Examples of ClusterClassifier

org.apache.mahout.clustering.ClusterClassifier
This classifier works with any clustering Cluster. It is initialized with a list of compatible clusters and thereafter it can classify any new Vector into one or more of the clusters based upon the pdf() function which each cluster supports. In addition, it is an OnlineLearner and can be trained. Training amounts to asking the actual model to observe the vector and closing the classifier causes all the models to computeParameters.
org.apache.mahout.clustering.classify.ClusterClassifier
This classifier works with any ClusteringPolicy and its associated Clusters. It is initialized with a policy and a list of compatible clusters and thereafter it can classify any new Vector into one or more of the clusters based upon the pdf() function which each cluster supports. In addition, it is an OnlineLearner and can be trained. Training amounts to asking the actual model to observe the vector and closing the classifier causes all the models to computeParameters. Because a ClusterClassifier implements Writable, it can be written-to and read-from a sequence file as a single entity. For sequential and mapreduce clustering in conjunction with a ClusterIterator; however, it utilizes an exploded file format. In this format, the iterator writes the policy to a single POLICY_FILE_NAME file in the clustersOut directory and the models are written to one or more part-n files so that multiple reducers may employed to produce them.

Examples of org.apache.mahout.clustering.ClusterClassifier

    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new org.apache.mahout.clustering.kmeans.Cluster(
          point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters);
    Path priorClassifier = new Path(output, "clusters-0");
    writeClassifier(prior, conf, priorClassifier);
    
    int maxIter = 10;
    ClusteringPolicy policy = new KMeansClusteringPolicy();
    new ClusterIterator(policy).iterateSeq(samples, priorClassifier, output, maxIter);
    for (int i = 1; i <= maxIter; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      CLUSTERS.add(posterior.getModels());
    }
  }

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier


  protected static ClusterClassifier readClassifier(Configuration config, Path path) throws IOException {
    SequenceFile.Reader reader = new SequenceFile.Reader(FileSystem.get(config), path, config);
    try {
      Writable key = new Text();
      ClusterClassifier classifierOut = new ClusterClassifier();
      reader.next(key, classifierOut);
      return classifierOut;
    } finally {
      Closeables.closeQuietly(reader);
    }

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

    List<Cluster> initialClusters = Lists.newArrayList();
    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new SoftCluster(point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters);
    Path priorClassifier = new Path(output, "classifier-0");
    writeClassifier(prior, conf, priorClassifier);
    
    ClusteringPolicy policy = new FuzzyKMeansClusteringPolicy();
    new ClusterIterator(policy).iterateSeq(samples, priorClassifier, output, maxIterations);
    for (int i = 1; i <= maxIterations; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      CLUSTERS.add(posterior.getModels());
    }
  }

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

                                                       int numIterations) throws IOException {
    List<Cluster> models = Lists.newArrayList();
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(numClusters)) {
      models.add((Cluster) cluster);
    }
    ClusterClassifier prior = new ClusterClassifier(models);
    Path samples = new Path("samples");
    Path output = new Path("output");
    Path priorClassifier = new Path(output, "clusters-0");
    Configuration conf = new Configuration();
    writeClassifier(prior, conf, priorClassifier);
    
    ClusteringPolicy policy = new DirichletClusteringPolicy(numClusters, numIterations);
    new ClusterIterator(policy).iterateSeq(samples, priorClassifier, output, numIterations);
    for (int i = 1; i <= numIterations; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      List<Cluster> clusters = Lists.newArrayList();
      for (Cluster cluster : posterior.getModels()) {
        if (isSignificant(cluster)) {
          clusters.add(cluster);
        }
      }
      CLUSTERS.add(clusters);

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

    List<Cluster> initialClusters = new ArrayList<Cluster>();
    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new SoftCluster(point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters);
    Path priorClassifier = new Path(output, "classifier-0");
    writeClassifier(prior, conf, priorClassifier);
    
    ClusteringPolicy policy = new FuzzyKMeansClusteringPolicy();
    new ClusterIterator(policy).iterate(samples, priorClassifier, output, maxIterations);
    for (int i = 1; i <= maxIterations; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      CLUSTERS.add(posterior.getModels());
    }
  }

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

                                                       int numIterations) throws IOException {
    List<Cluster> models = new ArrayList<Cluster>();
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(numClusters)) {
      models.add((Cluster) cluster);
    }
    ClusterClassifier prior = new ClusterClassifier(models);
    Path samples = new Path("samples");
    Path output = new Path("output");
    Path priorClassifier = new Path(output, "clusters-0");
    Configuration conf = new Configuration();
    writeClassifier(prior, conf, priorClassifier);
    
    ClusteringPolicy policy = new DirichletClusteringPolicy(numClusters, numIterations);
    new ClusterIterator(policy).iterate(samples, priorClassifier, output, numIterations);
    for (int i = 1; i <= numIterations; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      List<Cluster> clusters = new ArrayList<Cluster>();    
      for (Cluster cluster : posterior.getModels()) {
        if (isSignificant(cluster)) {
          clusters.add(cluster);
        }
      }
      CLUSTERS.add(clusters);

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new org.apache.mahout.clustering.kmeans.Cluster(
          point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters);
    Path priorClassifier = new Path(output, "clusters-0");
    writeClassifier(prior, conf, priorClassifier);
    
    int maxIter = 10;
    ClusteringPolicy policy = new KMeansClusteringPolicy();
    new ClusterIterator(policy).iterate(samples, priorClassifier, output, maxIter);
    for (int i = 1; i <= maxIter; i++) {
      ClusterClassifier posterior = readClassifier(conf, new Path(output, "classifier-" + i));
      CLUSTERS.add(posterior.getModels());
    }
  }

View Full Code Here

Examples of org.apache.mahout.clustering.ClusterClassifier

  }


  protected static ClusterClassifier readClassifier(Configuration config, Path path) throws IOException {
    SequenceFile.Reader reader = new SequenceFile.Reader(FileSystem.get(config), path, config);
    Writable key = new Text();
    ClusterClassifier classifierOut = new ClusterClassifier();
    reader.next(key, classifierOut);
    reader.close();
    return classifierOut;
  }

View Full Code Here

Examples of org.apache.mahout.clustering.classify.ClusterClassifier

      throw new IllegalStateException("No input clusters found in " + clustersIn + ". Check your -c argument.");
    }
    
    Path priorClustersPath = new Path(output, Cluster.INITIAL_CLUSTERS_DIR);
    ClusteringPolicy policy = new KMeansClusteringPolicy(convergenceDelta);
    ClusterClassifier prior = new ClusterClassifier(clusters, policy);
    prior.writeToSeqFiles(priorClustersPath);
    
    if (runSequential) {
      ClusterIterator.iterateSeq(conf, input, priorClustersPath, output, maxIterations);
    } else {
      ClusterIterator.iterateMR(conf, input, priorClustersPath, output, maxIterations);

View Full Code Here

Examples of org.apache.mahout.clustering.classify.ClusterClassifier

      throw new IllegalStateException("No input clusters found in " + clustersIn + ". Check your -c argument.");
    }
    
    Path priorClustersPath = new Path(output, Cluster.INITIAL_CLUSTERS_DIR);   
    ClusteringPolicy policy = new FuzzyKMeansClusteringPolicy(m, convergenceDelta);
    ClusterClassifier prior = new ClusterClassifier(clusters, policy);
    prior.writeToSeqFiles(priorClustersPath);
    
    if (runSequential) {
      ClusterIterator.iterateSeq(conf, input, priorClustersPath, output, maxIterations);
    } else {
      ClusterIterator.iterateMR(conf, input, priorClustersPath, output, maxIterations);

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.