A new version of the randomForest package is now available on CRAN. The
DESCRIPTION is:
Package: randomForest
Title: Breiman's random forest for classification and regression
Version: 3.4-1
Depends: R (>= 1.5.0)
Author: Fortran original by Leo Breiman and Adele Cutler, R port by Andy
Liaw and Matthew Wiener.
Description: Classification and regression based on a forest of trees using
random inputs.
Maintainer: Andy Liaw <andy_liaw at merck.com>
License: GPL version 2 or later
This version (3.4-1) contains bug fixes as well as some additional features:
o Error rates or MSE are returned as a vector, so one can
examine how they change as number of trees increases.
o Added a plot() method for randomForest objects, which
plots the error rates or MSEs.
o Added var.imp.plot() to plot the variable importance.
o Added partial.plot() for visualizing marginal effect of
a predictor variable in regression.
o Added functions grow() and combine(), which can be used
to aggregate several randomForest objects into one. This
can be useful, e.g., when the forests are ran on different
machines in parallel, as can be done quite easily with
Prof. Tierney's "snow" package.
As always, comments/bug reports/patches welcomed.
Regards,
Andy
Andy I. Liaw, PhD
Biometrics Research Phone: (732) 594-0820
Merck & Co., Inc. Fax: (732) 594-1565
P.O. Box 2000, RY84-16 Rahway, NJ 07065
mailto:andy_liaw at merck.com
------------------------------------------------------------------------------
