LightGBM用法速查表

内置方式建模

1.要把数据读取成Dataset格式
2.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'</