方法1:
rm(list=ls())
gc()
german_credit <- read.csv("C:/pic/credit/german_credit.csv",sep = ",")
names(german_credit)
# 需要将样本总体分为样本集和测试集
# 简单随机抽样
smp1<-sample(nrow(german_credit),300,replace=F)
train_data=german_credit[-smp1,]
test_data=german_credit[smp1,]
方法二:
library(caret)
train1 <-createDataPartition(y=german_credit$Creditability,p=0.75,list=FALSE)
train <- german_credit[train1, ]
test <- german_credit[-train1, ]