Example usage for org.apache.mahout.common.commandline DefaultOptionCreator clusteringOption

Introduction

In this page you can find the example usage for org.apache.mahout.common.commandline DefaultOptionCreator clusteringOption.

Prototype

public static DefaultOptionBuilder clusteringOption() 

Source Link

Document

Returns a default command line option for clustering specification.

Usage

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

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();/* w w  w.  j  a  v  a  2s . c  o  m*/
    addOutputOption();
    addOption(DefaultOptionCreator.distanceMeasureOption().create());
    addOption(DefaultOptionCreator.clustersInOption()
            .withDescription(
                    "The input centroids, as Vectors.  Must be a SequenceFile of Writable, Cluster/Canopy.  "
                            + "If k is also specified, then a random set of vectors will be selected"
                            + " and written out to this path first")
            .create());
    addOption(DefaultOptionCreator.numClustersOption()
            .withDescription(
                    "The k in k-Means.  If specified, then a random selection of k Vectors will be chosen"
                            + " as the Centroid and written to the clusters input path.")
            .create());
    addOption(DefaultOptionCreator.convergenceOption().create());
    addOption(DefaultOptionCreator.maxIterationsOption().create());
    addOption(DefaultOptionCreator.overwriteOption().create());
    addOption(DefaultOptionCreator.clusteringOption().create());
    addOption(DefaultOptionCreator.methodOption().create());

    if (parseArguments(args) == null) {
        return -1;
    }

    Path input = getInputPath();
    Path clusters = new Path(getOption(DefaultOptionCreator.CLUSTERS_IN_OPTION));
    Path output = getOutputPath();
    String measureClass = getOption(DefaultOptionCreator.DISTANCE_MEASURE_OPTION);
    if (measureClass == null) {
        measureClass = SquaredEuclideanDistanceMeasure.class.getName();
    }
    double convergenceDelta = Double.parseDouble(getOption(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION));
    int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
        HadoopUtil.delete(getConf(), output);
    }
    DistanceMeasure measure = ClassUtils.instantiateAs(measureClass, DistanceMeasure.class);

    Configuration conf = getConf();
    // clustersIn is used as host file
    MemCachedUtil.configHelper(conf, clusters.toUri().getPath());
    int k = Integer.parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION));
    MemKMeansUtil.kmeansConfigHelper(conf, k);

    // create the seeds
    log.info("Create seeds.");
    if (hasOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)) {
        MemRandomSeedGenerator.buildRandom(getConf(), input,
                Integer.parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)), measure);
    }
    boolean runClustering = hasOption(DefaultOptionCreator.CLUSTERING_OPTION);
    boolean runSequential = getOption(DefaultOptionCreator.METHOD_OPTION)
            .equalsIgnoreCase(DefaultOptionCreator.SEQUENTIAL_METHOD);
    if (getConf() == null) {
        setConf(new Configuration());
    }

    // run iteration
    run(getConf(), input, clusters, output, measure, convergenceDelta, maxIterations, runClustering,
            runSequential);
    return 0;
}

---