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': 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('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 numpy as np
from sklearn.metrics import mean_squared_error
import warnings
warnings.filterwarnings("ignore")

# 加载数据集
print('加载数据...')
df_train = pd.read_csv('./data/binary.train', header=None, sep='\t')
df_test = pd.read_csv('./data/binary.test', header=None, sep='\t')
W_train = pd.read_csv('./data/binary.train.weight', header=None)[0]
W_test = pd.read_csv('./data/binary.test.weight', header=None)[0]

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

num_train, num_feature = X_train.shape

# 加载数据的同时加载权重
lgb_train = lgb.Dataset(X_train, y_train,
                        weight=W_train, free_raw_data=False)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train,
                       weight=W_test, free_raw_data=False)

# 设定参数
params = {
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'metric': 'binary_logloss',
    'num_leaves': 31,
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
}

# 产出特征名称
feature_name = ['feature_' + str(col) for col in range(num_feature)]

print('开始训练...')
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                valid_sets=lgb_train,  # 评估训练集
                feature_name=feature_name,
                categorical_feature=[21])

模型的载入与预测

# 查看特征名称
print('完成10轮训练...')
print('第7个特征为:')
print(repr(lgb_train.feature_name[6]))

# 存储模型
gbm.save_model('./model/lgb_model.txt')

# 特征名称
print('特征名称:')
print(gbm.feature_name())

# 特征重要度
print('特征重要度:')
print(list(gbm.feature_importance()))

# 加载模型
print('加载模型用于预测')
bst = lgb.Booster(model_file='./model/lgb_model.txt')
# 预测
y_pred = bst.predict(X_test)
# 在测试集评估效果
print('在测试集上的rmse为:')
print(mean_squared_error(y_test, y_pred) ** 0.5)

接着之前的模型继续训练

# 继续训练
# 从./model/model.txt中加载模型初始化
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model='./model/lgb_model.txt',
                valid_sets=lgb_eval)

print('以旧模型为初始化，完成第 10-20 轮训练...')

# 在训练的过程中调整超参数
# 比如这里调整的是学习率
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                learning_rates=lambda iter: 0.05 * (0.99 ** iter),
                valid_sets=lgb_eval)

print('逐步调整学习率完成第 20-30 轮训练...')

# 调整其他超参数
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                valid_sets=lgb_eval,
                callbacks=[lgb.reset_parameter(bagging_fraction=[0.7] * 5 + [0.6] * 5)])

print('逐步调整bagging比率完成第 30-40 轮训练...')

自定义损失函数

# 类似在xgboost中的形式
# 自定义损失函数需要
def loglikelood(preds, train_data):
    labels = train_data.get_label()
    preds = 1. / (1. + np.exp(-preds))
    grad = preds - labels
    hess = preds * (1. - preds)
    return grad, hess


# 自定义评估函数
def binary_error(preds, train_data):
    labels = train_data.get_label()
    return 'error', np.mean(labels != (preds > 0.5)), False


gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                fobj=loglikelood,
                feval=binary_error,
                valid_sets=lgb_eval)

print('用自定义的损失函数与评估标准完成第40-50轮...')