Re: [R] tune svm

svm requires that your x input be a numeric matrix. The double quotes denote character values in your matrix, probably introduced as a result of conversion from a data frame. To convert to a numeric matrix and remove the double quotes: mode(mdt01bis) <- "numeric" -- View this message in context:

Re: [R] tune svm

Steve, Thanks a lot for your answer. I haven´t tried to deal with the situation yet, cause I had a field trip. I'll let you know if I can solve my problem with your observation. Bye, Juan P. Argañaraz Lic. en Ecología y Cons. del Ambiente Instituto de Hidrología de Llanuras CC 44 (B7300

Re: [R] tune svm

Hi, On Thu, May 13, 2010 at 3:54 PM, jparga wrote: > > Hello, I hope you can help me! > I`m trying to tune svm parameters: cost and gamma for a landsat image > classification, but I get an error and I can't understand it. > I write this: >> tune(svm, Class~., data = mdt01bis, ranges = list(gamma

[R] tune svm

Hello, I hope you can help me! I`m trying to tune svm parameters: cost and gamma for a landsat image classification, but I get an error and I can't understand it. I write this: > tune(svm, Class~., data = mdt01bis, ranges = list(gamma = 2^(-15:3), cost > = 2^(-5:15))) and R gives: Error en predic