[R] Error with BRugs 0.53 and 0.71, on Win7 with R 2.12.2 and 2.13.0 (crashes R GUI)
Chris Chapman
cnchapman at msn.com
Sun May 29 23:19:58 CEST 2011
Uwe -- thank you. No, this occurs on three different machines: two at work
(a Lenovo laptop running Win7-32, plus an HP workstation running Win7-64)
... and I just tried another Compaq desktop machine at home running
WinXP-32, with the same result.
I agree that this seems highly unusual since the examples are so simple and
obviously work in general; yet it is also highly replicable for me, and I'm
at a loss as to what might be the root cause given the different machines
and Windows versions. FWIW, everything else in my R environment (Rgui,
Tinn-R, RStudio, ggplot2, various other packages) runs OK. OpenBUGS in
itself also seems OK albeit in limited tests.
Could there be something in the "handleRes()" error that suggests anything
to examine (firewall, antivirus, file locations, or some file permissions,
perhaps? -- although those also vary across my machines, esp. from work to
home).
Thanks again,
-- Chris
--------------------------------------------------
From: "Uwe Ligges" <ligges at statistik.tu-dortmund.de>
Sent: Sunday, May 29, 2011 10:07 AM
To: "Chris Chapman" <cnchapman at msn.com>
Cc: <r-help at r-project.org>
Subject: Re: [R] Error with BRugs 0.53 and 0.71, on Win7 with R 2.12.2 and
2.13.0 (crashes R GUI)
> Sounds like a hardware problem to me, since I do not expereice any
> problems with the example you gave at first. Is this all on the same
> hardware?
>
> Uwe Ligges
>
>
>
> On 27.05.2011 18:38, Chris Chapman wrote:
>> I've run into persistent problems with OpenBUGS crashing when using BRugs
>> .53 and .71, and am hoping someone has suggestions. There is obviously
>> something unusual going on in my environment, but I'm at a loss as to
>> where to begin to try to solve it.
>>
>> In a nutshell, what happens is that, as soon as I call "modelCheck()" in
>> BRugs, it gets an error or crashes ... but only some of the time (90%<
>> p< 100%). Following are details:
>>
>> 1. OpenBUGS 3.0.3 + BRugs 0.531:
>> It works occasionally, but approximately 90% of the time, I get the
>> following error from modelCheck():
>> Error in handleRes(res[[3]]) :
>>
>> An OpenBUGS module or procedure was called that did not exist.
>>
>>
>>
>> The specific code seems not to matter, but here is an example (model
>> taken from the OpenBUGS tutorial):
>> modelString =
>> " model
>> {
>> for (i in 1:N) {
>> r[i] ~ dbin(p[i], n[i])
>> b[i] ~ dnorm(0, tau)
>> logit(p[i])<- alpha0 + alpha1 * x1[i] + alpha2 * x2[i]
>> + alpha12 * x1[i] * x2[i] + b[i]
>> }
>> alpha0 ~ dnorm(0, 1.0E-6)
>> alpha1 ~ dnorm(0, 1.0E-6)
>> alpha2 ~ dnorm(0, 1.0E-6)
>> alpha12 ~ dnorm(0, 1.0E-6)
>> tau ~ dgamma(0.001, 0.001)
>> sigma<- 1 / sqrt(tau)
>> }
>> "
>> print(modelString)
>> writeLines(modelString,con="model3.txt")
>> modelCheck( "model3.txt" )
>>
>> Which (usually) produces:
>>> modelCheck( "model3.txt" )
>> Error in handleRes(res[[3]]) :
>> An OpenBUGS module or procedure was called that did not exist.
>>
>> I've copied at the end of this message an example from a single R session
>> that shows how it may work sometimes but not others.
>>
>>
>> 2. OpenBUGS 3.2.1 + BRugs 0.71:
>>
>> As above, the model occasionally works, but mostly it crashes R on the
>> working".
>>
>>
>> I've tried the following combinations to try to get it to work:
>> A. Win7 32-bit + R 2.13 + BRugs 0.531 from standard CRAN repository
>> (installed from R)
>> B. Win7 32-bit + R 2.13 + BRugs 0.71 + OpenBUGS 3.2.1 (package and EXE
>> from OpenBUGS site)
>> C. Win7 64-bit [different machine] + R 2.13 (32-bit) + BRugs 0.531
>> D. Win7 64-bit + R 2.13 (32-bit) + BRugs 0.71 + OpenBugs 3.2.1
>> E. Win7 32-bit + *R 2.12.2* + BRugs 0.531 from standard CRAN repository
>> (installed from R)
>> F. Win7 64-bit + R 2.12.2 (32-bit) + BRugs 0.531
>> G. Win7 64-bit + R 2.12.2 (32-bit) + BRugs 0.71 + OpenBugs 3.2.1
>> H. ... and various combinations of removing all R and openbugs versions,
>> clean installs, and trying again
>>
>> In all cases, it occasionally works -- especially on first re-install of
>> the package -- but then generally gives the "handleRes" error with BRugs
>> 0.531 or crashes with BRugs 0.71.
>>
[[elided Hotmail spam]]
>>
>>
>> === example from a a single R session ===
>>
>> R version 2.13.0 (2011-04-13)
>>
>> Copyright (C) 2011 The R Foundation for Statistical Computing
>>
>> ISBN 3-900051-07-0
>>
>> Platform: i386-pc-mingw32/i386 (32-bit)
>>
>>
>> R is free software and comes with ABSOLUTELY NO WARRANTY.
>>
>> You are welcome to redistribute it under certain conditions.
>>
>> Type 'license()' or 'licence()' for distribution details.
>>
>>
>> Natural language support but running in an English locale
>>
>>
>> R is a collaborative project with many contributors.
>>
>> Type 'contributors()' for more information and
>>
>> 'citation()' on how to cite R or R packages in publications.
>>
>>
>> Type 'demo()' for some demos, 'help()' for on-line help, or
>>
>> 'help.start()' for an HTML browser interface to help.
>>
>> Type 'q()' to quit R.
>>
>>
>> Loading required package: proto
>>
>> Loading required package: grid
>>
>> Loading required package: reshape
>>
>> Loading required package: plyr
>>
>>
>> Attaching package: 'reshape'
>>
>>
>> The following object(s) are masked from 'package:plyr':
>>
>>
>> rename, round_any
>>
>>
>> [Previously saved workspace restored]
>>
>>
>>> install.packages("BRugs")
>>
>> Installing package(s) into 'C:/Users/cchap/Documents/R/win-library/2.13'
>>
>> (as 'lib' is unspecified)
>>
>> --- Please select a CRAN mirror for use in this session ---
>>
>> also installing the dependency 'coda'
>>
>>
>> trying URL
>> 'http://cran.fhcrc.org/bin/windows/contrib/2.13/coda_0.14-4.zip'
>>
>> Content type 'application/zip' length 200622 bytes (195 Kb)
>>
>> opened URL
>>
>> downloaded 195 Kb
>>
>>
>> trying URL
>> 'http://www.stats.ox.ac.uk/pub/RWin/bin/windows/contrib/2.13/BRugs_0.5-3.1.zip'
>>
>> Content type 'application/zip' length 5613828 bytes (5.4 Mb)
>>
>> opened URL
>>
>> downloaded 5.4 Mb
>>
>>
>> package 'coda' successfully unpacked and MD5 sums checked
>>
>> package 'BRugs' successfully unpacked and MD5 sums checked
>>
>>
>> The downloaded packages are in
>>
>> C:\Users\cchap\AppData\Local\Temp\RtmpoNcfyf\downloaded_packages
>>
>>> library(BRugs)
>>
>> Loading required package: coda
>>
>> Loading required package: lattice
>>
>> Welcome to BRugs running on OpenBUGS version 3.0.3
>>
>>> # Specify the model in BUGS language, but save it as a string in R:
>>
>>> modelString = "
>>
>> + model {
>>
>> + for ( i in 1:nFlips ) {
>>
>> + y[i] ~ dbern( theta )
>>
>> + }
>>
>> + theta ~ dunif( priorA , priorB )
>>
>> + priorA<- 0.6
>>
>> + priorB<- 1.0
>>
>> + }
>>
>> + " # close quote to end modelString
>>
>>>
>>
>>> # Write the modelString to a file, using R commands:
>>
>>> writeLines(modelString,con="model3.txt")
>>
>>> # Use BRugs to send the model.txt file to BUGS, which checks the model
>>> syntax:
>>
>>> modelCheck( "model3.txt" )
>>
>> model is syntactically correct
>>
>>
>>
>>
>> [ . run the model successfully!! .]
>>
>>
>>
>>
>> [ . now change just the prior definition and try to re-run .]
>>
>>
>>
>>
>>> modelString = "
>>
>> + model {
>>
>> + for ( i in 1:nFlips ) {
>>
>> + y[i] ~ dbern( theta )
>>
>> + }
>>
>> + theta ~ dunif( priorA , priorB )
>>
>> + priorA<- 0.4
>>
>> + priorB<- 0.6
>>
>> + }
>>
>> + " # close quote to end modelString
>>
>>>
>>
>>> # Write the modelString to a file, using R commands:
>>
>>> writeLines(modelString,con="model3.txt")
>>
>>> # Use BRugs to send the model.txt file to BUGS, which checks the model
>>> syntax:
>>
>>> modelCheck( "model3.txt" )
>>
>> Error in handleRes(res[[3]]) :
>>
>> An OpenBUGS module or procedure was called that did not exist.
>>
>>
>>
>> [[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>
More information about the R-help
mailing list