w.k.svm: Weighted Kernel SVM classification Model
In SkadiEye/ITRlearn: Individualized Treatment Rule Learning

Fit a Weighted Kernel SVM classification Model

1 2	w.k.svm(Y, X, W = NULL, C = 1, kernel = "gaussian", gamma = 1/dim(X)[2], c = 0, d = 3)

`Y`	A `factor` vector with two levels, a binary response.
`X`	A `numeric` matrix, the predictors.
`W`	A `numeric` matrix, the weights for all samples. The default is 1.
`C`	The coefficient for the regularizer.
`kernel`	The kernel function. gaussian: exp(-gamma(u-v)^2) polynomial: (gammauv + c)^d sigmoid: tanh(gammau*v + c)
`gamma`	Parameter needed for all kernels.
`c`	Parameter needed for polynomial and sigmoid kernels.
`d`	Parameter needed for sigmoid kernel.