I am trying to use SOM package to cluster some gene expression data. I got
stuck with 2 questions and can't not find any documents to resolve these
matters. I would really appreciate if anybody can shed some sort of light. Q1.
I clustered the data using SOM function and plotted it using plot function.
But I can't figure out how I can list the data elements belongs to different
clusters. I made a 5X5 SOM grid and there are 25 clusters. The plot tells me
how many data elements belongs to this different cluster grids but I want to
make separate list of them. I don't know how to deal with the
SOM.objectfrankly speaking.
Q2. The SOM package listed 5 functions
som.init
som
som.train
som.update and
som.project
I was wondering to get the best result in what order I should apply them?
Should I first initialize the som using som.init, then train it with
som.train and finally update it with som.update? Or just use som function
followed by som.update? As I have only one set of data I don't think I need
to use project function.
Thanks in advance and regards.
[[alternative HTML version deleted]]
______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
