Hi Ghada,
The value returned by Mclust ("m" in your example) has different
components from say the hierarchical clustering. The second argument
for "cluster.stats" is the cluster IDs of the objects in the initial
set. Perhaps if you call it like this:cluster.stats(d,m$classification) I don't have the mclust package, so this is a guess. Jim On Wed, Apr 29, 2015 at 3:39 AM, Ghada Almousa <[email protected]> wrote: > Hello dears > > I using (R tool) in my project > and I want to compare the results betwen k-mean cluster ,Hierarchical > cluster and EM cluster > I use cluster.stats() it's work on k-mean cluster and hrarichal cluster > but not work in EM > > Hello Dears > I Use R tool in my project > I want to do comparison of the results between the k-mean cluster > ,Hierarchical cluster and EM cluster > I use cluster.stats () function that it is working on a the k-mean > cluster ,Hierarchical cluster But do not work in EM > mydata<-(data) > my <-data.matrix(mydata) > d<-dist(as.matrix(my > library(mclust) > m <- Mclust(d, G =2) > cluster.stats(d, m > Error in max(clustering) : invalid 'type' (list) of argument > > [[alternative HTML version deleted]] > > ______________________________________________ > [email protected] mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. ______________________________________________ [email protected] mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
