[R] memory error with rpart()

[Ji Zhu]

I've figured it out.  When there is a "pure" terminal
node, the predict.rpart(type="prob") gives a probability
estimate 0, and the log() gives a NaN.  Then in the next
iteration, the memory error occurs.

Thanks to all!




>
> Dear all,
>
> I have a 100 iteration loop. Within each loop, there are some calls
> to rpart() like:
>
> ctl <- rpart.control(maxcompete=0, maxsurrogate=0, maxdepth=10)
> temp <- rpart(y~., x, w=wt, method="class", parms=list(split="gini"),
> control=ctl)
> res <- log(predict.rpart(temp, type="prob"))
> newres <- log(predict.rpart(temp, newdata=newx, type="prob"))
>
> The code runs fine for the first 30-60 iterations, then gives me the
> following error message and crashes:
>
> The instruction at "0x112b4143" referenced memory at "0x00000000".
> The memory could not be "read".
>
> Could anyone give me some hint about what this error message implies?
> Thanks a lot!
>
> I'm using R1.4.1 on Windows2000.
>
> -Ji Zhu
>
>

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._