ClusterTools Contents

ClusterTools User Guide



Wrapper for examplar clustering by DCLUSTE for feature based data


 A Feature based dataset or double array with M objects (rows).
 K Scalar or a vector of length N with desired numbers of clusters.  Default is a set of N clusterings with numbers that naturally  arise from the data.
 MSIZE Number of objects (M) above which processing is automatically  taken over by CLUSTME (default 2000). Use MSIZE = inf to avoid use  of CLUSTME.

 LAB M*N array with the results of the multi-level clusterings for the
 M objects. The columns refer to the N clusterings. They yield for  the objects the prototype indices of the clusters they belong to.


This routine performs a clustering based on message passing between data  points, see [1]. It is a wrapper around DCLUSTE which is based on  EXEMPLAR. That routine should be called directly to set other parameters  than its defaults.

EXEMPLAR does not return clusterings with a preset number of clusters K.  Its multilevel clustering is first made nested by RECLUSTN. Next the  desired number of clusters is realized by RECLUSTK.


 randreset;                     % take care of reproducability
 data = gendatclust1(20000);    % generate 20000 objects in 10 clusters
                                % Run Mean Shift clustering
 lab = cluste(data,[2 5 10 18 30 50 100],2000);
                                % Show scatterplot for 10 clusters
 figure; scatn(lab(:,3),data,'Exemplar'); 
 figure; clusteval(lab,data);   % Evaluation by active learning


[1] B.J. Frey and D. Dueck, Clustering by passing messages between data points, Science, vol. 315, pp. 972-976, 2007

See also

datasets, mappings, dclusth, clusth, clustf, clustk, clustm, clustme, clustke, modeclustf, clusteval, clustcerr, clustc, clustnum, clusthc,

ClusterTools Contents

ClusterTools User Guide

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