PRTools Contents

PRTools User Guide

prkmeans

PRKMEANS

PRTools k-means clustering

    [LABELS,B] = PRKMEANS(A,K,MAXIT,INIT)

Input
 A Matrix or dataset
 K Number of clusters to be found (optional; default: 2)
 MAXIT maximum number of iterations (optional; default: 50)
 INIT Labels for initialisation, or  'rand' : take at random K objects as initial means, or  'kcentres' : use KCENTRES for initialisation (default)

Output
 LABELS Cluster assignments, 1..K
 B Dataset with original data and labels LABELS:
 B = PRDATASET(A,LABELS)

Description

K-means clustering of data vectors in A. Iterations may be stopped before  stability is reached due to the setting of PRTIME

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.