self.train.kernel: Self training for a kernel matrix

Description Usage Arguments Value Author(s) References Examples

Description

This function can be used for classification of semi-supervised data by using the kernel support vector machine.

Usage

1
2
3
self.train.kernel(K, y, type = 'response', C = 1, cache = 40,
                  tol = 0.001, shrinking = TRUE, thrConf = 0.9,
                  maxIts = 10, percFull = 1, verbose = FALSE) 

Arguments

K

kernel matrix

y

lable vector

type

one of response, probabilities ,votes, decision indicating the type of output (default: response)

C

cost of constraints violation for SVM (default: 1)

cache

cache memory in MB for SVM (default: 40)

tol

tolerance of termination criterion for SVM (default: 0.001)

shrinking

option whether to use the shrinking-heuristics for OCSVM (default: TRUE)

thrConf

A number between 0 and 1, indicating the required classification confidence for an unlabelled case to be added to the labelled data set with the label predicted predicted by the classification algorithm (default: 0.9)

maxIts

The maximum number of iterations of the self-training process (default: 10)

percFull

A number between 0 and 1. If the percentage of labelled cases reaches this value the self-training process is stoped (default: 1)

verbose

A boolean indicating the verbosity level of the function (default: FALSE)

Value

prediction from the SVM

Author(s)

Dongmin Jung, Xijin Ge

References

Torgo, L. (2016) Data Mining using R: learning with case studies, second edition, Chapman & Hall/CRC.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
data(litG)
litG <- igraph.from.graphNEL(litG)
sg <- decompose(litG, min.vertices = 50)
sg <- sg[[1]]
K <- net.kernel(sg)
y <- rep(NA, length(V(sg)))
y[1:10] <- 1
y[11:20] <- 0
y <- factor(y)
self.train.kernel(K, y)

dongminjung/PPInfer documentation built on May 15, 2019, 10:41 a.m.