[BioC] Choosing the kernel for SVM (regression) using rminer package

[Steve Lianoglou]

Hi,

On Tue, Apr 1, 2014 at 6:32 AM, Paul [guest] <guest at bioconductor.org> wrote:
>
> In the rminer package by Paulo Cortez, using the mining function, it is possible to do a SVM regression.Using the script from the documentation
>
> SV=mining(V26~.,d,model="svm",Runs=10,method=v,mpar=m,search=s,feat="s")
>
> Is it possible to choose a kernel for the regression other than the default gaussian kernel? I would like to apply the same to a non-linear data and prefer to use a spline or other types of kernel for the same function.

It looks like this wraps the `ksvm` function from kernlab, and it
looks like the `...` arguments in the `mining` passes those params
through to functions it delegates to, so you should look at how to
specify kernels and what not in `ksvm`

Also: this isn't really a bioconductor related question and is
probably best directed to R-help (or maybe SO, even), but CCing the
maintainer was a good idea.

-steve

-- 
Steve Lianoglou
Computational Biologist
Genentech