {
    'task':'train',
    'boosting_type':'gbdt',
    'objective':'regression',
    'metric':{'l2','mae'},
    'num_leaves':31,
    'learning_rate':0.05,
    'feature_fraction':0.9,
    'bagging_fraction':0.8,
    'bagging_freq':5,
    'verbose':0
}
 
gbm = lgb.train(params,lgb_train,num_boost_round=100,valid_sets=lgb_eval,early_stopping_rounds=5)
 
lgb_predit = gbm.predict(X_test,num_iteration=gbm.best_iteration)
print(mean_squared_error(y_test,lgb_predit) ** 0.5)
 
#4.362611034426013