The R Project SVN R-packages

R version 2.15.0 (2012-03-30)
Copyright (C) 2012 The R Foundation for Statistical Computing
ISBN 3-900051-07-0
Platform: x86_64-unknown-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(rpart)
> mystate <- data.frame(state.x77, region=factor(state.region))
> names(mystate) <- c("population","income" , "illiteracy","life" ,
+        "murder", "hs.grad", "frost",     "area",      "region")
> #
> # This little test came out of a query that cp did not scale
> #  with the data size.  It does
> #
> # tdata = 20 copies of "mystate"  
> # trees with tdata and trees with mystate should be the same (they are)
> #  except for the n's
> tdata <- rbind(mystate, mystate, mystate, mystate, mystate)
> tdata <- rbind(tdata, tdata, tdata, tdata)
> tfit1 <- rpart(income ~ population + illiteracy + murder + hs.grad + region,
+                data = mystate, method = "anova", xval=0, cp=.089)
> tfit2 <- rpart(income ~ population + illiteracy + murder + hs.grad + region,
+                data = tdata, method='anova', xval=0, cp=.089, 
+                minsplit=400, minbucket=140)
> 
> all.equal(tfit1$splits[,-1], tfit2$splits[,-1])
[1] TRUE
>  
> 
> proc.time()
   user  system elapsed 
  0.237   0.049   0.324