Neelesh Gupta
2013-Jun-14 14:24 UTC
[R] How to interactively create manually guided Decision Tree
I am new in using R. I want to know all about building decision tree model in R. Few options which I searched are rpart and rattle to build a decision tree.Both the functions are giving me splits which are statistically appropriate. But I am not able to figure out how to change those splits as per my business requirement. for example : the automatic split of Age by using rattle is > 30 and <= 30 but I want a split of <= 20 , 21-30 , 30-50 and >= 50 I also want to know how to know the predictive strength of each variable after each split so that I can choose which variable should come next in my list. I Thanks in advance [[alternative HTML version deleted]]
Bert Gunter
2013-Jun-14 16:18 UTC
[R] How to interactively create manually guided Decision Tree
You need to do some reading, both about decision trees and R! What you need to do for R is to use cut() on Age (?cut) to create a new categorical variable, ageCat, say, and then use that in your tree building instead of Age. Cheers, Bert On Fri, Jun 14, 2013 at 7:24 AM, Neelesh Gupta <neelesh0 at gmail.com> wrote:> I am new in using R. I want to know all about building decision tree model > in R. > Few options which I searched are rpart and rattle to build a decision > tree.Both the functions are giving me splits which are statistically > appropriate. > > But I am not able to figure out how to change those splits as per my > business requirement. > > for example : the automatic split of Age by using rattle is > 30 and <= 30 > but I want a split of <= 20 , 21-30 , 30-50 and >= 50 > > I also want to know how to know the predictive strength of each variable > after each split so that I can choose which variable should come next in my > list. > > I > > Thanks in advance > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list > 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.-- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm