[R] Re : Re : Sort out number on value

What is the result with  x[x7.5] - Mail original - De : Yellow s1010...@student.hsleiden.nl À : r-help@r-project.org Cc : Envoyé le : Vendredi 20 avril 2012 21h31 Objet : Re: [R] Re : Sort out number on value I found out something strange when I used the same thing on another data

[R] Re : polar.plot add argument

Hi, Without data or script... Regards, Pascal - Mail original - De : Etienne RIFA etienne.r...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Mercredi 18 avril 2012 16h32 Objet : [R] polar.plot add argument Hello I try to create a polar.plot in order to represent some paths. I

[R] Re : image.plot specify colors for range of data points, please help

Hi,  image.plot(x, breaks=c(-100,-1,1,100), col=c('green','black','red')) Regards, Pascal - Mail original - De : David Lyon david_ly...@yahoo.com À : r-help@r-project.org r-help@r-project.org Cc : Envoyé le : Mercredi 18 avril 2012 0h00 Objet : [R] image.plot specify colors for range

[R] Re : Installing Kendall Package

Hello, Did you type 'library(Kendall)'? Regards. - Mail original - De : David Doyle kydaviddo...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Mardi 17 avril 2012 11h34 Objet : [R] Installing Kendall Package I know this is a dumb question but I'm pulling out what little hair I

[R] Re : Double precision calculation

Hi, I think that any web search engine is your friend:   http://rwiki.sciviews.org/doku.php?id=misc:r_accuracy Regards, Pascal De : Christofer Bogaso bogaso.christo...@gmail.com À : r-help@r-project.org Envoyé le : Mardi 10 avril 2012 18h18 Objet : [R]

[R] Re : taylor.diagram from plotrix package

Hi, ?sd ?cor.test ... Regards, Pascal De : anaraster rrast...@gmail.com À : r-help@r-project.org Envoyé le : Mardi 10 avril 2012 22h50 Objet : [R] taylor.diagram from plotrix package Is there a way to access the numeric results (standard deviation and

[R] Re : Spatstat users.

No I am not an active spatstat user __ 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,

[R] Re : Replace NaN with 0

Hi, try ?is.nan Regards - Mail original - De : garima_sharma garima1234sha...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Jeudi 29 mars 2012 18h19 Objet : [R] Replace NaN with 0 I need help with replacing NaN with zero (the value '0') in my dataset. How can I do this?

[R] Re : ROC Analysis

Hi Camille, Probably you have to check wether there is any infinte value in x. Or calculate something like that for your x-axis: x[1:(ll-1)]+diff(x)/2 Regards, Pascal - Mail original - De : Camille Leclerc camille.lecl...@ymail.com À : r-help@r-project.org Cc : Envoyé le : Lundi 26

[R] Re : ROC Analysis

Hi Camille, Does following work? ll - length(x) (TPR[1:(ll-1)]-TPR[2:ll])/(FPR[1:(ll-1)]-FPR[2:ll]) Regards, Pascal -- View this message in context: http://r.789695.n4.nabble.com/ROC-Analysis-tp4469203p4478233.html Sent from the R help mailing list archive at Nabble.com.

[R] Re : Elegant Code

Hi Raphael, Something like that? require(pscl)sim - numeric() for(i in 1:5){   eval(parse(text=paste('b',i,' - rigamma(50,1,1)',sep='')))   eval(parse(text=paste('theta',i,' - rgamma(50,0.5,(1/b',i,'))',sep='')))   eval(parse(text=paste('sim',i,' - rpois(50,theta',1,')',sep='')))  

[R] Re : ncd4 package

Hi, Package ncdf4 is not available for Windows. Regards, Pascal - Mail original - De : Amen amen.alya...@bordeaux.inra.fr À : r-help@r-project.org Cc : Envoyé le : Vendredi 16 mars 2012 16h39 Objet : [R] ncd4 package Hi I am using windows. I cant install ncdf4 package but it didn't

[R] Re : ROC Analysis

Hi Camille, Probably by adding these lines: fpf - unlist(performance(pred,fpr)@y.values) fnf - unlist(performance(pred,fnr)@y.values) pLhood - tpf/fpf   # Positive Likelihood Ratio nLhood - fnf/tnf   # Negative Likelihood Ratio par(mfrow=c(1,2)) plot(x, pLhood, t='l', xlab='Value',

[R] Re : ROC Analysis

Hi Camille, Do you need something like that? ### library(ROCR) data(ROCR.simple) pred - prediction(ROCR.simple$predictions, ROCR.simple$labels) tpf - unlist(performance(pred,tpr)@y.values) tnf - unlist(performance(pred,tnr)@y.values) x - rev(unlist(pred@cutoffs)) plot(x,

[R] Re : sum(hist$density) == 2 ?!

Hi Sam, ?hist gives: density     values f^(x[i]), as estimated density values. If all(diff(breaks) == 1), they are the relative frequencies counts/n and in general satisfy sum[i; f^(x[i]) (b[i+1]-b[i])] = 1, where b[i] = breaks[i]. 1st case,  density != frequency because all(diff(breaks) ==

[R] Re : ROC Analysis

Hi Camille, I am surprised by your answer. If you do: pred - prediction(ROCR.simple$predictions*1000, ROCR.simple$labels) x - rev(unlist(pred@cutoffs)) You can see than x values are now between 0 and 1000. So, it should be probably the same for your data. Regards, Pascal -- View this

[R] Re : gplots packages does not work

Hi Fernando, You have to reinstall package 'bitops' too. Regards, Pascal - Mail original - De : Fernando Pistón fpis...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Mardi 13 mars 2012 16h10 Objet : [R] gplots packages does not work I had installed de gplots package and then I

[R] Re : gplots packages does not work

Hi Fernando, To me, it is a good idea to regularly check the availability of update for installed packages, using 'update.packages()'. Regards, Pascal - Mail original - De : Fernando Pistón Pistón fpis...@ias.csic.es À : Steve Lianoglou mailinglist.honey...@gmail.com Cc :

[R] Re : A question on histogram - area much less than 1

Hi Miao, With option freq=FALSE, the function hist calculates densities, i.e. in your case, counts/total/length in-between breaks. h - hist(Y1, breaks=seq(0, 350, by=35),freq=FALSE) If you calculate:  h$counts/sum(h$counts)/35 = h$density Regards, Pascal - Mail original - De : jpm

[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

[R] Re : Problem with a Matrix

Hi Hamada, Could the following be helpful? dtf is your data.frame  nr - nrow(dtf) new.dtf - data.frame(Site.No=seq(1,nr/2)) new.dtf$XXX - dtf[seq(1,nr,2),3] new.dtf$YYY - dtf[seq(2,nr,2),3] or new.mat - numeric() new.mat - cbind(new.mat,dtf[seq(1,nr,2),3]) new.mat -

[R] Re : Re : Adding mean line to a lattice density plot

, not the x-axis scale. Thus, plottingat v='mean' won't work... Any suggestions? Kind regards, Kimmo 08.03.2012 09:49, Pascal Oettli wrote: Hi Kimmo, You can try to use the layer function from latticeExtra library: densityplot(~PV1CIV, groups=SGENDER, data=ISGFINC2,     lwd=2, col=1, lty=c

[R] Re : Moving average with loess

Hi Robert, You can try ?lowess Regards, Pascal - Mail original - De : Faryabi, Robert (NIH/NCI) [F] babak.fary...@nih.gov À : r-help@r-project.org r-help@r-project.org Cc : Envoyé le : Vendredi 9 mars 2012 8h43 Objet : [R] Moving average with loess Hello All, I just have a very

[R] Re : how to see inbuilt function(cor.test) how to get p-value from t-value(test of significance) ?

Hi, Please take a look at http://svn.r-project.org/R/trunk/src/library/stats/R/cor.test.R Pascal - Mail original - De : sagarnikam123 sagarnikam...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Mercredi 7 mars 2012 15h36 Objet : [R] how to see inbuilt function(cor.test) how to

[R] Re : Changing the size of a plot

Hi, Before your plot:    x11(width=x, height=y) In your .Rprofile (Linux) or Rprofile.site (Windows):   setHook(packageEvent(grDevices, onLoad), function(...) grDevices::X11.options(width=x, height=y))  where x and y are values you give for width and height of the window plot. Regards, Pascal

[R] Re : Problems with generalized linear model (glm) coefficients.

Hi Lucas, Do you apply your analysis in time or in space? Regards, Pascal   - Mail original - De : Lucas lpchaparro...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Mercredi 7 mars 2012 22h34 Objet : [R] Problems with generalized linear model (glm) coefficients. Hello to

[R] Re : repositories for 2.11 2.12

Hi Miklos, Probably you will have to use R CMD install and archive from http://cran.r-project.org/web/packages/ggplot2/index.html Regards, Pascal - Mail original - De : Miklós Emri e...@pet.dote.hu À : r-help@r-project.org Cc : Envoyé le : Mercredi 7 mars 2012 21h59 Objet : [R]

[R] Re : Re : Problems with generalized linear model (glm) coefficients.

Hi Lucas, Do you get the same sign using lm instead of glm? Regards, Pascal De : Lucas lpchaparro...@gmail.com À : Pascal Oettli kri...@ymail.com Cc : r-help@r-project.org r-help@r-project.org Envoyé le : Mercredi 7 mars 2012 23h02 Objet : Re: Re : [R

[R] Re : ADL in auto.arima [SEC=UNOFFICIAL]

Hi Richard, Could you provide a reproducible example? Regards, Pascal De : GAO  Richard richard@customs.gov.au À : r-help@r-project.org Envoyé le : Jeudi 8 mars 2012 10h10 Objet : [R] ADL in auto.arima [SEC=UNOFFICIAL] Hi, I am trying to run ADL model

[R] Cross-Power Spectral Density and Welch's Method

Hello to R uers, I am wondering if there is an easy way to perform a cross-power spectral density estimation of  two timeseries (x and y) using the Welch's method. Both packages bspec and oce provide a function to calculate the PSD with the Welch's method, but only for a timeserie. Thank you

[R] Re : legend

Hi Chintanu, Try this: legend (locator(1), Important ones, box.col=NA) Regards, Pascal - Mail original - De : Chintanu chint...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Jeudi 8 mars 2012 14h52 Objet : [R] legend Hi, A very simple thing that I'm unable to do. I did look

[R] Re : Doing Mathematica Quantile[] function in R

Hi Vihan, Perhaps quantile in stats package... Type ?quantile, you will get a lot of informations. Regards, Pascal - Mail original - De : Vihan Pandey vihanpan...@gmail.com À : r-help@r-project.org Cc : Envoyé le : Jeudi 8 mars 2012 15h08 Objet : [R] Doing Mathematica Quantile[]

[R] Re : Adding mean line to a lattice density plot

Hi Kimmo, You can try to use the layer function from latticeExtra library: densityplot(~PV1CIV, groups=SGENDER, data=ISGFINC2,   lwd=2, col=1, lty=c(1,2), pch=c(+,o),   key=list(text=list(lab=levels(ISGFINC2$SGENDER), col=1),   space=bottom, columns=2, border=T, lines=T, lwd=2,   lty=c(1,2),

[R] Re : percentile of a given value: is there a reverse quantile function?

Hi Felix, Have a look at ?pnorm and ?qnorm. And at ?Distributions Regards, Pascal - Mail original - De : drflxms drfl...@googlemail.com À : r-help@r-project.org Cc : Envoyé le : Samedi 3 mars 2012 21h37 Objet : [R] percentile of a given value: is there a reverse quantile function?

Re: [R] Does anyone knows a KMeans ++ package for R?

Dear Rui, What ++ means? There is kmeans in stats package. Best Regards, Pascal Le 29/02/2012 19:20, Rui Esteves a écrit : Dear all. I am searching for KMeans ++ for R. I cannot find it. Do you know any package with it? Best regards, Rui __

Re: [R] Does anyone knows a KMeans ++ package for R?

clustering algorithm. It was proposed in 2007 by David Arthur and Sergei Vassilvitskii, as an approximation algorithm for the NP-hard k-means problem—a way of avoiding the sometimes poor clusterings found by the standard k-means algorithm. On Wed, Feb 29, 2012 at 11:33 AM, Pascal Oettli oet...@eps.s.u

[R] Re : Create a function automatically from lm formula and coefficients?

Hi Keith, Do you mean as predict.lm can do? Regards, Pascal De : Keith Weintraub kw1...@gmail.com À : r-help@r-project.org Envoyé le : Jeudi 1 mars 2012 11h41 Objet : [R] Create a function automatically from lm formula and coefficients? I hope the subject

[R] Coverage probability for the normal distribution in plot.spec.coherency function.

Hello to the members of the list, I am using the 'spectrum' function from 'stats' package, to calculate the squared coherency between two time series. The function 'plot.spec.coherency' provides information for the coverage probability for the normal distribution. It seems that the

<    1   2   3   4   5