Example usage for weka.clusterers SimpleKMeans setDontReplaceMissingValues

Introduction

In this page you can find the example usage for weka.clusterers SimpleKMeans setDontReplaceMissingValues.

Prototype

public void setDontReplaceMissingValues(boolean r) 

Source Link

Document

Sets whether missing values are to be replaced.

Usage

From source file:entities.ArffFile.java

/**
 * Dada una lista de parametros, se ejecuta el filtro de microagregacion.
 * Todos estos parametros son entrada del usuario.
 * @param df Puede ser Euclidian o Manhattan distance, se especifica en la entrada.
 * @param numCluster/*w  ww .  j  a v  a  2 s  .  co  m*/
 * @param seed
 * @param maxIterations
 * @param replaceMissingValues
 * @param preserveInstancesOrder
 * @param attributes lista de los atributos que se desean generalizar con cluster
 */
public void microAgregacion(DistanceFunction df, int numCluster, int seed, int maxIterations,
        boolean replaceMissingValues, boolean preserveInstancesOrder, List<Integer> attributes)
        throws Exception {
    //instancesFilter = new Instances(instances);
    SimpleKMeans kMeans;
    kMeans = new SimpleKMeans();
    Instances uniqueAttributes;
    uniqueAttributes = new Instances(instancesFilter);
    List<String> names = new ArrayList<>();
    int i = 0;
    for (Integer attribute : attributes) {
        String name = new String(instancesFilter.attribute(attribute).name());
        if (instancesFilter.attribute(attribute).isDate() || instancesFilter.attribute(attribute).isString())
            throw new Exception("No se puede hacer cluster con atributos de tipo DATE o STRING");
        names.add(name);
    }
    while (uniqueAttributes.numAttributes() != attributes.size()) {
        if (!names.contains(uniqueAttributes.attribute(i).name()))
            uniqueAttributes.deleteAttributeAt(i);
        else
            i++;
    }
    try {
        kMeans.setNumClusters(numCluster);
        kMeans.setMaxIterations(maxIterations);
        kMeans.setSeed(seed);
        kMeans.setDisplayStdDevs(false);
        kMeans.setDistanceFunction(df);
        kMeans.setDontReplaceMissingValues(replaceMissingValues);
        kMeans.setPreserveInstancesOrder(preserveInstancesOrder);
        kMeans.buildClusterer(uniqueAttributes);
        //System.out.println(kMeans);
        for (int j = 0; j < uniqueAttributes.numInstances(); j++) {
            int cluster = kMeans.clusterInstance(uniqueAttributes.instance(j));
            for (int k = 0; k < uniqueAttributes.numAttributes(); k++) {
                if (uniqueAttributes.attribute(k).isNumeric())
                    uniqueAttributes.instance(j).setValue(k,
                            Double.parseDouble(kMeans.getClusterCentroids().instance(cluster).toString(k)));
                else
                    uniqueAttributes.instance(j).setValue(k,
                            kMeans.getClusterCentroids().instance(cluster).toString(k));
            }
        }
        replaceValues(uniqueAttributes, attributes);
    } catch (Exception ex) {
        Logger.getLogger(ArffFile.class.getName()).log(Level.SEVERE, null, ex);
    }
    //saveToFile("4");
}

---

From source file:org.montp2.m1decol.ter.clustering.KMeansClustering.java

License:Open Source License

public Clusterer computeClustering(String inPath, String outPath, Properties propertiesCluster)
        throws Exception {
    Instances inputInstances = WekaUtils.loadARFF(inPath);

    EuclideanDistance euclideanDistance = new EuclideanDistance();
    euclideanDistance.setAttributeIndices("first-last");
    euclideanDistance.setDontNormalize(false);
    euclideanDistance.setInvertSelection(false);

    SimpleKMeans kmeans = new SimpleKMeans();
    kmeans.setPreserveInstancesOrder(/*www  .  j  a va  2 s .  c o  m*/
            Boolean.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.PERSERVE_INSTANCE)));
    kmeans.setDontReplaceMissingValues(Boolean
            .valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.DONT_REPLACE_MISSING_VALUES)));
    kmeans.setDisplayStdDevs(
            Boolean.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.DISPLAY_STD_DEVS)));
    kmeans.setMaxIterations(
            Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.MAX_ITERATIONS)));
    kmeans.setNumClusters(
            Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.NUM_CLUSTERS)));
    kmeans.setSeed(10);
    //kmeans.setSeed(
    //      Integer.valueOf(propertiesCluster.getProperty(ClusterProperties.Kmeans.SEED)));
    kmeans.setDistanceFunction(euclideanDistance);
    kmeans.buildClusterer(inputInstances);

    WekaUtils.saveModel(kmeans, outPath);

    /*
    *
    * Pour obtenir les pourcentages de les clusters
    * ClusterEvaluation eval = new ClusterEvaluation();
    * eval.setClusterer(kmeans);
    * eval.evaluateClusterer(inputInstances);
    * System.out.println(eval.clusterResultsToString());
    *
    * */

    return kmeans;
}

---