Re: [R] BRugs: error when compiling model

2013-08-05 Thread Uwe Ligges
Please specify a reproducible example, i.e. what you did exactly, all 
the way before the error message.


Best,
Uwe Ligges


On 05.08.2013 17:06, Nash, Charles T C wrote:

Using:

R version 3.0.1 (2013-05-16) -- Good Sport
Platform: x86_64-w64-mingw32/x64 (64-bit)
OpenBUGS version 3.2.2 rev 1063
BRugs version 0.8-1


Hi there,

When using the modelCompile() function in BRugs package I get the following 
error:

Error in handleRes(res) : NA
In addition: Warning message:
running command 'C:/Program Files/R/R-3.0.1/library/BRugs/exec/BugsHelper.exe 
C:/Users/cnash/AppData/Local/Temp/RtmpMlFBjk C:/Users/cnash/AppData/Local/Temp/RtmpMlFBjk/trash 
filef441bdb5e62.bug C:/Users/cnash/AppData/Local/Temp/RtmpMlFBjk/cmds.txt 1' had status 5

The model is as follows:

MODEL {
for (i in 1:7932) {
  for (j in 1:2) {
Y[i,j] ~ dpois(mu[i, j])
log(mu[i, j])-  alpha[j] + 
log(cars[i])  + V[i,j]   + U[i]

V[i,j] ~   dnorm(0, tau.un[j])

 }
  }

U[1:7932] ~ car.normal(adj[], weights[], num[], tau.spatial)
for (k in 1:sumNumNeigh) {weights[k]-1}


for(j in 1:2){
   alpha[j] ~ dnorm( 0, 0.0001)
   tau.un[j] ~ dgamma(0.5, 0.0005)
   sigma.tau[j] - 1/tau.un[j]
}

tau.spatial ~ dgamma(0.5, 0.0005)
sigma.spatial - 1/tau.spatial

}

There are no NA's in my data, and the model compiles in Openbugs. Could it be 
an issue with 64bit R?

Thanks!

Charlie Nash

__
R-help@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.



__
R-help@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.


Re: [R] BRugs Error

2013-02-11 Thread Uwe Ligges



On 10.02.2013 22:43, David Winsemius wrote:


On Feb 10, 2013, at 12:28 PM, Uwe Ligges wrote:




On 10.02.2013 21:18, Paul Ossenbruggen wrote:

I installed XCode, XQuartz and OpenBUGS on my Mac using WINE.
When I tried to test my installation I received the following error.

If correct, BRugs does not exist for R 2.15.1.

Is there a means to get arrange this problem?


Please install BRugs from sources, a Mac binary is not available on CRAN.



If he is doing this with WINE doesn't he need a Windows version.



Ah, I ignored the wine part. Not sure if BRugs works at all in this 
case, since you'd need the R under wine as well. Does that work at all?


Perhaps better to use R2OpenBUGS in such a case that starts the OPenBUGS 
under wine control.


Uwe







Best,
Uwe Ligges






Thanks

Paul



The following code is an example from R Help bugs:


schools.sim - bugs(data, inits,

+ parameters, model.file, n.chains=3,
+ n.iter=1000,
+ n.thin=10,n.burnin=10,bin=1,
+ DIC=FALSE,debug=TRUE,
+ useWINE = TRUE,
+ program = OpenBUGS,
+ bugs.directory=c:/ProgramFiles/OpenBUGS/)


Is there a missing space in that path?



__
R-help@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.


Re: [R] BRugs Error

2013-02-10 Thread Uwe Ligges



On 10.02.2013 21:18, Paul Ossenbruggen wrote:

I installed XCode, XQuartz and OpenBUGS on my Mac using WINE. When I 
tried to test my installation I received the following error.

If correct, BRugs does not exist for R 2.15.1.

Is there a means to get arrange this problem?


Please install BRugs from sources, a Mac binary is not available on CRAN.

Best,
Uwe Ligges






Thanks

Paul



The following code is an example from R Help bugs:


schools.sim - bugs(data, inits,

+   parameters, model.file, n.chains=3,
+   n.iter=1000,
+   n.thin=10,n.burnin=10,bin=1,
+   DIC=FALSE,debug=TRUE,
+   useWINE = TRUE,
+   program = OpenBUGS,
+   bugs.directory=c:/ProgramFiles/OpenBUGS/)
Loading required package: BRugs
Error in openbugs(data, inits, parameters.to.save, model.file, n.chains,  :
   BRugs is required
In addition: Warning message:
In library(package, lib.loc = lib.loc, character.only = TRUE, logical.return = 
TRUE,  :
   there is no package called ‘BRugs’


[[alternative HTML version deleted]]



__
R-help@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.



__
R-help@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.


Re: [R] BRugs Error

2013-02-10 Thread David Winsemius


On Feb 10, 2013, at 12:28 PM, Uwe Ligges wrote:




On 10.02.2013 21:18, Paul Ossenbruggen wrote:
	I installed XCode, XQuartz and OpenBUGS on my Mac using WINE. When  
I tried to test my installation I received the following error.


If correct, BRugs does not exist for R 2.15.1.

Is there a means to get arrange this problem?


Please install BRugs from sources, a Mac binary is not available on  
CRAN.




If he is doing this with WINE doesn't he need a Windows version.



Best,
Uwe Ligges






Thanks

Paul



The following code is an example from R Help bugs:


schools.sim - bugs(data, inits,

+   parameters, model.file, n.chains=3,
+   n.iter=1000,
+   n.thin=10,n.burnin=10,bin=1,
+   DIC=FALSE,debug=TRUE,
+   useWINE = TRUE,
+   program = OpenBUGS,
+   bugs.directory=c:/ProgramFiles/OpenBUGS/)


Is there a missing space in that path?

--
David.

Loading required package: BRugs
Error in openbugs(data, inits, parameters.to.save, model.file,  
n.chains,  :

  BRugs is required
In addition: Warning message:
In library(package, lib.loc = lib.loc, character.only = TRUE,  
logical.return = TRUE,  :

  there is no package called ‘BRugs’


David Winsemius, MD
Alameda, CA, USA

__
R-help@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.


Re: [R] BRugs Error

2013-02-10 Thread Prof Brian Ripley

On 10/02/13 21:43, David Winsemius wrote:


On Feb 10, 2013, at 12:28 PM, Uwe Ligges wrote:




On 10.02.2013 21:18, Paul Ossenbruggen wrote:

I installed XCode, XQuartz and OpenBUGS on my Mac using WINE.
When I tried to test my installation I received the following error.

If correct, BRugs does not exist for R 2.15.1.

Is there a means to get arrange this problem?


Please install BRugs from sources, a Mac binary is not available on CRAN.



If he is doing this with WINE doesn't he need a Windows version.


Of what?

In theory BRugs on Mac OS X could talk to OpenBUGS running the latter 
under WINE.  Except on 32-bit Windows, BRugs works by running a helper 
executable that is linked to OpenBUGS.  So that helper would need to be 
compiled under Windows and be run through WINE.  Just installing BRugs 
from the sources on OS X would not achieve that: you would need to build 
BugsHelper under Windows (possibly via WINE) and alter the BRugs sources 
to run it via WINE.


As others have said on R-sig-mac, it would be almost certainly be 
simpler to modify your task to run using JAGS via rjags, and most likely 
simpler to run BRugs under R for Windows using a Windows emulator (WINE 
might suffice).






Best,
Uwe Ligges






Thanks

Paul



The following code is an example from R Help bugs:


schools.sim - bugs(data, inits,

+ parameters, model.file, n.chains=3,
+ n.iter=1000,
+ n.thin=10,n.burnin=10,bin=1,
+ DIC=FALSE,debug=TRUE,
+ useWINE = TRUE,
+ program = OpenBUGS,
+ bugs.directory=c:/ProgramFiles/OpenBUGS/)


Is there a missing space in that path?




--
Brian D. Ripley,  rip...@stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel:  +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UKFax:  +44 1865 272595

__
R-help@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.