R聚类

 data<-read.csv("D:\\data1\\20130320a.csv",head=T)
 dataframe<-  data.frame(chg=data$CHG,chg_pct=data$CHG_PCT,achg_pct=data$ACHG_PCT,turnover=data$TURNOVER,rows.names=data$STOCKCODE)
 scale<-scale(dataframe)
 d<-dist(scale)
 hc1<-hclust(d)
 hc2<-hclust(d,"average") 
 hc3<-hclust(d,"centroid") 
 hc4<-hclust(d,"ward") 
 plclust(hc1, hang=-1); 
 re<-rect.hclust(hc1,k=18)

 for(i in 1:length(re)) {
   write.csv(re[[i]],paste("d:\\data1\\resultcsv",i,".txt"),append=TRUE,row.names=FALSE)
  }

从文本读入数据，聚类后保存结果到文件。

http://blog.sina.com.cn/s/blog_6d5ee5530101fyt5.html

data<-read.csv("D:\\data1\\20130320a.csv",head=T)
dataframe<-data.frame(chg=data$CHG,chg_pct=data$CHG_PCT,achg_pct=data$ACHG_PCT,turnover=data$TURNOVER,rows.names=data$STOCKCODE)
scale<-scale(dataframe)
d<-dist(scale)
hc4<-hclust(d,"ward")
result=cutree(hc4,k=10)
mds=cmdscale(d,k=2,eig=T)
x = mds$points[,1]
y = mds$points[,2]
library(ggplot2)
p=ggplot(data.frame(x,y),aes(x,y))
p+geom_point(size=3,alpha=0.8,
aes(colour=factor(result),
shape=10))
p+geom_point(size=3,alpha=0.8,
aes(colour=factor(result),
shape=1:10))
p+geom_point(size=3,alpha=0.8,
aes(colour=factor(result))
)