[R] automate save.image

Dear all, Sometimes, during an R session, my computer hangs and I loose all the objects created during this session. Is there a way to automatically type save.image() and savehistory() every 5 minutes? Best regards, Remigijus __ [EMAIL PROTECTED]

RE: [R] ts vs. POSIX

Well, I'm not sure I understand the question exactly, but you might want to have a look at the package 'its', as Achim said. A practical example might look like: You have a .csv file as follows (I have chosen the date format at random). ,x,y Monday 08-Sep-2003,1,11 Monday 15-Sep-2003,2,22

[R] long algo

Hi everyone, I ve been using R for months and find it really practical and straight forward. However (the inevitable however), I am finding it very slow for one of my operations: it s basically an itertation over i and j in a pretty big table (4* 4608). It takes 30 minutes Thanks Ps:if it

[R] Kendall rank correlation

I would like to know how can I calculate and plot the sequential values of the statistics u(t) and u'(t)? [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Re: [R] long algo

Is well know that R is inefficent on loops. When you have to perform heavy loop is better to use a call to fortran or c code (.Fortran() , .C() functions) A.S. Alessandro Semeria Models and Simulations Laboratory Montecatini Environmental Research Center (Edison

Re: [R] Loading a sub-package

On 28-Oct-03 Prof Brian Ripley wrote: On Tue, 28 Oct 2003 [EMAIL PROTECTED] wrote: But MASS is huge! Hence the query. (I've also had occasion to filch single functions from other libraries as well). MASS is *not* huge, and indeed is negligible compared to what is already loaded. nlme

Re: [R] long algo

william ritchie wrote: Hi everyone, I ve been using R for months and find it really practical and straight forward. However (the inevitable however), I am finding it very slow for one of my operations: it s basically an itertation over i and j in a pretty big table (4* 4608). It takes 30

Re: [R] Loading a sub-package

Short answers: Setting R_DEFAULT_PACKAGES changes the startup packages, as ?Startup says. You should not need methods unless you are using S4 classes yourself, as any package you might use that needs it is supposed to load it. Methods adds a considerable overhead to R's startup time and

[R] P-values in ncf package

Group, I'm currently trying to find out how the function correlog in the ncf package may be useful to me for calculating cross-correlograms. The function's output includes P-values for all distance classes, but it seems that only positive values can become significant. Is this true and correct?

[R] Re: presentation of software

Dear Jason, see this on page 20 (article by Simon Jackman) http://web.polmeth.ufl.edu/tpm/TPM11N2.pdf I bet it will help you in organizing your talk (I have done something similar recently). Cheers Giovanni Giovanni Millo Research Dept. Assicurazioni Generali SpA +39 040 671184 Original

[R] stacked histogram

Is there a way to do a stacked histogram, using color. I have two groups with the complication that one group is about 6% of the total. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

[R] I have a problem with the log2 function

Dear R users, according the help(log), the function log2(x) should give the natural logarithm of x. I expect in case of x=2 to to get 0.6931, however, R gives me 1 as a result. Similar, logb(2,2) gives 1 again. I'm wondering if I have missed something ? Yours Frank -- Frank Mattes, MD

Re: [R] I have a problem with the log2 function

Frank Mattes [EMAIL PROTECTED] writes: Dear R users, according the help(log), the function log2(x) should give the natural logarithm of x. I expect in case of x=2 to to get 0.6931, however, R gives me 1 as a result. Similar, logb(2,2) gives 1 again. I'm wondering if I have missed

RE: [R] automate save.image

You can use the callback manager that Duncan Temple Lang implemented in R. Search the R-help archive for auto-save. Andy From: Remigijus Lapinskas [mailto:[EMAIL PROTECTED] Dear all, Sometimes, during an R session, my computer hangs and I loose all the objects created during this

[R] add and drop methods for mlm objects

Hello, I would like to fit several responses depending on the same parameters. Thus I generate an mlm object. On the other hand, for further analysis, I would like to be able to simplify as much as possible the models. Of course, there is no reason that the same formula applies for every

[R] conflicts(detail=TRUE)

Why this? R conflicts(detail=TRUE) $package:methods [1] body- $package:base [1] body- R mahmood arai __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Re: [R] R performance on Unix

morozov wrote: Hi I'm observing a huge difference in the performance speed of R on Windows and Unix, even though I know that my Unix machine is much more powerful than my Win machine. I've had this experience on a Unix machine that I thought was much more powerful than my Windows machine. On

[R] One inflated Poisson or Negative Binomal regression

Hello I am interested in Poisson or (ideally) Negative Binomial regression with an inflated number of 1 responses I have seen JK Lindsey's fmr function in the gnlm library, which fits zero inflated Poisson (ZIP) or zero inflated negative binomial regression, but the help file states that for '

[R] /usr/lib/R/library vs /usr/local/lib/R/site-library

I would appreciate getting a clarification of /usr/lib/R/library vs /usr/local/lib/R/site-library. I am running R 1.8 on Debian Linux. On one occasion doing update.packages() resulted in versions of one or more libraries being placed in one of these directories without removing the old

[R] grid: dividing units by numbers

How can I divide a unit by an number or average a vector of units, e.g.: u1 - unit( 3, 'npc' ) u2 - unit( 6, 'npc' ) u1 / 2 ( u1 + u2 ) / 2 mean( unit.c(u1,u2) ) I would use that e.g. to to calculate the coordinates of the midpoint of a line. Wolfram

[R] Where is rmutil package?

Pursing my earlier question, when I tried loading Lindsey's gnlm, I got a message Loading required package: rmutil Warning message: There is no package called 'rmutil' in: library(package, character.only = TRUE, logical = TRUE, warn.conflicts = warn.conflicts, According to the R

Re: [R] /usr/lib/R/library vs /usr/local/lib/R/site-library

Frank E Harrell Jr wrote: I would appreciate getting a clarification of /usr/lib/R/library vs /usr/local/lib/R/site-library. I am running R 1.8 on Debian Linux. On one occasion doing update.packages() resulted in versions of one or more libraries being placed in one of these directories without

Re: [R] /usr/lib/R/library vs /usr/local/lib/R/site-library

Frank E Harrell Jr [EMAIL PROTECTED] writes: 1 I would appreciate getting a clarification of /usr/lib/R/library vs 1 /usr/local/lib/R/site-library. I am running R 1.8 on Debian Linux. 1 On one occasion doing update.packages() resulted in versions of one 1 or more libraries being placed in one of

[R] evaluating expression within nls()

Dear R experts, I'd like to fit data with weighted function fcn(data, p1, p2). At first I used the standard form: nls(~ fcn(data, p1, p2), start = list(p1 = p01, p2 = p02), data = data) Then, I decided to change fcn() that it would be able to accept expression as an

Re: [R] grid: dividing units by numbers

On Wednesday 29 October 2003 09:36, Wolfram Fischer wrote: How can I divide a unit by an number or average a vector of units, e.g.: u1 - unit( 3, 'npc' ) u2 - unit( 6, 'npc' ) u1 / 2 0.5 * u1 ( u1 + u2 ) / 2 0.5 * (u1 + u2) mean( unit.c(u1,u2) ) Not sure

[R] importing SAS data

I am trying to import a permanent SAS data set using read.ssd in the foreign library. I get the following error: list.files(C:/temp) [1] newdat1.sas7bdat snpm1.sas7bdat test1.sas library(foreign) newdat1 - read.ssd(C:/temp,newdat1) SAS failed. SAS program at

[R] rmutil located

Thanks to all who pointed out that rmutil is also on Jim Lindsey's site. Peter __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Re: [R] /usr/lib/R/library vs /usr/local/lib/R/site-library

On Wed, Oct 29, 2003 at 07:51:16AM -0800, A.J. Rossini wrote: Frank E Harrell Jr [EMAIL PROTECTED] writes: 1 I would appreciate getting a clarification of /usr/lib/R/library vs 1 /usr/local/lib/R/site-library. I am running R 1.8 on Debian Linux. 1 On one occasion doing update.packages()

Re: [R] Cigarettes $20.95 per carton S/H

I was acurrent costomer. and now I cannot find the website. i was very happy with the service you provided what happenend dawn corvin [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list

RE: [R] importing SAS data

There is a utility called dataload at: http://www.vsn-intl.com/genstat/downloads/datald.htm that says it can convert SAS files (and numerous other formats) to csv and other formats. I have successfully used it to convert Excel xls files to csv although I don't have experience with its

Re: [R] evaluating expression within nls()

On Wed, Oct 29, 2003 at 06:54:05PM +0300, Timur Elzhov wrote: Yes, in help(nls) is pointed, that Arguments: data: an optional data frame in which to evaluate the variables in `formula' But, I'd like 'nls' to see my expression 'expr'... :-/ How can I do that? Sorry, I

Re: [R] importing SAS data

It is not explicitly stated in the help for read.ssd(), but the description says: generates a SAS program to convert the ssd contents to SAS transport format and then uses read.xport to obtain a dataframe I would imagine that generates a SAS program implies that SAS itself must be available to

[R] constrOptim doesn´t send arguments to optim!(?)

Hi, I think that there something wrong with the 'constrOptim' max/minimization function because she doesn´t send extra arguments to 'optim' call. Fact: When I use optim in a f(x,theta)-like function, everything goes ok. But using constrOptim with the same function leads to error... Proof: Make

Re: [R] /usr/lib/R/library vs /usr/local/lib/R/site-library

Dirk Eddelbuettel [EMAIL PROTECTED] writes: [1] And one day from BioC (Tony and I are only about a good year late ;-) Well, I'm waiting for the release of 1.3 :-P. bset, -tony -- [EMAIL PROTECTED]http://www.analytics.washington.edu/ Biomedical and Health Informatics

[R] test for connectedness

Hi, in a 2-way linear model with missing data the normal equations can sometimes be separated in 2 or more independent sets of equations brought about by the nature of the missing data. As far as I know this phenomenon is called 'connectedness' of the data. Does anyone know of a test or

Re: [R] constrOptim doesn´t send arguments to optim!(?)

I'm not sure this is necessarily a bug in constrOptim. I think the problem is that while `...' is in fact passed to optim(), the objective function is evaluated in constrOptim a few times before optim() is called and `...' is not passed in those cases. The easiest way to make this problem go

[R] constrained OLS

Hi, I would like to know if anyone has any idea of how to run an OLS with constraints? thank you Soyoko __ Ms. Soyoko Umeno Graduate Research Assitant for the Illinois-Missouri Biotechnology Alliance (IMBA) at http://www.imba.missouri.edu/ Ph.D. Student at

[R] constrained OLS on coefficient

Hi, I would like to know if anyone has any idea of how to run an OLS with constraints? I need to contraint a coefficient estimate in the model equal to 1, and I am not sure how to include it into the OLS estimation... I was hoping to find something like cnsreg in STATA.. thank you Soyoko

Re: [R] constrained OLS on coefficient

Use lm() or glm() with argument 'offset' set to the value of the column whose coefficient must be 1. See help(lm). - tom blackwell - u michigan medical school - ann arbor - On Wed, 29 Oct 2003, umeno wrote: Hi, I would like to know if anyone has any idea of how to run an OLS with

Re: [R] constrained OLS on coefficient

I don't know STATA, but if you want to force a specific regression coefficient to be 1, I think that can be done with the formula. Consider the following: DF - data.frame(x1=1:6, x2=rep(1:2, 3), y=rep(1:3, 2)) lm(y-x1~x2-1, DF) The formula y-x1~x2-1 fits a noconstant

Re: [R] Where is rmutil package?

Peter Flom [EMAIL PROTECTED] writes: Pursing my earlier question, when I tried loading Lindsey's gnlm, I got a message Loading required package: rmutil Warning message: There is no package called 'rmutil' in: library(package, character.only = TRUE, logical = TRUE, warn.conflicts =

Re: [R] grid: dividing units by numbers

Hi Deepayan Sarkar wrote: On Wednesday 29 October 2003 09:36, Wolfram Fischer wrote: How can I divide a unit by an number or average a vector of units, e.g.: u1 - unit( 3, 'npc' ) u2 - unit( 6, 'npc' ) u1 / 2 0.5 * u1 ( u1 + u2 ) / 2 0.5 * (u1 + u2) mean( unit.c(u1,u2)

Re: [R] importing SAS data

Gabor Grothendieck [EMAIL PROTECTED] writes: There is a utility called dataload at: http://www.vsn-intl.com/genstat/downloads/datald.htm that says it can convert SAS files (and numerous other formats) to csv and other formats. I have successfully used it to convert Excel xls files

Re: [R] importing SAS data

On 29 Oct 2003 21:10:02 +0100 Peter Dalgaard [EMAIL PROTECTED] wrote: Gabor Grothendieck [EMAIL PROTECTED] writes: There is a utility called dataload at: http://www.vsn-intl.com/genstat/downloads/datald.htm that says it can convert SAS files (and numerous other formats) to csv

[R] loglm() uses only a reference to data, and not data itself - is that on purpose??

Dear all, Consider the following: library(MASS); data(HairEyeColor) l1 - loglm(~ 1+2+3, data=HairEyeColor) myloglm - function(){ nd - HairEyeColor v - loglm(~ 1+2+3, data=nd) return(v) } l2 - myloglm() Now, step(l1) works, whereas step(l2) does not, the problem being that data nd

[R] restarting split.screen

Is there a way of `restarting' split.screen? This is what I am getting: close.screen() [1] 10 11 12 13 close.screen(all=TRUE) Error in par(args) : parameter i in mfg is out of range graphics.off() x11() close.screen() [1] 10 11 12 13 close.screen(all=TRUE) Error in par(args) : parameter i

[R] svm from e1071 package

I am starting to use svm from e1071 and I wonder how exactly crossvalidation is implemented. Whenever I run svm.model - svm(y ~ ., data = trainset, cross = 3) on my data I get dirrerent values for svm.model$MSE e.g. [1] 0.9517001 1.7069627 0.6108726 [1] 0.3634670 0.9165497 1.4606322 This

Re: [R] restarting split.screen (solved)

Ok, after realizing that even restarting R did not work, I found the solution to my problem: grep(split,ls(all=T),value=T) [1] .split.cur.screen.split.par.list .split.saved.pars [4] .split.screens .split.valid.screens rm(list=grep(split,ls(all=T),value=T)) Sorry for the

Re: [R] svm from e1071 package

This suggests to me that data are scrambled each time - the last time I looked at libsvm python interface this is what was done. Is this the same here (I hope) ? yes. g., David __ [EMAIL PROTECTED] mailing list

Re: [R] importing SAS data

On 29 Oct 2003, Peter Dalgaard wrote: as if no other Unix than Sun Solaris existed. Also, the program is in the public domain but the source is not included. Does anyone know what the author's long-term plans are with this? (It's a GenStat complimentary item, so GenStat non-users obviously

[R] packaging a package addon

I am trying to package some code that is a tweak to the survival package. When I asked earlier, the list consensus was that it would be best to do this as a separate package, dependent on survival. This is proving a bit tricky. I have some run-time and compile time concerns. Run-time, my R

[R] A Question for Statisticians about SCHWARZ, SHIBATA, RICE ...

Hi! I'm looking for a 'source' about these 'distributions'. SGMASQ, AIC, FPE, HQ, SCHWARZ, SHIBATA, GCV, RICE I would like to use _one_ book ('source') that would have information about all of these. Thank you, len - Exclusive Video Premiere -

RE: [R] loglm() uses only a reference to data, and not data itsel f - is that on purpose??

loglm() is a port of an original written for S-PLUS. The fact that it carries only a reference to the data frame is neither intentional nor unintentional, but an unnoticed side-effect. I can see advantages both ways. (I'm not so sure, either, that what you say is standard behaviour for model

[R] Re: packaging a package addon

I have some mixed results to report. I went ahead and built a package with the dependency, my changed files, and a few headers. I left the headers in the same directory as the C files. My first attempt passed R CMD check, though there were no examples to exercise the code. When I tried to run

[R] Trouble reshaping some data

I would appreciate some advice on the following task. I have some data that currently looks like this: t1 - data.frame(id=c(1,1,2,2), aspect=c(A,B,A,B), score=c(10,9,11,12)) I'd like it to look like this: id A B 1 10 9 2 11 12 reshape() looks like a good candidate for this job but

[R] legend over-prints barplot bar

When I create a bar plot, the legend is obscuring the rightmost bar. I haven't found a setting that appears to affect the positioning of the legend - any tips re moving the legend would be most appreciated. paul sorenson __ [EMAIL PROTECTED] mailing

Re: [R] Re: packaging a package addon

You might need to install before checking. Sometimes that helps. I still havn't figured out exactly why... Ross Boylan [EMAIL PROTECTED] writes: I have some mixed results to report. I went ahead and built a package with the dependency, my changed files, and a few headers. I left the

Re: [R] packaging a package addon

On Wed, 29 Oct 2003, Ross Boylan wrote: I am trying to package some code that is a tweak to the survival package. When I asked earlier, the list consensus was that it would be best to do this as a separate package, dependent on survival. This is proving a bit tricky. I have some

Re: [R] Where is rmutil package?

http://alpha.luc.ac.be/~jlindsey/rcode.html From: Peter Flom [EMAIL PROTECTED] To: [EMAIL PROTECTED] Subject: [R] Where is rmutil package? Date: Wed, 29 Oct 2003 10:49:10 -0500 Pursing my earlier question, when I tried loading Lindsey's gnlm, I got a message Loading required package: rmutil