数据来源:

http://archive.ics.uci.edu/ml/datasets/Bank+Marketing

数据预处理：

导入数据：

getwd()
setwd("d:/Rdata/bank")
getwd()
bankdata<-read.csv("bank-additional-full.csv",sep=";")
sum(is.na(bankdata))

查看原始数据状态

summary(bankdata)

用众数插补

table(bankdata=="unknown")
max(table(bankdata$job))
max(table(bankdata$education))
bankdata$marital[which(bankdata$marital=="unknown")]<-"married"
bankdata$default[which(bankdata$default=="unknown")]<-"no"
bankdata$housing[which(bankdata$housing=="unknown")]<-"yes"
bankdata$loan[which(bankdata$loan=="unknown")]<-"no"
bankdata$education[which(bankdata$education=="unknown")]<-"university.degree"
bankdata$job[which(bankdata$job=="unknown")]<-"admin."

1对age进行重编码

attach(bankdata)
lab<-c("younge","wrinkly","elder")
bankdata$age_cat=cut(age,breaks = c(0,35,55,100),right = FALSE,labels = lab)
table(bankdata$age_cat)

2对job进行重编码

c1<-c("admin.","blue-collar","entrepreneur")
c2<-c("housemaid","management","self-employed","services","technician")
c3<-c("retired","student","unemployed")
bankdata<-within(bankdata,{
job_cat<-NA
job_cat[job %in% c1]<-"high-income"
job_cat[job %in% c2]<-"middle-income"
job_cat[job %in% c3]<-"low-income"
})

table(bankdata$job_cat)

3对education进行重编码

c4<-c("basic.4y","basic.6y","basic.9y")
c5<-c("high.school","professional.course","university.degree")
bankdata<-within(bankdata,{
edu_cat<-NA
edu_cat[education %in% "illiterate"]<-"high-income"
edu_cat[education %in% c4]<-"middle-income"
edu_cat[education %in% c5]<-"low-income"
})
table(bankdata$edu_cat)

4对month进行重编码

c6<-c("jan","feb","mar")
c7<-c("apr","may","jun")
c8<-c("jul","aug","sep")
c9<-c("oct","nov","dec")
bankdata<-within(bankdata,{
mon_cat<-NA
mon_cat[month %in% c6]<-"q1"
mon_cat[month %in% c7]<-"q2"
mon_cat[month %in% c8]<-"q3"
mon_cat[month %in% c9]<-"q4"
})
table(bankdata$mon_cat)

5查看pdays的数据情况并对pdays进行重编码

table(bankdata$pdays)
bankdata<-within(bankdata,{
pdays_cat<-NA
pdays_cat[pdays<28]<-"long"
pdays_cat[pdays<8]<-"short"
pdays_cat[pdays==999]<-"never"
})
detach(bankdata)

将字符型的字段改为因子型的

bankdata$job_cat<-factor(bankdata$job_cat)
bankdata$edu_cat<-factor(bankdata$edu_cat)
bankdata$mon_cat<-factor(bankdata$mon_cat)
bankdata$pdays_cat<-factor(bankdata$pdays_cat)

查看数据状态

summary(bankdata)

进行标准正态化

tosacle<-function(x){
return (scale(x,center = TRUE,scale=TRUE))
}
bankdata$camp<-scale(bankdata$campaign,center = TRUE,scale=TRUE)
bankdata$pre<-scale(bankdata$previous,center = TRUE,scale=TRUE)
bankdata[,16:20]<-apply(bankdata[,16:20], 2, tosacle)

筛选字段形成新的数据框，用于相关性分析

attach(bankdata)
c10<-c("age_cat","job_cat","marital","edu_cat","default",
"housing","loan,contact","mon_cat","day_of_week","camp",
"pdays_cat","pre","poutcome",
"emp.var.rate","cons.price.idx",
"cons.conf.idx","euribor3m","nr.employed","y")
newdata<-temp[which(names(temp)%in%c10)]
newdata<-bankdata[which(names(bankdata)%in%c10)]
detach(bankdata)
summary(newdata)
str(newdata[,1:18])

相关性分析

将数据集中的每个列的相关系数统计出来并保存在一个corr的参数中

newtmp<-data.frame(newdata[,6:10],newdata[,17:18])
corr <- cor(newtmp)
install.packages("corrplot",dependencies = T)
corrplot(corr)

选取变量

c11<-c("euribor3m","nr.employed","emp.var.rate")
tmp<-names(newdata)%in%c11
newdata2<-newdata[,!tmp]
summary(newdata2)

==========================================================

建立模型:

数据分区，按照变量accept变量进行等比抽样，80%为训练集，20%为测试集

library(caret)
ind <- createDataPartition(newdata2$y,times=1,p=0.8,list=F)
train <- newdata2[ind,] # 训练集
test <- newdata2[-ind,] # 测试集
prop.table(table(newdata2$y))
prop.table(table(train$y))
prop.table(table(test$y))

构建分类模型cart

library(rpart)
mod <- rpart(train$y~.,data=train)

对测试集数据进行预测

pred <- predict(mod,test,type="class")
pred

构建混淆矩阵，查看预测效果

查看训练集的误差率

(a <- table(train$y,predict(mod,train,type="class")))
paste0(round((sum(a)-sum(diag(a)))/sum(a),4)*100,"%")

查看测试集的误差率

(b <- table(test$y,predict(mod,test,type="class")))
paste0(round((sum(b)-sum(diag(b)))/sum(b),4)*100,"%")