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

Introduction

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

Prototype

public static DefaultOptionBuilder distanceMeasureOption() 

Source Link

Document

Returns a default command line option for specification of distance measure class to use.

Usage

From source file:chapter5.KMeanSample.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();//from w  w  w .jav a 2 s . c  om
    addOutputOption();
    addOption(DefaultOptionCreator.distanceMeasureOption().create());
    addOption(DefaultOptionCreator.numClustersOption().create());
    addOption(DefaultOptionCreator.t1Option().create());
    addOption(DefaultOptionCreator.t2Option().create());
    addOption(DefaultOptionCreator.convergenceOption().create());
    addOption(DefaultOptionCreator.maxIterationsOption().create());
    addOption(DefaultOptionCreator.overwriteOption().create());

    Map<String, String> argMap = parseArguments(args);
    if (argMap == null) {
        return -1;
    }

    Path input = getInputPath();
    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);
    if (hasOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)) {
        int k = Integer.parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION));
        run(getConf(), input, output, measure, k, convergenceDelta, maxIterations);
    } else {
        double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
        double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
        run(getConf(), input, output, measure, t1, t2, convergenceDelta, maxIterations);
    }
    return 0;
}

---

From source file:cn.macthink.hadoop.tdt.clustering.canopy.CanopyClustering.java

License:Apache License

@Override
public int run(String[] args) throws Exception {

    addInputOption();/*from  w w w . j ava 2  s.  c om*/
    addOutputOption();
    addOption(DefaultOptionCreator.distanceMeasureOption().create());
    addOption(DefaultOptionCreator.t1Option().create());
    addOption(DefaultOptionCreator.t2Option().create());
    addOption(DefaultOptionCreator.overwriteOption().create());

    Map<String, List<String>> argMap = parseArguments(args);
    if (argMap == null) {
        return -1;
    }

    Path input = getInputPath();
    Path output = getOutputPath();
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
        HadoopUtil.delete(new Configuration(), output);
    }
    String measureClass = getOption(DefaultOptionCreator.DISTANCE_MEASURE_OPTION);
    double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
    double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
    DistanceMeasure measure = ClassUtils.instantiateAs(measureClass, DistanceMeasure.class);

    run(input, output, measure, t1, t2);
    return 0;
}

---

From source file:com.eniyitavsiye.mahoutx.hadoop.Job.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();/*  www.j a va  2 s.c o m*/
    addOutputOption();
    addOption(DefaultOptionCreator.distanceMeasureOption().create());
    addOption(DefaultOptionCreator.numClustersOption().create());
    addOption(DefaultOptionCreator.t1Option().create());
    addOption(DefaultOptionCreator.t2Option().create());
    addOption(DefaultOptionCreator.convergenceOption().create());
    addOption(DefaultOptionCreator.maxIterationsOption().create());
    addOption(DefaultOptionCreator.overwriteOption().create());

    Map<String, List<String>> argMap = parseArguments(args);
    if (argMap == null) {
        return -1;
    }

    Path input = getInputPath();
    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);
    if (hasOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)) {
        int k = Integer.parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION));
        run(getConf(), input, output, measure, k, convergenceDelta, maxIterations);
    } else {
        double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
        double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
        run(getConf(), input, output, measure, t1, t2, convergenceDelta, maxIterations);
    }
    return 0;
}

---

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.  ja v  a2s  .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;
}

---

From source file:org.conan.mymahout.clustering.syntheticcontrol.fuzzykmeans.Job.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();//from   w  w w . j  av  a 2  s .c  o  m
    addOutputOption();
    addOption(DefaultOptionCreator.distanceMeasureOption().create());
    addOption(DefaultOptionCreator.convergenceOption().create());
    addOption(DefaultOptionCreator.maxIterationsOption().create());
    addOption(DefaultOptionCreator.overwriteOption().create());
    addOption(DefaultOptionCreator.t1Option().create());
    addOption(DefaultOptionCreator.t2Option().create());
    addOption(M_OPTION, M_OPTION, "coefficient normalization factor, must be greater than 1", true);

    Map<String, List<String>> argMap = parseArguments(args);
    if (argMap == null) {
        return -1;
    }

    Path input = getInputPath();
    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));
    float fuzziness = Float.parseFloat(getOption(M_OPTION));

    addOption(new DefaultOptionBuilder().withLongName(M_OPTION).withRequired(true)
            .withArgument(new ArgumentBuilder().withName(M_OPTION).withMinimum(1).withMaximum(1).create())
            .withDescription("coefficient normalization factor, must be greater than 1").withShortName(M_OPTION)
            .create());
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
        HadoopUtil.delete(getConf(), output);
    }
    DistanceMeasure measure = ClassUtils.instantiateAs(measureClass, DistanceMeasure.class);
    double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
    double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
    run(getConf(), input, output, measure, t1, t2, maxIterations, fuzziness, convergenceDelta);
    return 0;
}

---