similar to: regularized dfa rda (Klar): problems with predictions

Sorry, I forgot to mention that I used the package "klaR". > > Dear all, I am trying to do a n-fold cross-validation for a > regularized discrimant function analysis using rda from the package > klaR. However, I have problems to predict the groups from the > test/validation sample. The exmaples of the R documantation and > some online webpage also do not work.

Dear all, I have a question on the shardsplot package:klaR(see the below Example). Plese tell me the meanings of " logstand <- t((t(logcount) / sdlogcount) * c(1,2,6,5,5,3))", much more. Why does this example use "c(1,2,6,5,5,3)" ? Examples: # Compute clusters and an Eight Directions Arranged Map for the # country data. Plotting the result.

Hi, I'm trying to use "stepclass" to do a stepwise variable selection with method=lda. I keep getting this warning message, which shows up once for each variable added to the model during variable selection: Warning message: error(s) in modeling/prediction step in: cv.rate(vars = c(model, tryvar), data = data, grouping = grouping, I don't know how to interpret this warning. I

Hi, a colleague ran a stepwise discriminant analysis twice in a row and got different results, suggesting some "sochasticity" in the algorithms involved. I looked at her data and found that there was a lot of collinearity, so that I reckoned that maybe "stepclass" (klaR) cannot find a clear winner when trying to include a new variable and makes a random choice. Is that true?

I use Windows, R version 2.5.1 When I try to run stepclass (klaR) I get an error message/warning saying: 1: error(s) in modeling/prediction step in: cv.rate(vars = c(model, tryvar), data = data, grouping = grouping, ... Actually, I look 16 warnings of this type. Can anyone tell me what this means? Also, it returns only 2 out of the 79 variables as important, however these variables

Hi, I run R 2.10.1 under ubuntu 10.04 LTS (Lucid Lynx) and klaR version 0.6-4. I compute a model over a 2 classes dataset (composed of 700 examples). To that aim, I use the function NaiveBayes provided in the package klaR. When I then use the prediction function : predict(my_model, new_data). I get the following warning : "In FUN(1:747[[747L]], ...) : Numerical 0 probability with

Hello, I used the lda function from the MASS (VR) package and the rda function from the klaR package. I wanted to compare the result of this two functions by using the same training set. Thus, I used the rda function with lambda=1 an gamma=0, I should emulate the lda function and I should obtain the same result. But this it not the case, the two result are very different. My training set is

Hello I try to fit a LDA and RDA model to the same data, which has two classes. The problem now is that the training errors of the LDA model and the training error of the RDA model with alpha=0 are not the same. In my understanding this should be the case. Am I wrong? Can someone explain what the reason for this difference could be? Here my code: LDA model: =========== % x is a dataframe tmp =

Han-Lin I don't think I have seen a reply so I will suggest that maybe you could try a different approach than what you are thinking about doing. I believe the current best practice is to use the weights as a covariate in a regression model - and bytheway - the weights are the inverse of the probabilities of selection - not the probabilities. Fundamentally, there is a difficulty in making

Hi all, I would greatly appreciate if someone was so kind and share with us a package or method that uses a regularized regression approach that balances a regression model performance and model complexity. That said I would be most grateful is there is an R-package that combines Ridge (sum of squares coefficients), Lasso: Sum of absolute coefficients and Best Subsets: Number of coefficients as

Dear R-users, we are happy to announce the release of our R package parcor. The package contains tools to estimate the matrix of partial correlations based on different regularized regression methods: Lasso, adaptive Lasso, PLS, and Ridge Regression. In addition, parcor provides cross-validation based model selection for Lasso, adaptive Lasso and Ridge Regression. More details can be found

Dear R-users, we are happy to announce the release of our R package parcor. The package contains tools to estimate the matrix of partial correlations based on different regularized regression methods: Lasso, adaptive Lasso, PLS, and Ridge Regression. In addition, parcor provides cross-validation based model selection for Lasso, adaptive Lasso and Ridge Regression. More details can be found

Author: keerthi Repository: /hg/zfs-crypto/gate Revision: 02abb98de0d64950ccf922e93b5f29cce65c46c9 Log message: 6297318 Orphan dfA files found on cascading SUN print host Files: update: usr/src/lib/print/job.c update: usr/src/lib/print/misc.c

Dear all, I would be very grateful if you could help me with: Given the regularized gamma function Reg=int_0^r (x^(k-1)e^(-x))dx/int_0^Inf (x^(k-1)e^(-x))dx ; 0<r<Inf (which is eventually the ratio of the Incomplete gamma function by the gamma function), does anyone know of a package in R that would evaluate the derivative of the inverse of Reg with respect to k? I am aware that the

Ivan, Thanks for working on the DFA generator. I'll take a look at the changes in detail but from your description, I like the general nature of the modifications. -Anshu --- Qualcomm Innovation Center, Inc is a member of the Code Aurora Forum On 6/14/2012 8:22 AM, Ivan Llopard wrote: > Hi, > > I've refactored the DFA generator in TableGen because it takes too > much

Hello, We have a system which creates thousands of regression/classification models and in cases where we have only one input variable NaiveBayes throws an error. Maybe I am mistaken and I shouldn't expect to have a model with only one input variable. We use R version 2.6.0 (2007-10-03). We use caret (v4.1.19), but have tested similar code with klaR (v.0.5.8), because caret relies on

Hi Ivan, > I missed last 2 commits made by Alexey. Following his advices, I > updated the patch. It should be ok now. > Thanks Anshu! > > I've recently added more functional units to our Schedule.td and the > generation time became painfully long. In fact, the main problem was > in writeTableAndAPI(). I propose another patch to fix it: > - Fixed memory leaks. > -

Hi ! Right now I am learning to use svm functions available in R and trying to use these function with given example. I was stuck with svmlight function which is available in klaR package. Any help would be appreciated regarding this function. 1. I am unable to use svmlight( ) which is available in package: klaR. Although I have downloaded klaR_0.6-3 package from

Dear developeRs, my package FrF2.catlg128 holds large catalogues and is supposed to gain additional ones. All the catalogues are intended for the user. So far, the catalogues were stored in the data directory, and LazyData was "no". I understand that this is not considered wise any more (if it ever was), so that I want to change to LazyData "yes" with the next release

Hi Ivan, The patch looks good to me. I have a couple of minor comments: +void State::AddInsnClass(unsigned InsnClass, Add a top level comment describing the function + std::map<State*, std::set<Transition*, ltTransition>, ltState> stateTransitions; You should be able to use SmallSet here. Also, this line exceeds 80 columns. On a related note, is the CachedTable mechanism in