Dear R community, I am trying to write my own user defined split function for rpart. I read the example in the tests directory and I understand the general idea of the how to implement user defined splitting functions. However, I am having troubles with addressing the data frame used in calling rpart in my split functions. For example, in the evaluation function that is called once per node, I want to fit a proportional odds model to the data in the node and use its deviance as node deviance:
evalf <- function(y,x,parms) { pomnode<-polr(dataframe$y~dataframe$x,dataframe,weights=dataframe$Freq) more code } The dataframe used in the polr call should be the data of the current node. How can I address the data of the current node and assign it to the dataframe? Thank you for your help, Tobias Guennel ______________________________________________ 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 and provide commented, minimal, self-contained, reproducible code.