I would recommend that you use auglag() rather than constrOptim.nl() in the
package "alabama." It is a better algorithm, and it does not require feasible
starting values.
Best,
Ravi
-Original Message-
From: Rainer M Krug [mailto:rai...@krugs.de]
Sent: Thursday, October 01, 2015 3:37
Envoyé de mon iPhone
> Le 1 oct. 2015 à 15:17, Ravi Varadhan a écrit :
>
> I would recommend that you use auglag() rather than constrOptim.nl() in the
> package "alabama." It is a better algorithm, and it does not require
> feasible starting values.
Thanks - that was one question I wanted
Ravi Varadhan writes:
> Hi Rainer,
> It is very simple to specify the constraints (linear or nonlinear) in
> "alabama" . They are specified in a function called `hin', where the
> constraints are written such that they are positive.
OK - I somehow missed the part that, when the values x are val
Hi Rainer,
It is very simple to specify the constraints (linear or nonlinear) in "alabama"
. They are specified in a function called `hin', where the constraints are
written such that they are positive. Your two nonlinear constraints would be
written as follows:
hin <- function(x, LAI) {
h <-
FMRPROG wrote
> I am generating random numbers from a normal distribution using
> [snip]
>
> I need to optimize the speed WITHOUT using the rnorm function but have no
> idea how to do this. I assume I should minimise what goes in the loop?
>
> Any help would be very much appreciated.
Looks like
On 22-11-2012, at 22:55, Дмитрий Островский wrote:
> I am trying to optimize custom likelyhood with nlminb()
> Arguments h and f are meant to be fixed.
>
> example.R:
>
> compute.hyper.log.likelyhood <- function(a, h, f) {
> a1 <- a[1]
> a2 <- a[2]
> l <- 0.0
> for (j in 1:length(f)) {
>
On Wed, Nov 14, 2012 at 8:23 PM, Sam Asin wrote:
> Hello,
>
> I am fairly new with R and am having trouble finding an optimal group. I
> checked the help functions for the various optimize commands and it was a
> little over my head.
>
> I have a dataset with 4 columns, name, type, value, and cos
On Thu, Nov 15, 2012 at 7:49 PM, Sam Asin wrote:
> Hey,
>
> It's actually not homework, what gave you that impression?
Real data sets don't usually have people named A,B,C with wages 3,4,5. ;-)
To your question at hand, it's close to a classic problem in
combinatorial optimization known as the k
Hey,
It's actually not homework, what gave you that impression? I graduated in
May and studied Math, economics, and international relations, so I don't
have much of a programming background. This is a project that I'm working
on out of personal interest.
Obviously, I've tried doing some homewor
Sam:
1. Homework? R has a no homework policy.
2. But in any case, check out the Optimization task view on CRAN. You
should be able to find something there that meets your needs.
Of course, if something is "a little over your head," that's not an
excuse, but rather an admission that you have to d
will try my best to explain it more. But please do reply.
Regards,
B.Nataraj
-Original Message-
From: David Winsemius [mailto:dwinsem...@comcast.net]
Sent: Thursday, May 31, 2012 8:19 PM
To: Nataraj B (ORLL-Biotech)
Cc: r-help@r-project.org
Subject: Re: [R] Optimizing variables represented
Inline ...
On Thu, May 31, 2012 at 9:09 AM, Kjetil Halvorsen
wrote:
> If you want an helpful answer, you must describe your real problem
> MUCH better! This is way too confused.
Absolutely! -- But we certainly can say:
>
> Kjetil
>
> On Thu, May 31, 2012 at 7:37 AM, wrote:
>>
>> Dear R-list
If you want an helpful answer, you must describe your real problem
MUCHbetter! This is way too confused.
Kjetil
On Thu, May 31, 2012 at 7:37 AM, wrote:
>
> Dear R-list members,
>
> I have a matrix with non-numeric variables in it and I have to optimize the
> variables of the matrix in a fo
On May 31, 2012, at 7:37 AM, > wrote:
Dear R-list members,
I have a matrix with non-numeric variables in it and I have to
optimize the variables of the matrix in a formula using optim
routine of the stats4 package. I know the matrix can only take
numeric data
Some of the things you
On Wed, May 23, 2012 at 10:56:43PM -0700, kylmala wrote:
> Hi,
>
> and thanks for replying this. Yes, you are right that the term
> min(24/bb,26/cc) is actually min(bb/24,cc/26) - my mistake. But still I
> don't get it. If the objective function is
>
> #min(m1,m2,m3)
> f.obj <- c(1, 1, 1)
>
> #
Hi,
and thanks for replying this. Yes, you are right that the term
min(24/bb,26/cc) is actually min(bb/24,cc/26) - my mistake. But still I
don't get it. If the objective function is
#min(m1,m2,m3)
f.obj <- c(1, 1, 1)
#and we now that
# a+aa<=15
# b+bb+bbb<=35
# cc+ccc<=40
# so
# 1a + 0b +
On Wed, May 23, 2012 at 12:35:31AM -0700, kylmala wrote:
> Hi,
>
> I have a problem with R optimization. I try to copy excel solver acts to R.
> Solver has some problems with nonlinear optimisation.
>
> Suppose we have resources: (X,Y,Z)=(20, 30, 25) and services:
> matrix(10,11,0, 13,12,10, 0,24
I'have tried to do something like that staring values:
pars=c(x1=1,x2=1,x3=1,x4=1,x5=1,x6=1,x7=1)
and the function
f=function(pars){
min(pars[1]/10,pars[2]/11)+min(pars[3]/20,pars[4]/22,pars[5]/25)+min(pars[6]/36,pars[7]/28)
}
optim(pars,f)
but how can I get the constraints in there also?
--
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi Patrick,
thanks a lot. No, I am not using MKL, but I am going to try the flags
you mention in your blog.
Cheers,
Rainer
On 11/12/2010 03:58 PM, Richardson, Patrick wrote:
> Rainer,
>
> The attached link might give you some insight. It's for co
I am trying to estimate an Arrhenius-exponential model in R. I have one
vector of data containing failure times, and another containing
corresponding temperatures. I am trying to optimize a maximum likelihood
function given BOTH these vectors. However, the optim command takes only
one such vect
Optim uses vectors of _parameters_, not of data. You add a
(likelihood) function, give initial values of the parameters, and get
the optimized parameters back. See ?optim and the examples therein. It
contains an example for optimization using multiple data columns.
Cheers
Joris
On Fri, Jun 25, 20
Duncan Murdoch a écrit :
On 22/01/2010 12:52 PM, Christophe Genolini wrote:
Thanks both of you.
>
> > Inf - Inf
> [1] NaN
So isn't the line 9 useless ? If either x[i] or y[i] are NA, then dev
will be NA and !ISNAN(dev) will detect it...
Sothe loop cool be
8.for(i = 0 ; i < taille ; i++)
On 22/01/2010 12:52 PM, Christophe Genolini wrote:
Thanks both of you.
>
> > Inf - Inf
> [1] NaN
So isn't the line 9 useless ? If either x[i] or y[i] are NA, then dev
will be NA and !ISNAN(dev) will detect it...
Sothe loop cool be
8.for(i = 0 ; i < taille ; i++) {
10.dev = (x[i] -
A side note: The NA vs NaN does not seem to play a role here, because:
#define both_non_NA(a,b) (!ISNAN(a) && !ISNAN(b))
So, it is the same type of test used in line 9 and in line 11.
/Henrik
On Fri, Jan 22, 2010 at 9:52 AM, Christophe Genolini
wrote:
> Thanks both of you.
>
>>
>> > Inf - Inf
Thanks both of you.
> Inf - Inf
[1] NaN
So isn't the line 9 useless ? If either x[i] or y[i] are NA, then dev
will be NA and !ISNAN(dev) will detect it...
Sothe loop cool be
8.for(i = 0 ; i < taille ; i++) {
10.dev = (x[i] - y[i]);
11.if(!ISNAN(dev)) {
12. dist +
Christophe Genolini wrote:
Hi the list,
I need to write some efficient distances function, so I read the code
for the Euclidean distance.
I do not understand the purpose of the line 11 : if x[i] and y[i] are
not NA (line 9), can dev be NA ?
As Romain said, the test is for NaN as well as N
Bonjour Christophe,
NA and NaN are different things... Actually this is tricky because NA is
implemented as a special kind of NaN :
See this extract of R_ext/Arith.h :
int R_IsNA(double); /* True for R's NA only */
int R_IsNaN(double);/* True for special NaN, *not* for
Ravi Varadhan wrote:
Look at nlminb() or optim(), in particular the option `method = "L-BFGS-B"' or the
function spg() in "BB" package.
With these you can optimize over any number of variables.
Ravi.
Hi Ravi,
Thanks for the leads, I'll take a look, though right now I have
run into problems
Look at nlminb() or optim(), in particular the option `method = "L-BFGS-B"' or
the function spg() in "BB" package.
With these you can optimize over any number of variables.
Ravi.
Ravi Varadhan, Ph.D.
Assistant Professor,
Div
Hi Max,
Thanks for the suggestion, that's exactly what I was looking for. Thanks
again.
Paul
--
View this message in context:
http://www.nabble.com/Optimizing-Multiple-Models...any-suggestions--tp21979556p22006494.html
Sent from the R help mailing list archive at Nabble.com.
_
See:
http://cran.r-project.org/web/views/Optimization.html
On Thu, Feb 12, 2009 at 11:31 AM, Paul Heinrich Dietrich
wrote:
>
> There are multiple marketing models in place to predict individual-level
> probabilities of whether or not someone would respond to a solicitation,
> whether or not they
Wolfgang Raffelsberger wrote:
Dear list,
I'm wondering how to optimize functions/processes like the one shown
below (which simplifies something we're trying to do with very large
datasets).
In many cases I've noticed that using apply, sapply etc can help
speeding up processes, but in this ca
32 matches
Mail list logo
