similar to: Help for using nnet in R for NN training and testing

I am trying to implement a simple r-svm example using the iris data (only two of the classes are taken and data is within the code). I am running into some errors. I am not an expert on svm's. If any one has used it, I would appreciate their help. I am appending the code below. Thanks../Murli ####################################################### ### R-code for R-SVM ### use leave-one-out

Hello, I have two questions. The svmpath package provides a svmpath function: --- fit <- svmpath(xtrain, ytrain, kernel.function = radial.kernel, param.kernel = 0.8) --- 1) How to get the optimal lambda value out of this result? The svmpath package also provides a predict function: --- ytest <- predict(fit, xtest) --- How to get a score (or a probability of belonging to one of the two

Dear list I am using the mvr function of the package pls.pcr to compute PLS resgression using a X matrix of gene expression variables and a Y matrix of medical varaibles. I would like to obtain the R2 (sum of squares captured by the model) and Q2 (proportion of total sum of squares captured in leave-one-out cross validation) of the model. I am not sure if there are specific slots in the

Dear members, My name is Seungho Huh. I am a statistician who tries to use the Kernel PLS method in a classification problem. I am sending this email to ask you something about the "kernelpls" function in R (pls.pcr package). I would like to obtain the predicted Y values for test data, using the Kernel PLS method. Let's take the example in the R help: > data(NIR) >

Hey! How do I get the confusion matrix after performing 10-fold cross validation from SVM in R? When I try to print it, I get the confusion matrix without cross validation. I need to compute PPV. Should I report PPV without CV and total accuracy with CV? I am confused. > svmtrain <- svm(xtrain,ytrain,kernel="sigmoid",cross=10) > pred <- predict(svmtrain, xtrain) >

You need to do some extra work if you want to do classification with a regression method. One simple way to do classification with PLS is to code the classes as 0s and 1s (assuming there are only two classes) or -1s and 1s, fit the model, then threshold the prediction; e.g., those with predicted values < 0.5 (in the 0/1 coding) get labeled as 0s. There's a predict() method for mvr

I use the svm package kernlab .I have two question. In R library(kernlab) m=ksvm(xtrain,ytrain,type="C-svc",kernel=custom function, C=10) alpha(m) alphaindex(m) I can get alpha value and alpha index about package. 1. Assumption that number of sample are 20. number of support vectors are 15. then rest 5`s alphas are 0? 2. I want use kernelMatrix xtrain=as.matrix(xtrain)

Hi, I am writing to seek some guidance regarding using Lasso regression with the R package LARS. I have introductory statistics background but I am trying to learn more. Right now I am trying to duplicate the results in a paper for shRNA prediction "An accurate and interpretable model for siRNA efficacy prediction, Jean-Philippe Vert et. al, Bioinformatics" for a Bioinformatics project

Hello, I'm using recursive SVM script (rSVM - http://www.stanford.edu/group/wonglab/RSVMpage/R-SVM.html ) on some microarray data. The data to be input are log2, as numeric matrix w/ attributes -- str(svm_num_mat) num [1:10, 1:12340] 13.1 13.1 13.1 13.1 13.0 ... - attr(*, "dimnames")=List of 2 ..$ : chr [1:10] "rma_log2_con_sample_1"

Hello, together I'm trying to use user defined kernel. I know that kernlab offer user defined kernel(custom kernel functions) in R. I used data spam including package kernlab. (number of variables=58 number of examples =4061) i'm user defined kernel's form, kp=function(d,e){ as=v*d bs=v*e cs=as-bs cs=as.matrix(cs) exp(-(norm(cs,"F")^2)/2) }

Hello, I have a classification tree. I want to obtain a ROC curve for this test. What is the easiest way to obtain one? -Anjali --------------------------------- [[alternative HTML version deleted]]

I'm puzzled by as.matrix. It appears to work differently for Surv objects. Here is a session from my computer: tmt% R --vanilla > library(survival) Loading required package: splines > ytest <- Surv(1:3, c(1,0,1)) > is.matrix(ytest) >[1] TRUE > attr(ytest, 'type') [1] "right" > attr(as.matrix(ytest), 'type') [1] "right" >

The standard errors produced by predict.glm with type = "response" seem wrong. Here is an example using R 1.2 windows version along with the same problem in Splus. The standard errors for type = "link" are the same in both systems. R1.2> set.seed(10) R1.2> ytest <- 100*.95^(0:9) + rnorm(10,sd = 5) R1.2> ytest [1] 103.96964 97.60590 88.43220 85.90504

Dear R-users, While making a prediction using the randomForest function (package randomForest) I'm getting the following error message: "Error in predict.randomForest(model, newdata = CV) : No forest component in the object" Here's my complete code. For reproducing this task, please find my 2 data sets attached ( http://www.nabble.com/file/p17855119/data.rar data.rar ).

Hi, I am using errorest function from ipred package. I am hoping to perform "bootstrap 0.632+" and "bootstrap leave one out". According to the manual page for errorest, i use the following command: ce632[i]<-errorest(ytrain ~., data=mydata, model=lda, estimator=c("boot","632plus"), predict=mypredict.lda)$error It didn't work. I then tried the

Hi, here are three results of random forest (version 4.0-1). The results seem to be more or less the same which is strange because I changed the classwt. I hoped that for example classwt=c(0.45,0.1,0.45) would result in fewer cases classified as class 2. Did I understand something wrong? Christian x1rf <- randomForest(x=as.data.frame(mfilters[cvtrain,]),

Dear R-help, I was bitten by the behavior of all() when given logical(0): It is TRUE! (And any(logical(0)) is FALSE.) Wouldn't it be better to return logical(0) in both cases? The problem surfaced because some un-named individual called randomForest(x, y, xtest, ytest,...), and gave y as a two-level factor, but ytest as just numeric vector. I thought I check for that in my code by testing

Hi all, Can some one tell me the difference between the following two formulas? 1. epiG.rf <-randomForest(gamma~.,data=data, na.action = na.fail,ntree = 300,xtest = NULL, ytest = NULL,replace = T, proximity =F) 2.epiG.rf <-randomForest(gamma~.,data=data, na.action = na.fail,ntree = 300,xtest = NULL, ytest = NULL,replace = T, proximity =F) [[alternative HTML version deleted]]

Sir, This query is related to randomForest regression using R. I have a dataset called qsar.arff which I use as my training set and then I run the following function - rf=randomForest(x=train,y=trainy,xtest=train,ytest=trainy,ntree=500) where train is a matrix of predictors without the column to be predicted(the target column), trainy is the target column.I feed the same data

Hello R community, I have cross-posted with r-sig-geo as this issue could fall under either interest group I believe. I just came accross the alphahull package and am very pleased I may not need to use CGAL anymore for this purpose. However, I am having a problem computing alpha shapes with my point data, and it seems to have to do with the spatial configuration of my points (which form