Re: [R] Data Rearrangement

Hi Did you try what I had suggested? In what aspect it does not fulfil your request? Petr From: dila radi [mailto:dilarad...@gmail.com] Sent: Friday, February 28, 2014 9:25 AM To: PIKAL Petr Subject: Re: [R] Data Rearrangement Dear Petr, Im so sorry for the inconvenience caused by the data.

[R] OrchardSprays reference

Dear all, Does anyone have a PDF of the classic OrchardSprays reference (data(OrchardSprays)): C. G. Butler, D. J. Finney, P. Schiele (1943) Experiments on the poisoning of honeybees by insecticidal and fungicidal sprays used in orchards. Ann Appl Biol 30:143–150. Thanks very much and best

Re: [R] expressions (nesting, substitution, 2-stage evaluation)

David: Oh yes! That is certainly the right way. Much better than what I suggested. I actually first thought about doing this, but didn't get the form right (I wanted to substitute within the expression, rather than substituting the whole expression).Of course,one can always use bquote() instead

[R] Conditional polygon colouring

Dear R users I want to paint parts of a polygon with different colours conditional to values of the variable. Example: f-seq(1,33) g-sin(f) i-rep(0,33) ff-c(f,rev(f)) gg-c(g,rev(i)) plot(ff,gg,type=n) polygon(ff,gg,col=2) # but I wanted to plot areas below and above the x-axis with different

Re: [R] expressions (nesting, substitution, 2-stage evaluation)

e.g. this doesn't work: vectorA = c( bquote(TNF-*alpha), bquote(IFN-*gamma) ) for(ii in vectorA) { plot(0:1,0:1) title(main = paste(asdfsadf,ii)) } Use bquote's .() operator in the call to plot() or title(), as in: par(mfrow=c(2,1)) for(ii in vectorA) {

Re: [R] Conditional polygon colouring

The simplest way is to use clip(): clip(0, 33, -1, 0) polygon(ff,gg,col=2) clip(0, 33, 0, 1) polygon(ff,gg,col=4) - David L Carlson Department of Anthropology Texas AM University College Station, TX 77840-4352 -Original Message- From:

[R] logit estimation is not convergent!

Dear all, I estimate a logit model with the function glm and I have estimation not convergent. Is it possible to increase the maximal number of iterartion in the function glm? Or any other suggestion? Thanks! Mei-Yuan Chen Department of Finance National Chung Hsing University Taichung,

[R] Solving Classification problems in R

Dear all, I would like some advices on R packages to solve classification problems. I have tried to search among the Task views, but couldn't find anything. Can somebody recommend me some packages? Some of the features I am looking for: - deal with multiple classes - use customized cost

Re: [R] Solving Classification problems in R

Focus on MASS, CCA and e1071 packages Brgds, Sergio Il 28/feb/2014 17:47 Luca Cerone luca.cer...@gmail.com ha scritto: Dear all, I would like some advices on R packages to solve classification problems. I have tried to search among the Task views, but couldn't find anything. Can somebody

Re: [R] Solving Classification problems in R

Do you mean supervised or unsupervised classification. If supervised, I have had great success using gradient boosted classification in package gbm. multinomial distribution will get you multiple classes and it will select relevant predictors by itself given the training data. Not sure about the

Re: [R] Data Rearrangement

You actually want cast() from the reshape package, not melt(). I would recommend using dcast() from reshape2, the newer version of reshape. Jean-Olivier Irisson — Université Pierre et Marie Curie Laboratoire d'Océanographie de Villefranche 181 Chemin du Lazaret 06230 Villefranche-sur-Mer Tel: +33

Re: [R] Solving Classification problems in R

Thanks for the advices Sergio and Jean-Olivier. Of course I forgot, but I am interested in supervised classification! I'll go through the packages you suggested to me! Any ideas for Neural Networks and Random Forests instead? Luca Cerone Tel: +34 692 06 71 28 Skype: luca.cerone On Fri, Feb 28,

Re: [R] logit estimation is not convergent!

On 28/02/2014 16:07, mei_yuan wrote: Dear all, I estimate a logit model with the function glm and I have estimation not convergent. Is it possible to increase the maximal number of iterartion in the function glm? Or any other suggestion? Thanks! Yes. See the help page, which refers you to

Re: [R] Solving Classification problems in R

http://cran.r-project.org/web/views/MachineLearning.html for a task view you missed. On 28/02/2014 17:10, Luca Cerone wrote: Thanks for the advices Sergio and Jean-Olivier. Of course I forgot, but I am interested in supervised classification! I'll go through the packages you suggested to me!

Re: [R] how is the model resample performance calculated by caret?

On Fri, Feb 28, 2014 at 1:13 AM, zhenjiang zech xu zhenjiang...@gmail.com wrote: Dear all, I did a 5-repeat of 10-fold cross validation using partial least square regression model provided by caret package. Can anyone tell me how are the values in plsTune$resample calculated? Is that

Re: [R] New to R

Please give a reproducible example. When I run your code I get object 'stocks' not found. So what is stocks? On Thu, Feb 27, 2014 at 11:24 PM, George Katsuras geoka...@hotmail.com wrote: I successfully downloaded and loaded the stockPortfolio and quadprog packages, but when I entered the

Re: [R] Solving Classification problems in R

Now I feel quite stupid :) I was assuming that since there is a Clustering one there would have been a Classification one as well :) Thanks for pointing it out to me! Luca Cerone Tel: +34 692 06 71 28 Skype: luca.cerone On Fri, Feb 28, 2014 at 6:38 PM, Prof Brian Ripley rip...@stats.ox.ac.uk

[R] Importance Sampling and a bunch of questions

I have gone through quite a few papers but they all fail to give me the intuition. So i posted here : http://stackoverflow.com/questions/22060675/r-monte-carlo-integration-using-importance-sampling/22064557?noredirect=1#22064557 and here (CrossValidated):

[R] stepAIC with lm

Hi everybody,I'm a beginner in R so this question it could may simple for u (I hope it).I need to study the interaction between 4 independent variables (x1, x2, x3, x4) and a dependent variable (y). So I've used a list of regression models (using the lm function) as:REGR.LIN-lm(y~0+x1+x2+x3+x4)now

[R] do calculation within expression(), text in plot

Dear Helpers, I would like to add some text to my plot, containing a variable and the calculated value for the variable. As I would like to produce many plots, I hope this can be done automatically. Unfortunately I can't get R to do the calculation for cor(nou,dak) when

[R] pivot table

hi..i would create a pivot table in R and i would create two levels of columns. I'll try to explain better. I have a table so done: id agency offer month product 1 aL gen star 2 bM feb meteor 3

[R] include sql statements

Hi, first of all: I am new to R. Anyway, I would like to include sql files in my r-script, which I load via source(scriptname) in the CLI. The sql files (i.e. stmt.sql) contains select statements with joins, line breaks, various characters, they can be quite long. My question is, is there a way

[R] Map plotting in a box

Hi everyone, I am using the script below to create a map plot of Ireland.

[R] Saving a map as a postscript file

Hi all, I am running the script below to produce a map. The problem I am having is saving it as a postscript file. A postscript file is created, but it is blank. I have also run this is linux (with different paths) and I get the same thing (blank postscript file). Does anyone know how to do

[R] (no subject)

Hai There are in the r package called poLCA and this package using the latent class. Is there a package to resolve latent profile and what and how we can support the answer with an example Thank you [[alternative HTML version deleted]] __

Re: [R] Data Rearrangement

HI Dila, You have to order it afterwards. res - transform(melt(dat,id.var=c(Year,Day)),Month=match(variable,month.abb),Amount=value)[,-c(3:4)] res1 - res[with(res,order(Year,Month,Day)),] A.K. On Friday, February 28, 2014 2:16 AM, dila radi dilarad...@gmail.com wrote: Dear Arun, Thank you

[R] sub function problem

Dear all, I write a R function that it should handles strings like removing spaces at the beginning or returning NA according an IF condition. Here you are the code: corregge.CF - function(stringa){ nc - nchar(stringa) stringa - sub(^ , , stringa) stringa - sub( +$, , stringa) if

[R] Points to spatial polygons

Hi All, With the risk of asking an obvious question: I have use the following code to generate hexagonal tessellation: lambertCRS-+proj=laea coords1-matrix(c(-30,31,-30,80,50,80,50,31,-30,31),ncol=2, byrow=TRUE) coords=project(coords1,lambertCRS) pg=Polygon(coords) HexPts=spsample(pg,

Re: [R] include sql statements

On 28/02/2014 5:16 AM, Streng Ge-heim wrote: Hi, first of all: I am new to R. Anyway, I would like to include sql files in my r-script, which I load via source(scriptname) in the CLI. The sql files (i.e. stmt.sql) contains select statements with joins, line breaks, various characters, they can

Re: [R] do calculation within expression(), text in plot

Unfortunately I can't get R to do the calculation for cor(nou,dak) when I use expression().. text(0,2.2,expression(paste(r[Pearson],=, cor(nou,dak) , sep= )),pos=4, cex=1.5) Use bquote() and its .() operator, as in with(mtcars, { plot(wt, mpg) text(4, 30,

Re: [R] data.frmae : Error: unexpected numeric constant in:

I used copy -paste. I will try to find the mistake. I know the source , but is is more complicated, because I have to define the hierarchical structure of the table before I load this 6000 or more records, then I fill in the table whit this frequencies. Thanks Bea 2014-02-28 0:19 GMT+01:00

[R] which(rsts$date2011-03-01)

Hello, I have a dataframe called rsts. It looks like this: head(rsts) date Value 1 2012-08-0745 2 2013-11-1047 3 2014-01-2828 4 2013-10-2250 5 2013-06-1335 6 2013-05-2832 where I ran as.Date(date) to get the date column as date objects. I tried this:

Re: [R] which(rsts$date2011-03-01)

You need to write: rstst=rsts[-which(rsts$dateas.Date('2011-03-01')),] Here is what you had as the expression since it was not a Date object: 2011-03-01 [1] 2007 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

Re: [R] pivot table

Is this what you want: x id agency offer month product 1 1 a L genstar 2 2 b M feb meteor 3 3 c N genmoon 4 4 d O marchmoon require(reshape2) dcast(x, agency + offer ~ product, fun = length) Using product as value column: use

Re: [R] Solving Classification problems in R

I did forget that reading LDA package could also help Sergio Il 28/feb/2014 19:39 Luca Cerone luca.cer...@gmail.com ha scritto: Now I feel quite stupid :) I was assuming that since there is a Clustering one there would have been a Classification one as well :) Thanks for pointing it out to

[R] aggregate and sum on some columns fromduplicate rows

Hi list, I have a dataframe df looking like this one: St.SamSpVar1 Var2NTPT ST1.S1Sp112aa2032 ST1.S1Sp232bb4526 ST1.S1Sp112aa 3 5 ST1.S1Sp347cc8935 ST1.S2Sp125dd2966 ST1.S2Sp2

Re: [R] Saving a map as a postscript file

On Feb 28, 2014, at 8:22 AM, Ciara O'Hara wrote: Hi all, I am running the script below to produce a map. The problem I am having is saving it as a postscript file. A postscript file is created, but it is blank. I have also run this is linux (with different paths) and I get the same

Re: [R] aggregate and sum on some columns fromduplicate rows

Hi again, Sorry for disturbing. After posting I suddenly found a solution. As it may help someone else here it goes. df du1 - duplicated(df[,c(St.Sam,Species)],fromLast = F) du2 - duplicated(df[,c(St.Sam,Species)],fromLast = T) X - df[du1|du2,] aggRows - aggregate(cbind(NT,PT)

Re: [R] Map plotting in a box

On 01/03/14 03:53, Ciara O'Hara wrote: Hi everyone, I am using the script below to create a map plot of Ireland.

Re: [R] aggregate and sum on some columns fromduplicate rows

Hi, You could use ?ddply library(plyr) cbind(ddply(dat,.(St.Sam,Sp),function(x) x[!duplicated(x$Var1),])[,-c(5:6)],ddply(dat,.(St.Sam,Sp),colwise(sum,.(NT,PT)))[,-c(1:2)])    St.Sam  Sp Var1 Var2 NT PT 1  ST1.S1 Sp1   12   aa 23 37 2  ST1.S1 Sp2   32   bb 45 26 3  ST1.S1 Sp3   47   cc 89 35 4 

[R] Problem importing file in R after switching from windows to Ubuntu

Dear R List, today i have installed Ubuntu as i decided to give this a try after running R in windows was always running out of memory in making my figures. I have copied my working folders into Ubuntu and changed the WD and the \\ into /. I tried to re run the script and it was going all well

[R] [R-pkgs] new package: hrr version 1.0.1

Dear R users, as I often have to visually divide my R output into blocks, especially when I create R executable scripts, I created hrr in the hope that this simple package might come in handy to you. I released it to CRAN today. It is a simple package to create and print fully customisable

Re: [R] aggregate and sum on some columns fromduplicate rows

If, 'dat' is the dataset: res - as.data.frame(do.call(rbind,lapply(split(dat,list(dat$St.Sam,dat$Sp),drop=TRUE),function(x) c(unlist(x[1,1:4]),colSums(x[,5:6])  row.names(res) - 1:nrow(res) res    St.Sam  Sp Var1 Var2 NT PT 1  ST1.S1 Sp1   12   aa 23 37 2  ST1.S2 Sp1   25   dd 29 66 3 

Re: [R] (no subject)

HI Farnoosh, Try: D1= c(5/25/2012 14:48, 5/29/2012 16:53,  6/1/2012 18:30) D2= c(6/8/2012 21:26, 6/11/2012 15:10 , 6/14/2012 17:57) as.numeric(as.POSIXct(D2,format=%m/%d/%Y %H:%M)-as.POSIXct(D1,format=%m/%d/%Y %H:%M)) #days #[1] 14.27639 12.92847 12.97708 #or

[R] a geographical factor

Hi. I have a dataframe called radSamp which looks like this: head(radSamp[,c(3,4,5)]) Latitude Longitude Value 1 39.16094 140.488345 2 32.84428 -117.224047 3 35.80605 139.378928 4 35.07816 -106.612350 5 35.83174 136.202735 6 34.78944 137.949632 This is radiation

Re: [R] New to R

Hi George, Please keep the R mailing list copied--I've added them back. The example on the webpage you listed is wrong, in a way that would be obvious if you took the time to familiarize yourself with the basics of R. stocks has no names. Best, Ista On Fri, Feb 28, 2014 at 6:45 PM, George

Re: [R] Problem importing file in R after switching from windows to Ubuntu

Hi Christian, I know you've checked many times, but it is very likely that you are not typing the file name correctly, or that the file is not where you think it is. Please run these lines and post the output back here: setwd(~/Documents/DATABASES/Functional_Annotations) list.files() Best, Ista

[R] How to change the label size in axis

Hi everyone, I am using the axis command to draw extra axis on the right. How do I change the text size of the labels as in axis (4, at=c(1:9), labels='some text', las=1). I can't find an argument to change the text size for the labels. Thanks. Jun [[alternative HTML version

Re: [R] Map plotting in a box

On 03/01/2014 01:53 AM, Ciara O'Hara wrote: Hi everyone, I am using the script below to create a map plot of Ireland.

Re: [R] a geographical factor

I'm too lazy to figure out the details of what you are trying to do, but I think it is possible that you might find the facilities of the spatstat package useful and that these might save you some wheel-reinvention. Look in particular at the quadrats(), tess() and im() functions. cheers,

Re: [R] a geographical factor

Hi, Thanks. I see that quadrats, Divides window into rectangular quadrats and returns the quadrats as a tessellation. Do you know what they mean by window? And I saw this: W - square(10) Z - quadrats(W, 4, 5) plot http://inside-r.org/r-doc/graphics/plot(Z) data

Re: [R] How to change the label size in axis

On 03/01/2014 02:08 PM, Jun Shen wrote: Hi everyone, I am using the axis command to draw extra axis on the right. How do I change the text size of the labels as in axis (4, at=c(1:9), labels='some text', las=1). I can't find an argument to change the text size for the labels. Thanks. Hi

[R] Multilevel analysis for ordinal responses

Dear all, I need to fit a multielvel model for an ordinal response. Does R have a command for conducting a multilevel ordinal logistic regression when the model violates the parallel regression or proportional odds assumption? Additionally, are there any tests to check the parallel regression

[R] reshape non-square matrix

Hi list I have a matrix of size m x n (m and n are different, hence non square!) I want to melt it in such a way that I get a df of 3 columns. m ,n and cell value in the original matrix. Any suggestions? -- *Chirag Gupta* Department of Crop, Soil, and Environmental Sciences, 115 Plant Sciences

Re: [R] reshape non-square matrix

On 01/03/14 14:49, Chirag Gupta wrote: Hi list I have a matrix of size m x n (m and n are different, hence non square!) I want to melt it in such a way that I get a df of 3 columns. m ,n Surely you mean i, j (i = 1, ..., m), j = 1, ..., n). and cell value in the original matrix. Yes:

Re: [R] a geographical factor

On 01/03/14 16:36, Bill wrote: Hi, Thanks. I see that quadrats, Divides window into rectangular quadrats and returns the quadrats as a tessellation. Do you know what they mean by window? Yes, I do. And so would you if you read the documentation that comes with spatstat. Perhaps start with

Re: [R] reshape non-square matrix

library(reshape2) mx - matrix( 1:12, nrow=3 ) mxdf - melt( mx ) names( mxdf ) - c( m, n, value ) --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.usBasics: