I am trying to optimize a likelihood function using NLMINB. After running
without a problem for quite a few iterations (enough that my intermediate
output extends further than I can scroll back), it tries a vector of parameter
values NaN. This has happened with multiple Monte Carlo datasets, a
On 2007-12-21, Louis Martin <[EMAIL PROTECTED]> wrote:
> Hi,
>
> I am running the following loop, but it takes hours to run as n is big. Is
> there any way "apply" can be used? Thanks.
> ### Start
> nclass <- dim(data)[[2]] - 1
> z <- matrix(0, ncol = nclass, nrow = nclass)
> n <- dim(
Hi Louis,
You could try this:
# find the index of the maximum value in each row of _data_, #
disregarding the last column classified <-
apply(data[,-(nclass+1)],1,which.max)
## or, if the maximum may be repeated:
classified <- apply(data[,-(nclass+1)], 1, FUN = function(x) which(x ==
max(x)))
#
To check for NA, use is.na. For instance your second ifelse should read:
ifelse(is.na(Sheet1$Claims),0,Sheet1$Claims))
Converting Sheet1$Claims to character doesn't have the effect you
think it does. NA is still NA, it does not become "NA". Try for
instance:
as.character(NA)
as.character(NA)
Hi,
I am running the following loop, but it takes hours to run as n is big. Is
there any way "apply" can be used? Thanks.
### Start
nclass <- dim(data)[[2]] - 1
z <- matrix(0, ncol = nclass, nrow = nclass)
n <- dim(data)[[1]]
x <- c(1:nclass)
# loop starts
for(loop in 1:n) {
Dear all,
I am comparing two regression models, one by nls() and other by mle() packages.
I know how do plot the estimated values using curve() function, but I need the
predicted to use on other functions and I don´t know how do get the predicted
value my mle model.
Any help are welcome.
mil
You can use a loop...
If x,y and z are your vectors containing Nx,Ny and Nz
numbers respectively, then
for (Ix in 1:Nx) for (Iy in 1:Ny) for (Iz in 1:Nz) {
Point <- c(x[Ix],y[Iy],z[Iz])
do whatever you need with Point
}
A (probably better) compromise may be:
a <- matrix(0,nrow = Ny*Nz, ncol = 3)
Could someone help me with the following code snippet. The results are not
what I expect:
> Sheet1$Claims[1:10]
[1] NA 1 2 NA NA NA NA NA NA NA
> Sheet1[1:10,"SubmissionStatus"]
[1] Declined Bound Bound Bound Bound Bound Declined
Dead Declined
[10] Not Taken
Leve
I would like to try the SSA approach with my data.
If i am not mistaken there is a package named "clim.pact" in the R
repository that does that.
I tried to download on my Linux box and it failed as it cannot resolve a
dependency that is only needed
for Windows platform (that is written in the site
I would expect this regression towards the mean behavior on a new or hold out
dataset, not on the training data. In RF terminology, this means that the
model prediction from predict is the in-bag estimate, but the out-of-bag
estimate is what you want for prediction. In Joshua's example,
rf.rf$pred
Thanks for your Inputs!
Joh
Johannes Graumann wrote:
> Hi all,
>
> Does anybody have a magic trick handy to isolate directly consecutive
> integers from something like this:
> c(1,2,3,4,7,8,9,10,12,13)
>
> The result should be, that groups 1-4, 7-10 and 12-13 are consecutive
> integers ...
>
This is OK if the ratio is positive, but for -50
divided by 12 the floor is -5 and the remainder is 10
(and not -4 and -2 as one may want). By the way, using
%% and %/% leads to same result.
Using trunc will remedy the situation, i.e.
> x <- -50
> y <- 12
> a <- trunc(x/y)
> r <- x - a*y
> a
[1] -
Duncan, thank you for the suggestion. This should be a plain text message,
perhaps it will post correctly to the R-help Archives.
-- TMK --
212-460-5430home
917-656-5351cell
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/
On 20/12/2007 5:46 PM, Talbot Katz wrote:
> Hi Duncan. Thank you for responding. Here is the URL in the R-help Archives
> for the original message I posted in this thread:
>
> https://stat.ethz.ch/pipermail/r-help/2007-December/148923.html
>
> When I go to that page, I see the scrub message.
On 21/12/2007, at 10:53 AM, Greg Snow wrote:
>
> 5.2 if this is just to make someone happy who always wants a p-value,
> but doesn't understand it and will never actually use it, then use
> runif.
A fortune?
cheers,
Rolf Turner
#
Hi Duncan. Thank you for responding. Here is the URL in the R-help Archives
for the original message I posted in this thread:
https://stat.ethz.ch/pipermail/r-help/2007-December/148923.html
When I go to that page, I see the scrub message. I can read your response at:
https://stat.ethz.ch/
Hi Xin,
You can use the nlsolve() function that I have written to solve a nonlinear
system of equations. It converts a root finding problem into a minimization
problem, and uses optim() to find the minimizer.
A well-known problem with this approach to root-finding is that a local
minimum of th
> my.obj<-c("a1","a2","a3")
> paste(my.obj, collapse=" ")
[1] "a1 a2 a3"
On Dec 20, 2007 5:15 PM, Milton Cezar Ribeiro <[EMAIL PROTECTED]> wrote:
> Dear all,
>
> I have a object like my.obj<-c("a1","a2","a3") and I would like
> my.new.obj="a1 a2 a3".
> I tryed to do my.new.obj<-paste(my.obj,sep=
On Thu, 2007-12-20 at 22:43 +0100, Johannes Graumann wrote:
> Hi all,
>
> Does anybody have a magic trick handy to isolate directly consecutive
> integers from something like this:
> c(1,2,3,4,7,8,9,10,12,13)
>
> The result should be, that groups 1-4, 7-10 and 12-13 are consecutive
> integers ..
?sep
paste(my.obj, collapse=" ")
HTH ..
Peter Alspach
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Milton
> Cezar Ribeiro
> Sent: Friday, 21 December 2007 11:15 a.m.
> To: R-help
> Subject: [R] collapsing a list in a var.
>
> Dear all,
Dear all,
I have a object like my.obj<-c("a1","a2","a3") and I would like my.new.obj="a1
a2 a3".
I tryed to do my.new.obj<-paste(my.obj,sep=" ") but it return three entries and
I need only one entry as result.
Any idea?
Miltinho
Brazil.
para armazenamento!
[[alternative HTML versi
Joh,
x <- c(1,2,3,4,7,8,9,10,12,13)
which(diff(x) != 1)
gives the indices of the 'jumps'.
Gabor
On Thu, Dec 20, 2007 at 10:43:05PM +0100, Johannes Graumann wrote:
> Hi all,
>
> Does anybody have a magic trick handy to isolate directly consecutive
> integers from something like this:
> c(1,2,3,
Hi all,
Does anybody have a magic trick handy to isolate directly consecutive
integers from something like this:
c(1,2,3,4,7,8,9,10,12,13)
The result should be, that groups 1-4, 7-10 and 12-13 are consecutive
integers ...
Thanks for any hints, Joh
__
The other one I should have mentioned:
5.1: Use the glm function with family = poisson. The counts are the y
variable and the x variable is either 0/1 or a 2 level factor indicating
which group the values come from. The p-value for the slope of x tests
for a difference in the 2 groups.
5.2 if
?ifelse
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
[EMAIL PROTECTED]
(801) 408-8111
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Armelini, Guillermo
> Sent: Wednesday, December 19, 2007 10:21 AM
> To: [
One possibility is to use the cnvrt.coords function from the
TeachingDemos package. It shows an example of putting a rectangle
across multiple plots. You would need to create the 1st (top) plot,
find the coordinate of the top and convert that to device coordinates,
then create the rest of your p
When running a function in parallel using for example the clusterCall
function in Snow is it possible to call other user-written functions from
each cluster? I get an error when I try to do this. I tried to source the
function on each cluster using the clusterEvalQ function but this doesn't
s
On 20/12/2007 3:43 PM, Talbot Katz wrote:
> Occasionally when I click on a posting in the archives, I don't see the
> actual message, but instead, something like the following:
>
> An embedded and charset-unspecified text was scrubbed...
> Name: not available
> Url:
> https://stat.ethz.ch/piper
Have you looked at the SQLiteDF package? It seems like it would do what
you want in a better way and much simpler. Even if that does not work
then a database approach (look at the other db packages, probably RODBC
first) could be simpler, faster, and easier. You may also want to look
at the g.da
Hi Livia,
There are several ways to do this. Try:
a=50/12
floor(a) will give you the entire portion, and
a-floor(a) will give you the remainder.
Julian
livia wrote:
> Hello everyone,
>
> I have got a question about a simple calculation. If I would like to
> calculate 50/12 and return the re
Occasionally when I click on a posting in the archives, I don't see the actual
message, but instead, something like the following:
An embedded and charset-unspecified text was scrubbed...
Name: not available
Url:
https://stat.ethz.ch/pipermail/r-help/attachments/200712XX/aXXX/attachment.pl
On Tue, 18-Dec-2007 at 11:21AM -0500, James W. MacDonald wrote:
|> Duncan Murdoch wrote:
|> > Yes, I agree. (As an aside, there's actually a capital S in
|> > smoothScatter(), and it's a bit of a pain to install, because
|> > geneplotter depends on something that depends on DBI, which is not so
|
There are a few different options that you can try depending on your
problem and your preferences:
1. For large lambda the poisson can be approximated by a normal, for
large n (even for small lambda) the mean is approximately normal due to
the central limit theorem. So if your lambda and n are l
I know that I'm a fool for trying to get this working under windows but I'm
obliged. Note I have R 2.6.1 and the latest cygwin. I'm running winxp sp2.
1) If I issue: R CMD INSTALL RSPerl_0.92-1.tar.gz, it fails as such
-- Making package RSPerl
***
What I see is the predictions being less extreme than the
actual values -- predictions for large actual values are smaller
than the actual, and predictions for small actual values are
larger than the actual. That makes sense to me. The object
is to maximize out-of-sample predictive power, not in-
On 20/12/2007 2:13 PM, Thompson, David (MNR) wrote:
> Hello,
>
> I am trying to set my environment to streamline the downloading /
> updating of packages. I have been through R-intro.html (10.8
> Customizing-the-environment), R-FAQ (5.2 How can add-on packages be
> installed?), rw-FAQ, and help pa
>From: Waverley <[EMAIL PROTECTED]>
>Date: 2007/12/20 Thu PM 01:29:04 CST
>To: [EMAIL PROTECTED]
>Subject: [R] Question how to get up triangle of a matrix
?upper.tri
>Is there a simple way to get up triangle of a matrix and return as a vector?
>
>Thanks much.
>
>--
>Waverley @ Palo Alto
>
>_
Is there a simple way to get up triangle of a matrix and return as a vector?
Thanks much.
--
Waverley @ Palo Alto
__
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.o
Hello,
I have a bug in my data that read.csv doesn't like, but _only_ when
specifying "na.strings = 'missing'". If I delete the offending Chinese
characters the problem goes away as well. I'm satisfied that the
problems with this data file are fixed, but is there anything I can to
do avoid
Hello,
I am trying to set my environment to streamline the downloading /
updating of packages. I have been through R-intro.html (10.8
Customizing-the-environment), R-FAQ (5.2 How can add-on packages be
installed?), rw-FAQ, and help pages for Sys.setenv {base},
download.packages {utils}, etc.,.
I
It not entirely clear, but I think that you are looking for
seq(t-1, 1)
-Christos
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Owe Jessen
> Sent: Thursday, December 20, 2007 1:29 PM
> To: [EMAIL PROTECTED]
> Subject: [R] Recursive solution wit
Hello,
i just ran into the following problem: I wanted to recursively solve
equations of the type x_1[t]=x_1[t+1]+beta*x_2[t], and used a for-loop
written
for(j in c(1:t-1, recursive=TRUE){
...
}
This didn't work, so i resolved to writing
for(j in c(10,9,...,1){
which worked, but is not terri
Nicolas Ris sophia.inra.fr> writes:
> I am trying to analyse the data of the box 10.5 in the Biometry from
> Sokal and Rohlf (2001) using R. This is a three-level nested anova with
> equal sample size : 3 different treatments are compared ; 2 rats (coded
> 1 or 2) / treatment are studied ; 3 p
Dear R-users,
I am trying to analyse the data of the box 10.5 in the Biometry from
Sokal and Rohlf (2001) using R. This is a three-level nested anova with
equal sample size : 3 different treatments are compared ; 2 rats (coded
1 or 2) / treatment are studied ; 3 preparations (coded 1, 2 or 3) /
> Perhaps as long as you're learning a new plotting system, you might also
> check out whether ggplot2 might be an option.
>
> I did a quick and dirty version (which I'm sure Hadley can improve and
> also remind me how to get rid of the legend that shows the "3" that I
> set the size to).
>
> Assum
On Dec 20, 2007 4:56 PM, Bert Jacobs <[EMAIL PROTECTED]> wrote:
> Hi,
>
> The problem is probably that my Var4, does not contain number but factor
> information, and therefore I think Gabor's suggestion does not work.
> The same holds for Hadley's solution with the functions melt/cast, where the
>
Hi,
The problem is probably that my Var4, does not contain number but factor
information, and therefore I think Gabor's suggestion does not work.
The same holds for Hadley's solution with the functions melt/cast, where the
resulting dataframe looks OK, but the dataframe is filled with the number o
Charilaos Skiadas <[EMAIL PROTECTED]> wrote:
> > 2. What's the easiest way to read such a data array from a text
> > file?
> > I can do some editing of a csv file produced from the
> > spreadsheet,
> > but don't really know what to aim for.
>
> Here is the code I used to read your ex
HI Tom,
On Dec 20, 2007, at 9:06 AM, Tom Sgouros wrote:
>
> Hello:
>
> I have been give a spreadsheet to work with formed as one big table.
> What it consists of is a 10-row-by-40-column table for each of
> about 70
> different locations. In other words, the table row names are repeated
> 70 ti
Dear all,
I use a nested design with lm and glm, with factor2 nested within
factor1. In order to test for the significance of both factors, I use
anova tables on the obtained models such as follows:
/> mod1<-lm(A~factor1/factor2)
> amod1<-anova(mod1, test="F")
Analysis of Variance Table
Respon
your description is pretty vague, at least for me...
it would be very helpful to have the "commented, minimal, self-
contained, reproducible code"...
but, anyways, you might want to take a look at the try() command.
best
b
On Dec 20, 2007, at 3:24 AM, Milton Cezar Ribeiro wrote:
Dear all,
useR's.
I am working with an algorithm in which I will need to create combinations
of all the points I have in a matrix. When I have 2 variables, I simply use
expand.grid() to do this. Sometimes I am faced with 3 or more variables and
if I run expand.grid(), R cannot process it due to the huge
Dear R-help,
I have a data set consisting of measurements made on multiple
subjects. Measurement sessions are repeated for each subject on
multiple dates. Not all subjects have the same number of
sessions. To create a factor that represents the session, I do
the following:
data <- read.csv('te
You may be haning Ion coerced into a factor. Have a
look at
http://finzi.psych.upenn.edu/R/Rhelp02a/archive/98260.html
for some discussion of this.
I find that I usually set
options(stringsAsFactors = FALSE) just because of
this but as Gabor points out it may have its own
disadvantages in shar
reshape package.
--- Bert Jacobs <[EMAIL PROTECTED]> wrote:
>
> In which package do I find the "cast" function. At
> the moment it's not
> recognized.
> Thx,
> Bert
>
> -Original Message-
> From: John Kane [mailto:[EMAIL PROTECTED]
> Sent: 19 December 2007 17:57
> To: Bert Jacobs; 'ha
On Dec 19, 2007 9:42 AM, David Hewitt <[EMAIL PROTECTED]> wrote:
>
>
> David Barron-3 wrote:
> >
> > You can calculate the AIC as follows:
> >
> > (fm1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy))
> > aic1 <- AIC(logLik(fm1))
> >
> >
> Is AIC() [extractAIC()] "valid" for models with rand
Eric --
Please don't cross post
Please simplify your example so that others do not have to work hard
to understand what you are asking
See additional response on the Bioconductor mailing list.
Martin
"Eric Lecoutre" <[EMAIL PROTECTED]> writes:
> Dear R-helpers & bioconductor
>
>
> Sorry for c
In which package do I find the "cast" function. At the moment it's not
recognized.
Thx,
Bert
-Original Message-
From: John Kane [mailto:[EMAIL PROTECTED]
Sent: 19 December 2007 17:57
To: Bert Jacobs; 'hadley wickham'
Cc: [EMAIL PROTECTED]
Subject: Re: [R] Reshape Dataframe
I think if yo
eugen pircalabelu <[EMAIL PROTECTED]> wrote in
news:[EMAIL PROTECTED]: >
> I have 4 questions which trouble me:
>
snip 1-3
>
> 4. I want to modify the scale of my axes within a plot but i really
> could not find this option. I think there is such an option, but i
> can not find it.
> x<-rn
Hello:
I have been give a spreadsheet to work with formed as one big table.
What it consists of is a 10-row-by-40-column table for each of about 70
different locations. In other words, the table row names are repeated
70 times, once for each of the locations (whose names also appear in the
same
When using the wireframe function you need to create a 2D grid for your two X
variables. Try the "expand.grid" function on your data, then run the
wireframe on that result
Brad B-2 wrote:
>
> Hello,
> I am trying to get a surface plot of a data set that looks like the
> following,
> 1 2
Dear R-helpers & bioconductor
Sorry for cross-posting, this concerns R-programming stuff applied on
Bioconductor context.
Also sorry for this long message, I try to be complete in my request.
I am trying to write a subset method for a specific class (ExpressionSet
from Bioconductor) allowing sel
Its a FAQ:
http://cran.r-project.org/doc/FAQ/R-FAQ.html#How-can-I-capture-or-ignore-errors-in-a-long-simulation_003f
On Dec 20, 2007 3:24 AM, Milton Cezar Ribeiro <[EMAIL PROTECTED]> wrote:
> Dear all,
>
> I am simulating some regressions in a for() looping and sometimes occours
> some error and
R-users,
My question is related to earlier posts about benefits of quadcore over
dualcore computers; I am trying to setup a cluster of windows xp
computers so that eventually I could make use of 10-20 cpu:s, but for
learning how to do this, I am playing around with two laptops.
I thought that the
See 'akima' package.
On 20/12/2007, Brad B <[EMAIL PROTECTED]> wrote:
> Hello,
> I am trying to get a surface plot of a data set that looks like the
> following,
> 1 2 5.6
> 5 9 2.4
> 9 8 9.8
> ... to (60,000 rows down)
>
> From my homework, the persp function only works with evenly s
Greetings to you.
My name is Mr. Ray Orfan the Personal Assistant (PA) to the Head of an
important International Organization. I have been directed to seek foriegn
partnership with an interested foreigner on an issue relating to money.
The issue invloved will be beneficial to all concerned an
Hello,
I am trying to get a surface plot of a data set that looks like the following,
1 2 5.6
5 9 2.4
9 8 9.8
... to (60,000 rows down)
From my homework, the persp function only works with evenly spaced data
points with the z data beeing in a matrix. my data is not in that f
You could do:
> x <- c('A','B','A','C','C','B')
> x
[1] "A" "B" "A" "C" "C" "B"
> mapply(function(i) sum(x[1:i] == x[i]),1:length(x))
[1] 1 1 2 1 2 2
>
--- Eric Lecoutre <[EMAIL PROTECTED]> wrote:
> Dear R-help,
>
> I am trying to have a generic way to assess the
> replicates in a character
>
One possibility is:
> x
[1] "A" "B" "C" "D" "A" "C" "D" "B"
> y
[1] 10 11 9 8 12 4 5 7
> basic_map
[[1]]
[1] "A" "B"
[[2]]
[1] "C" "D"
> a <- which(sapply(basic_map,function(u) x %in%
u),arr.ind=TRUE)
> aggregate(y,list(a[order(a[,1]),2]),sum)
Group.1 x
1 1 40
2 2 26
>
---
Dear Ajay,
At present, unfortunately, we have so mechanism for distributing code
associated with R News articles. We're considering changes to the
infrastructure that supports R News, including providing the kind of
facility that you suggest. I'm afraid that the best that I can suggest for
now is
Dear Jose,
> -Original Message-
> From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
> project.org] On Behalf Of Jose
> Sent: December-19-07 11:27 AM
> To: [EMAIL PROTECTED]
> Subject: Re: [R] Correlation when one variable has zero variance
> (polychoric?)
>
> Dear John,
>
> > I also ran
Jonas Malmros wrote:
> Hi everybody,
>
> I wonder if there is a built-in function similar to Matlab's "normfit"
> which computes 95% CI based on the normality assumption.
> So, I have a vector of values and I want to calculate 95% normal CI.
> Of course, I could write my own function, no problem, b
Thank you very much for your reply. I found the information on your home
page very useful.
What I want to do is a PLS regression of a data set with 60 features for
calibration purposes.
In order to optimize the performance of the calibration I have to find
out what features to use
in the PLS r
Hi everybody,
I wonder if there is a built-in function similar to Matlab's "normfit"
which computes 95% CI based on the normality assumption.
So, I have a vector of values and I want to calculate 95% normal CI.
Of course, I could write my own function, no problem, but I still
wonder if built-in fu
Try this:
jpeg("UserDA%02dT.jpg")
sapply(1:10, function(x)plot(rnorm(100)))
dev.off()
On 20/12/2007, Daniel Jegelka <[EMAIL PROTECTED]> wrote:
> Hello, i only got a small problem.
>
> i try to create automatic new dataframes, or png´s. the main problem i
> got is:
>
> how can i create automatic a
Hello, i only got a small problem.
i try to create automatic new dataframes, or png´s. the main problem i
got is:
how can i create automatic a new name for a file (read out by simply
"for") -
i tried to use "(paste...) but theres an errormessage, about a wrong
declination. R told it is as.charact
On 20-Dec-07 08:24:40, Milton Cezar Ribeiro wrote:
> Dear all,
>
> I am simulating some regressions in a for() looping and sometimes
> occours some error and the R stop my batch processing. I would like do
> save the step where the error happned and continue my for() looping.
> Is there a way to d
library(R.utils);
for (ii in 1:12) {
value <- my.fun(my.list[ii]);
saveObject(value, file=sprintf("data%02d.RData", ii));
rm(value); gc();
}
for (ii in 1:12) {
value <- loadObject(sprintf("data%02d.RData", ii));
}
On 18/12/2007, Marie Pierre Sylvestre <[EMAIL PROTECTED]> wrote:
> Dear R
one way is the following:
V1 <- c(1,1,1,2,3,3,3,3)
V2 <- LETTERS[c(1,1,2,1,3,1,3,2)]
tab <- table(V1, ave(V1, V1, FUN = seq_along))
vals <- as.vector(t(tab))
vals[vals != 0] <- unlist(split(V2, V1))
vals[vals == 0] <- NA
matrix(vals, nrow(tab), ncol(tab), TRUE)
I hope it helps.
Best,
Dimitris
Dear all,
I am simulating some regressions in a for() looping and sometimes occours some
error and the R stop my batch processing. I would like do save the step where
the error happned and continue my for() looping.
Is there a way to do that?
Thanks In Advance.
Miltinho
para armazenamento!
Dear useRs,
The December 2007 issue of `R News' is now available on CRAN under the
Documentation/Newsletter link.
Torsten
(on behalf of the R News Editorial Board)
___
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-announce
__
Dear John,
> I also ran the same analysis in 2005
> (what has changed in the package polycor since then, I don't know) and the
> results were different. I think back then I contrasted them with SAS
> and they were the same.
John> I don't entirely follow this. Are you referring to the table above
82 matches
Mail list logo
