Great suggestion!! Will give that a try.
________________________________
From: William Dunlap [[email protected]]
Sent: Tuesday, December 02, 2014 4:49 PM
To: Ramiro Barrantes
Cc: [email protected]
Subject: Re: [R] How to have NLME return when convergence not reached
You could try using R.utils::withTimeout(expr, timeout=10) to cause an error
when evaluating the expression expr takes longer than 10 seconds. Wrap that in
tryCatch or try to catch the error and examine the outputs of lapply for ones
of class "TimeoutException" to find the ones that took too long.
E.g.,
>
> system.time(z <- lapply(1:10, function(p)tryCatch(withTimeout(timeout=5,
+ { for(i in seq_len(10^p))log(sqrt(i)) ; p }),
+ error=function(e)e))
+ )
user system elapsed
13.521 1.516 15.065
> sapply(z, function(zi)class(zi)[1])
[1] "integer" "integer" "integer" "integer"
[5] "integer" "integer" "integer"
"TimeoutException"
[9] "TimeoutException" "simpleError"
The first 7 iterations finished within 5 seconds, the next 2 timed out,
and the last had a different error (cannot allocate 74.5 Gb vector).
(R.utils's TimeoutException has an exceptionally long printout so I didn't
show the entire result.)
Bill Dunlap
TIBCO Software
wdunlap tibco.com<http://tibco.com>
On Tue, Dec 2, 2014 at 12:57 PM, Ramiro Barrantes
<[email protected]<mailto:[email protected]>> wrote:
Hello,
I am trying to fit many hundreds of simulated datasets using NLME (it's all in
a big loop in R). Some don't seem to converge. I am working on addressing the
issues by perhaps adjusting my simulation, or tweaking iteration steps in nlme,
etc. However, when it doesn't converge, NLME just hangs, and my program either
stalls for hours/days or takes over the computer memory and everything crashes
eventually. Is there a way to tell nlme to stop when it doesn't seem to be
converging somehow? I have been looking at the parameters in nlmeControl()
but see nothing obvious.
Thanks in advance,
Ramiro
[[alternative HTML version deleted]]
______________________________________________
[email protected]<mailto:[email protected]> mailing list -- To
UNSUBSCRIBE and more, see
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.
[[alternative HTML version deleted]]
______________________________________________
[email protected] mailing list -- To UNSUBSCRIBE and more, see
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.
