>
> Hi all,
>
> I need some help about how to calculate w in a SVR in package e1071.
>
> I have a regression y_i=f(x_i)+e
>
> where f(*x*)=(w,phi(x))+b
>
> then go on with the SVR calculation I know that w*=Sum_i=1^n [(á_i -
> á*_i)K(x,x_i) ] where á_i and á*_i are the lagrangian multipliers of the
> dual form.
>
> o.k but how I will get it in R?
>
> When I run my model I have information about the model but I don't know how
> to use it to get w. Where are the alphas? Is w a vector or a value?
>
> Someone can help me please.
>
> Regards,
>
> Marlene
>
> svm.m1 <- svm(q ~ ., data = train, cost = 100, gamma = 1e-05)
>
> svm.m1
>
> Call:
> svm(formula = q ~ ., data = train, cost = 100, gamma = 1e-05)
>
>
> Parameters:
> SVM-Type: eps-regression
> SVM-Kernel: radial
> cost: 100
> gamma: 1e-05
> epsilon: 0.1
>
>
> Number of Support Vectors: 187
>
>
>
>
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
