[R] R equivalent to Matlab's Bayes net toolbox

Peter Dalgaard p.dalgaard at biostat.ku.dk
Wed Jul 18 09:07:19 CEST 2007


On Wed, 2007-07-18 at 03:52 +0000, Jose wrote:

> The thing that I don't understand in the gR page is why there are so many 
> different packages and why they are not very integrated:

You have to understand the gR project for that. It started from a number
of completely separate pieces of software within the general field of
graphical models, and tried to bring people together and make the
existing pieces of software accessible from R. Given that the active
core of the group was really just a handful of people with limited R
programming experience (much of the original code was written in
dialects of Pascal/Delphi), the project must be said to have had some
success. However, the most pronounced effect has been to bring those old
codes out in the open, but seamless integration would be quite far into
the horizon.



More information about the R-help mailing list