similar to: Cross-validation

R users, I have a problem with function strwidth in 2.7.1. I'm trying to set the plot margins in a way that horizontal column labels will fit to the graph. tmp.t is a list of data.frame objects. This code works well in 2.6.0. ...snip.. library(gplots) for (i in names(tmp.t)) { bmp(filename=paste(i, "_", Sys.Date(), ".bmp", sep=""), width=1038,

I am writing a report using Sweave with specific R output incorporated into the text using the Sexpr{} command. I have run into two specific issues: 1) If the result inside the Sexpr{} command is an integer less than 10 I would like to print the ?word? for that number ? e.g., ?seven? for 7. 2) If a p-value is ?equal to zero? to some arbitrary number of decimal places -- e.g.,

Hi, after upgrading my R install from 2.5 -> 2.6.1 and performing multiple iterations of update.packages(), I am getting an odd error when trying to plot a calibration curve from the val.prob() function in package Design. when running this function (which used to work) I get the following error message: Error in .C("lowess", x = as.double(xy$x[o]), as.double(xy$y[o]), n,

I have produced a series of graphs with the png command, however when I have finally printed these out the black text appears to have a colour shadow with blue or red on either side of the letter. I tried increasing my res to 1200 and this improved it somewhat, but the text is still not sharp and occassionally these "shadows" will still print. I initially thought this was an issue with

I have found Sweave() to be great for producing PDF documents. I have been experimenting with RweaveHTML (from the R2HTML) package and have had moderate success. My main issue has been that I simply want the R output to be shown verbatim in the HTML document but RweaveHTML tends to convert most output to a table, for example. So, is there a way to force the RweaveHTML driver to simply provide

Hello, I have the following function that receives a "function pointer" formal parameter name "fnc": loocv <- function(data, fnc) { n <- length(data.x) score <- 0 for (i in 1:n) { x_i <- data.x[-i] y_i <- data.y[-i] yhat <- fnc(x=x_i,y=y_i) score <- score + (y_i - yhat)^2 } score <- score/n

Hy, I got the following problem when trying to build a rpart model and using everything but LOOCV. Originally, I wanted to used k-fold partitioning, but every partitioning except LOOCV throws the following warning: ---- Warning message: In nominalTrainWorkflow(dat = trainData, info = trainInfo, method = method, : There were missing values in resampled performance measures. ----- Below are some

Hi, Newbie question about the pls package. Setup: Mac OS 10.3.9 R: Aqua GUI 1.01, v 2.0.1 I want to get R^2 and Q^2 (LOO and Leave-10-Out) values for each component for my model. I was running into a few problems so I played with the example a little and the results do not match up with the comments in the help pages. $ library(pls) $ data(NIR) $ testing.plsNOCV <- plsr(y ~ X, 6, data =

I'm seeing some strange behavior while using the snow package for networked computers. I believe it's caused by name space resolution issues, and would appreciate any suggestions tracking it down. First, is there a way to find out what frame (as in frames in environments, not data frames) a name is being obtained from or put into? Second, how closely does the evaluation environment in

Dear R helpers I'm attempting to create a matrix of scatterplots with X-Y mean lines and regression lines added to each plot in the matrix. I have managed to create the first plot I would like using scatterplot but have run into an odd result when I use par() to set up the page to take multiple plot. Specifically, the mean and regression lines appear to plot in the second plot window, not

How to select the number of PLS components for GPLS for data sets with few samples? Concrete problem: My data set: 9 samples of class A and 37 of class B with 254 descriptors. In the paper: "Classification Using Generalized Partial Least Squares", Beiying Ding, Robert Gentleman, Bioconductor Project Working Papers, year 2004, paper 5 Section 2.6 Assessing Prediction: Cite:

Using R 1.7.0 I get * checking parcv-manual.tex ... ERROR Could not create DVI version. Although there is no apparent error. The dvi file exists. Possibly there is some problem with my TeX setup, but the following messages don't suggest that either. Here's the full log, which does show some documentation issues: sheep:~$R CMD check --library=.R/library/ src/parcv * checking for working

I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err <- function( formu=NULL, data=NULL ){ cost.fn <- function(cl, pred) mean( abs(cl-pred) > 0.5 ) glmfit <- glm(

Seems crossval from library(bootstrap) can only be used for leave-one-out and k-fold cross validation? Here is a dumb question, suppose n=80, how to do exactly leave-50-out cross validation? K-fold cross validation is not eligible for this case since n/ngroup is not an integer. Thanks!

The function crossval (in library bootstrap) works well for the first degree polynomial model, but in the case of the second degree model I got an error message (see below). I would be very greatfull if somebody could give some advices for the following: > library(bootstrap) > > x<-c(22,23.4,24.9,28.5,29.8,31.6,34.2,36.4,37.7,39) >

Dear all, not really a R question but: If I want to check for the classification accuracy of a LDA with previous PCA for dimensionality reduction by means of the LOOCV method: Is it ok to do the PCA on the WHOLE dataset ONCE and then run the LDA with the CV option set to TRUE (runs LOOCV) -- OR-- do I need - to compute for each 'test-bag' (the n-1 observations) a PCA

I have tried installing the package (ROCR) with this command: Install.packages(ROCR) And with this command on the command line R CMD INSTALL ROCR_1.0-4.tar.gz But both times I get exactly the same error shown below, I don't understand what is wrong, is this an error in the package code? Thank you Philip probinson@bioinform08:/tmp/RtmpO0rFbx/downloaded_packages$ R CMD

Good afternoon. I would like to know if there is any function in R to do LOOCV with these classifiers: 1)SVM 2)Neural Networks 3)C4.5 ( J48) 4)KNN Thanks a lot! [[alternative HTML version deleted]]

Hi all, Has anyone tried to do k-fold cross validation for flexible discriminant analysis ( mda library), for example, using crossval() in bootstrap? The problem is that the function crossval() requires a separate matrix for predictors and another for responses, whereas the function fda(), using the formula argument only. Is there another way of doing k-fold cross validation for functions which

Full_Name: Gustaf Rydevik Version: 2.7.1 OS: Win XP professional Submission from: (NULL) (130.237.97.254) The following lines of code crash R 2.7.1 (=cause R to show "The R gui has encountered a problem and needs to close"....). Replicated on two WinXp professional machines, as well as by Uwe Ligges. > sessionInfo() R version 2.7.1 (2008-06-23) i386-pc-mingw32 locale: