wsvm: wsvm to solve the subject-weighted SVM

Description Usage Arguments Value

View source: R/benchmark_models.R

Description

wsvm to solve the subject-weighted SVM

Usage

1
wsvm(X, A, wR, kernel = "linear", sigma = 0.05, C = 1, e = 1e-05)

Arguments

X:

n by p feature matrix

A:

label

wR:

instance weight

kernel:

propensity score with length n, can be either "rbf" or "linear", default is "linear"

sigma:

hyper-parameter in SVM rbf kernel

C:

hyper-parameter in SVM rbf kernel

e:

least tolerated error

Value

object of rbfcl or linearcf classs wsvm()


sambiostat/WAPL documentation built on May 26, 2020, 12:17 a.m.