Example usage for org.apache.mahout.clustering AbstractCluster formatVector

Introduction

In this page you can find the example usage for org.apache.mahout.clustering AbstractCluster formatVector.

Prototype

public static String formatVector(Vector v, String[] bindings) 

Source Link

Document

Return a human-readable formatted string representation of the vector, not intended to be complete nor usable as an input/output representation

Usage

From source file:DisplayClustering.java

License:Apache License

protected static List<Cluster> readClustersWritable(Path clustersIn) {
    List<Cluster> clusters = Lists.newArrayList();
    Configuration conf = new Configuration();
    for (ClusterWritable value : new SequenceFileDirValueIterable<ClusterWritable>(clustersIn, PathType.LIST,
            PathFilters.logsCRCFilter(), conf)) {
        Cluster cluster = value.getValue();
        log.info("Reading Cluster:{} center:{} numPoints:{} radius:{}", cluster.getId(),
                AbstractCluster.formatVector(cluster.getCenter(), null), cluster.getNumObservations(),
                AbstractCluster.formatVector(cluster.getRadius(), null));
        clusters.add(cluster);/*from  w  w  w.  j  a  v a 2s .  com*/
    }
    return clusters;
}

---

From source file:com.modofo.molo.cluster.DisplayClustering.java

License:Apache License

protected static List<Cluster> readClustersWritable(Path clustersIn) {
    List<Cluster> clusters = Lists.newArrayList();
    Configuration conf = new Configuration();
    for (ClusterWritable value : new SequenceFileDirValueIterable<ClusterWritable>(clustersIn, PathType.LIST,
            PathFilters.logsCRCFilter(), conf)) {
        Cluster cluster = value.getValue();
        log.info("Reading Cluster:{} center:{} numPoints:{} radius:{}",
                new Object[] { cluster.getId(), AbstractCluster.formatVector(cluster.getCenter(), null),
                        cluster.getNumObservations(),
                        AbstractCluster.formatVector(cluster.getRadius(), null) });
        clusters.add(cluster);//from  www.  j a v  a 2s.c om
    }
    return clusters;
}

---

From source file:edu.indiana.d2i.htrc.kmeans.MemCachedKMeansDriver.java

License:Apache License

private static Path buildClustersSeq(Configuration conf, Path input, Path clustersIn, Path output,
        DistanceMeasure measure, int maxIterations, String delta) throws IOException {

    KMeansClusterer clusterer = new KMeansClusterer(measure);
    Collection<Cluster> clusters = Lists.newArrayList();

    MemKMeansUtil.configureWithClusterInfo(conf, clustersIn, clusters);
    if (clusters.isEmpty()) {
        throw new IllegalStateException("Clusters is empty!");
    }/*from   www .  j  a  v a 2 s  .  c o m*/
    boolean converged = false;
    int iteration = 1;
    while (!converged && iteration <= maxIterations) {
        log.info("K-Means Iteration: {}", iteration);
        FileSystem fs = FileSystem.get(input.toUri(), conf);
        for (VectorWritable value : new SequenceFileDirValueIterable<VectorWritable>(input, PathType.LIST,
                PathFilters.logsCRCFilter(), conf)) {
            clusterer.addPointToNearestCluster(value.get(), clusters);
        }
        converged = clusterer.testConvergence(clusters, Double.parseDouble(delta));
        Path clustersOut = new Path(output, AbstractCluster.CLUSTERS_DIR + iteration);
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf, new Path(clustersOut, "part-r-00000"),
                Text.class, Cluster.class);
        try {
            for (Cluster cluster : clusters) {
                if (log.isDebugEnabled()) {
                    log.debug("Writing Cluster:{} center:{} numPoints:{} radius:{} to: {}", new Object[] {
                            cluster.getId(), AbstractCluster.formatVector(cluster.getCenter(), null),
                            cluster.getNumPoints(), AbstractCluster.formatVector(cluster.getRadius(), null),
                            clustersOut.getName() });
                }
                writer.append(new Text(cluster.getIdentifier()), cluster);
            }
        } finally {
            Closeables.closeQuietly(writer);
        }
        clustersIn = clustersOut;
        iteration++;
    }
    Path finalClustersIn = new Path(output, AbstractCluster.CLUSTERS_DIR + (iteration - 1)
            + org.apache.mahout.clustering.Cluster.FINAL_ITERATION_SUFFIX);
    FileSystem.get(conf).rename(new Path(output, AbstractCluster.CLUSTERS_DIR + (iteration - 1)),
            finalClustersIn);
    return finalClustersIn;
}

---

From source file:io.github.thushear.display.DisplayClustering.java

License:Apache License

protected static List<Cluster> readClusters(Path clustersIn) {
    List<Cluster> clusters = new ArrayList<Cluster>();
    Configuration conf = new Configuration();
    for (Cluster value : new SequenceFileDirValueIterable<Cluster>(clustersIn, PathType.LIST,
            PathFilters.logsCRCFilter(), conf)) {
        log.info("Reading Cluster:{} center:{} numPoints:{} radius:{}",
                new Object[] { value.getId(), AbstractCluster.formatVector(value.getCenter(), null),
                        value.getNumPoints(), AbstractCluster.formatVector(value.getRadius(), null) });
        clusters.add(value);/*from ww w  . j  a  v  a 2s  .  com*/
    }
    return clusters;
}

---

From source file:sample.DisplayClustering.java

License:Apache License

protected static List<Cluster> readClustersWritable(Path clustersIn) {
    List<Cluster> clusters = new ArrayList<>();
    Configuration conf = new Configuration();
    for (ClusterWritable value : new SequenceFileDirValueIterable<ClusterWritable>(clustersIn, PathType.LIST,
            PathFilters.logsCRCFilter(), conf)) {
        Cluster cluster = value.getValue();
        System.out.println("Cluster: " + cluster.getId() + " "
                + AbstractCluster.formatVector(cluster.getCenter(), null) + " " + cluster.getNumObservations()
                + " " + AbstractCluster.formatVector(cluster.getRadius(), null));
        clusters.add(cluster);//from  www  .ja v  a 2s  .  c  om
    }
    return clusters;
}

---