testEvolutiveDynamicConfluenceFastKmeans: Evolving Clustering Dynamic Weights K-means algorithm

In DavidGMarquez/evolvingClusteringR: Evolving Clustering

Description

Evolving Clustering

Usage

testEvolutiveDynamicConfluenceFastKmeans(file, samplesToInitMeta,
  parameters)

Arguments

file	path to CSV file with the data
samplesToInitMeta	number of samples to init the data
parameters	parameters to use

Value

A list with the error, the elapsed time and the final clusterModel

Examples

tf = tempfile()
iris2 = iris
iris2$Species = as.numeric(iris2$Species)
iris2 <- iris2[sample(nrow(iris2)),]
write.table(iris2,tf,row.names=FALSE, col.names=FALSE,sep=",")
samplesToInitMeta=50
parameters=list(memory=2,KinitMclust=3)
resultsA=testEvolutiveDynamicConfluenceFastKmeans(tf,samplesToInitMeta,parameters)
resultsA$clusterModel$fit
plot(iris2[,-5],col=resultsA$clusterModel$fit)
parameters<-list(memory=0.01,KinitMclust=3)
resultsB=testEvolutiveDynamicConfluenceFastKmeans(tf,samplesToInitMeta,parameters)
resultsB$clusterModel$fit
plot(iris2[,-5],col=resultsB$clusterModel$fit)

DavidGMarquez/evolvingClusteringR documentation built on May 22, 2019, 2:01 p.m.