opf_distance: Generates the precomputed distance file for the OPF...

In LibOPF: Design of Optimum-Path Forest Classifiers

Generates the precomputed distance file for the OPF classifier

Description

Generates the precomputed distance file for the OPF classifier

Usage

opf_distance(dataSet, distanceOp, normalize = 0)

Arguments

dataSet	The subGraph object, normaly is the whole data
distanceOp	Distance calculation option
normalize	Distance normalization? 1- yes 0 - no

Details

Options for distance calculation:
1 - Euclidean
2 - Chi-Square
3 - Manhattan (L1)
4 - Canberra
5 - Squared Chord
6 - Squared Chi-Squared
7 - BrayCurtis

Value

Returns the distance matrix

Examples

dat <- opf_read_subGraph(system.file("extdata/boat.dat",package = "LibOPF"))
dist <- opf_distance(dat,3,0)
X <- opf_split(dat,0.5,0,0.5,0)
T <- X$training
T2 <- X$testing
Y <- opf_train(T,dist)
class <- opf_classify(T2, Y$classifier,dist)
acc <- opf_accuracy(T2, class)

LibOPF documentation built on Feb. 16, 2023, 10:13 p.m.