lightGBM实践【图文】

lightGBM实践

import datetime
import numpy as np
import pandas as pd
import lightgbm as lgb
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
%matplotlib inline

# 加载数据集
breast = load_breast_cancer()
# 获取特征值和目标指
X,y = breast.data,breast.target
# 获取特征名称
feature_name = breast.feature_names

print(len(y))
print(X.shape)

# 数据集划分
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# 数据格式转换
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

# 参数设置
boost_round = 50 # 迭代次数              
early_stop_rounds = 10 # 验证数据若在early_stop_rounds轮中未提高，则提前停止

params = {
    'boosting_type': 'gbdt',  # 设置提升类型
    'objective': 'regression',  # 目标函数
    'metric': {'l2', 'auc'},  # 评估函数
    'num_leaves': 31,  # 叶子节点数
    'learning_rate': 0.05,  # 学习速率
    'feature_fraction': 0.9,  # 建树的特征选择比例
    'bagging_fraction': 0.8,  # 建树的样本采样比例
    'bagging_freq': 5,  # k 意味着每 k 次迭代执行bagging
    'verbose': 1  # <0 显示致命的, =0 显示错误 (警告), >0 显示信息
}

# 模型训练:加入提前停止的功能
results = {}
gbm = lgb.train(params,
                lgb_train,
                num_boost_round= boost_round,
                valid_sets=(lgb_eval, lgb_train),
                valid_names=('validate','train'),
                early_stopping_rounds = early_stop_rounds,
                evals_result= results)

# 模型预测
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)
y_pred

# 模型评估
lgb.plot_metric(results)
plt.show()

# 绘制重要的特征
lgb.plot_importance(gbm,importance_type = "split")
plt.show()

更多文章请关注《万象专栏》