Re: [R] (Fisher) Randomization Test for Matched Pairs: Permutation Data Setup Based on Signs
On Thu, Mar 08, 2012 at 09:49:20PM -0800, Ghandalf wrote: Hi, I am currently attempting to write a small program for a randomization test (based on rank/combination) for matched pairs. If you will please allow me to introduce you to some background information regarding the test prior to my question at hand, or you may skip down to the bold portion for my issue. There are two sample sizes; the data, as I am sure you guessed, is matched into pairs and each pair's difference is denoted by Di. The test statistic =*T* = Sum(Di) (only for those Di 0). The issue I am having is based on the method required to use in R to setup the data into the proper structure. I am to consider the absolute value of Di, without regard to their sign. There are 2^n ways of assigning + or - signs to the set of absolute differences obtained, where n = the number of Dis. That is, we can assign + signs to all n of the |Di|, or we might assign + to |D1| but - signs to |D2| to |Dn|, and so forth. So, for example, if I have *D1=-16, D2=-4, D3=-7, D4=-3, D5=-5, D6=+1, and D7=-10 and n=7. * I need to consider the 2^7 ways of assigning signs that result in the lowest sum of the positive absolute difference. To exemplify further, we have * -16, -4, -7, -3, -5, -1, -10T = 0 -16, -4, -7, -3, -5, +1, -10 T = 1 -16, -4, -7, +3, -5, -1, -10 T = 3 -16, -4, -7, +3, -5, +1, -10 T = 4 * ... and so on. Hi. The minimum sum of positive absolute differencies is always zero and is achieved for every sign combination, which assigns -1 to all nonzero abs(Di) and any sign to zero abs(Di). In particular, the combination rep(-1, times=7) is a solution. I am not sure, whether this is, what you are asking for. Can you give more detail? Petr Savicky. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] (Fisher) Randomization Test for Matched Pairs: Permutation Data Setup Based on Signs
On Mar 11, 2012, at 03:17 , R. Michael Weylandt wrote: In general, I *think* this is a hard problem (it sounds knapsack-ish) but since you are on small enough data sets, that's probably not so important: if I understand you right, this little function will help you. plusminus - function(n){ t(as.matrix(do.call(expand.grid, rep(list(c(-1,1)), n } plusminus(3) plusminus(5) If you multiply the output of this function by your data set you will have rows corresponding to all possible sign choices: e.g., plusminus(3) * c(1,2,3) Then you can colSums() using only the positive elements: x - plusminus(3) * c(1,2,3) x[x 0] - 0 colSums(x) To wrap this all in one function: I'd do something like this: test.statistic - function(v){ m - t(as.matrix(do.call(expand.grid, rep(list(c(-1, 1)), length(v) x - m * v x[x0] - 0 out - rbind(m * v, colSums(x)) rownames(out)[length(rownames(out))] - Sum of Positive Elements out } X - test.statistic(c(-16, -4, -7, -3, -5, +1, -10)) X[,1:10] Hopefully that helps (I'm a little fuzzy on your overall goal -- so that second bit might be a red herring) Looks pretty much OK to me. Just one note: In this sort of problem, you can do away with the business of the sum of the positive elements and just do the sum. This is because sum(x[x0])-sum(x[x0]) == sum(abs(x)) sum(x[x0])+sum(x[x0]) == sum(x) and the sum(abs(x)) is of course the same, no matter how you assign signs to x. Add the two equations and divide by two and you get sum(x[x0]) == (sum(x) + sum(abs(x))/2 This in turn means that you can just do allsums - as.matrix(do.call(expand.grid, rep(list(c(-1,1)), n))) %*% scores and then mean(allsums = sum(scores)) to get the proportion of more extreme test statistics. You can even leave the signs on the scores in the computation of allsums because that will just affect the order of the sign-permuted samples. Michael On Fri, Mar 9, 2012 at 12:49 AM, Ghandalf mool...@hotmail.com wrote: Hi, I am currently attempting to write a small program for a randomization test (based on rank/combination) for matched pairs. If you will please allow me to introduce you to some background information regarding the test prior to my question at hand, or you may skip down to the bold portion for my issue. There are two sample sizes; the data, as I am sure you guessed, is matched into pairs and each pair's difference is denoted by Di. The test statistic =*T* = Sum(Di) (only for those Di 0). The issue I am having is based on the method required to use in R to setup the data into the proper structure. I am to consider the absolute value of Di, without regard to their sign. There are 2^n ways of assigning + or - signs to the set of absolute differences obtained, where n = the number of Dis. That is, we can assign + signs to all n of the |Di|, or we might assign + to |D1| but - signs to |D2| to |Dn|, and so forth. So, for example, if I have *D1=-16, D2=-4, D3=-7, D4=-3, D5=-5, D6=+1, and D7=-10 and n=7. * I need to consider the 2^7 ways of assigning signs that result in the lowest sum of the positive absolute difference. To exemplify further, we have * -16, -4, -7, -3, -5, -1, -10T = 0 -16, -4, -7, -3, -5, +1, -10 T = 1 -16, -4, -7, +3, -5, -1, -10 T = 3 -16, -4, -7, +3, -5, +1, -10 T = 4 * ... and so on. So, if you are willing to help me, I am having trouble on setting up my data as illustrated above./ How do I create (a code for) the 2^n lines of data required with all the possible combinations of + and - in order to calculate the positive values in each line (the test statistic, T)?/ I have tried to use combn(d=data set, n=7) with a data set, d, consisting of both the positive and negative sign of the respective value, to no avail. I apologize if this is lengthy, I was not sure how to ask the aforementioned question without incorrectly portraying my thoughts. If any clarification is required then I will by more than willing to oblige with any further explanation. I have searched for possible solutions, but alas, came out empty handed. Thank you. -- View this message in context: http://r.789695.n4.nabble.com/Fisher-Randomization-Test-for-Matched-Pairs-Permutation-Data-Setup-Based-on-Signs-tp4458606p4458606.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. --
Re: [R] How do I do a pretty scatter plot using ggplot2?
On 03/10/2012 11:37 AM, Michael wrote: Hi all, I am trying hard to do the following and have already spent a few hours in vain: I wanted to do the scatter plot. But given the high dispersion on those dots, I would like to bin the x-axis and then for each bin of the x-axis, plot the quantiles of the y-values of the data points in each bin: 1. Uniform bin size on the x-axis; 2. Equal number of observations in each bin; How to do that in R? I guess for the sake of prettyness, I'd better do it in ggplot2? Hi Michael, While it is not in ggplot2, a variation on the count.overplot function might do what you want. This function displays counts of closely spaced points rather than the points, but it applies the same area of aggregation across the whole plot. Getting the equal x bins is easy, and I assume that you mean equal observations within each bin, not across all bins. If you are stuck, I can probably hack up something from count.overplot. Jim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Interfacing between Optimization Software and R
Dear all I was wondering, if there are reasons for R-Users to use (commercial) solver packages like GAMS, AMPL, Matlab, etc. These packages can solve all kind of mathematical optimization problems like (non-) linear problems, mixed complementarity problems, etc. Why I want to know? GAMS corporation developed a R package to send data from GAMS to R (or vice versa). It is called gdxrxw. I use this package a lot for my network models I solve with GAMS, sending the results from GAMS to R for plotting, generating tables in LaTeX and statistical analysis (see some of my post on blog.modelworks.ch). However, until now, for my personal use, I don't use the package the other way around (R - Gams). I am writing a small article on this interface and was wondering if there are situations, where R-Users would be grateful for having the possibility to interact with solver software. Any reaction would be very much appreciated. Renger Modelworks Gewerbestrasse 15 3600 Thun - Switzerland +41 79 818 53 73 i...@modelworks.ch blog.modelworks.ch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Matrix negative fraction power
Dear list, I understand that to raise matrix A to power (-1/2) we should use something like this: eigen(A)$vectors%*%diag(1/sqrt(eigen(A)$values))%*%t(eigen(A)$vectors) [from previous discussions: http://r.789695.n4.nabble.com/matrix-power-td900335.html] But this will only do it for negative sqrt of the matrix not for other fraction powers like (-3/2). Seeing that these things be can done seamlessly in Matlab, I am wondering if I am missing something in R. Examples in Matlab: A = 1 1 1 1 2 3 1 3 6 A^(-1/2 )= 1.5099 -0.82620.1937 -0.82621.9586 -0.6937 0.1937 -0.69370.6937 A^(-3/2)= 7.2020 -9.04813.3560 -9.0481 13.6591 -5.4371 3.3560 -5.43712.2749 Thank you in advance. -- Ebrahim Jahanshiri [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Interfacing between Optimization Software and R
You missed a lot of indications, most prominently the task view http://cran.r-project.org/web/views/Optimization.html On 11/03/2012 07:18, Renger van Nieuwkoop wrote: Dear all I was wondering, if there are reasons for R-Users to use (commercial) solver packages like GAMS, AMPL, Matlab, etc. These packages can solve all kind of mathematical optimization problems like (non-) linear problems, mixed complementarity problems, etc. Why I want to know? GAMS corporation developed a R package to send data from GAMS to R (or vice versa). It is called gdxrxw. I use this package a lot for my network models I solve with GAMS, sending the results from GAMS to R for plotting, generating tables in LaTeX and statistical analysis (see some of my post on blog.modelworks.ch). However, until now, for my personal use, I don't use the package the other way around (R - Gams). I am writing a small article on this interface and was wondering if there are situations, where R-Users would be grateful for having the possibility to interact with solver software. Any reaction would be very much appreciated. Renger Modelworks Gewerbestrasse 15 3600 Thun - Switzerland +41 79 818 53 73 i...@modelworks.ch blog.modelworks.ch __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Brian D. Ripley, rip...@stats.ox.ac.uk 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@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [R-sig-eco] Landscape ecology in R
Hi Manuel, I've taken the liberty of adding the r-help list back to this email, even though you sent your reply just to me, so that others may contribute. On Fri, Mar 9, 2012 at 6:27 PM, Manuel Spínola mspinol...@gmail.com wrote: Thank you Sarah, I am thinking more on habitat mapping and landscape metrics. Then you've probably seen the adehabitat* and SDMTools packages. I have been using several packages but I would like to see something more integrated for teaching. It appear that there is a landscape package but I am trying to see where can I download it. The R Way is to have many special-purpose packages: task views are very useful to streamline installation. What specifically are you looking for that what you're using doesn't provide? I don't think there's a landscape package yet, just plans to create a landscape package, although I have no idea what's it's intended to do. Sarah 2012/3/9 Sarah Goslee sarah.gos...@gmail.com What kind of landscape ecology analysis? There's a whole task view on spatial analysis. There's another task view on environmetrics. Both have material of interest to landscape ecologists. There are various packages that do habitat mapping, and landscape metrics, or interface with GIS software. Landscape ecology is such a broad discipline that we need more context to answer in more detail, but there's plenty of relevant material. I'm teaching a workshop on R for landscape ecologists at the US-IALE meeting next month, incidentally. Sarah On Fri, Mar 9, 2012 at 5:53 PM, Manuel Spínola mspinol...@gmail.com wrote: Dear list members, I am looking for any reference or material on landscape ecology analysis in R. Thank you very much in advance. Best, Manuel -- Sarah Goslee http://www.functionaldiversity.org __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] function input as variable name (deparse/quote/paste) ??
On Sat, Mar 10, 2012 at 04:01:21PM -0800, casperyc wrote: Sorry if I wasn't stating what I really wanted or it was a bit confusing. Basically, there are MANY datasets to run suing the same function I have written a function to analyze it and returns a LIST of useful out put in the variable 'res' (to the workspace). I also created another script run.r such as myname(dat1) myname(dat2) myname(dat3) myname(dat4) myname(dat5) For now, each time the output in the main workspace 'res' (the list) is over written. I want it to have different suffix to differentiate them. So I can have a look later after the batch is run. I see no advantage in having that information in variable names. Just - add the name of the data set to the information that is included in the returned list. - run your function with sapply() and the returned list of sapply will be a list of lists. -- Hans Ekbrand (http://sociologi.cjb.net) h...@sociologi.cjb.net __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] too many open devices
Many thanks for your answer. I am using someone else's code that has worked fine for some time and don't know much about R graphics. Windows are being opened, the clutter is definitely there, and it looks like dev.off is not being used. So at least it probably is not a stupid attack on my part. So your response was helpful. Thanks for taking the time to respond. Harold On Sun, Mar 11, 2012 at 1:39 AM, Patrick Connolly p_conno...@slingshot.co.nz wrote: On Sat, 10-Mar-2012 at 02:21PM -0600, harold kincaid wrote: | I am getting too many open devices after 60 graphs. The archived | comments on this problem were too sketchy to be helpful. Any ideas? With minimal information, my guess might not be correct, but I suspect you're plotting to a Windows device and a new one is opened for each of your plots. That would be some clutter on your screen. You'd make life simpler if you used a pdf device that uses a new page for each of your plots which can be hundreds of pages if you like. Check out the help for pdf(), making sure you don't forget the dev.off() part. HTH -- ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~. ___ Patrick Connolly {~._.~} Great minds discuss ideas _( Y )_ Average minds discuss events (:_~*~_:) Small minds discuss people (_)-(_) . Eleanor Roosevelt ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Matrix negative fraction power
On Sun, Mar 11, 2012 at 1:46 AM, Ebrahim Jahanshiri e.jahansh...@gmail.com wrote: Dear list, I understand that to raise matrix A to power (-1/2) we should use something like this: eigen(A)$vectors%*%diag(1/sqrt(eigen(A)$values))%*%t(eigen(A)$vectors) [from previous discussions: http://r.789695.n4.nabble.com/matrix-power-td900335.html] But this will only do it for negative sqrt of the matrix not for other fraction powers like (-3/2). Not sure why you think this won't work for -3/2 - simply use eigen(A)$values^(-3/2) instead of the 1/sqrt(eigen(A)$values) and you're good to go. Generalizations to other powers are left as exercise for the reader :) Peter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Matrix negative fraction power
On Sun, Mar 11, 2012 at 8:56 AM, Peter Langfelder peter.langfel...@gmail.com wrote: On Sun, Mar 11, 2012 at 1:46 AM, Ebrahim Jahanshiri e.jahansh...@gmail.com wrote: Dear list, I understand that to raise matrix A to power (-1/2) we should use something like this: eigen(A)$vectors%*%diag(1/sqrt(eigen(A)$values))%*%t(eigen(A)$vectors) [from previous discussions: http://r.789695.n4.nabble.com/matrix-power-td900335.html] But this will only do it for negative sqrt of the matrix not for other fraction powers like (-3/2). Not sure why you think this won't work for -3/2 - simply use eigen(A)$values^(-3/2) instead of the 1/sqrt(eigen(A)$values) and you're good to go. Generalizations to other powers are left as exercise for the reader :) also please be kind to your poor computer and store and reuse eigen(A), that is not trivial to compute! Peter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Joshua Wiley Ph.D. Student, Health Psychology Programmer Analyst II, Statistical Consulting Group University of California, Los Angeles https://joshuawiley.com/ __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Efficient access to elements of a list of lists
Hi, I have a long list of lists from which I want to efficiently extract and rbind elements. So I'm using the approach below: f - function(i){ out - replicate(5, list(matrix(rnorm(80), nc=20))) names(out) - letters[1:5] out } set.seed(1) lst - lapply(1:1.5e6, f) (t0 - system.time(tmp - do.call(rbind, lapply(lst, '[[', 'b' Is there anything better/faster than the do.call+rbind+lapply combo above? On this example, the combo takes roughly 20s on my machine... but on the data I'm working with, it takes more than 1 minute... And given that I need to repeat the task several times, the cumul. amount of time is significant for me. Thank you for any suggestion/comment, benilton __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Fwd: Matrix negative fraction power
Thank you very much Peter, Indeed this should be left to the reader/practitioner. But I think -at least for the sake of comparison with matlab- we could have it in the core R. I would definitely try to learn more about R and implement it later. Cheers, Ebrahim On Sun, Mar 11, 2012 at 11:56 PM, Peter Langfelder peter.langfel...@gmail.com wrote: On Sun, Mar 11, 2012 at 1:46 AM, Ebrahim Jahanshiri e.jahansh...@gmail.com wrote: Dear list, I understand that to raise matrix A to power (-1/2) we should use something like this: eigen(A)$vectors%*%diag(1/sqrt(eigen(A)$values))%*%t(eigen(A)$vectors) [from previous discussions: http://r.789695.n4.nabble.com/matrix-power-td900335.html] But this will only do it for negative sqrt of the matrix not for other fraction powers like (-3/2). Not sure why you think this won't work for -3/2 - simply use eigen(A)$values^(-3/2) instead of the 1/sqrt(eigen(A)$values) and you're good to go. Generalizations to other powers are left as exercise for the reader :) Peter -- Ebrahim Jahanshiri Spatial and Numerical lab ITMA Universiti Putra Malaysia 43300, Selangor, Malaysia +60172002427 e.jahansh...@gmail.com -- Ebrahim Jahanshiri Spatial and Numerical lab ITMA Universiti Putra Malaysia 43300, Selangor, Malaysia +60172002427 e.jahansh...@gmail.com [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Matrix negative fraction power
If my memory is correct, the archives of this list contains several discussions of round off error problems associated with different methods for computing things like this. The Matrix package (part of the base distribution) contains a function expm, whose help file says, The expm package contains newer (partly faster and more accurate) algorithms for expm() and includes logm and sqrtm. This suggests to me that the most numerically stable way to get an arbitrary power p of a matrix M in R might be as follows: expm(p*logm(M)) If compute time becomes an issue, I would want to do numerical comparisons of the results from this with the results from the your other method. Hope this helps. Spencer p.s. I found the above in part by using findFn('expm') after library(sos). On 3/11/2012 9:14 AM, Joshua Wiley wrote: On Sun, Mar 11, 2012 at 8:56 AM, Peter Langfelder peter.langfel...@gmail.com wrote: On Sun, Mar 11, 2012 at 1:46 AM, Ebrahim Jahanshiri e.jahansh...@gmail.com wrote: Dear list, I understand that to raise matrix A to power (-1/2) we should use something like this: eigen(A)$vectors%*%diag(1/sqrt(eigen(A)$values))%*%t(eigen(A)$vectors) [from previous discussions: http://r.789695.n4.nabble.com/matrix-power-td900335.html] But this will only do it for negative sqrt of the matrix not for other fraction powers like (-3/2). Not sure why you think this won't work for -3/2 - simply use eigen(A)$values^(-3/2) instead of the 1/sqrt(eigen(A)$values) and you're good to go. Generalizations to other powers are left as exercise for the reader :) also please be kind to your poor computer and store and reuse eigen(A), that is not trivial to compute! Peter __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Spencer Graves, PE, PhD President and Chief Technology Officer Structure Inspection and Monitoring, Inc. 751 Emerson Ct. San José, CA 95126 ph: 408-655-4567 web: www.structuremonitoring.com __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Matrix negative fraction power
On 11-03-2012, at 17:52, Spencer Graves wrote: If my memory is correct, the archives of this list contains several discussions of round off error problems associated with different methods for computing things like this. The Matrix package (part of the base distribution) contains a function expm, whose help file says, The expm package contains newer (partly faster and more accurate) algorithms for expm() and includes logm and sqrtm. This suggests to me that the most numerically stable way to get an arbitrary power p of a matrix M in R might be as follows: expm(p*logm(M)) I have just tested and it should be this library(expm) expm((-1/2)*logm(A)) expm((-3/2)*logm(A)) Berend __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Matrix negative fraction power
On 11-03-2012, at 18:18, Berend Hasselman wrote: On 11-03-2012, at 17:52, Spencer Graves wrote: If my memory is correct, the archives of this list contains several discussions of round off error problems associated with different methods for computing things like this. The Matrix package (part of the base distribution) contains a function expm, whose help file says, The expm package contains newer (partly faster and more accurate) algorithms for expm() and includes logm and sqrtm. This suggests to me that the most numerically stable way to get an arbitrary power p of a matrix M in R might be as follows: expm(p*logm(M)) I have just tested and it should be this library(expm) expm((-1/2)*logm(A)) expm((-3/2)*logm(A)) Indeed. It's getting on and I made a muddle. Berend __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] function input as variable name (deparse/quote/paste) ??
Thank you everyone for your reply. Like I said in my original post, this is just a demonstrative example of my 'big' self written script. My 'big' function take several inputs, of which the first 1 is the dataset and returns a LIST variable 'res-list()' to the workspace with many information. The names of my actual datasets are NOT in any pattern, like 'dat1', 'dat2', 'dat3'. That's why i wonder if I can modify the line 'res-' in anyway to be 'res.dat-' where 'dat' in the first input. So I can CALL via 'res.dat' (or res.newdata, res.olddata, res.tmpdata,res.hisdata) in the workspace any time I want to have a look. - ### PhD candidate in Statistics School of Mathematics, Statistics and Actuarial Science, University of Kent ### -- View this message in context: http://r.789695.n4.nabble.com/function-input-as-variable-name-deparse-quote-paste-tp4462841p4464294.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Efficient access to elements of a list of lists
On Sun, Mar 11, 2012 at 9:18 AM, Benilton Carvalho beniltoncarva...@gmail.com wrote: Hi, I have a long list of lists from which I want to efficiently extract and rbind elements. So I'm using the approach below: f - function(i){ out - replicate(5, list(matrix(rnorm(80), nc=20))) names(out) - letters[1:5] out } set.seed(1) lst - lapply(1:1.5e6, f) (t0 - system.time(tmp - do.call(rbind, lapply(lst, '[[', 'b' Is there anything better/faster than the do.call+rbind+lapply combo above? The [[ function involves method dispatching. You can avoid that by using .subset2(). That may save you some (micro?)seconds. Now, if all extracted elements are truly of the same dimensions; bList - lapply(lst, FUN='[[', 'b') str(head(bList)) List of 6 $ : num [1:4, 1:20] 0.936 -0.844 -0.221 -0.581 -2.513 ... $ : num [1:4, 1:20] -0.2618 0.0259 -1.3131 -0.0547 -0.3296 ... $ : num [1:4, 1:20] -1.589 0.844 -1.121 0.21 -0.846 ... $ : num [1:4, 1:20] -1.192 -1.268 1.688 -0.295 0.466 ... $ : num [1:4, 1:20] 2.504 -0.833 -1.751 1.117 -0.775 ... $ : num [1:4, 1:20] 0.119 -0.313 1.741 0.403 -0.261 ... then you can avoid the rbind(), by doing an unlist()/dim()/aperm(), e.g. # Extract 'b' as an 4-by-20-by-1.5e6 array dim - dim(bList[[1]]); n - length(bList); bArray - unlist(bList, use.names=FALSE); dimA - c(dim, n); dim(bArray) - dimA; # If you really need a matrix, then... # Turing into a (4*1.5e6)-by-20 array dimM - dim; dimM[1] - n*dimM[1]; bMatrix - aperm(bArray, perm=c(1,3,2)); dim(bMatrix) - dimM; You owe me a beer ;) /Henrik On this example, the combo takes roughly 20s on my machine... but on the data I'm working with, it takes more than 1 minute... And given that I need to repeat the task several times, the cumul. amount of time is significant for me. Thank you for any suggestion/comment, benilton __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Efficient access to elements of a list of lists
Thanks Henrik!!! Hope to pay your beer soon. :) b __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Warnings when plotting after x11() in R 2.14.2
On 08.03.2012 21:03, Mark Seeto wrote: Dear R-help, I recently upgraded from R 2.13.1 to R 2.14.2 and now get warning messages when plotting after using x11(). Example: plot(rnorm(10))### no warnings x11(); plot(rnorm(10)) Warning messages: 1: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 2: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 3: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 4: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 5: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 6: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 7: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 8: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 9: In title(...) : Font family not found in Windows font database 10: In title(...) : Font family not found in Windows font database plot(rnorm(10))### After using x11(), I get warnings even when x11() is not used There were 18 warnings (use warnings() to see them) warnings() Warning messages: 1: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 2: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 3: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 4: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 5: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 6: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 7: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 8: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 9: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 10: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 11: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 12: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 13: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 14: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 15: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 16: In axis(side = side, at = at, labels = labels, ...) : Font family not found in Windows font database 17: In title(...) : Font family not found in Windows font database 18: In title(...) : Font family not found in Windows font database This happens in both the 32 and 64 bit versions of R 2.14.2, and it also happens with ggplot2 plots. I'm using RGui on Windows 7. It did not happen with R 2.13.1. It's not a major problem, because the plots still appear to be produced correctly, but if anyone can tell me how to fix it, I'd appreciate it. Use dev.new() rather than x11(). Under Windows, there is a windows() device but no x11() device. R tries hard to work around your user error (calling x11() under Windows). Uwe Ligges Thanks, Mark Seeto __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] extracting data from unstructured (text?) file
Dear R community, I have the following problem I hoped you could help me with. My data is save in thousand of files with a weird extension containing for numbers and a z. For example *.1405z. With list.files I managed to load this data into R. It looks like this (the row numbers are not in the original file): 35 :LATEST STAGE 3.60 FT AT 730 AM CST ON 0102 36 .ER ARCT20102 C DC21020813/DH12/HGIFF/DIH6 37 :QPF FORECAST6AM NOON6PM MDNT 38 .E1 :0102: / 3.5/ 3.4/ 3.5 39 .E2 :0103: / 3.5/ 3.0/ 2.5/ 2.1 40 .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 41 .E4 :0105: / 1.2/ 1.8/ 2.3/ 2.7 42 .E5 :0106: / 3.0/ 3.0/ 3.1/ 3.3 43.E6 :0107: / 3.4 I need the table in rows 37 to 43 in a matrix, for example: 0201 NA3.53.43.5 0103 3.53.02.5 2.1 0104 1.81.51.31.2 01051.2 1.82.32.7 0106 3.03.03.13.3 0107 3.4NANA NA Unfortunately the row numbers vary per file. I can call up each line with file[40,1] for line 40 for example. It returns: [1] .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 38 Levels: .E1 :0102: / 3.5/ 3.4/ 3.5 ... So I have two problems really: 1. How do I detect the table in the file (resp. the line where the table starts)? 2. How do I break up each line to write the values into a matrix? Feel free to suggest an entirely different approach if you think that is helpful. Thanks a lot! Frauke -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4464423.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] extracting data from unstructured (text?) file
Can you at least provide a subset of 2 files so we can see how the data is really stored in the file and what the separators are between the 'columns' of data. Also how do you determine where the data actually starts for the rows that you want to pull off. This will aid in determining how to parse the data. On Sun, Mar 11, 2012 at 3:07 PM, frauke fh...@andrew.cmu.edu wrote: Dear R community, I have the following problem I hoped you could help me with. My data is save in thousand of files with a weird extension containing for numbers and a z. For example *.1405z. With list.files I managed to load this data into R. It looks like this (the row numbers are not in the original file): 35 :LATEST STAGE 3.60 FT AT 730 AM CST ON 0102 36 .ER ARCT2 0102 C DC21020813/DH12/HGIFF/DIH6 37 :QPF FORECAST 6AM NOON 6PM MDNT 38 .E1 :0102: / 3.5/ 3.4/ 3.5 39 .E2 :0103: / 3.5/ 3.0/ 2.5/ 2.1 40 .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 41 .E4 :0105: / 1.2/ 1.8/ 2.3/ 2.7 42 .E5 :0106: / 3.0/ 3.0/ 3.1/ 3.3 43 .E6 :0107: / 3.4 I need the table in rows 37 to 43 in a matrix, for example: 0201 NA 3.5 3.4 3.5 0103 3.5 3.0 2.5 2.1 0104 1.8 1.5 1.3 1.2 0105 1.2 1.8 2.3 2.7 0106 3.0 3.0 3.1 3.3 0107 3.4 NA NA NA Unfortunately the row numbers vary per file. I can call up each line with file[40,1] for line 40 for example. It returns: [1] .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 38 Levels: .E1 :0102: / 3.5/ 3.4/ 3.5 ... So I have two problems really: 1. How do I detect the table in the file (resp. the line where the table starts)? 2. How do I break up each line to write the values into a matrix? Feel free to suggest an entirely different approach if you think that is helpful. Thanks a lot! Frauke -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4464423.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Data Munger Guru What is the problem that you are trying to solve? Tell me what you want to do, not how you want to do it. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] extracting data from unstructured (text?) file
Hi Frauke, Try unix commands with R's system() function. Example: Let's say you have a matrix like this in the file (note: the first element is missing) called hello.txt 10 100 2 20 200 3 30 300 4 40 400 5 50 500 You can try something like: hello = system(cut -f1 hello.txt, intern=T) VP. On 11 March 2012 19:07, frauke fh...@andrew.cmu.edu wrote: Dear R community, I have the following problem I hoped you could help me with. My data is save in thousand of files with a weird extension containing for numbers and a z. For example *.1405z. With list.files I managed to load this data into R. It looks like this (the row numbers are not in the original file): 35 :LATEST STAGE 3.60 FT AT 730 AM CST ON 0102 36 .ER ARCT20102 C DC21020813/DH12/HGIFF/DIH6 37 :QPF FORECAST6AM NOON6PM MDNT 38 .E1 :0102: / 3.5/ 3.4/ 3.5 39 .E2 :0103: / 3.5/ 3.0/ 2.5/ 2.1 40 .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 41 .E4 :0105: / 1.2/ 1.8/ 2.3/ 2.7 42 .E5 :0106: / 3.0/ 3.0/ 3.1/ 3.3 43.E6 :0107: / 3.4 I need the table in rows 37 to 43 in a matrix, for example: 0201 NA3.53.43.5 0103 3.53.02.5 2.1 0104 1.81.51.31.2 01051.2 1.82.32.7 0106 3.03.03.13.3 0107 3.4NANA NA Unfortunately the row numbers vary per file. I can call up each line with file[40,1] for line 40 for example. It returns: [1] .E3 :0104: / 1.8/ 1.5/ 1.3/ 1.2 38 Levels: .E1 :0102: / 3.5/ 3.4/ 3.5 ... So I have two problems really: 1. How do I detect the table in the file (resp. the line where the table starts)? 2. How do I break up each line to write the values into a matrix? Feel free to suggest an entirely different approach if you think that is helpful. Thanks a lot! Frauke -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4464423.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Problems when building a package for Windows 64
Hello I have recently installed R 2.14.2 on a brand new pc running Windows 64. One of things I would like to do is to recompile my R package (with C and fortran source codes) for this new environment (it works on a mac and on a linux box). To this end, I had rtools 2.14 downloaded and installed (I have also added 2.14.2/bin/x64 to PATH so that Rcmd works on a terminal). On a cmd terminal I issue the command Rcmd INSTALL build name_of_my_package to get (x86 works fine) *** arch - x64 cygwin warning: MS-DOS style path detected: C:/PROGRA~1/R/R-214~1.2/etc/x64/Makeconf Preferred POSIX equivalent is: /cygdrive/c/PROGRA~1/R/R-214~1.2/etc/x64/Makeco nf CYGWIN environment variable option nodosfilewarning turns off this warning. Consult the user's guide for more details about POSIX paths: http://cygwin.com/cygwin-ug-net/using.html#using-pathnames gfortran -m64 -O2 -mtune=core2 -c correl.f -o correl.o f951.exe: sorry, unimplemented: 64-bit mode not compiled in make: *** [correl.o] Error 1 ERROR: compilation failed for package What am I missing? Many thanks Ed [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problems when building a package for Windows 64
On 11/03/2012 19:43, Eduardo Mendes wrote: Hello I have recently installed R 2.14.2 on a brand new pc running Windows 64. One of things I would like to do is to recompile my R package (with C and fortran source codes) for this new environment (it works on a mac and on a linux box). To this end, I had rtools 2.14 downloaded and installed (I have also added 2.14.2/bin/x64 to PATH so that Rcmd works on a terminal). That's the error you made. That toolchain is the default for R = 2.14.1 but not for 2.14.2. Please do the homework the posting guide asked of you, e.g. read http://cran.r-project.org/bin/windows/Rtools/ or if you want to use the earlier version of Rtools, read http://cran.r-project.org/doc/manuals/R-admin.html and set MkRules.local accordingly. On a cmd terminal I issue the command Rcmd INSTALL build name_of_my_package to get (x86 works fine) *** arch - x64 cygwin warning: MS-DOS style path detected: C:/PROGRA~1/R/R-214~1.2/etc/x64/Makeconf Preferred POSIX equivalent is: /cygdrive/c/PROGRA~1/R/R-214~1.2/etc/x64/Makeco nf CYGWIN environment variable option nodosfilewarning turns off this warning. That's in the manual, too Consult the user's guide for more details about POSIX paths: http://cygwin.com/cygwin-ug-net/using.html#using-pathnames gfortran -m64 -O2 -mtune=core2 -c correl.f -o correl.o f951.exe: sorry, unimplemented: 64-bit mode not compiled in make: *** [correl.o] Error 1 ERROR: compilation failed for package What am I missing? Many thanks Ed [[alternative HTML version deleted]] The posting guide asked you not to send HTML. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Did we mention the posting guide? -- Brian D. Ripley, rip...@stats.ox.ac.uk 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@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] extracting data from unstructured (text?) file
Thank you for the quick reply! I have attached two files. http://r.789695.n4.nabble.com/file/n4464511/sample1.1339z sample1.1339z http://r.789695.n4.nabble.com/file/n4464511/sample2.1949z sample2.1949z -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4464511.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Problems when building a package for Windows 64
Dear Prof. Ripley Many thanks. rtools 2.15 did the job. One note if I may - In the rtools site one reads rtools215.exe - r2.14.1 to R 2.15.x No rtoosl214.exe - r 2.13.x or R.2.14.x yes which can mislead the reader. 2.14.x could mean 2.14.2 and no could mean that rtools-2.15 is not read for prime time. Ed [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Siegel-Tukey test for equal variability (code)
Update: The siegel Tukey code is now fixed (both on the github page, and the blog's post): https://github.com/talgalili/R-code-snippets/blob/master/siegel.tukey.r http://www.r-statistics.com/2010/02/siegel-tukey-a-non-parametric-test-for-equality-in-variability-r-code/ Best, Tal On Sat, Mar 10, 2012 at 12:05 AM, Tal Galili tal.gal...@gmail.com wrote: With coordination with the code's author (Daniel), The updated code has been uploaded to github here: https://github.com/talgalili/R-code-snippets/blob/master/siegel.tukey.r And also the following post was updated with the code: http://www.r-statistics.com/2010/02/siegel-tukey-a-non-parametric-test-for-equality-in-variability-r-code/ I suspect that the code still needs some tweaks so it will be able to take care of two vectors of different lengths. Tal Contact Details:--- Contact me: tal.gal...@gmail.com | 972-52-7275845 Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) | www.r-statistics.com (English) -- On Fri, Mar 9, 2012 at 11:11 PM, Daniel Malter dan...@umd.edu wrote: #The code of rank 1 in the previous post should have read #rank1-apply(iterator1,1,function(x) x+base1) #corrected code below siegel.tukey=function(x,y,id.col=TRUE,adjust.median=F,rnd=-1,alternative=two.sided,mu=0,paired=FALSE,exact=FALSE,correct=TRUE, conf.int=FALSE,conf.level=0.95){ if(id.col==FALSE){ data=data.frame(c(x,y),rep(c(0,1),c(length(x),length(y } else { data=data.frame(x,y) } names(data)=c(x,y) data=data[order(data$x),] if(rnd-1){data$x=round(data$x,rnd)} if(adjust.median==T){ cat(\n,Adjusting medians...,\n,sep=) data$x[data$y==0]=data$x[data$y==0]-(median(data$x[data$y==0])) data$x[data$y==1]=data$x[data$y==1]-(median(data$x[data$y==1])) } cat(\n,Median of group 1 = ,median(data$x[data$y==0]),\n,sep=) cat(Median of group 2 = ,median(data$x[data$y==1]),\n,\n,sep=) cat(Testing median differences...,\n) print(wilcox.test(data$x[data$y==0],data$x[data$y==1])) cat(Performing Siegel-Tukey rank transformation...,\n,\n) sort.x-sort(data$x) sort.id-data$y[order(data$x)] data.matrix-data.frame(sort.x,sort.id) base1-c(1,4) iterator1-matrix(seq(from=1,to=length(x),by=4))-1 rank1-apply(iterator1,1,function(x) x+base1) iterator2-matrix(seq(from=2,to=length(x),by=4)) base2-c(0,1) rank2-apply(iterator2,1,function(x) x+base2) #print(rank1) #print(rank2) if(length(rank1)==length(rank2)){ rank-c(rank1[1:floor(length(x)/2)],rev(rank2[1:ceiling(length(x)/2)])) } else{ rank-c(rank1[1:ceiling(length(x)/2)],rev(rank2[1:floor(length(x)/2)])) } unique.ranks-tapply(rank,sort.x,mean) unique.x-as.numeric(as.character(names(unique.ranks))) rank.matrix-data.frame(unique.x,unique.ranks) ST.matrix-merge(data.matrix,rank.matrix,by.x=sort.x,by.y=unique.x) print(ST.matrix) cat(\n,Performing Siegel-Tukey test...,\n,sep=) ranks0-ST.matrix$unique.ranks[ST.matrix$sort.id==0] ranks1-ST.matrix$unique.ranks[ST.matrix$sort.id==1] cat(\n,Mean rank of group 0: ,mean(ranks0),\n,sep=) cat(Mean rank of group 1: ,mean(ranks1),\n,sep=) print(wilcox.test(ranks0,ranks1,alternative=alternative,mu=mu,paired=paired,exact=exact,correct=correct, conf.int=conf.int,conf.level=conf.level)) } Examples: x - c(33, 62, 84, 85, 88, 93, 97, 4, 16, 48, 51, 66, 98) id - c(0,0,0,0,0,0,0,1,1,1,1,1,1) siegel.tukey(x,id,adjust.median=F,exact=T) x-c(0,0,1,4,4,5,5,6,6,9,10,10) id-c(0,0,0,1,1,1,1,1,1,0,0,0) siegel.tukey(x,id) x - c(85,106,96, 105, 104, 108, 86) id-c(0,0,1,1,1,1,1) siegel.tukey(x,id) x-c(177,200,227,230,232,268,272,297,47,105,126,142,158,172,197,220,225,230,262,270) id-c(rep(0,8),rep(1,12)) siegel.tukey(x,id,adjust.median=T) -- View this message in context: http://r.789695.n4.nabble.com/Siegel-Tukey-test-for-equal-variability-code-tp1565053p4460705.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] extracting data from unstructured (text?) file
Here is one way assuming the data start after QPF FORECAST: setwd('/temp') # where the data is files - c('sample1.htm', 'sample2.htm') # files to read # assumes 4 columns of data fields - list(c(19, 24), c(30, 35), c(41, 46), c(52, 57)) #columns of data results - lapply(files, function(.file){ + inData - FALSE # switch to indicate in data + collection - NULL # will hold the data + inputFile - file(.file, 'r') # open the connection + repeat{ + input - readLines(inputFile, n = 1) + if (inData){ # parse the line and collect data + key - sub(^.E[0-9]+[^:]*:([^:]+).*, \\1, input) + if (nchar(key) != 4){ # done with data; return result + colnames(collection) - colNames + close(inputFile) + return(collection) + } + # get the data assuming that 'fields' defines where data is + cols - numeric(length(fields)) + for (i in seq_along(fields)){ + cols[i] - as.numeric(substring(input + , fields[[i]][1] + , fields[[i]][2] + ) + ) + } + collection - rbind(collection, cols) + rownames(collection)[nrow(collection)] - key + } else { # looking for the start of the data + if (grepl(^:QPF FORECAST, input)){ + # extract the column names + colNames - NULL + for (i in seq_along(fields)){ + colNames - c(colNames, substring(input + , fields[[i]][1] + , fields[[i]][2] + ) + ) + } + inData - TRUE # now get the data + } + } + } + }) Warning message: NAs introduced by coercion print(results) [[1]] 7AM1PM7PM1AM 0830 NA5.64.43.8 08313.33.02.62.5 09012.32.22.22.1 09022.12.02.02.0 09032.01.91.91.9 09041.8 NA NA NA [[2]] 7AM1PM7PM1AM 0604 NA NA7.08.4 06059.49.28.67.8 06066.85.64.23.5 06073.23.02.92.8 06082.82.82.72.7 06092.7 NA NA NA On Sun, Mar 11, 2012 at 4:07 PM, frauke fh...@andrew.cmu.edu wrote: Thank you for the quick reply! I have attached two files. http://r.789695.n4.nabble.com/file/n4464511/sample1.1339z sample1.1339z http://r.789695.n4.nabble.com/file/n4464511/sample2.1949z sample2.1949z -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4464511.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Jim Holtman Data Munger Guru What is the problem that you are trying to solve? Tell me what you want to do, not how you want to do it. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] CRAN (and crantastic) updates this week
CRAN (and crantastic) updates this week New packages * EffectStars (1.0) Maintainer: Unknown Author(s): Gunther Schauberger License: GPL-2 http://crantastic.org/packages/EffectStars The package provides functions to visualize regression models with categorical response. The effects of the covariates are plotted with star plots in order to allow for an optical impression of the fitted model. * extraBinomial (2.0) Maintainer: Xin Yang Author(s): Xin Yang License: GPL-3 http://crantastic.org/packages/extraBinomial This package tests for differences in minor allele frequency between groups and is based on an extra-binomial variation model for pooled sequencing data. A set of simulated pooled sequencing data can be generated using this package. * Familias (1.0) Maintainer: Petter Mostad Author(s): Petter Mostad mos...@chalmers.se License: GPL-2 http://crantastic.org/packages/Familias This package represents a bare-bones implementation of an interface to the core Familias functions (www.familias.name), which are programmed in C++. The package itself functions as a kind of database, where information about persons, pedigrees, allele systems and observations for persons are entered stepwise. In the end, probability calculations are made. * JPSurv (1.0.1) Maintainer: Yongwu Shao Author(s): Yongwu Shao yws...@gmail.com, License: GPL (= 2) http://crantastic.org/packages/JPSurv Functions, methods, and datasets for cancer survival analysis, including the proportional hazard relative survival model, the join point relative survival model. * kappaSize (1.0) Maintainer: Michael A Rotondi Author(s): Michael A Rotondi mroto...@yorku.ca License: GPL (= 2) http://crantastic.org/packages/kappaSize This package contains basic tools for the purpose of sample size estimation in studies of interobserver/interrater agreement (reliability). This package contains sample size estimation functions for both the power-based and confidence interval-based methods, with binary or multinomial outcomes and two through six raters. * koRpus (0.04-27) Maintainer: m.eik michalke Author(s): m.eik michalke meik.micha...@hhu.de, with contributions from Earl Brown eabr...@csumb.edu, Alberto Mirisola, and Laura Hauser License: GPL (= 3) http://crantastic.org/packages/koRpus A set of tools to analyze texts. Includes, amongst others, functions for automatic language detection, hyphenation, several indices of lexical diversity (e.g., type token ratio, HD-D/vocd-D, MTLD) and readability (e.g., Flesch, SMOG, LIX, Dale-Chall). Basic import functions for language corpora are also provided, to enable frequency analyses (supports Celex and Leipzig Corpora Collection file formats). #' Note: For full functionality a local installation of TreeTagger is recommended. Be encouraged to send feedback to the author(s)! * networkDynamic (0.2-2) Maintainer: Ayn Leslie-Cook Author(s): Ayn Leslie-Cook, Zack Almquist, Pavel N. Krivitsky, Skye Bender-deMoll, David R. Hunter, Martina Morris, Carter T. Butts License: GPL-3 http://crantastic.org/packages/networkDynamic Simple interface routines to facilitate the handling of network objects with complex intertemporal data. * qLearn (1.0) Maintainer: Bibhas Chakraborty Author(s): Jingyi Xin, Bibhas Chakraborty, and Eric B. Laber License: GPL-2 http://crantastic.org/packages/qLearn Functions to implement Q-learning for estimating optimal dynamic treatment regimes from two stage sequentially randomized trials, and to perform inference via m-out-of-n bootstrap for parameters indexing the optimal regime. * Rdistance (1.0) Maintainer: Trent McDonald Author(s): Trent McDonald License: GNU General Public License http://crantastic.org/packages/Rdistance Analysis of line transect surveys. Estimates distance-based sightability functions and abundances. * relSim (0.1-33) Maintainer: James M. Curran Author(s): James M. Curran License: GPL (= 2) http://crantastic.org/packages/relSim A set of tools to explore the behaviour statistics used for forensic DNA interpretation when close relatives are involved * RForcecom (0.1) Maintainer: Takekatsu Hiramura Author(s): Takekatsu Hiramura License: BSD http://crantastic.org/packages/RForcecom RForcecom provides the connection to Force.com (Salesforce.com) from R. * SAScii (0.1) Maintainer: Anthony Joseph Damico Author(s): Anthony Joseph Damico License: GPL (= 2) http://crantastic.org/packages/SAScii Using any importation code designed for SAS users to read ASCII files into sas7bdat files, the SAScii package parses through the INPUT block of a (.sas) syntax file to design the parameters needed for a read.fwf function call. This allows the user to specify the location of the ASCII (often a .dat) file and the location
Re: [R] Which non-parametric regression would allow fitting this type of data? (example given).
Hello Bert, Thanks so much for these suggestions. They led me to the package LPCM, which I found worked best with minimum tuning. lpc1 = lpc(cbind(X,Y), scaled=TRUE, h=c(0.05,0.05)) plot(lpc1) ... et voila! All the best, Emmanuel On 11 March 2012 00:37, Bert Gunter gunter.ber...@gene.com wrote: Thanks for the example. Have you tried fitting a principal curve via either the princurve or pcurve packages? I think this might work for what you want, but no guarantees. Note that loess, splines, etc. are all fitting y|x, that is, a nonparametric regression of y on x. That is not what you say you want, so these approaches are unlikely to work. -- Bert On Sat, Mar 10, 2012 at 6:20 PM, Emmanuel Levy emmanuel.l...@gmail.com wrote: Hi, I'm wondering which function would allow fitting this type of data: tmp=rnorm(2000) X.1 = 5+tmp Y.1 = 5+ (5*tmp+rnorm(2000)) tmp=rnorm(100) X.2 = 9+tmp Y.2 = 40+ (1.5*tmp+rnorm(100)) X.3 = 7+ 0.5*runif(500) Y.3 = 15+20*runif(500) X = c(X.1,X.2,X.3) Y = c(Y.1,Y.2,Y.3) plot(X,Y) The problem with loess is that distances for the goodness of fit are calculated on the Y-axis. However, distances would need to be calculated on the normals of the fitted curve. Is there a function that provide this option? A simple trick in that case consists in swapping X and Y, but I'm wondering if there is a more general solution? Thanks for your input, Emmanuel __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Bert Gunter Genentech Nonclinical Biostatistics Internal Contact Info: Phone: 467-7374 Website: http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How do I do a pretty scatter plot using ggplot2?
Could you please show me an example for my two cases? Thanks a lot! On Sun, Mar 11, 2012 at 3:55 AM, Jim Lemon j...@bitwrit.com.au wrote: On 03/10/2012 11:37 AM, Michael wrote: Hi all, I am trying hard to do the following and have already spent a few hours in vain: I wanted to do the scatter plot. But given the high dispersion on those dots, I would like to bin the x-axis and then for each bin of the x-axis, plot the quantiles of the y-values of the data points in each bin: 1. Uniform bin size on the x-axis; 2. Equal number of observations in each bin; How to do that in R? I guess for the sake of prettyness, I'd better do it in ggplot2? Hi Michael, While it is not in ggplot2, a variation on the count.overplot function might do what you want. This function displays counts of closely spaced points rather than the points, but it applies the same area of aggregation across the whole plot. Getting the equal x bins is easy, and I assume that you mean equal observations within each bin, not across all bins. If you are stuck, I can probably hack up something from count.overplot. Jim [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] extracting data from unstructured (text?) file
Wow Jim, this is much more than I expected. Thank you!! It took me a while to figure out what exactly you are doing in that code. But I think I understand and it definitely runs. May I ask you two follow up questions? First, some of my files have data from two or more cities in them. So I have trouble that it picks the right city. What makes it difficult is that not in all files will a city be called the same. Sometimes it might be van Buren, other times Arkansas River at van Buren. Sometimes the target city is the first in the file, other times further down. Here is an example: http://r.789695.n4.nabble.com/file/n4465068/sample3.txt sample3.txt . Additionally, some files miss the city that I am looking for. Second, I would like extract some more data from the files, printed in bold below. I thought of storing this data in an extra line appended to the main table or so. I do manage to extract one at a time, but of course it takes ages to run the process over and over again to get all the data. :ARKANSAS RIVER AT VAN BUREN :FLOOD STAGE * 22.0 * : :LATEST STAGE*19.25* FT AT *400 AM* CST ON *010100* .ER VBUA40101 C DC21010823/DH12/HGIFF/DIH6 :QPF FORECAST6AM NOON6PM MDNT .E1 :0101: / 19.3/ 19.4/ 19.4 .E2 :0102: / 19.4/ 19.4/ 19.4/ 19.4 .E3 :0103: / 19.4/ 19.4/ 19.4/ 19.4 .E4 :0104: / 19.4/ 19.4/ 19.4/ 19.4 .E5 :0105: / 19.4/ 19.4/ 19.4/ 19.4 .E6 :0106: / 19.4 .ER VBUA40101 C DC21010823/DH12/PPQFZ/DIH6/ 0.00/0.00/0.00/0.00 .ER VBUA40101 C DC21010823/DH12/QTIFF/DIH6 :QPF FORECAST6AM NOON6PM MDNT .E1 :0101: / 0.98/ 2.78/ 8.66 .E2 :0102: / 9.88/ 8.70/ 7.36/ 7.48 .E3 :0103: / 8.25/ 8.42/ 8.53/ 9.02 Please Jim, only answer these questions if you have time. I certainly appreciate any help very much. Thank you, Frauke -- View this message in context: http://r.789695.n4.nabble.com/extracting-data-from-unstructured-text-file-tp4464423p4465068.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] specify GARCH model, using garchFit()
Hello, Ive fitted a Garch(2,1) model with function 'garchFit()' from the package 'fGarch': m1 - garchFit(formula = ~garch(2,1),data = X,trace = F) * See 'summary(m1)' OUTPUT BELOW * PROBLEM: My alpha1 term is not significant and I would like to make a NEW model, say m2, that does not contain alpha1, but I am not sure how to specify this with the garchFit() arguments. I assume it must be done by changing the formula argument (replacing ~garch(2,1) with something), but am unsure; not an expert in this statistical field. Has anyone worked with these and know the fix? Thanks, Ash ### OUTPUT: summary(m1) Title: GARCH Modelling Call: garchFit(formula = ~garch(2, 1), data =X, trace = F) Meanand Variance Equation: data ~ garch(2, 1) environment: 0x03c0c84c [data =ex3.5$sp5] ConditionalDistribution: norm Coefficient(s): mu omegaalpha1alpha2 beta1 0.630047 0.716062 0.048446 0.096263 0.838793 Std.Errors: based on Hessian ErrorAnalysis: Estimate Std. Error t value Pr(|t|) mu 0.63005 0.140724.477 7.56e-06 *** omega0.71606 0.262642.726 0.0064 ** alpha1 0.048450.03096 1.565 0.1176 alpha2 0.096260.04354 2.211 0.0271 * beta10.83879 0.02477 33.858 2e-16 *** --- Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1 [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] to Michael ... Re: How do I do a pretty scatter plot using ggplot2?
Hi Michael, I am trying the solution you've suggested below: DAT - data.frame(x = runif(1000, 0, 20), y = rnorm(1000)) DAT$xbin - with(DAT, cut(x, seq(0, 20, 2))) p - ggplot(DAT, aes(x = x, y = y)) + geom_point(alpha = 0.2) + stat_quantile(aes(colour = ..quantile..), quantiles = seq(0.05, 0.95, by=0.05)) + facet_wrap(~ xbin, scales = free) print(p) --- But my big problem is: I don't know how to modify the code above to do it for equal # of points in each bin along the x-axis? i.e. the 2nd case in the original problem: 2. Equal number of observations in each bin; ? Thanks a lot! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] to Michael ... Re: How do I do a pretty scatter plot using ggplot2?
And also, no matter how I changed the quantiles = seq(0.05, 0.95, by=0.05)) line, the number of lines in each bin and the number of legends on the right side of the each plot are different... What's the catch? Am I missing something here? I thought the number of quantile lines and the number of legends should be exactly the same, no? On Sun, Mar 11, 2012 at 8:54 PM, Michael comtech@gmail.com wrote: Hi Michael, I am trying the solution you've suggested below: DAT - data.frame(x = runif(1000, 0, 20), y = rnorm(1000)) DAT$xbin - with(DAT, cut(x, seq(0, 20, 2))) p - ggplot(DAT, aes(x = x, y = y)) + geom_point(alpha = 0.2) + stat_quantile(aes(colour = ..quantile..), quantiles = seq(0.05, 0.95, by=0.05)) + facet_wrap(~ xbin, scales = free) print(p) --- But my big problem is: I don't know how to modify the code above to do it for equal # of points in each bin along the x-axis? i.e. the 2nd case in the original problem: 2. Equal number of observations in each bin; ? Thanks a lot! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.htmlhttp://www.r-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Idea/package to linearize a curve along the diagonal?
Hi, I am trying to normalize some data. First I fitted a principal curve (using the LCPM package), but now I would like to apply a transformation so that the curve becomes a straight diagonal line on the plot. The data used to fit the curve would then be normalized by applying the same transformation to it. A simple solution could be to apply translations only (e.g., as done after a fit using loess), but here rotations would have to be applied as well. One could visualize this as the stretching of a curve, i.e., during such an unfolding process, both translations and rotations would need to be applied. Before I embark on this (which would require me remembering long forgotten geometry principles) I was wondering if you can think of packages or tricks that could make my life simpler? Thanks for any input, Emmanuel Below I provide an example - the black curve is to be brought along the diagonal, and all data points normal to a small segment (of the black curve) would undergo the same transformation as it - what small is remains to be defined though. tmp=rnorm(2000) X.1 = 5+tmp Y.1 = 5+ (5*tmp+rnorm(2000)) tmp=rnorm(1000) X.2 = 9+tmp Y.2 = 40+ (1.5*tmp+rnorm(1000)) X.3 = 7+ 0.5*runif(500) Y.3 = 15+20*runif(500) X = c(X.1,X.2,X.3) Y = c(Y.1,Y.2,Y.3) lpc1 = lpc(cbind(X,Y), scaled=FALSE, h=c(1,1) ) plot(lpc1) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] SEM eigen value error 0 X 0 matrix
Using R-studio, I am trying to run a structural equation model and I am running into problems with testing my primary model. Once I specify everything and try to run it I get this error: Error in eigen(S, symmetric = TRUE, only.values = TRUE) : 0 x 0 matrix And when I look at the object for my primary model in my workspace, which is created after I specify it, it lists all my model components, but has a whole bunch of 'NA' values listed after my components. I have no idea why they are listed there because I omitted all of the 'NA' values from my data and can verify this by a visual inspection. Here is my specified model: # Primary model wellbeing.model - specifyModel() belonging - optimism, path1 autonomy - optimism, path2 optimism - wellbeing, path3 belonging - belonging_hapmar, patha belonging - belonging_attend, pathb belonging - belonging_cowrkint, pathc autonomy - autonomy_overwork, pathd autonomy - autonomy_famwkoff, pathe autonomy - autonomy_hrsrelax, pathf optimism - optimism_confinan, pathg optimism - optimism_goodlife, pathh optimism - optimis_conlegis, pathi wellbeing - wellbeing_happy, pathj wellbeing - wellbeing_health, pathk wellbeing - wellbeing_life, pathl belonging - autonomy, covariance1 autonomy_overwork - autonomy_famwkoff, covariance2 autonomy_overwork - autonomy_hrsrelax, covariance3 autonomy_hrsrelax - autonomy_famwkoff, covariance4 belonging - belonging, variance1 autonomy - autonomy, variance2 optimism - optimism, disturbance1 optimism_confinan - optimism_goodlife, disturbance2 optimism_goodlife - optimism_conlegis, disturbance3 optimism_confinan - optimism_conlegis, disturbance4 wellbeing - wellbeing, disturbance5 wellbeing_happy - wellbeing_health, disturbance6 wellbeing_happy - wellbeing_life, disturbance7 wellbeing_health - wellbeing_life, disturbance8 wellbeing.analysis - sem( wellbeing.model, gss.data.cov, nrow(gss.data_C) ) summary( wellbeing.analysis ) stdCoef( wellbeing.analysis ) effects( wellbeing.analysis ) pathDiagram( wellbeing.analysis, WellbeingPathModel, standardize=TRUE, edge.labels=values ) And here are my model components once specified: structure(c(belonging - optimism, autonomy - optimism, optimism - wellbeing, belonging - belonging_hapmar, belonging - belonging_attend, belonging - belonging_cowrkint, autonomy - autonomy_overwork, autonomy - autonomy_famwkoff, autonomy - autonomy_hrsrelax, optimism - optimism_confinan, optimism - optimism_goodlife, optimism - optimis_conlegis, wellbeing - wellbeing_happy, wellbeing - wellbeing_health, wellbeing - wellbeing_life, belonging - autonomy, autonomy_overwork - autonomy_famwkoff, autonomy_overwork - autonomy_hrsrelax, autonomy_hrsrelax - autonomy_famwkoff, belonging - belonging, autonomy - autonomy, optimism - optimism, optimism_confinan - optimism_goodlife, optimism_goodlife - optimism_conlegis, optimism_confinan - optimism_conlegis, wellbeing - wellbeing, wellbeing_happy - wellbeing_health, wellbeing_happy - wellbeing_life, wellbeing_health - wellbeing_life, belonging_hapmar - belonging_hapmar, belonging_attend - belonging_attend, belonging_cowrkint - belonging_cowrkint, autonomy_overwork - autonomy_overwork, autonomy_famwkoff - autonomy_famwkoff, autonomy_hrsrelax - autonomy_hrsrelax, optimism_confinan - optimism_confinan, optimism_goodlife - optimism_goodlife, optimis_conlegis - optimis_conlegis, wellbeing_happy - wellbeing_happy, wellbeing_health - wellbeing_health, wellbeing_life - wellbeing_life, path1, path2, path3, patha, pathb, pathc, pathd, pathe, pathf, pathg, pathh, pathi, pathj, pathk, pathl, covariance1, covariance2, covariance3, covariance4, variance1, variance2, disturbance1, disturbance2, disturbance3, disturbance4, disturbance5, disturbance6, disturbance7, disturbance8, V[belonging_hapmar], V[belonging_attend], V[belonging_cowrkint], V[autonomy_overwork], V[autonomy_famwkoff], V[autonomy_hrsrelax], V[optimism_confinan], V[optimism_goodlife], V[optimis_conlegis], V[wellbeing_happy], V[wellbeing_health], V[wellbeing_life], NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), .Dim = c(41L, 3L), class = semmod) I have no idea where the 'NA' values are coming from. Any help would be most appreciated! - Jessica -- View this message in context: http://r.789695.n4.nabble.com/SEM-eigen-value-error-0-X-0-matrix-tp4465139p4465139.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Idea/package to linearize a curve along the diagonal?
Aren't you just reinventing the inverse of a function? --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. Emmanuel Levy emmanuel.l...@gmail.com wrote: Hi, I am trying to normalize some data. First I fitted a principal curve (using the LCPM package), but now I would like to apply a transformation so that the curve becomes a straight diagonal line on the plot. The data used to fit the curve would then be normalized by applying the same transformation to it. A simple solution could be to apply translations only (e.g., as done after a fit using loess), but here rotations would have to be applied as well. One could visualize this as the stretching of a curve, i.e., during such an unfolding process, both translations and rotations would need to be applied. Before I embark on this (which would require me remembering long forgotten geometry principles) I was wondering if you can think of packages or tricks that could make my life simpler? Thanks for any input, Emmanuel Below I provide an example - the black curve is to be brought along the diagonal, and all data points normal to a small segment (of the black curve) would undergo the same transformation as it - what small is remains to be defined though. tmp=rnorm(2000) X.1 = 5+tmp Y.1 = 5+ (5*tmp+rnorm(2000)) tmp=rnorm(1000) X.2 = 9+tmp Y.2 = 40+ (1.5*tmp+rnorm(1000)) X.3 = 7+ 0.5*runif(500) Y.3 = 15+20*runif(500) X = c(X.1,X.2,X.3) Y = c(Y.1,Y.2,Y.3) lpc1 = lpc(cbind(X,Y), scaled=FALSE, h=c(1,1) ) plot(lpc1) __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] ggplot2: coord_polar
Hello HelpeRs, The last print statement in the code segment below results in : Error in data$x[data$x == -Inf] - range$x.range[1] : replacement has length zero R version 2.14.1 Patched (2011-12-23 r57982) ggplot2: version 0.90 OS : Linux (64bit) Any thoughts? Many Thanks, A. ## code segment starts here df - data.frame( trt = factor(c(1, 1, 2, 2)), resp = c(1, 5, 3, 4), group = factor(c(1, 2, 1, 2)), se = c(0.1, 0.3, 0.3, 0.2) ) df2 - df[c(1,3),] limits - aes(ymax = resp + se, ymin=resp - se) dodge - position_dodge(width=0.9) p - ggplot(df2, aes(fill=group, y=resp, x=trt)) p - p + geom_bar(position=dodge) # This is OK print(p) # This is OK print(p + coord_polar()) p - p + geom_errorbar(limits, position=dodge, width=0.25) # This is OK print(p) # Error at the next statement print(p + coord_polar()) [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] How to plot diagonal line at any coordinate range in R
Dear expert How can we plot diagonal across (from bottom-left-hand corner to top right-hand corner), at any given coordinate range For example plot(c(-2,3), c(-1,5), type = n, xlab=x, ylab=y, asp = 1) or plot(c(0,1000), c(0,334), type = n, xlab=x, ylab=y, asp = 1) I tried abline with the following but failed: abline(0,1,col=red) - G.V. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] How to plot diagonal line at any coordinate range in R
Your requirement that the line go from bottom-left to top-right regardless of the coordinates is inconsistent with a slope of 1. Are you sure that is your requirement? --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. Gundala Viswanath gunda...@gmail.com wrote: Dear expert How can we plot diagonal across (from bottom-left-hand corner to top right-hand corner), at any given coordinate range For example plot(c(-2,3), c(-1,5), type = n, xlab=x, ylab=y, asp = 1) or plot(c(0,1000), c(0,334), type = n, xlab=x, ylab=y, asp = 1) I tried abline with the following but failed: abline(0,1,col=red) - G.V. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Re : How to plot diagonal line at any coordinate range in R
Hi G.V. Does it fit to your request? plot(c(-2,3), c(-1,5), type = n, xlab=x, ylab=y, asp = 1) dg - par(usr) segments(dg[1],dg[3],dg[2],dg[4], col='red') Regards, Pascal - Mail original - De : Gundala Viswanath gunda...@gmail.com À : r-h...@stat.math.ethz.ch Cc : Envoyé le : Lundi 12 mars 2012 14h15 Objet : [R] How to plot diagonal line at any coordinate range in R Dear expert How can we plot diagonal across (from bottom-left-hand corner to top right-hand corner), at any given coordinate range For example plot(c(-2,3), c(-1,5), type = n, xlab=x, ylab=y, asp = 1) or plot(c(0,1000), c(0,334), type = n, xlab=x, ylab=y, asp = 1) I tried abline with the following but failed: abline(0,1,col=red) - G.V. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.