Hello R-devel: I have written a package, called "woods", that does classification trees (R function CT), and currently, only the most basic functionality of Random Forest, e.g. bagged trees with choices about sample size, with/without replacement, size of (random) subset of covariates drawn when nodes are split. My reason for writing this is twofold. First, I wanted to base this development entirely in C (as others have done), but using data structures such as a node, pointer to node (for trees), and pointer to pointer of node (for forests) implemented in C. The algorithm which does bagging isn't any faster (its 30% slower) than one by Leo Breiman/Adele Cutler/Andy Liaw/ Matt Weiner. The CT function runs about equally as fast as Professor Brian Ripley's.
The only interesting feature is that the tree structure has been implemented in C. Its a neater way to carry stuff around and I am guessing would make future implementation easier. Because of its inherent redundancy from the users standpoint, it isn't something to send to CRAN. However, I was wondering whether anyone is interested in a copy? Grant Izmirlian NCI ______________________________________________ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
