Homework—聚類分析

> A<-c('Y','Y','N','N','Y')
> B<-c('N','Y','Y','Y','N')
> C<-c('Y','Y','Y','Y','N')
> D<-c('Y','Y','Y','Y','Y')
> E<-c('N','N','N','Y','N')
> F<-c('Y','N','Y','Y','Y')
> mydata<-rbind(A,B,C,D,E,F)
> mydata
  [,1] [,2] [,3] [,4] [,5]
A "Y"  "Y"  "N"  "N"  "Y" 
B "N"  "Y"  "Y"  "Y"  "N" 
C "Y"  "Y"  "Y"  "Y"  "N" 
D "Y"  "Y"  "Y"  "Y"  "Y" 
E "N"  "N"  "N"  "Y"  "N" 
F "Y"  "N"  "Y"  "Y"  "Y"
> mydata[which(mydata=="Y")]=1
> mydata[which(mydata=="N")]=0
> mydata
  [,1] [,2] [,3] [,4] [,5]
A "1"  "1"  "0"  "0"  "1" 
B "0"  "1"  "1"  "1"  "0" 
C "1"  "1"  "1"  "1"  "0" 
D "1"  "1"  "1"  "1"  "1" 
E "0"  "0"  "0"  "1"  "0" 
F "1"  "0"  "1"  "1"  "1" 
> mydist<-dist(mydata,method="euclidean")
> mydist
         A        B        C        D        E
B 2.000000                                    
C 1.732051 1.000000                           
D 1.414214 1.414214 1.000000                  
E 2.000000 1.414214 1.732051 2.000000         
F 1.732051 1.732051 1.414214 1.000000 1.732051
> mycluster<-hclust(mydist)
> plot(mycluster)
> result<-cutree(mycluster,3)
> for(i in 1:3){show(mydata[which(result==i)])}
[1] “1” “1” “1”
[1] “0” “1”
[1] “0”