Java Code Examples for weka.clusterers.SimpleKMeans#setPreserveInstancesOrder()

public void clusterData(){	
	kmeans = new SimpleKMeans();
	kmeans.setSeed(10);
	try {
		kmeans.setPreserveInstancesOrder(true);
		kmeans.setNumClusters(10);
		kmeans.buildClusterer(cpu);
		int[] assignments = kmeans.getAssignments();
		int i = 0;
		for(int clusterNum : assignments) {
			System.out.printf("Instance %d -> Cluster %d\n", i, clusterNum);
			i++;
		}
	} catch (Exception e1) {
	}
}
 

private List<Series<Number, Number>> buildClusteredSeries() throws Exception {
	List<XYChart.Series<Number, Number>> clusteredSeries = new ArrayList<>();

	// to build the cluster we remove the class information
	Remove remove = new Remove();
	remove.setAttributeIndices("3");
	remove.setInputFormat(data);
	Instances dataToBeClustered = Filter.useFilter(data, remove);

	SimpleKMeans kmeans = new SimpleKMeans();
	kmeans.setSeed(10);
	kmeans.setPreserveInstancesOrder(true);
	kmeans.setNumClusters(3);
	kmeans.buildClusterer(dataToBeClustered);

	IntStream.range(0, 3).mapToObj(i -> {
		Series<Number, Number> newSeries = new XYChart.Series<>();
		newSeries.setName(String.valueOf(i));
		return newSeries;
	}).forEach(clusteredSeries::add);

	int[] assignments = kmeans.getAssignments();
	for (int i = 0; i < assignments.length; i++) {
		int clusterNum = assignments[i];
		clusteredSeries.get(clusterNum).getData().add(instancetoChartData(data.get(i)));
	}

	return clusteredSeries;
}
 

public static void main(String[] args) throws Exception {
    
    // We'll use this data throughout, see Ex01_Datahandling
    int seed = 0;
    Instances[] trainTest = DatasetLoading.sampleItalyPowerDemand(seed);
    Instances inst = trainTest[0];
    Instances inst2 = trainTest[1];
    inst.addAll(inst2);

    // Create an object from one of the time series or vector clusters implemented.
    // Call the buildClusterer method with your data. Most clusters will need the number of clusters k to be set.
    UnsupervisedShapelets us = new UnsupervisedShapelets();
    us.setNumberOfClusters(inst.numClasses());
    us.buildClusterer(inst);

    // You can find the cluster assignments for each data instance by calling getAssignments().
    // The index of assignments array will match the Instances object, i.e. index 0 with value 1 == first instance
    // of data assigned to cluster 1.
    int[] tsAssignments = us.getAssignments();
    System.out.println("UnsupervisedShapelets cluster assignments:");
    System.out.println(Arrays.toString(tsAssignments));

    // A popular metric for cluster evaluation is the Rand index. A utility method is available for calculating
    // this.
    double tsRandIndex = ClusteringUtilities.randIndex(tsAssignments, inst);
    System.out.println("UnsupervisedShapelets Rand index:");
    System.out.println(tsRandIndex);

    // weka also implements a range of clustering algorithms. Any class value must be removed prior to use.
    Instances copy = new Instances(inst);
    deleteClassAttribute(copy);
    SimpleKMeans km = new SimpleKMeans();
    km.setNumClusters(inst.numClasses());
    km.setPreserveInstancesOrder(true);
    km.buildClusterer(copy);

    int[] wekaAssignments = km.getAssignments();
    System.out.println("SimpleKMeans cluster assignments:");
    System.out.println(Arrays.toString(wekaAssignments));

    double wekaRandIndex = ClusteringUtilities.randIndex(wekaAssignments, inst);
    System.out.println("SimpleKMeans Rand index:");
    System.out.println(wekaRandIndex);
}