HOFS: Higher Order Mutual Information Approximation for Feature...

In KrzyGajow/HOFS: Higher Order Mutual Information Approximation for Feature Selection

Higher Order Mutual Information Approximation for Feature Selection

Usage

HOFS( data, label, C = 0.2, Nfeatures = 10, samplePct = 0.1, verbose = F, seed = 666 )

Arguments

data	Data.frame with the invesigated features.
label	Column with the target feature.
C	Predefined constant C, assessing whether create new subset.
Nfeatures	Nunber of features to be selected.
samplePct	Percentage of observations that are sampled to speed up the computation.
verbose	Switch for tracing selection.
seed	Seed for Pseudo-Random Number Generator.

Value

List with the selected features along with the coresponding rank.

Examples

library("HOFS")
data(iris)
Results <- HOFS( data = iris[ , -5 ], label = iris[ , 5, drop = F ], Nfeatures = 4 )

KrzyGajow/HOFS documentation built on April 4, 2022, 1:56 a.m.