python模型lgbm调优工具_机器学习应用之LGBM详解

内置方式建模要把数据读取成Dataset格式

lgb.train去训练

# coding: utf-8

import json

import lightgbm as lgb

import pandas as pd

from sklearn.metrics import mean_squared_error

# 加载数据集合

print('加载数据...')

df_train = pd.read_csv('../data/regression.train.txt', header=None, sep='\t')

df_test = pd.read_csv('../data/regression.test.txt', header=None, sep='\t')

# 设定训练集和测试集

y_train = df_train[0].values

y_test = df_test[0].values

X_train = df_train.drop(0, axis=1).values

X_test = df_test.drop(0, axis=1).values

# 构建lgb中的Dataset格式

lgb_train = lgb.Dataset(X_train, y_train)

lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

# 敲定好一组参数

params = {

'task': 'train',

'boosting_type': 'gbdt',

'objective': 'regression',

'metric': {'l2', 'auc'},

'num_leaves': 31,

'learning_rate': 0.05,

'feature_fraction': 0.9,

'bagging_fraction': 0.8,

'bagging_freq': 5,

'verbose': 0

}

print('开始训练...')

# 训练

gbm = lgb.train(params,

lgb_train,

num_boost_round=20,

valid_sets=lgb_eval,

early_stopping_rounds=5)

# 保存模型

print('保存模型...')

# 保存模型到文件中

gbm.save_model('../../tmp/model.txt')

print('开始预测...')

# 预测

y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)

# 评估

print('预估结果的rmse为:')

print(mean_squared_error(y_test, y_pred) ** 0.5)添加样本权重训练

# coding: utf-8

import json

import lightgbm as lgb

import pandas as pd

import num