11月15日

一.wholesaled数据做分类分析

1
channel分类

data<-read.csv(file.choose())
mydata<-data[,-2]
data<-read.csv(file.choose())
head(data)
Channel Region Fresh Milk Grocery Frozen Detergents_Paper Delicassen
1 2 3 12669 9656 7561 214 2674 1338
2 2 3 7057 9810 9568 1762 3293 1776
3 2 3 6353 8808 7684 2405 3516 7844
4 1 3 13265 1196 4221 6404 507 1788
5 2 3 22615 5410 7198 3915 1777 5185
6 2 3 9413 8259 5126 666 1795 1451
mydata<-data[,-2]
traindata<-mydata[2*(1:220),]
textdata<-mydata[2*(1:220)-1,]
mymodel<-rpart(Channel~.,data=traindata,method=“class”,parms=list(split=“information”))
rpart.plot(mymodel)
predictresult<-predict(mymodel,textdata[,-1],type=“class”)
table(textdata[,1],predictresult)
predictresult
1 2
1 147 9
2 14 50

2 region分类分析

mydata2<-data[,-1]
traindata<-mydata2[2*(1:220),]
textdata<-mydata2[2*(1:220)-1,]
mymodel<-rpart(Region~.,data=traindata,method=“class”,parms=list(split=“information”))
rpart.plot(mymodel)
predictresult<-predict(mymodel,textdata[,-1],type=“class”)
table(textdata[,1],predictresult)
predictresult
1 2 3
1 1 0 38
2 2 0 21
3 6 0 152

二
对数据的聚类分析