Cross entropy clustering

My kids love mickey mouse. 😉
If you have mickey mouse plot, can you cluster the data reasonably ?
R package named gmum.r provides interesting solution to do it.
The package has many features for data analysis. If reader who has interest it please use it.
I used the package to cluster mickey mouse data!

library(gmum.r)
data("cec.mouse1.spherical")
plot(  cec.mouse1.spherical )

Mickey mouse !

Next, compare k-means and CEC.

 k<-kmeans(cec.mouse1.spherical,10)
plot(cec.mouse1.spherical,col=k$cluster) 

Oh! colorful mickey !!!

Next use CEC.

c <- CEC(k=3, x=dataset, control.nstart=10, method.type='spherical')
plot(c)


The result fits my feeling.

I think CEC is similar to EM based clustering.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s