I am working on the development of multi-species volume allometric equation from diameter (DBH). I would like to form groups of species with the largest possible volume-diameter correlations by making a supervised classification (according to the functional traits of the species, phytogeographic area etc.) and an unsupervised classification (using classification algorithms). And between HAC, Kmeans and Random Forest what should i choose (Obviously I will try all algorithm and choose the best fit).Thank you for your suggestions and your help.
Have a look at http://gradientdescending.com/unsupervised-random-forest-example/ and https://lgatto.github.io/IntroMachineLearningWithR/unsupervised-learning.html
IMO this is the best book available on Clustering: Finding Groups in Data: An Introduction to Cluster Analysis | Leonard Kaufman, Peter J. Rousseeuw | download (b-ok.cc) The R programs are available here: https://www.google.com/search?client=firefox-b-1-d&q=R+package+for+Finding+Groups+in+Data
Best wishes, David Booth
You can take a look to "RWeka" Package.
https://cran.r-project.org/web/packages/RWeka/RWeka.pdf
It can be helpful.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package