R语言学习笔记-K平均算法(聚类)

《R语言学习笔记-K平均算法(聚类)》由会员上传分享，免费在线阅读，更多相关内容在行业资料-天天文库。

1、R语言学习笔记-K平均算法（聚类）k-meansClusteringThispagedemonstratesk-meansclusteringwithR.>newiris<-iris>newiris$Species<-NULLApplykmeanstonewiris,andstoretheclusteringresultinkc.Theclusternumberissetto3.>(kc<-kmeans(newiris,3))K-meansclusteringwith3clustersofsizes38,50,62

2、Clustermeans:Sepal.LengthSepal.WidthPetal.LengthPetal.Width16.8500003.0736845.7421052.07105325.0060003.4280001.4620000.24600035.9016132.7483874.3935481.433871Clusteringvector:[1]22222222222222222222222222222[30]22222222222222222222233133333[59]3333333333333333

3、3331333333333[88]33333333333331311113111111331[117]11131313113311111311113111311[146]13113Withinclustersumofsquaresbycluster:[1]23.8794715.1510039.82097Availablecomponents:[1]"cluster""centers""withinss""size"ComparetheSpecieslabelwiththeclusteringresult>table

4、(iris$Species,kc$cluster)123setosa0500versicolor2048virginica36014Plottheclustersandtheircentres.Notethattherearefourdimensionsinthedataandthatonlythefirsttwodimensionsareusedtodrawtheplotbelow.Someblackpointsclosetothegreencentre(asterisk)areactuallyclosertot

5、heblackcentreinthefourdimensionalspace.>plot(newiris[c("Sepal.Length","Sepal.Width")],col=kc$cluster)>points(kc$centers[,c("Sepal.Length","Sepal.Width")],col=1:3,pch=8,cex=2)