featureVector {penaltyLearning}

featureVector

Description

Compute a feature vector of constant length which can be used as an input for supervised penalty learning. The output is a target interval of log(penalty) values that achieve minimum incorrect labels (see targetIntervals).

Usage

featureVector(data.vec)

Arguments

data.vec

numeric vector of ordered data.

Value

Numeric vector of features.

Author(s)

Toby Dylan Hocking

Examples

x <- rnorm(10)
penaltyLearning::featureVector(x)
if(requireNamespace("neuroblastoma")){
  data(neuroblastoma, package="neuroblastoma", envir=environment())
  one <- subset(neuroblastoma$profiles, profile.id=="1" & chromosome=="1")
  (f.vec <- penaltyLearning::featureVector(one$logratio))
}