[R] Crash report: projection pursuit & predict

[Ben Bolker]

Horace Tso <Horace.Tso <at> pgn.com> writes:
 
> I'm using 2.11.1 under the 32-bit Windows XP. I've also tested the 
> codes under a 64-bit Ubuntu and the same
> problem occurred. By the way, right before Rgui shuts down, the \
> pop-up window suggests it's a runtime
> error in C++.
> 
> Here are the codes that cause the crash,
> 
> library(mlbench)
> data(BostonHousing2)
> BH = BostonHousing2[,-c(1:5)]
> dat1 = BH[1:200,]
> dat2 = BH[201:400,]
> mod = ppr(log(cmedv)~., data=dat1, optlevel=0, nterms=2, max.terms=5)
> pred = predict(mod, newdata=dat2)
> 
> Thks.
> 
> HT
> 
   On 32-bit Ubuntu, clean session (--vanilla), it seems to work the first
time and crash the second:

> sessionInfo()
R version 2.11.1 (2010-05-31) 
i486-pc-linux-gnu 

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=C              LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     
> library(mlbench)
> data(BostonHousing2)
> BH = BostonHousing2[,-c(1:5)]
> dat1 = BH[1:200,]
> dat2 = BH[201:400,]
> mod = ppr(log(cmedv)~., data=dat1, optlevel=0, nterms=2, max.terms=5)
> pred = predict(mod, newdata=dat2)
> 
> library(mlbench)
> data(BostonHousing2)
> BH = BostonHousing2[,-c(1:5)]
> dat1 = BH[1:200,]
> dat2 = BH[201:400,]
> mod = ppr(log(cmedv)~., data=dat1, optlevel=0, nterms=2, max.terms=5)

 *** caught segfault ***
address 0xe0000024, cause 'memory not mapped'