lightgbm algorithm case of kaggle（上）
苏高生，西南财经大学统计学硕士毕业，现就职于中国电信，主要负责企业存量客户大数据分析、数据建模。研究方向：机器学习，最喜欢的编程语言：R语言，没有之一。
E-mail：sugs01@outlook.com
往期回顾：
零、案例背景介绍与建模思路说明
1.背景介绍
本案例使用的数据为kaggle中“Santander Customer Satisfaction”比赛的数据。此案例为不平衡二分类问题，目标为最大化auc值（ROC曲线下方面积）。竞赛题目链接为：https://www.kaggle.com/c/santander-customer-satisfaction 。目前此比赛已经结束。
2.建模思路
本文档采用微软开源的lightgbm算法进行分类，运行速度极快，超过xgboost算法与rxFastForest算法。
1) 读取数据；
2) 并行运算：由于lightgbm包可以通过设置相应参数进行并行运算，因此不再调用doParallel与foreach包进行并行运算；
3) 特征选择：使用mlr包提取了99%的信息增益；
4) 调参：逐步调试lgb.cv函数的参数，并多次调试，直到满意为止；
5) 集成预测结果：在每个参数的适宜范围内随机抽取参数值构建lightgbm模型，并将多个模型进行集成，输出预测结果；本案例所用程序输出结果的ROC值为0.832023,已绝对超过Private Leaderboard排名第一的结果(0.829072)。
一、读取数据
options(java.parameters = "-Xmx8g") ## 特征选择时使用，但是需要在加载包之前设置,否则无效
library(readr)
lgb_tr1 <- read_csv("C:/Users/Administrator/Documents/kaggle/scs_lgb/train.csv")
lgb_te1 <- read_csv("C:/Users/Administrator/Documents/kaggle/scs_lgb/test.csv")
二、数据探索
1.设置并行运算
library(dplyr)
library(mlr)
library(parallelMap)
parallelStartSocket(2)
2.数据各列初步探索
summarizeColumns(lgb_tr1) %>% View()
3.处理缺失值
#impute missing values by mean and mode
imp_tr1 <- impute(
as.data.frame(lgb_tr1),
classes = list(
integer = imputeMean(),
numeric = imputeMean()
)
)
imp_te1 <- impute(
as.data.frame(lgb_te1),
classes = list(
integer = imputeMean(),
numeric = imputeMean()
)
)
## 处理缺失值后summarizeColumns(imp_tr1$data) %>% View()
4.观察训练数据类别的比例–数据类别不平衡
table(lgb_tr1$TARGET)
5.剔除数据集中的常数列
lgb_tr2 <- removeConstantFeatures(imp_tr1$data)
lgb_te2 <- removeConstantFeatures(imp_te1$data)
6.保留训练数据集与测试数据及相同的列
tr2_name <- data.frame(tr2_name = colnames(lgb_tr2))
te2_name <- data.frame(te2_name = colnames(lgb_te2))
tr2_name_inner <- tr2_name %>%
inner_join(te2_name, by = c('tr2_name' = 'te2_name'))
TARGET = data.frame(TARGET = lgb_tr2$TARGET)
lgb_tr2 <- lgb_tr2[, c(tr2_name_inner$tr2_name[2:dim(tr2_name_inner)[1]])]
lgb_te2 <- lgb_te2[, c(tr2_name_inner$tr2_name[2:dim(tr2_name_inner)[1]])]
lgb_tr2 <- cbind(lgb_tr2, TARGET)
三、特征筛选–信息增益
library(lightgbm)
library(ggplot2)
1.试算最优的weight参数
grid_search <- expand.grid(
weight = seq(1, 30, 2))
lgb_rate_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr2$TARGET * i + 1) / sum(lgb_tr2$TARGET * i + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr2[, 1:300]),
label = lgb_tr2$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc'
)
# 交叉验证
lgb_tr2_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
learning_rate = .1,
num_threads = 2,
early_stopping_rounds = 10
)
lgb_rate_1[i] <- unlist(lgb_tr2_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr2_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- lgb_rate_1
ggplot(grid_search,aes(x = weight, y = perf)) +
geom_point()
结论：从此图可知auc值受权重影响不大,在weight=9时达到最大,weight>=11时呈负相关
2.特征选择
1)特征选择
lgb_tr2$TARGET <- factor(lgb_tr2$TARGET)
lgb.task <- makeClassifTask(data = lgb_tr2, target = 'TARGET')
lgb.task.smote <- oversample(lgb.task, rate = 9)
fv_time <- system.time(
fv <- generateFilterValuesData(
lgb.task.smote,
method = c('information.gain')
)
)
2)制图查看
library(ggvis)
plotFilterValues(fv)
plotFilterValuesGGVIS(fv)
3)提取99%的信息增益(lightgbm算法效率极高，因此可以取更多的变量)
fv_data2 <- fv$data %>%
arrange(desc(information.gain)) %>%
mutate(info_gain_cul = cumsum(information.gain) / sum(information.gain))
fv_data2_filter <- fv_data2 %>% filter(info_gain_cul <= 0.99)
dim(fv_data2_filter)
fv_feature <- fv_data2_filter$name
lgb_tr3 <- lgb_tr2[, c(fv_feature, 'TARGET')]
lgb_te3 <- lgb_te2[, fv_feature]
4)写出数据
write_csv(lgb_tr3, 'C:/users/Administrator/Documents/kaggle/scs_lgb/lgb_tr3.csv')
write_csv(lgb_te3, 'C:/users/Administrator/Documents/kaggle/scs_lgb/lgb_te3.csv')
四、算法
lgb_tr <- rxImport('C:/Users/Administrator/Documents/kaggle/scs_lgb/lgb_tr3.csv')
lgb_te <- rxImport('C:/Users/Administrator/Documents/kaggle/scs_lgb/lgb_te3.csv')
1.调试weight参数
grid_search <- expand.grid(
weight = 1:30
)
perf_weight_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * i + 1) / sum(lgb_tr$TARGET * i + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc'
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
learning_rate = .1,
num_threads = 2,
early_stopping_rounds = 10
)
perf_weight_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_weight_1
ggplot(grid_search,aes(x = weight, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在weight=2时达到最大
2.调试learning_rate参数
grid_search <- expand.grid(
learning_rate = 2 ^ (-(8:1))
)
perf_learning_rate_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_learning_rate_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_learning_rate_1
ggplot(grid_search,aes(x = learning_rate, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在learning_rate=2^(-3)时达到最大
3.调试num_leaves参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = seq(50, 1000, 50))
perf_num_leaves_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_num_leaves_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_num_leaves_1
ggplot(grid_search,aes(x = num_leaves, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在num_leaves=600时达到最大
4.调试min_data_in_leaf参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
min_data_in_leaf = 2 ^ (1:7))
perf_min_data_in_leaf_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
min_data_in_leaf = grid_search[i, 'min_data_in_leaf']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_min_data_in_leaf_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_min_data_in_leaf_1
ggplot(grid_search,aes(x = min_data_in_leaf, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值对min_data_in_leaf不敏感，因此不做调整
5.调试max_bin参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 2 ^ (5:10))
perf_max_bin_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_max_bin_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_max_bin_1
ggplot(grid_search,aes(x = max_bin, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在max_bin=2^6时达到最大,需要再次微调max_bin值
6.微调max_bin参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 10 * (3:12)
)
perf_max_bin_2 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_max_bin_2[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)
[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_max_bin_2
ggplot(grid_search,aes(x = max_bin, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在max_bin=30时达到最大
7.调试min_data_in_bin参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 2 ^ (1:9)
)
perf_min_data_in_bin_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_min_data_in_bin_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_min_data_in_bin_1
ggplot(grid_search,aes(x = min_data_in_bin, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在min_data_in_bin=64时达到最大,但是变化极其细微,因此不做调整
8.调试feature_fraction参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 64,
feature_fraction = seq(.5, 1, .02)
)
perf_feature_fraction_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin'],
feature_fraction = grid_search[i, 'feature_fraction']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_feature_fraction_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_feature_fraction_1
ggplot(grid_search,aes(x = feature_fraction, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在feature_fraction=.64时达到最大,feature_fraction在[.62, .70]之间时，auc值保持稳定,表现较好;从.64开始呈下降趋势
9.调试min_sum_hessian参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 64,
feature_fraction = .64,
min_sum_hessian = seq(0, .02, .001)
)
perf_min_sum_hessian_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin'],
feature_fraction = grid_search[i, 'feature_fraction'],
min_sum_hessian = grid_search[i, 'min_sum_hessian']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_min_sum_hessian_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_min_sum_hessian_1
ggplot(grid_search,aes(x = min_sum_hessian, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在min_sum_hessian=0.04时达到最大,建议min_sum_hessian取值在[0.001, 0.005]区间,auc趋于最大
10.调试lamda参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 64,
feature_fraction = .64,
min_sum_hessian = .004,
lambda_l1 = seq(0, .01, .002),
lambda_l2 = seq(0, .01, .002)
)
perf_lamda_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin'],
feature_fraction = grid_search[i, 'feature_fraction'],
min_sum_hessian = grid_search[i, 'min_sum_hessian'],
lambda_l1 = grid_search[i, 'lambda_l1'],
lambda_l2 = grid_search[i, 'lambda_l2']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_lamda_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_lamda_1
ggplot(data = grid_search, aes(x = lambda_l1, y = perf)) +
geom_point() +
facet_wrap(~ lambda_l2, nrow = 5)
结论：从此图可知建议去lambda_l1 = .002, lambda_l2 = .008，即在不影响auc值的情况下，尽量增加lambda值以降低模型复杂度
11.调试drop_rate参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 64,
feature_fraction = .64,
min_sum_hessian = .004,
lambda_l1 = .002,
lambda_l2 = .008,
drop_rate = seq(0, 1, .1)
)
perf_drop_rate_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin'],
feature_fraction = grid_search[i, 'feature_fraction'],
min_sum_hessian = grid_search[i, 'min_sum_hessian'],
lambda_l1 = grid_search[i, 'lambda_l1'],
lambda_l2 = grid_search[i, 'lambda_l2'],
drop_rate = grid_search[i, 'drop_rate']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_drop_rate_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_drop_rate_1
ggplot(data = grid_search, aes(x = drop_rate, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在drop_rate=0.3时达到最大,在[.3, .4]之间较好；在[0, 1]变化不大
12.调试max_drop参数
grid_search <- expand.grid(
learning_rate = .125,
num_leaves = 600,
max_bin = 30,
min_data_in_bin = 64,
feature_fraction = .64,
min_sum_hessian = .004,
lambda_l1 = .002,
lambda_l2 = .008,
drop_rate = .3,
max_drop = seq(1, 10, 2)
)
perf_max_drop_1 <- numeric(length = nrow(grid_search))
for(i in 1:nrow(grid_search)){
lgb_weight <- (lgb_tr$TARGET * 2 + 1) / sum(lgb_tr$TARGET * 2 + 1)
lgb_train <- lgb.Dataset(
data = data.matrix(lgb_tr[, 1:137]),
label = lgb_tr$TARGET,
free_raw_data = FALSE,
weight = lgb_weight
)
# 参数
params <- list(
objective = 'binary',
metric = 'auc',
learning_rate = grid_search[i, 'learning_rate'],
num_leaves = grid_search[i, 'num_leaves'],
max_bin = grid_search[i, 'max_bin'],
min_data_in_bin = grid_search[i, 'min_data_in_bin'],
feature_fraction = grid_search[i, 'feature_fraction'],
min_sum_hessian = grid_search[i, 'min_sum_hessian'],
lambda_l1 = grid_search[i, 'lambda_l1'],
lambda_l2 = grid_search[i, 'lambda_l2'],
drop_rate = grid_search[i, 'drop_rate'],
max_drop = grid_search[i, 'max_drop']
)
# 交叉验证
lgb_tr_mod <- lgb.cv(
params,
data = lgb_train,
nrounds = 300,
stratified = TRUE,
nfold = 10,
num_threads = 2,
early_stopping_rounds = 10
)
perf_max_drop_1[i] <- unlist(lgb_tr_mod$record_evals$valid$auc$eval)[length(unlist(lgb_tr_mod$record_evals$valid$auc$eval))]}
grid_search$perf <- perf_max_drop_1
ggplot(data = grid_search, aes(x = max_drop, y = perf)) +
geom_point() +
geom_smooth()
结论：从此图可知auc值在max_drop=5时达到最大,在[1, 10]区间变化较小
==========未完待续==========
公众号后台回复关键字即可学习
回复 R R语言快速入门及数据挖掘
回复 Kaggle案例 Kaggle十大案例精讲（连载中）
回复 文本挖掘 手把手教你做文本挖掘
回复 可视化 R语言可视化在商务场景中的应用
回复 大数据 大数据系列免费视频教程
回复 量化投资 张丹教你如何用R语言量化投资
回复 用户画像 京东大数据，揭秘用户画像
回复 数据挖掘 常用数据挖掘算法原理解释与应用
回复 机器学习 人工智能系列之机器学习与实践
回复 爬虫 R语言爬虫实战案例分享