weka.clusterers.EM Java Examples

public void generateClassToCluster(){
	Remove filter = new Remove();
	filter.setAttributeIndices("" + (weather.classIndex() + 1));
	try {
		filter.setInputFormat(weather);
		Instances dataClusterer = Filter.useFilter(weather, filter);
		clusterer = new EM();
		clusterer.buildClusterer(dataClusterer);
		ClusterEvaluation eval = new ClusterEvaluation();
		eval.setClusterer(clusterer);
		eval.evaluateClusterer(weather);

		System.out.println(eval.clusterResultsToString());
	} catch (Exception e) {
	}
}
 

@SuppressWarnings("unchecked")
private HashMap<Integer, Integer> sortAndpPrintCluster(EM clusterer) {
    List<double[]> vals = new ArrayList<double[]>(clusterer.getNumClusters());
    for (int c = 0; c < clusterer.getNumClusters(); c++) {
        vals.add(new double[]{clusterer.getClusterModelsNumericAtts()[c][0][0],   // mean
                clusterer.getClusterModelsNumericAtts()[c][0][1],  // var
                clusterer.getClusterModelsNumericAtts()[c][0][2], // prior
                clusterer.getClusterPriors()[c], // priors normalized
                c // cluster number
        });
    }
    Collections.sort(vals, new Comparator() {
        public int compare(Object o1, Object o2) {
            double[] d1 = (double[]) o1;
            double[] d2 = (double[]) o2;
            return (int) Math.signum(d1[0] - d2[0]);
        }
    });
    for (int c = 0; c < vals.size(); c++) {
        logger.trace("Cluster " + c + ":" + vals.get(c)[0] + " Var:" + vals.get(c)[1] + " Z:" + vals.get(c)[2] + " Prior:" + vals.get(c)[3] + " Cluster:" + vals.get(c)[4]);
    }
    return mergeClusters(vals);
}
 

private int guessNumClusters(EM clusterer, Instances instances, int start, int end) throws Exception {
    ClusterEvaluation eval = new ClusterEvaluation();
    int bestNum = start;
    double best = Double.POSITIVE_INFINITY;
    double bic;
    for (int c = start; c <= end; c++) {
        clusterer.setNumClusters(c);
        clusterer.buildClusterer(instances);
        eval.setClusterer(clusterer);
        eval.evaluateClusterer(instances);
        bic = bic(eval.getLogLikelihood(), c, instances.numInstances());
        logger.trace("numCluster " + c + " -> BIC: " + bic);
        if (bic < best) {
            best = bic;
            bestNum = c;
            logger.trace("bestNum: " + bestNum);
        }
    }
    return bestNum;
}
 

public static void main(String[] args) throws Exception {
    Instances data = GenerateTestVessels.getData();
    data.setClassIndex(-1); // No class index.

    Remove rm = new Remove();
    rm.setAttributeIndices("1");
    rm.setInputFormat(data);
    data = Filter.useFilter(data,rm);
    System.out.println(data);


    EM cw = new EM();

    cw.buildClusterer(data);
    System.out.println(cw);

    System.out.println(cw.clusterInstance(data.firstInstance()));
}
 

@Override
public ClusteringResult performClustering(Instances dataset, ParameterSet parameters) {

  List<Integer> clusters = new ArrayList<Integer>();
  String[] options = new String[2];
  EM clusterer = new EM();

  int numberOfIterations =
      parameters.getParameter(EMClustererParameters.numberOfIterations).getValue();
  options[0] = "-I";
  options[1] = String.valueOf(numberOfIterations);

  try {
    clusterer.setOptions(options);
    clusterer.buildClusterer(dataset);
    Enumeration<?> e = dataset.enumerateInstances();
    while (e.hasMoreElements()) {
      clusters.add(clusterer.clusterInstance((Instance) e.nextElement()));
    }
    ClusteringResult result = new ClusteringResult(clusters, null, clusterer.numberOfClusters(),
        parameters.getParameter(EMClustererParameters.visualization).getValue());
    return result;

  } catch (Exception ex) {
    logger.log(Level.SEVERE, null, ex);
    return null;
  }
}
 

@Override
public ClusteringResult performClustering(Instances dataset, ParameterSet parameters) {

  List<Integer> clusters = new ArrayList<Integer>();
  String[] options = new String[2];
  EM clusterer = new EM();

  int numberOfIterations =
      parameters.getParameter(EMClustererParameters.numberOfIterations).getValue();
  options[0] = "-I";
  options[1] = String.valueOf(numberOfIterations);

  try {
    clusterer.setOptions(options);
    clusterer.buildClusterer(dataset);
    Enumeration<?> e = dataset.enumerateInstances();
    while (e.hasMoreElements()) {
      clusters.add(clusterer.clusterInstance((Instance) e.nextElement()));
    }
    ClusteringResult result = new ClusteringResult(clusters, null, clusterer.numberOfClusters(),
        parameters.getParameter(EMClustererParameters.visualization).getValue());
    return result;

  } catch (Exception ex) {
    logger.log(Level.SEVERE, null, ex);
    return null;
  }
}
 

public static void main(String args[]) throws Exception{
	
	//load data
	Instances data = new Instances(new BufferedReader(new FileReader("data/bank-data.arff")));
	
	// new instance of clusterer
	EM model = new EM();
	// build the clusterer
	model.buildClusterer(data);
	System.out.println(model);
	
	double logLikelihood = ClusterEvaluation.crossValidateModel(model, data, 10, new Random(1));
	System.out.println(logLikelihood);


}