[R] Hierarchical clustering with centroid method
Dear everybody! In the function hclust, at each stage distances between clusters are recomputed by the Lance-Williams dissimilarity update formula according to the particular clustering method being used. Using centroid method, Lance-Williams recurrence formula works properly only for euclidean distance. How is it possible to use properly centroid method with manhattan distance ? Thanks [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Plot zooming i.e. changing ylim according to xlim
Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Cheers, Henrik Andersson ## Example -- in reality more numbers, no function x - seq(0,20) y - exp(-x) plot(y~x,type='l') ## Zoom in the end, to see what's happenning plot(y~x,type='l',xlim=c(19,20)) ## Try other ylim plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1)) ## Not enough plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1E-8)) ## Better - Henrik Andersson Netherlands Institute of Ecology - Centre for Estuarine and Marine Ecology P.O. Box 140 4400 AC Yerseke Phone: +31 113 577473 [EMAIL PROTECTED] http://www.nioo.knaw.nl/ppages/handersson __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plot zooming i.e. changing ylim according to xlim
Search the archives for zoom and you will find plenty of answers on this question. RSiteSearch(zoom) Tom -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Henrik Andersson Sent: Tuesday, 26 July 2005 4:16 PM To: r-help@stat.math.ethz.ch Subject: [R] Plot zooming i.e. changing ylim according to xlim Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Cheers, Henrik Andersson ## Example -- in reality more numbers, no function x - seq(0,20) y - exp(-x) plot(y~x,type='l') ## Zoom in the end, to see what's happenning plot(y~x,type='l',xlim=c(19,20)) ## Try other ylim plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1)) ## Not enough plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1E-8)) ## Better - Henrik Andersson Netherlands Institute of Ecology - Centre for Estuarine and Marine Ecology P.O. Box 140 4400 AC Yerseke Phone: +31 113 577473 [EMAIL PROTECTED] http://www.nioo.knaw.nl/ppages/handersson __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plot zooming i.e. changing ylim according to xlim
Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Mulholland, Tom wrote: Search the archives for zoom and you will find plenty of answers on this question. RSiteSearch(zoom) Tom I looked there already, but I could only find interactive zooming, which is also nice, but I want a non-interactive function that automagically changes the y-axis to fit only the data specified in the part of the x-axis, or the other way around. I guess that was not very clear from my first post. - Henrik __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plot zooming i.e. changing ylim according to xlim
Hi Not avoiding trial and error but you can do it interactively by point clicking on a plot. replot function (x, y, type = l) { body - locator(2) plot(x, y, xlim = range(body$x), ylim = range(body$y), type = type) } HTH Best regards Petr Pikal On 26 Jul 2005 at 10:16, Henrik Andersson wrote: Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Cheers, Henrik Andersson ## Example -- in reality more numbers, no function x - seq(0,20) y - exp(-x) plot(y~x,type='l') ## Zoom in the end, to see what's happenning plot(y~x,type='l',xlim=c(19,20)) ## Try other ylim plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1)) ## Not enough plot(y~x,type='l',xlim=c(19,20),ylim=c(0,1E-8)) ## Better - Henrik Andersson Netherlands Institute of Ecology - Centre for Estuarine and Marine Ecology P.O. Box 140 4400 AC Yerseke Phone: +31 113 577473 [EMAIL PROTECTED] http://www.nioo.knaw.nl/ppages/handersson __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing formula arguments cv.glm
Adai, using traceback() helps, as does giving a reproducible example when reporting a problem. However, the problem is I think the line d.glm - update(glmfit, data = data[j.in, , drop = FALSE]) in cv.glm. I think that should be d.glm - eval.parent(update(glmfit, data = data[j.in, , drop = FALSE], evaluate = FALSE)) as in add.default and many other places. Could you please confirm that is the cause? Brian On Mon, 25 Jul 2005, Adaikalavan Ramasamy wrote: I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err - function( formu=NULL, data=NULL ){ cost.fn - function(cl, pred) mean( abs(cl-pred) 0.5 ) glmfit - glm( formula=formu, data=data, family=binomial ) print(glmfit is OK) err- cv.glm( data=data, glmfit=glmfit, cost=cost.fn, K=nrow(data) )$delta[2] print(cv.glm OK) } When I run the above function line by line with the arguments from below, it works fine. But when I call it as function, I get this : rm( glmfit, formu, cv.err ) # cleanup if required logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) [1] glmfit is OK Error in model.frame(formula = formu, data = data[j.in, , drop = FALSE], : Object formu not found I think this has something to do with formula and environments but I do not know enough to solve it myself. I searched the archive without much help (perhaps I was using the wrong keywords). Any help would be very much appreciated. Thank you. Regards, -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Wolfson College Annexe Tel : 01865 284 408 Linton Road, Oxford OX2 6UD Fax : 01865 284 424 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plot zooming i.e. changing ylim according to xlim
Well here is the better shot x - seq(0,20) y - exp(-x) plot(x,y, type=l) intervalx-c(19,20) intervaly-y[x%in%intervalx] plot(x,y, xlim=range(intervalx), ylim=range(intervaly), type=l) HTH Petr On 26 Jul 2005 at 11:13, Henrik Andersson wrote: Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Mulholland, Tom wrote: Search the archives for zoom and you will find plenty of answers on this question. RSiteSearch(zoom) Tom I looked there already, but I could only find interactive zooming, which is also nice, but I want a non-interactive function that automagically changes the y-axis to fit only the data specified in the part of the x-axis, or the other way around. I guess that was not very clear from my first post. - Henrik __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] sort a table
hi all, I need to sort a table like this one: n tmp s 1 215 0 2 654 1 3 213 0 4 569 1 5 954 1 6 562 1 7 252 0 8 555 0 9 988 1 I want to organize it with tmp increasing to produce the same tab but ordered by tmp I think it is simple but just show me how good you are in R ... thks guillaume. // Webmail Oreka : http://www.oreka.com __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] sort a table
[EMAIL PROTECTED] wrote: hi all, I need to sort a table like this one: n tmp s 1 215 0 2 654 1 3 213 0 4 569 1 5 954 1 6 562 1 7 252 0 8 555 0 9 988 1 test - read.table(clipboard,header=T) test[order(test$tmp),] n tmp s 3 3 213 0 1 1 215 0 7 7 252 0 8 8 555 0 6 6 562 1 4 4 569 1 2 2 654 1 5 5 954 1 9 9 988 1 Happy? Cheers, Henrik Andersson __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] problem with Hershey fonts
This was reported to me by a colleague in China, so I may not be reproducing exactly what they are seeing (which I suspect is rw2011), but this is what I see: version _ platform i386--netbsdelf arch i386 os netbsdelf system i386, netbsdelf status major2 minor1.1 year 2005 month06 day 20 language R help(Hershey) : : If the 'vfont' argument to one of the text-drawing functions ('text', 'mtext', 'title', 'axis', and 'contour') is a character vector of length 2, Hershey vector fonts are used to render the text. : The other useful escape sequences all begin with '\\'. These are described below. Remember that backslashes have to be doubled in R character strings, so they need to be entered with _four_ backslashes. : : plot(runif(100)) # to get something on the screen text(0, 1, '\\Re', vfont=c('serif', 'plain')) # works title(main = '\\Re', vfont=c('serif','plain'))# doesn't work, and... Warning message: parameter vfont could not be set in high-level plot() function mtext('\\Re', 2, vfont=c('serif','plain'))# doesn't work, but... Warning message: Hershey fonts not yet implemented for mtext() in: mtext(text, side, line, outer, at, adj, padj, cex, col, font, axis(3, at=50, tick=F, labels='\\Re', vfont=c('serif','plain')) # doesn't work Now at least mtext() 'redeems' itself with its Warning, but title() contradicts the help(Hershey), and axis() just gets it wrong by printing the characters \Re (or \\Re when the string is specified as 'Re' as alluded to in the Hershey documentation - but somewhat contradicted by the success of the text() call above). Now perhaps the problem is just with the Hershey documentation (or my reading of it), but I don't know what is supposed to work. Or is there some combination that I haven't tried? Ray Brownrigg __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing formula arguments cv.glm
Dear Prof. Ripley, Thank you for your response. See below for my comments. On Tue, 2005-07-26 at 10:57 +0100, Prof Brian Ripley wrote: Adai, using traceback() helps, as does giving a reproducible example when reporting a problem. You are right. The traceback below indicates that your guess is correct. 10: model.frame(formula = formu, data = data[j.in, , drop = FALSE], drop.unused.levels = TRUE) The example is actually reproducible but you need the load the boot package first (which I failed to mention). However, the problem is I think the line d.glm - update(glmfit, data = data[j.in, , drop = FALSE]) in cv.glm. I think that should be d.glm - eval.parent(update(glmfit, data = data[j.in, , drop = FALSE], evaluate = FALSE)) as in add.default and many other places. Could you please confirm that is the cause? I believe this is the cause but the fix may need bit more tweaking. I get the following error message with your fix. Error in [.data.frame(data, j.in, , drop = FALSE) : Object j.in not found The traceback gives the final same output as original one but this is numbered at 12 instead. Could it be because j.in is created within the for() loop environment ? I do not know how to fix this and would appreciate any help. For your convenience, you can find the script with your current fix at the following URL www.cbrg.ox.ac.uk/~ramasamy/cv.glm2.R Thank you very much. Much appreciated. Regards, Adai Brian On Mon, 25 Jul 2005, Adaikalavan Ramasamy wrote: I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err - function( formu=NULL, data=NULL ){ cost.fn - function(cl, pred) mean( abs(cl-pred) 0.5 ) glmfit - glm( formula=formu, data=data, family=binomial ) print(glmfit is OK) err- cv.glm( data=data, glmfit=glmfit, cost=cost.fn, K=nrow(data) )$delta[2] print(cv.glm OK) } When I run the above function line by line with the arguments from below, it works fine. But when I call it as function, I get this : rm( glmfit, formu, cv.err ) # cleanup if required logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) [1] glmfit is OK Error in model.frame(formula = formu, data = data[j.in, , drop = FALSE], : Object formu not found I think this has something to do with formula and environments but I do not know enough to solve it myself. I searched the archive without much help (perhaps I was using the wrong keywords). Any help would be very much appreciated. Thank you. Regards, -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Wolfson College Annexe Tel : 01865 284 408 Linton Road, Oxford OX2 6UD Fax : 01865 284 424 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] any package to fit such model?
I have search the internet but none are found.The lme function is like the proc mixed the SAS.But I know no package to fit the model described in http://gsbwww.uchicago.edu/computing/research/SASManual/ets/chap20/sect17.htm ,which fit with the proc tscs in SAS. Thank you. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] OpenBSD and large R vectors
Is anyone running R on OpenBSD? I've got R-2.1.1 installed on OpenBSD -current and have some microarray datasets that took ~1.4 GB RAM on FreeBSD (computer has 4 GB total, Pentium 4 system). With FreeBSD, setting maxdsiz in /boot/loader.conf worked very well. With OpenBSD, even after setting maxdsiz to ~1.8 GB for a new kernel and changing /etc/login.conf, R runs into memory problems and gives the could not allocate vector of... error. Then R locks up and starts taking progressively more CPU time until it gets killed. This is a stock R installation and a generic OpenBSD except for the altered MAXDSIZ in vmparam.h. I'm guessing that these problems stem at least in part from OpenBSD's memory allocation safety mechanisms. Still, are there any R or OpenBSD compile options / tweaks I can do to make things work? Thanks, jon butchar __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing formula arguments cv.glm
On Tue, 26 Jul 2005, Adaikalavan Ramasamy wrote: Dear Prof. Ripley, Thank you for your response. See below for my comments. On Tue, 2005-07-26 at 10:57 +0100, Prof Brian Ripley wrote: Adai, using traceback() helps, as does giving a reproducible example when reporting a problem. You are right. The traceback below indicates that your guess is correct. 10: model.frame(formula = formu, data = data[j.in, , drop = FALSE], drop.unused.levels = TRUE) The example is actually reproducible but you need the load the boot package first (which I failed to mention). However, the problem is I think the line d.glm - update(glmfit, data = data[j.in, , drop = FALSE]) in cv.glm. I think that should be d.glm - eval.parent(update(glmfit, data = data[j.in, , drop = FALSE], evaluate = FALSE)) as in add.default and many other places. Could you please confirm that is the cause? I believe this is the cause but the fix may need bit more tweaking. I get the following error message with your fix. Error in [.data.frame(data, j.in, , drop = FALSE) : Object j.in not found The traceback gives the final same output as original one but this is numbered at 12 instead. Could it be because j.in is created within the for() loop environment ? I do not know how to fix this and would appreciate any help. Ah, that needs a different fix, namely Call - glmfit$call Call$data - data[j.in, , drop=FALSE] d.glm - eval.parent(Call) which works for me when I modify your script accordingly. (You can take the first line outside the loop, for tidiness.) For your convenience, you can find the script with your current fix at the following URL www.cbrg.ox.ac.uk/~ramasamy/cv.glm2.R Thank you very much. Much appreciated. Regards, Adai Brian On Mon, 25 Jul 2005, Adaikalavan Ramasamy wrote: I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err - function( formu=NULL, data=NULL ){ cost.fn - function(cl, pred) mean( abs(cl-pred) 0.5 ) glmfit - glm( formula=formu, data=data, family=binomial ) print(glmfit is OK) err- cv.glm( data=data, glmfit=glmfit, cost=cost.fn, K=nrow(data) )$delta[2] print(cv.glm OK) } When I run the above function line by line with the arguments from below, it works fine. But when I call it as function, I get this : rm( glmfit, formu, cv.err ) # cleanup if required logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) [1] glmfit is OK Error in model.frame(formula = formu, data = data[j.in, , drop = FALSE], : Object formu not found I think this has something to do with formula and environments but I do not know enough to solve it myself. I searched the archive without much help (perhaps I was using the wrong keywords). Any help would be very much appreciated. Thank you. Regards, -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Wolfson College Annexe Tel : 01865 284 408 Linton Road, Oxford OX2 6UD Fax : 01865 284 424 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] grep help needed
Dear Denis, I don't believe that anyone fielded your question -- my apologies if I missed a response. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Denis Chabot Sent: Monday, July 25, 2005 9:46 PM To: R list Subject: [R] grep help needed Hi, In another thread (PBSmapping and shapefiles) I asked for an easy way to read shapefiles and transform them in data that PBSmapping could use. One person is exploring some ways of doing this, but it is possible I'll have to do this manually. With package maptools I am able to extract the information I need from a shapefile but it is formatted like this: [[1]] [,1] [,2] [1,] -55.99805 51.68817 [2,] -56.00222 51.68911 [3,] -56.01694 51.68911 [4,] -56.03781 51.68606 [5,] -56.04639 51.68759 [6,] -56.04637 51.69445 [7,] -56.03777 51.70207 [8,] -56.02301 51.70892 [9,] -56.01317 51.71578 [10,] -56.00330 51.73481 [11,] -55.99805 51.73840 attr(,pstart) attr(,pstart)$from [1] 1 attr(,pstart)$to [1] 11 attr(,nParts) [1] 1 attr(,shpID) [1] NA [[2]] [,1] [,2] [1,] -57.76294 50.88770 [2,] -57.76292 50.88693 [3,] -57.76033 50.88163 [4,] -57.75668 50.88091 [5,] -57.75551 50.88169 [6,] -57.75562 50.88550 [7,] -57.75932 50.88775 [8,] -57.76294 50.88770 attr(,pstart) attr(,pstart)$from [1] 1 attr(,pstart)$to [1] 8 attr(,nParts) [1] 1 attr(,shpID) [1] NA I do not quite understand the structure of this data object (list of lists I think) Actually, it looks like a list of matrices, each with some attributes (which, I gather, aren't of interest to you). but at this point I resorted to printing it on the console and imported that text into Excel for further cleaning, which is easy enough. I'd like to complete the process within R to save time and to circumvent Excel's limit of around 64000 lines. But I have a hard time figuring out how to clean up this text in R. If I understand correctly what you want, this seems a very awkward way to proceed. Why not just extract the matrices from the list, stick on the additional columns that you want, stick the matrices together, name the columns, and then output the data to a file? M1 - Data[[1]] # assuming that the original list is named Data M2 - Data[[2]] M1 - cbind(1, 1:nrow(M1), M1) M2 - cbind(2, 1:nrow(M2), M2) M - rbind(M1, M2) colnames(M) - c(PID, POS, X, Y) write.table(M, Data.txt, row.names=FALSE, quote=FALSE) It wouldn't be hard to generalize this to any number of matrices and to automate the process. I hope that this helps, John What I need to produce for PBSmapping is a file where each block of coordinates shares one ID number, called PID, and a variable POS indicates the position of each coordinate within a shape. All other lines must disappear. So the above would become: PID POS X Y 1 1 -55.99805 51.68817 1 2 -56.00222 51.68911 1 3 -56.01694 51.68911 1 4 -56.03781 51.68606 1 5 -56.04639 51.68759 1 6 -56.04637 51.69445 1 7 -56.03777 51.70207 1 8 -56.02301 51.70892 1 9 -56.01317 51.71578 1 10 -56.00330 51.73481 1 11 -55.99805 51.73840 2 1 -57.76294 50.88770 2 2 -57.76292 50.88693 2 3 -57.76033 50.88163 2 4 -57.75668 50.88091 2 5 -57.75551 50.88169 2 6 -57.75562 50.88550 2 7 -57.75932 50.88775 2 8 -57.76294 50.88770 First I imported this text file into R: test - read.csv2(test file.txt,header=F, sep=;, colClasses = character) I used sep=; to insure there would be only one variable in this file, as it contains no ; To remove lines that do not contain coordinates, I used the fact that longitudes are expressed as negative numbers, so with my very limited knowledge of grep searches, I thought of this, which is probably not the best way to go: a - rep(-, length(test$V1)) b - grep(a, test$V1) this gives me a warning (Warning message: the condition has length 1 and only the first element will be used in: if (is.na(pattern)) { but seems to do what I need anyway c - seq(1, length(test$V1)) d - c %in% b e - test$V1[d] Partial victory, now I only have lines that look like [1,] -57.76294 50.88770 But I don't know how to go further: the number in square brackets can be used for variable POS, after removing the square brackets and the comma, but this requires a better knowledge of grep than I have. Furthermore, I don't know how to add a PID (polygon ID) variable, i.e. all lines of a polygon must have the same ID, as in the example above (i.e. each time POS == 1, a new polygon starts and PID needs to be incremented by 1, and PID is kept constant for lines where POS ! 1). Any help will be much appreciated. Sincerely, Denis Chabot __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] text on some lines
Hi, I would like to write text on 2 lines for example. For example, if you have a long sentence and you want to cut it at the 45 caracter and put the continuation underneath! Is it possible? Thanks Sabine - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] text on some lines
Navarre Sabine wrote: Hi, I would like to write text on 2 lines for example. For example, if you have a long sentence and you want to cut it at the 45 caracter and put the continuation underneath! Is it possible? Do you mean for output to console / in plots? Simply insert a \n (newline), for example. Uwe Ligges Thanks Sabine - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] text on some lines
plot(1:10,type=n) title(main=cut in the 45 char \n new line) pay attention to the \n,which means new line. is it what you want? === 2005-07-26 21:59:04 您在来信中写道:=== Hi, I would like to write text on 2 lines for example. For example, if you have a long sentence and you want to cut it at the 45 caracter and put the continuation underneath! Is it possible? Thanks Sabine - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html = = = = = = = = = = = = = = = = = = = = 2005-07-26 -- Deparment of Sociology Fudan University Blog:http://sociology.yculblog.com __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Association rules
Hello ! I just start in using R, and I have already questions... I want to use the arules package : I have installed the package, and have the arules package 's reference manual, but I haven't yet understood how to use it. I have my data (from Excel, .txt), that I have read on R : I think (hope !) it's ok Then, what must I do first to analyse my data (to identify the association rules) ? I suppose I have to transform my file, but how ? Which commands must I use to ? Thanks for all ! Sophie ! __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] text on some lines
On Tue, 26 Jul 2005, Uwe Ligges wrote: Navarre Sabine wrote: I would like to write text on 2 lines for example. For example, if you have a long sentence and you want to cut it at the 45 caracter and put the continuation underneath! Is it possible? Do you mean for output to console / in plots? Simply insert a \n (newline), for example. And strwrap() will help you insert it in the right place, e.g. x - For example, if you have a long sentence and you want to cut it at the 45 caracter and put the continuation underneath! strwrap(x, 45) [1] For example, if you have a long sentence [2] and you want to cut it at the 45 caracter [3] and put the continuation underneath! paste(strwrap(x, 45), collapse=\n) [1] For example, if you have a long sentence\nand you want to cut it at the 45 caracter\nand put the continuation underneath! the latter for use when plotting. -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Association rules
library(foreign) in the foreign package,you can use read.csv command to read the csv file.you can use excel to open the file and save as cvs file.you should read the manuals first,which tells in details how to import your data into R. before you use the command frome the arules package,you should first type the command library(arules) === 2005-07-26 22:18:48 您在来信中写道:=== Hello ! I just start in using R, and I have already questions... I want to use the arules package : I have installed the package, and have the arules package 's reference manual, but I haven't yet understood how to use it. I have my data (from Excel, .txt), that I have read on R : I think (hope !) it's ok Then, what must I do first to analyse my data (to identify the association rules) ? I suppose I have to transform my file, but how ? Which commands must I use to ? Thanks for all ! Sophie ! __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html = = = = = = = = = = = = = = = = = = = = 2005-07-26 -- Deparment of Sociology Fudan University Blog:http://sociology.yculblog.com __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing formula arguments cv.glm
It works ! Thank you very much. Can I request this fix in the next version of boot package please if it is likely not to break compatibility with other functions. The modified cv.glm function can be found at www.cbrg.ox.ac.uk/~ramasamy/cv.glm2.R Thank you again. Regards, Adai On Tue, 2005-07-26 at 13:06 +0100, Prof Brian Ripley wrote: On Tue, 26 Jul 2005, Adaikalavan Ramasamy wrote: Dear Prof. Ripley, Thank you for your response. See below for my comments. On Tue, 2005-07-26 at 10:57 +0100, Prof Brian Ripley wrote: Adai, using traceback() helps, as does giving a reproducible example when reporting a problem. You are right. The traceback below indicates that your guess is correct. 10: model.frame(formula = formu, data = data[j.in, , drop = FALSE], drop.unused.levels = TRUE) The example is actually reproducible but you need the load the boot package first (which I failed to mention). However, the problem is I think the line d.glm - update(glmfit, data = data[j.in, , drop = FALSE]) in cv.glm. I think that should be d.glm - eval.parent(update(glmfit, data = data[j.in, , drop = FALSE], evaluate = FALSE)) as in add.default and many other places. Could you please confirm that is the cause? I believe this is the cause but the fix may need bit more tweaking. I get the following error message with your fix. Error in [.data.frame(data, j.in, , drop = FALSE) : Object j.in not found The traceback gives the final same output as original one but this is numbered at 12 instead. Could it be because j.in is created within the for() loop environment ? I do not know how to fix this and would appreciate any help. Ah, that needs a different fix, namely Call - glmfit$call Call$data - data[j.in, , drop=FALSE] d.glm - eval.parent(Call) which works for me when I modify your script accordingly. (You can take the first line outside the loop, for tidiness.) For your convenience, you can find the script with your current fix at the following URL www.cbrg.ox.ac.uk/~ramasamy/cv.glm2.R Thank you very much. Much appreciated. Regards, Adai Brian On Mon, 25 Jul 2005, Adaikalavan Ramasamy wrote: I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err - function( formu=NULL, data=NULL ){ cost.fn - function(cl, pred) mean( abs(cl-pred) 0.5 ) glmfit - glm( formula=formu, data=data, family=binomial ) print(glmfit is OK) err- cv.glm( data=data, glmfit=glmfit, cost=cost.fn, K=nrow(data) )$delta[2] print(cv.glm OK) } When I run the above function line by line with the arguments from below, it works fine. But when I call it as function, I get this : rm( glmfit, formu, cv.err ) # cleanup if required logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) logistic.LOOCV.err( formu=as.formula(r~stage+xray+acid), data=nodal ) [1] glmfit is OK Error in model.frame(formula = formu, data = data[j.in, , drop = FALSE], : Object formu not found I think this has something to do with formula and environments but I do not know enough to solve it myself. I searched the archive without much help (perhaps I was using the wrong keywords). Any help would be very much appreciated. Thank you. Regards, -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Wolfson College Annexe Tel : 01865 284 408 Linton Road, Oxford OX2 6UD Fax : 01865 284 424 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] passing formula arguments cv.glm
On Tue, 26 Jul 2005, Adaikalavan Ramasamy wrote: It works ! Thank you very much. Can I request this fix in the next version of boot package please if it is likely not to break compatibility with other functions. The modified cv.glm function can be found at www.cbrg.ox.ac.uk/~ramasamy/cv.glm2.R Yes, it will be there if it survives enough tests. -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] SETAR Estimation
Dear R-helpers, I was wondering if anyone has or knows someone who might have an implementation of algorithm for estimating SETAR models including the lag-order. For some reason my code gives me a bit wrong results. I am fighting with it for a week and cannot bring it down. Thanks a million in advance, Sincerely, Evgueni McGill University Department of Economics __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] farimaSim
Hello! I installed the fSeries package to get some farima time-series which i tried with farimaSim, but unfortunately i got always an error. I tried it this way: farimaSim(n = 1000, model = list(ar = 0.5, d = 0.3, ma = 0.1), method=freq) Error in farimaSim(n = 1000, model = list(ar = 0.5, d = 0.3, ma = 0.1), : ... used in an incorrect context Some ideas? Regards, ___ _ /_|_| Hansi Weissensteiner /o\__/O\= [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Assign new observations to Clara clusters
Dear all, I need to assign new observations to cluster groups previously identified for a different dataset. The original clustering was performed using Clara. I gess one way is to assign each new observation to the nearest medioid of the original cluster. Is there a way of doing this in R? Is there a better way of classifying new observations into clusters? Thanks a lot, Nestor __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Assign new observations to Clara clusters
On Tue, 26 Jul 2005, Nestor Fernandez wrote: Dear all, I need to assign new observations to cluster groups previously identified for a different dataset. The original clustering was performed using Clara. I gess one way is to assign each new observation to the nearest medioid of the original cluster. Is there a way of doing this in R? Is there a better way of classifying new observations into clusters? If you have the medoids (and these are in the fit object), use knn1 (in package class) to assign. Cluster analysis is not really designed to classify new observations. With Euclidean distance the above is possible, but I would probably take the clusters formed and used them to do a supervised classification: your default option is edited NN-1 classification and you may well be able to do better, depending on the size of the problem. -- Brian D. Ripley, [EMAIL PROTECTED] 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@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Compute dissimilarity matrix for ordinal data
Dear All, I have been trying to use the daisy routine to compute the dissimilarity matrix but I have not been successful in defining the data as ordinal. Might you kindly help me please? Thanks in advance and best regards, Tom __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] farimaSim
Hansi == Hansi Weissensteiner [EMAIL PROTECTED] on Tue, 26 Jul 2005 17:40:45 +0200 writes: Hansi Hello! I installed the fSeries package to get some Hansi farima time-series which i tried with farimaSim, but Hansi unfortunately i got always an error. I tried it this Hansi way: farimaSim(n = 1000, model = list(ar = 0.5, d = 0.3, ma = 0.1), method=freq) Hansi Error in farimaSim(n = 1000, model = list(ar = 0.5, d Hansi = 0.3, ma = 0.1), : ... used in an incorrect context Hansi Some ideas? Yes, the function farimaSim() is bogous, pretty obviously if you look at it. I've wondered for a while if we (R developers) shouldn't improve R CMD check so as to require that every exported function in a package must have at least one running example. For the farimaSim(), there is no call possible without an error message. Package 'fracdiff', though much older, has a working fracdiff.sim() function. Martin Maechler, ETH Zurich __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] plotting horizontally
Hello, Is there any way to use plot() horizontally similar to boxplot(., horiz=TRUE)? I want to use to illustrate the distribution of y-values on an adjacent plot using layout(). Thanks in advance for any help. Regards, --Dan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] any package to fit such model?
Have you looked at ?lm, including the examples? The link in your email described a standard one-way, fixed effects ANOVA, and the lm help page includes a worked example for that. spencer graves ronggui wrote: I have search the internet but none are found.The lme function is like the proc mixed the SAS.But I know no package to fit the model described in http://gsbwww.uchicago.edu/computing/research/SASManual/ets/chap20/sect17.htm ,which fit with the proc tscs in SAS. Thank you. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Spencer Graves, PhD Senior Development Engineer PDF Solutions, Inc. 333 West San Carlos Street Suite 700 San Jose, CA 95110, USA [EMAIL PROTECTED] www.pdf.com http://www.pdf.com Tel: 408-938-4420 Fax: 408-280-7915 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] draw ellipse of equal concentration
Dear all, do you know some routines to draw ellipses and its axes given the algebraic equation? The application is to draw ellipses of equal concentration for bivariate normal distribution given the vector mean and the covariance matrix. Thank you. Sincerely, Salvatore Ingrassia * Prof. Salvatore Ingrassia Dipartimento di Economia e Statistica Facoltà di Economia Universita' della Calabria 87036 Arcavacata di Rende (CS), Italy Tel. +39 0984 492432Fax +39 0984 492421 e-mail: [EMAIL PROTECTED] http://www.ecostat.unical.it/Ingrassia/ * [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] draw ellipse of equal concentration
On 7/26/2005 1:49 PM, Salvatore Ingrassia wrote: Dear all, do you know some routines to draw ellipses and its axes given the algebraic equation? The application is to draw ellipses of equal concentration for bivariate normal distribution given the vector mean and the covariance matrix. The ellipse package can draw ellipses. Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] tapply t.test
I cannot find in the literature a way to conduct the following t.test on 2 objects, A and B A B col1 col2 col3 col1 col2 col3 Where col(i)'s name is identical in both A and B (they are names of tissues). How do I test (t.test) if each tissue across the object is signifanctly different?? (i'm pretty sure I have to use tapply()) Also is there a way to multi plot all 89 tissues showing the A values and the B values.. thank you __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] FFT post-processing
List, Can anyone point me at a user guide for doing signals processing after applying the FFT? I'm looking for some info on postprocessing steps, trying to see if there are any packages already written, etc. TIA, Pete __ [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] cluster
Dear Weiwei, your question sounds a bit too general and complicated for the R-list. Perhaps you should look for personal statistical advice. The quality of methods (and especially distance choice) for down-sampling ceratinly depends on the structure of the data set. I do not see at the moment why you need any down-sampling at all, and you should find out first if and why it's a good thing to do (by whatever method). An obvious candidate for a clustering algorithm would be pam/clara in package cluster, because this approach chooses points already in the data set as cluster centroids (and produces therefore a proper subsample), which does not apply to most other clustering methods. However, in C. Hennig and L. J. Latecki: The choice of vantage objects for image retrieval. Pattern Recognition 36 (2003), 2187-2196. the clustering approach has been clearly outperformed by some stepwise selection approaches for down-sampling - admittedly in a different kind of problem, but I think that the reasons for this may apply also to your situation, You can compare different clusterings (or choices of a subset) by cross-validation or bootstrap applied to the resulting decision tree in the classification problem. Best, Christian On Mon, 25 Jul 2005, Weiwei Shi wrote: Dear listers: Here I have a question on clustering methods available in R. I am trying to down-sampling the majority class in a classification problem on an imbalanced dataset. Since I don't want to lose information in the original dataset, I don't want to use naive down-sampling: I think using clustering on the majority class' side to select representative samples might help. So, my question is, which clustering method should be tested to get the best result. I think the key thing might be the selection of distance considering the next step in which I would like to use decision trees. Please share your experience in using clustering (Any available implementation outside R is also welcome) weiwei -- Weiwei Shi, Ph.D Did you always know? No, I did not. But I believed... ---Matrix III __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html *** NEW ADDRESS! *** Christian Hennig University College London, Department of Statistical Science Gower St., London WC1E 6BT, phone +44 207 679 1698 [EMAIL PROTECTED], www.homepages.ucl.ac.uk/~ucakche __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] alaska map?
Look at: http://www.census.gov/geo/www/cob/bdy_files.html There are shapefiles of the 50 states there, outlines, counties, and others. Greg Snow, Ph.D. Statistical Data Center, LDS Hospital Intermountain Health Care [EMAIL PROTECTED] (801) 408-8111 Caitlin Burgess [EMAIL PROTECTED] 07/25/05 01:37PM Hello, I've installed the Becker and Wilks maps, mapdata, and mapproj packages so I can begin to try these out for some work I need to do on a map of Alaska but I don't know where to find a map of Alaska. Has anyone solved this already and could help? Thanks very much in advance, Caitlin __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] error with scan
Hi: I am trying to read a large (50+ lines) with scan() as read.table is unable to read it. I get a strange error (below) which says that 'a real' was expected and '5' was read. Can someone help? Thanks, jp type=list(a=0,b=0,c=0,d=0,e=0,f=,g=0,h=0,i=0) tmp2 - scan(file=tmp2.txt, what=type, sep=,, quote=\, dec=., skip=1, nmax=541502) Erreur dans scan(file = tmp2.txt, what = type, sep = ,, quote = \, : scan() attendait 'a real' et a reçu '5' __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] T test across tissues
I cannot find in the literature a way to conduct the following t.test on 2 objects, A and B A B col1 col2 col3 col1 col2 col3 Where col(i)'s name is identical in both A and B (they are names of tissues). How do I test (t.test) if each tissue across the object is signifanctly different?? (i'm pretty sure I have to use tapply()) Also is there a way to multi plot all 89 tissues showing the A values and the B values.. thank you __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plot zooming i.e. changing ylim according to xlim
On 7/26/05, Henrik Andersson [EMAIL PROTECTED] wrote: Dear R-gurus, I would like to zoom in a plot, e.g. I select a region on the x-axis and then I would like the ranges on the y-axis to change accordingly. Is it possible to do this with existing functions, or do I have to invent some data selection before plotting? See below a short example, where I select ylim with trial and error, which I want to avoid. Cheers, Henrik Andersson ## Example -- in reality more numbers, no function x - seq(0,20) y - exp(-x) plot(y~x,type='l') ## Zoom in the end, to see what's happenning plot(y~x,type='l',xlim=c(19,20)) I tend to use constructs like plot(y~x,type='l', subset = x 15) (18 is not very interesting). Deepayan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] a question about fft ( fast fourier transform)
Dear listers In R, if I have a sequence x(t), t=1,...N, fft(x) is actually giving us sum(x(t)exp(-i*omega*t)) at fourier frequency omega= 2*pi*i/N, i=0,1,...(N-1). The question is if I want to calculate sum(x(t)exp(-i*2*omega*t)), how can I do it? thanks a lot! --- liyun (Lauren) Ma Dept of Statistics North Carolina State University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Help on T test
ok I created a matrix C with A B CA1 B1C1 .. . the columns contain the gene expression values.. I ran the following t.test: apply(C, 1, function(x) t.test( x[1:3], x[4,6] )$p.value ) which outputs out 16063 pvalues (the number of rows) I just want to output 3 pvalues showing if A's column is different from A1 etc.. any help would be great.. thank you.. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] grep help needed
Thanks for your help, the proposed solutions were much more elegant than what I was attempting. I adopted a slight modification of Tom Mulholland's solution with a piece from John Fox's solution, but many of you had very similar solutions. require(maptools) nc - read.shape(system.file(shapes/sids.shp, package = maptools) [1]) mappolys - Map2poly(nc, as.character(nc$att.data$FIPSNO)) selected.shapes - which(nc$att.data$SID74 20) # just to make it a smaller example submap - subset(mappolys, nc$att.data$SID74 20) final.data - NULL for (j in 1:length(selected.shapes)){ temp.verts - matrix(as.vector(submap[[j]]),ncol = 2) n - length(temp.verts[,1]) temp.order - 1:n temp.data - cbind(rep(j,n),temp.order,temp.verts) final.data - rbind(final.data,temp.data) } colnames(final.data) - c(PID, POS, X, Y) final.data my.data - as.data.frame(final.data) class(my.data) - c(PolySet, data.frame) attr(my.data, projection) - LL meta - nc[2]$att.data[selected.shapes,] PID - seq(1,length(submap)) meta.data - cbind(PID, meta) class(meta.data) - c(PolyData, data.frame) attr(meta.data, projection) - LL It would be nice if a variant of this was incorporated into PBSmapping to make it easier to import data from shapefiles! Thanks again for your help, Denis Chabot Le 05-07-26 à 00:48, Mulholland, Tom a écrit : -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Denis Chabot Sent: Tuesday, 26 July 2005 10:46 AM To: R list Subject: [R] grep help needed Hi, In another thread (PBSmapping and shapefiles) I asked for an easy way to read shapefiles and transform them in data that PBSmapping could use. One person is exploring some ways of doing this, but it is possible I'll have to do this manually. With package maptools I am able to extract the information I need from a shapefile but it is formatted like this: [[1]] [,1] [,2] [1,] -55.99805 51.68817 [2,] -56.00222 51.68911 [3,] -56.01694 51.68911 [4,] -56.03781 51.68606 [5,] -56.04639 51.68759 [6,] -56.04637 51.69445 [7,] -56.03777 51.70207 [8,] -56.02301 51.70892 [9,] -56.01317 51.71578 [10,] -56.00330 51.73481 [11,] -55.99805 51.73840 attr(,pstart) attr(,pstart)$from [1] 1 attr(,pstart)$to [1] 11 attr(,nParts) [1] 1 attr(,shpID) [1] NA [[2]] [,1] [,2] [1,] -57.76294 50.88770 [2,] -57.76292 50.88693 [3,] -57.76033 50.88163 [4,] -57.75668 50.88091 [5,] -57.75551 50.88169 [6,] -57.75562 50.88550 [7,] -57.75932 50.88775 [8,] -57.76294 50.88770 attr(,pstart) attr(,pstart)$from [1] 1 attr(,pstart)$to [1] 8 attr(,nParts) [1] 1 attr(,shpID) [1] NA I do not quite understand the structure of this data object (list of lists I think) but at this point I resorted to printing it on the console and imported that text into Excel for further cleaning, which is easy enough. I'd like to complete the process within R to save time and to circumvent Excel's limit of around 64000 lines. But I have a hard time figuring out how to clean up this text in R. What I need to produce for PBSmapping is a file where each block of coordinates shares one ID number, called PID, and a variable POS indicates the position of each coordinate within a shape. All other lines must disappear. So the above would become: PID POS X Y 1 1 -55.99805 51.68817 1 2 -56.00222 51.68911 1 3 -56.01694 51.68911 1 4 -56.03781 51.68606 1 5 -56.04639 51.68759 1 6 -56.04637 51.69445 1 7 -56.03777 51.70207 1 8 -56.02301 51.70892 1 9 -56.01317 51.71578 1 10 -56.00330 51.73481 1 11 -55.99805 51.73840 2 1 -57.76294 50.88770 2 2 -57.76292 50.88693 2 3 -57.76033 50.88163 2 4 -57.75668 50.88091 2 5 -57.75551 50.88169 2 6 -57.75562 50.88550 2 7 -57.75932 50.88775 2 8 -57.76294 50.88770 First I imported this text file into R: test - read.csv2(test file.txt,header=F, sep=;, colClasses = character) I used sep=; to insure there would be only one variable in this file, as it contains no ; To remove lines that do not contain coordinates, I used the fact that longitudes are expressed as negative numbers, so with my very limited knowledge of grep searches, I thought of this, which is probably not the best way to go: a - rep(-, length(test$V1)) b - grep(a, test$V1) this gives me a warning (Warning message: the condition has length 1 and only the first element will be used in: if (is.na(pattern)) { but seems to do what I need anyway c - seq(1, length(test$V1)) d - c %in% b e - test$V1[d] Partial victory, now I only have lines that look like [1,] -57.76294 50.88770 But I don't know how to go further: the number in square brackets can be used for variable POS, after removing the square brackets and the comma, but this requires a better knowledge of grep than I have. Furthermore, I don't know how to add a PID (polygon ID) variable, i.e. all lines of a polygon must have the same ID, as in the example above (i.e. each
Re: [R] cluster
Dear Chris: You are right and It IS too general. I think I should ask like what kind of cluster algorithms or functions are available in R , which might be easier. But for that, I probably can google or use help() in R to find out. I want to know more about the performance of clustering on this kind of problems and hope someone can share previous experince if he/she had similar situation or problems before. And I will share my experience later :) As to the reason of using downsampling here, it is one fo the straightforward ways to deal with imbalanced data classification problem. In my understanding of classification problems, among others, two things are important: feature construction/selection and sample selection. I had an idea (which might be discovered by others) that finding the best subset of features in clustering (to get highest inter-cluster dissimilarities and the largest intra-cluster similarity) might help the next classification process. I quickly read through the abstract of your paper and I think your approach here is applying feature selection (use p instead of n), while here, in my proposal, I would like to try both. thanks for further advice! weiwei On 7/26/05, Christian Hennig [EMAIL PROTECTED] wrote: Dear Weiwei, your question sounds a bit too general and complicated for the R-list. Perhaps you should look for personal statistical advice. The quality of methods (and especially distance choice) for down-sampling ceratinly depends on the structure of the data set. I do not see at the moment why you need any down-sampling at all, and you should find out first if and why it's a good thing to do (by whatever method). An obvious candidate for a clustering algorithm would be pam/clara in package cluster, because this approach chooses points already in the data set as cluster centroids (and produces therefore a proper subsample), which does not apply to most other clustering methods. However, in C. Hennig and L. J. Latecki: The choice of vantage objects for image retrieval. Pattern Recognition 36 (2003), 2187-2196. the clustering approach has been clearly outperformed by some stepwise selection approaches for down-sampling - admittedly in a different kind of problem, but I think that the reasons for this may apply also to your situation, You can compare different clusterings (or choices of a subset) by cross-validation or bootstrap applied to the resulting decision tree in the classification problem. Best, Christian On Mon, 25 Jul 2005, Weiwei Shi wrote: Dear listers: Here I have a question on clustering methods available in R. I am trying to down-sampling the majority class in a classification problem on an imbalanced dataset. Since I don't want to lose information in the original dataset, I don't want to use naive down-sampling: I think using clustering on the majority class' side to select representative samples might help. So, my question is, which clustering method should be tested to get the best result. I think the key thing might be the selection of distance considering the next step in which I would like to use decision trees. Please share your experience in using clustering (Any available implementation outside R is also welcome) weiwei -- Weiwei Shi, Ph.D Did you always know? No, I did not. But I believed... ---Matrix III __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html *** NEW ADDRESS! *** Christian Hennig University College London, Department of Statistical Science Gower St., London WC1E 6BT, phone +44 207 679 1698 [EMAIL PROTECTED], www.homepages.ucl.ac.uk/~ucakche -- Weiwei Shi, Ph.D Did you always know? No, I did not. But I believed... ---Matrix III __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] error with scan
Can you show us the first line of the file? The error means that in one of the values you specified as numeric (first, second, third, fourth, fifth, seventh, eighth, ninth), it found the character value it displayed. Otherwise, this looks like a good use of scan. Kevin -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Jean-Pierre Gattuso Sent: Tuesday, July 26, 2005 11:52 AM To: r-help@stat.math.ethz.ch Cc: Jean-Pierre Gattuso Subject: [R] error with scan Hi: I am trying to read a large (50+ lines) with scan() as read.table is unable to read it. I get a strange error (below) which says that 'a real' was expected and '5' was read. Can someone help? Thanks, jp type=list(a=0,b=0,c=0,d=0,e=0,f=,g=0,h=0,i=0) tmp2 - scan(file=tmp2.txt, what=type, sep=,, quote=\, dec=., skip=1, nmax=541502) Erreur dans scan(file = tmp2.txt, what = type, sep = ,, quote = \, : scan() attendait 'a real' et a reçu '5 ' __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] plotting horizontally
On Tue, 2005-07-26 at 08:58 +0700, [EMAIL PROTECTED] wrote: Hello, Is there any way to use plot() horizontally similar to boxplot(., horiz=TRUE)? I want to use to illustrate the distribution of y-values on an adjacent plot using layout(). Thanks in advance for any help. Regards, --Dan Have you looked at the last example in ?layout, which has a scatterplot with marginal histograms for the x and y axes? Alternatively, you can generally reverse the x and y values for most plots. For example, compare: d - density(rnorm(100)) # Vertical density plot plot(d) # Horizontal density plot plot(d$y, d$x, type = l, xlab = Density, main = density(y = rnorm(100)), ylab = paste(N =, d$n, Bandwidth =, formatC(d$bw))) HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] elegant solution to transform vector into percentages?
Hi, I am looking for an elegant way to transform a vector into percentages of values that meet certain criteria. store-c(1,1.4,3,1.1,0.3,0.6,4,5) # now I want to get the precentages of values # that fall into the categories =M , M =N , N # let M -.8 N - 1.2 # In my real example I have many more of these cutoff-points # What I did is: out - matrix(NA,1,3) out[1,1] - ( (sum(store=M)) /length(store) )*100 out[1,2] - ( (sum(store M store= N )) /length(store) )*100 out[1,3] - ( (sum(store N)) /length(store) )*100 colnames(out)-c(percent=M,percentM =N,percentN) out But this gets very tedious if I have many cutoff-points. Does anybody know a more elegant way to do this task? Thanks so much. Cheers, Jens __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] choose between dates and times
Dear R-helpers, I have the following data: yhappenat x 5185 (07/22/05 00:05:14) 14 5186 (07/22/05 00:15:14) 14 5187 (07/22/05 00:25:14) 14 5188 (07/22/05 00:35:14) 14 .. I want to choose between 07/25/05 15:30:00 and 07/26/05 12:30:00. Anybody had experience in handling this kind of data? Is there a simple way to subset by the variable 'happenat'? Thanks. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] elegant solution to transform vector into percentages?
hist() or cut() followed by tabulate() would probably be the ingredients you'd want. Reid Huntsinger -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Tuesday, July 26, 2005 3:49 PM To: r-help@stat.math.ethz.ch Subject: [R] elegant solution to transform vector into percentages? Hi, I am looking for an elegant way to transform a vector into percentages of values that meet certain criteria. store-c(1,1.4,3,1.1,0.3,0.6,4,5) # now I want to get the precentages of values # that fall into the categories =M , M =N , N # let M -.8 N - 1.2 # In my real example I have many more of these cutoff-points # What I did is: out - matrix(NA,1,3) out[1,1] - ( (sum(store=M)) /length(store) )*100 out[1,2] - ( (sum(store M store= N )) /length(store) )*100 out[1,3] - ( (sum(store N)) /length(store) )*100 colnames(out)-c(percent=M,percentM =N,percentN) out But this gets very tedious if I have many cutoff-points. Does anybody know a more elegant way to do this task? Thanks so much. Cheers, Jens __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] elegant solution to transform vector into percentages?
use 'cut': store-c(1,1.4,3,1.1,0.3,0.6,4,5) x.1 - cut(store, breaks=c(-Inf,.8,1.2,Inf)) table(x.1)/length(x.1)*100 x.1 (-Inf,0.8] (0.8,1.2] (1.2,Inf] 25 25 50 On 7/26/05, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: Hi, I am looking for an elegant way to transform a vector into percentages of values that meet certain criteria. store-c(1,1.4,3,1.1,0.3,0.6,4,5) # now I want to get the precentages of values # that fall into the categories =M , M =N , N # let M -.8 N - 1.2 # In my real example I have many more of these cutoff-points # What I did is: out - matrix(NA,1,3) out[1,1] - ( (sum(store=M)) /length(store) )*100 out[1,2] - ( (sum(store M store= N )) /length(store) )*100 out[1,3] - ( (sum(store N)) /length(store) )*100 colnames(out)-c(percent=M,percentM =N,percentN) out But this gets very tedious if I have many cutoff-points. Does anybody know a more elegant way to do this task? Thanks so much. Cheers, Jens __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Jim Holtman What the problem you are trying to solve? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] / Right division.
Dear R gurus. Is there an R function equivalent to octaves / (Right division) withouth forming the inverse of Y' using solve ? [snip - from octave docu] Right division. This is conceptually equivalent to the expression (inverse (y') * x')' but it is computed without forming the inverse of Y'. If the system is not square, or if the coefficient matrix is singular, a minimum norm solution is computed. [snip] Thanks Eryk __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] / Right division.
On 7/26/2005 4:02 PM, nwew wrote: Dear R gurus. Is there an R function equivalent to octaves / (Right division) withouth forming the inverse of Y' using solve ? [snip - from octave docu] Right division. This is conceptually equivalent to the expression (inverse (y') * x')' but it is computed without forming the inverse of Y'. If the system is not square, or if the coefficient matrix is singular, a minimum norm solution is computed. If x is a vector, I think it's solve(t(Y), x). If x is stored as a 1xn matrix, you'd use t(solve(t(Y), t(x)). If you're trying to do multiple operations at once, you probably need to use the second form. Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] choose between dates and times
If happenat is not a datetime value, convert it with strptime(). Then, one solution is to transform it in the following way: num.time - as.numeric(format(happenat,%Y%m%d%H%M%S)) This way, 07/22/05 00:05:14 becomes 20050722000514, and you can subset your data frame with dfr[which(num.time = 20050725153000 num.time = 20050726123000),] hth, b. -Original Message- From: Kerry Bush [mailto:[EMAIL PROTECTED] Sent: Tuesday, July 26, 2005 3:54 PM To: r-help@stat.math.ethz.ch Subject: [R] choose between dates and times Dear R-helpers, I have the following data: yhappenat x 5185 (07/22/05 00:05:14) 14 5186 (07/22/05 00:15:14) 14 5187 (07/22/05 00:25:14) 14 5188 (07/22/05 00:35:14) 14 .. I want to choose between 07/25/05 15:30:00 and 07/26/05 12:30:00. Anybody had experience in handling this kind of data? Is there a simple way to subset by the variable 'happenat'? Thanks. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] elegant solution to transform vector into percentages?
On Tue, 2005-07-26 at 15:48 -0400, [EMAIL PROTECTED] wrote: Hi, I am looking for an elegant way to transform a vector into percentages of values that meet certain criteria. store-c(1,1.4,3,1.1,0.3,0.6,4,5) # now I want to get the precentages of values # that fall into the categories =M , M =N , N # let M -.8 N - 1.2 # In my real example I have many more of these cutoff-points # What I did is: out - matrix(NA,1,3) out[1,1] - ( (sum(store=M)) /length(store) )*100 out[1,2] - ( (sum(store M store= N )) /length(store) )*100 out[1,3] - ( (sum(store N)) /length(store) )*100 colnames(out)-c(percent=M,percentM =N,percentN) out But this gets very tedious if I have many cutoff-points. Does anybody know a more elegant way to do this task? Thanks so much. Cheers, Jens Something alone the lines of: store - c(1, 1.4, 3, 1.1, 0.3, 0.6, 4, 5) M - 0.8 N - 1.2 x - hist(store, br = c(min(store), M, N, max(store)), plot = FALSE)$counts pct.x - prop.table(x) * 100 names(pct.x) - c(percent = M,percent M = N,percent N) pct.x percent = M percent M = Npercent N 25 25 50 I think that should do it. See ?hist for more information and take note of the 'include.lowest' and 'right' arguments relative to whether or not values are or are not included in the specified intervals. See ?prop.table as well. Also be acutely aware of potential problems with exact equality comparisons with floating point numbers and the break points...if you have a float value equal to a breakpoint in your vector. HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] choose between dates and times
Kerry Bush [EMAIL PROTECTED] writes: Dear R-helpers, I have the following data: yhappenat x 5185 (07/22/05 00:05:14) 14 5186 (07/22/05 00:15:14) 14 5187 (07/22/05 00:25:14) 14 5188 (07/22/05 00:35:14) 14 .. I want to choose between 07/25/05 15:30:00 and 07/26/05 12:30:00. Anybody had experience in handling this kind of data? Is there a simple way to subset by the variable 'happenat'? Thanks. Simple, perhaps not. This stuff always gets a little heavy, but start here: strptime((07/22/05 00:05:14),format=(%m/%d/%y %H:%M:%S)) + as.POSIXct(2005-07-22 00:06:00) [1] FALSE strptime((07/22/05 00:05:14),format=(%m/%d/%y %H:%M:%S)) + as.POSIXct(2005-07-22 00:05:00) [1] TRUE Once you figure out how this works, the rest should follow. -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Wishart Density
Dear R users, I am doing MCMC using Metropolis-Hastings. My model is bivariate-log-normal and the prior for variance-covariance is wishart distribution. I am wondering if there are some simple codes about how to get the density of Wishart distribution in my case ? Thanks in advance. Meihua [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Help on T test
Mark, Please do not post the same question to both R-help and BioC-help mailing lists because 1) there are many people who are on both lists and 2) people's replies will be archived in two different places making it harder to others to search in future. Please see the responses on BioC-help list. Regards, Adai On Tue, 2005-07-26 at 15:28 -0400, mark salsburg wrote: ok I created a matrix C with A B CA1 B1C1 .. . the columns contain the gene expression values.. I ran the following t.test: apply(C, 1, function(x) t.test( x[1:3], x[4,6] )$p.value ) which outputs out 16063 pvalues (the number of rows) I just want to output 3 pvalues showing if A's column is different from A1 etc.. any help would be great.. thank you.. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] elegant solution to transform vector into percentages?
Why not write a function ? Here is one. mytable - function(x, br){ n - length(br) tb - table( cut( x, breaks=c(-Inf, br, Inf) ) ) tb - 100 * tb / sum(tb) tb.n - paste( c(, br), c(br, ), sep= x = ) tb.n[1] - paste(x = , br[1], sep=) tb.n[n+1] - paste(x , br[n], sep=) names(tb) - tb.n return(tb) } mytable( store, br=c(0.8, 1.2) ) x = 0.8 0.8 x = 1.2x 1.2 25 25 50 You might want to do a bit more testing especially at the break points. However I do not like the output of the above because the names of the table overlaps. Here is another function that might have nicer output. mytable2 - function(x, br){ tb - as.matrix( mytable( x=x, br=br ) ) colnames(tb) - Percentage return(tb) } mytable2( store, br=c(0.8, 1.2) ) Percentage x = 0.8 25 0.8 x = 1.2 25 x 1.250 Hope this helps. Regards, Adai On Tue, 2005-07-26 at 15:48 -0400, [EMAIL PROTECTED] wrote: Hi, I am looking for an elegant way to transform a vector into percentages of values that meet certain criteria. store-c(1,1.4,3,1.1,0.3,0.6,4,5) # now I want to get the precentages of values # that fall into the categories =M , M =N , N # let M -.8 N - 1.2 # In my real example I have many more of these cutoff-points # What I did is: out - matrix(NA,1,3) out[1,1] - ( (sum(store=M)) /length(store) )*100 out[1,2] - ( (sum(store M store= N )) /length(store) )*100 out[1,3] - ( (sum(store N)) /length(store) )*100 colnames(out)-c(percent=M,percentM =N,percentN) out But this gets very tedious if I have many cutoff-points. Does anybody know a more elegant way to do this task? Thanks so much. Cheers, Jens __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Durbin test for Incomplete block
Hi R-users, Does anyone know of a package that contains a function to conduct Durbin's test and it's extension for incomplete block designs, as described in Rayner and Best 2001 A contingency Table Approach to Nonparametric Testing? Peter -- ISR-Porto __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Difficulty getting standard deviation of ALL odds ratios with glm function, logistic regression, need cov of parameters
I am trying to do logistic regression with a categorical predictor variable with the glm() function, family=binomial. Using glm() I would like to be able to calculate the confidence intervals of all three possible odds ratios for a factor (the factor has three categories). Three categories imply two columns of 0's and 1's in the design matrix, and two parameter estimates with their SE's. Two confidence intervals for odds ratios can be easily calculated, the third confidence interval can be calculated if I know the SE of B1-B2, but this requires the covariance matrix of parameter estimates, which is not given to my knowledge. My initial thought was that Cov(B1,B2)=0, but this cannot be true or the variance estimates would depend on how you set up the design matrix (the factor symbolized by 0,0 would always have a higher SD). Please help me find the covariance of the parameter estimates. Thank you in advance, Garrett Fox __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Anybody have a binary version of SJava for rw2001 (Windows)?
I am not a techie and have been struggling 2 days solid to try and install SJava (the source from http://www.omegahat.org/RSJava/). Does anybody have a binary file for me (I am Windows XP and rw2001)? I have tried installing Perl, mingwin and the cygwin tools but still no luck. When I try R CMD INSTALL c:\SJava_0.78-0.tar.gz I get the following (and havent a clue what it could mean): -Making package SJava-- Building JNI header files... Extracting the classes from Environment.jar /jdk1.3/bin/jar: not found RForeignReference /jdk1.3/bin/javah: not found ROmegahat Interpreter /jdkl.3/bin/javah: not found REvaluator /jdkl.3/bin/Javah: not found RManualFunctionActionListener /jdk1.3/bin/javah: not found /jdkl.3/bin/javah: not found adding build stamp to DESCRIPTION running src/Makefile.win (cd .. ; ./configure.win c:/PROGRW1/R/rw200l) /configure.win: not found make[3]: *** [conf ig] Error 127 make[2]: *** [srcDynLib] Error 2 make[1]: *** [all] Error 2 make: *** [pkgSJava] Error 2 *** Installation of SJava failed *** --- [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Difficulty getting standard deviation of ALL odds ratios with glm function, logistic regression, need cov of parameters
On Tue, 26 Jul 2005, Garrett Fox wrote: I am trying to do logistic regression with a categorical predictor variable with the glm() function, family=binomial. Using glm() I would like to be able to calculate the confidence intervals of all three possible odds ratios for a factor (the factor has three categories). Three categories imply two columns of 0's and 1's in the design matrix, and two parameter estimates with their SE's. Two confidence intervals for odds ratios can be easily calculated, the third confidence interval can be calculated if I know the SE of B1-B2, but this requires the covariance matrix of parameter estimates, which is not given to my knowledge. vcov(your.model) returns the variance-covariance matrix. -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] problem with Hershey fonts
Hi Ray Brownrigg wrote: This was reported to me by a colleague in China, so I may not be reproducing exactly what they are seeing (which I suspect is rw2011), but this is what I see: version _ platform i386--netbsdelf arch i386 os netbsdelf system i386, netbsdelf status major2 minor1.1 year 2005 month06 day 20 language R help(Hershey) : : If the 'vfont' argument to one of the text-drawing functions ('text', 'mtext', 'title', 'axis', and 'contour') is a character vector of length 2, Hershey vector fonts are used to render the text. : The other useful escape sequences all begin with '\\'. These are described below. Remember that backslashes have to be doubled in R character strings, so they need to be entered with _four_ backslashes. : : plot(runif(100)) # to get something on the screen text(0, 1, '\\Re', vfont=c('serif', 'plain')) # works title(main = '\\Re', vfont=c('serif','plain'))# doesn't work, and... Warning message: parameter vfont could not be set in high-level plot() function mtext('\\Re', 2, vfont=c('serif','plain'))# doesn't work, but... Warning message: Hershey fonts not yet implemented for mtext() in: mtext(text, side, line, outer, at, adj, padj, cex, col, font, axis(3, at=50, tick=F, labels='\\Re', vfont=c('serif','plain')) # doesn't work Now at least mtext() 'redeems' itself with its Warning, but title() contradicts the help(Hershey), and axis() just gets it wrong by printing the characters \Re (or \\Re when the string is specified as 'Re' as alluded to in the Hershey documentation - but somewhat contradicted by the success of the text() call above). Now perhaps the problem is just with the Hershey documentation (or my reading of it), but I don't know what is supposed to work. Or is there some combination that I haven't tried? The problem with title() has been reported before (PR#7031), but thanks for pointing out the extension to axis() and mtext() as well. The good news is that the 'vfont' argument has been superseded. It was a horrible way of incorporating Hershey fonts (I should know, I did it) and a much better way now exists via par(family=). The following modification of your example should work: plot(runif(100))# to get something on the screen oldf - par(family=HersheySerif) text(0, 1, '\\Re') title(main = '\\Re') mtext('\\Re', 2) axis(3, at=50, tick=F, labels='\\Re') par(oldf) The bad news is that, as you point out, the documentation is lacking. I will make some updates so that this solution is easier to find in future. Paul -- Dr Paul Murrell Department of Statistics The University of Auckland Private Bag 92019 Auckland New Zealand 64 9 3737599 x85392 [EMAIL PROTECTED] http://www.stat.auckland.ac.nz/~paul/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] spss.read factor reversal
Hi, I'm having a problem with spss.read reversing my factor input. Here is the input copied from the spss data editor: color cost 1 2.30 2 2.40 3 3.00 1 2.10 1 1.00 1 2.00 2 4.00 2 3.20 2 2.33 3 2.44 3 2.55 For color, red=1, blue=2, and green = 3. It's type is 'String' and out=read.spss(file) out $COLOR [1] green blue red green green green blue blue blue red red Levels: red blue green $COST [1] 2.30 2.40 3.00 2.10 1.00 2.00 4.00 3.20 2.33 2.44 2.55 attr(,label.table) attr(,label.table)$COLOR green blue red 3 2 1 attr(,label.table)$COST NULL attr(,variable.labels) COLOR COST color cost =EOF=== Notice that the $COLOR factor data are inverted, looking at the integer output we see: as.integer(out$COLOR) [1] 3 2 1 3 3 3 2 2 2 1 1 The spss original data looks like this: 1 2 3 1 1 1 2 2 2 3 3 I can easily invert the output mathematically with: q = sapply(m,function(x){ x + 2*(median(unique(m))-x)}) (m is composed of sequential integers starting at one) ,but it seems as though something wrong is happening with read.spss. Any ideas? Joel Bremson Graduate Student UC Davis [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] CART analysis
Is there an R package that can be used for CART analysis? Thank you, John John Sorkin M.D., Ph.D. Chief, Biostatistics and Informatics Baltimore VA Medical Center GRECC and University of Maryland School of Medicine Claude Pepper OAIC University of Maryland School of Medicine Division of Gerontology Baltimore VA Medical Center 10 North Greene Street GRECC (BT/18/GR) Baltimore, MD 21201-1524 410-605-7119 - NOTE NEW EMAIL ADDRESS: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] spss.read factor reversal
I think it is doing what is supposed to do but I never used read.spss, so take this with a pinch of salt. In R when you use as.integer on a factor, the one with the lowest level gets a value of 1 and so on. The lowest level of the factor can determined from levels() function. f - factor( c(Green, Green, Red, Blue), levels=c(Red, Blue, Green) ) levels(f) [1] Red Blue Green as.integer(f) [1] 3 3 1 2 But the levels of a factor can be changed as.integer( factor( f, levels=c(Green, Blue, Red ) ) ) [1] 1 1 3 2 You can also try setting use.value.labels=FALSE in read.spss function and then creating a factor out of it. Regards, Adai On Tue, 2005-07-26 at 17:04 -0700, Joel Bremson wrote: Hi, I'm having a problem with spss.read reversing my factor input. Here is the input copied from the spss data editor: color cost 1 2.30 2 2.40 3 3.00 1 2.10 1 1.00 1 2.00 2 4.00 2 3.20 2 2.33 3 2.44 3 2.55 For color, red=1, blue=2, and green = 3. It's type is 'String' and out=read.spss(file) out $COLOR [1] green blue red green green green blue blue blue red red Levels: red blue green $COST [1] 2.30 2.40 3.00 2.10 1.00 2.00 4.00 3.20 2.33 2.44 2.55 attr(,label.table) attr(,label.table)$COLOR green blue red 3 2 1 attr(,label.table)$COST NULL attr(,variable.labels) COLOR COST color cost =EOF=== Notice that the $COLOR factor data are inverted, looking at the integer output we see: as.integer(out$COLOR) [1] 3 2 1 3 3 3 2 2 2 1 1 The spss original data looks like this: 1 2 3 1 1 1 2 2 2 3 3 I can easily invert the output mathematically with: q = sapply(m,function(x){ x + 2*(median(unique(m))-x)}) (m is composed of sequential integers starting at one) ,but it seems as though something wrong is happening with read.spss. Any ideas? Joel Bremson Graduate Student UC Davis [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] CART analysis
RSiteSearch(CART) should bring up a few hits including http://finzi.psych.upenn.edu/R/Rhelp02a/archive/25850.html Regards, Adai On Tue, 2005-07-26 at 20:25 -0400, John Sorkin wrote: Is there an R package that can be used for CART analysis? Thank you, John John Sorkin M.D., Ph.D. Chief, Biostatistics and Informatics Baltimore VA Medical Center GRECC and University of Maryland School of Medicine Claude Pepper OAIC University of Maryland School of Medicine Division of Gerontology Baltimore VA Medical Center 10 North Greene Street GRECC (BT/18/GR) Baltimore, MD 21201-1524 410-605-7119 -- NOTE NEW EMAIL ADDRESS: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] CART analysis
--- Adaikalavan Ramasamy [EMAIL PROTECTED] wrote: RSiteSearch(CART) should bring up a few hits including http://finzi.psych.upenn.edu/R/Rhelp02a/archive/25850.html CART is a trademarked statistical procedure owned by Salford Systems of San Diego, CA. If you're looking for an R-package that implements the procedures described in the Breiman, Friedman, Olshen, and Stone book entitled Classification and Regression Trees, the closest you can come to the original algorithm is the R-package called rpart, by Therneau and Atkinson. If you combine that with Andy Liaw's randomForest, you have a pretty potent set of tools. If you really want CART, you need to contact Salford Systems for their implementation and pay their very expensive licensing fees. Dr. Marc R Feldesman Professor Chair Emeritus Department of Anthropology Portland State University Portland, OR 97207 Please respond to all emails at: [EMAIL PROTECTED] Some people live and die by actuarial tables Groundhog Day __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] trellis graphics/ trellis.par.set()
Background: OS: Linux Mandrake 10.1 release: R 2.0.0 editor: GNU Emacs 21.3.2 front-end: ESS 5.2.3 - Colleagues I want to increase the size of the axis markings and labels on some trellis graphs, and I am having some trouble with trellis.par.set() trellis.par.set(par.xlab.text.cex = list(cex=1.5)) is not quite right, and having read the documentation, I wonder if anyone help me get the graphical parameter right? print(trellis.par.get()) returns $par.xlab.text.cex Best fishes Sam Sam McClatchie, Biological oceanography South Australian Aquatic Sciences Centre PO Box 120, Henley Beach 5022 Adelaide, South Australia email [EMAIL PROTECTED] Telephone: (61-8) 8207 5448 FAX: (61-8) 8207 5481 Research home page http://www.members.iinet.net.au/~s.mcclatchie/ /\ ...xX(° °)Xx / \\ (((° (((° ...xX(°O°)Xx __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Error in FUN(newX[, i], ...) : `x' must be atomic
Hello Group, What is the meaning of the error. is there any place to look for this. I guess 'atomic' seems to be OOP related concept. thank you srini __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Error in FUN(newX[, i], ...) : `x' must be atomic
Perhaps a reproducible example and short explanation of what you want to do might help. I suspect that you fed a null value into a function that expects a non-null value or something. On Tue, 2005-07-26 at 19:22 -0700, Srinivas Iyyer wrote: Hello Group, What is the meaning of the error. is there any place to look for this. I guess 'atomic' seems to be OOP related concept. thank you srini __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Error in FUN(newX[, i], ...) : `x' must be atomic
Actually, atoms are originally a Lisp concept. Objects are either atoms or not. Atoms are data types that cannot be taken apart, such as numbers or symbols. Lists and vectors (of length 1) are examples of non-atomic data types. Did you pass a vector to FUN? Cheers, Simon. At 12:22 PM 27/07/2005, Srinivas Iyyer wrote: Hello Group, What is the meaning of the error. is there any place to look for this. I guess 'atomic' seems to be OOP related concept. thank you srini __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Simon Blomberg, B.Sc.(Hons.), Ph.D, M.App.Stat. Centre for Resource and Environmental Studies The Australian National University Canberra ACT 0200 Australia T: +61 2 6125 7800 email: Simon.Blomberg_at_anu.edu.au F: +61 2 6125 0757 CRICOS Provider # 00120C __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Problem specifying function for mle operation
Hello fellow R users, Below are two cases using the mle operation from the stats4 package. In CASE 1 the code runs fine, in CASE 2 errors occur: CASE 1 x, alpha_current, s, and n are vectors of the same length. ll_beta-function(b0=0,b1=0) -sum(s*b0+s*b1*x+s*alpha_current-n*log(1+exp(b0+b1*x+alpha_current))) fit_beta-mle(ll_beta) CASE 2 The error message is as follows = Error in validObject(.Object) : invalid class mle object: invalid object for slot fullcoef in class mle: got class list, should be or extend class numeric x,s,n, and alpha are vectors of the same length (5 dimensions in this specific case). ll_alpha-function(alpha=c(0.5,0.5,0.5,0.5,0.5)) -sum(s*b0+s*b1*x+s*alpha-n*log(1+exp(b0+b1*x+alpha))-0.5*(alpha/sigma)^2) fit_alpha-mle(ll_alpha) MY THEORY: I think it has something to do with the fact that the function argument is a vector in CASE 2. Hope this doesn't mean I have to re-write the function in a way that it doesn't require vector inputs. Any suggestions on how to make CASE 2 work would be appreciated. peace Narcyz. This message is intended for the addressee named and may con...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] gamma distribution
Hi R Users This is a code I wrote and just want to confirm if the first 1000 values are raw gamma (z) and the next 1000 values are transformed gamma (k) or not. As I get 2000 rows once I import into excel, the p - values beyond 1000 dont look that good, they are very high. -- sink(a1.txt); for (i in 1:1000) { x-rgamma(10, 2.5, scale = 10) y-rgamma(10, 2.5, scale = 10) z-wilcox.test(x, y, var.equal = FALSE) print(z) x1-log(x) y1-log(y) k-wilcox.test(x1, y1, var.equal = FALSE) print(k) } --- any suggestions are welcome thanks -devarshi __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] A question about par.plot in gamlss
Hello I am using the following code to plot a data matrix into a form that seems suitable for the use of par.plot. library(gamlss) a-matrix(c(1,2,3,4,5,6,7,8,9,8,7,6),nrow=3) rownames(a)-c(trt1,trt2,trt3) colnames(a)-c(col1,col2,col3,col4) hpar.plot-function(ZZ){ ZZvar-c(t(ZZ)) ZZtrt-c(matrix(rep(1:ncol(ZZ),nrow(ZZ ZZcov-as.factor(c(t(matrix(rep(rownames(ZZ),ncol(ZZ)),nrow=nrow(ZZ) par.plot(ZZvar ~ ZZtrt,sub=ZZcov) } hpar.plot(a) I keep getting the following error message: Error in eval(expr, envir, enclos) : Object ZZvar not found I am unable to figure out my error. Can someone help please? Thanks in advance. Hari __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html