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.classify.ClusterClassifier

      runSequentialDirichletClusterer(input, output, modelDist, numClusters, numIterations, alpha0);
    } else {
      runSequentialDirichletClassifier(input, output, modelDist, numClusters, numIterations, alpha0);
    }
    for (int i = 1; i <= numIterations; i++) {
      ClusterClassifier posterior = new ClusterClassifier();
      String name = i == numIterations ? "clusters-" + i + "-final" : "clusters-" + i;
      posterior.readFromSeqFiles(new Configuration(), new Path(output, name));
      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.classify.ClusterClassifier

    throws IOException {
    List<Cluster> models = Lists.newArrayList();
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(numClusters)) {
      models.add((Cluster) cluster);
    }
    ClusterClassifier prior = new ClusterClassifier(models, new DirichletClusteringPolicy(numClusters, alpha0));
    Path priorPath = new Path(output, Cluster.INITIAL_CLUSTERS_DIR);
    prior.writeToSeqFiles(priorPath);
    Configuration conf = new Configuration();
    ClusterIterator.iterateSeq(conf, input, priorPath, output, numIterations);
  }

View Full Code Here

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

    List<Cluster> initialClusters = Lists.newArrayList();
    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new org.apache.mahout.clustering.kmeans.Kluster(point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters, new KMeansClusteringPolicy(convergenceDelta));
    Path priorPath = new Path(output, Cluster.INITIAL_CLUSTERS_DIR);
    prior.writeToSeqFiles(priorPath);
    
    ClusterIterator.iterateSeq(conf, samples, priorPath, output, maxIterations);
    loadClustersWritable(output);
  }

View Full Code Here

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

    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2), 1, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }

View Full Code Here

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

    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2), 1, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }

View Full Code Here

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

    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new CosineDistanceMeasure();
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2), 1, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }

View Full Code Here

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

    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new SoftCluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new SoftCluster(new DenseVector(2), 1, measure));
    models.add(new SoftCluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new FuzzyKMeansClusteringPolicy());
  }

View Full Code Here

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

  private static ClusterClassifier newGaussianClassifier() {
    List<Cluster> models = Lists.newArrayList();
    models.add(new GaussianCluster(new DenseVector(2).assign(1), new DenseVector(2).assign(1), 0));
    models.add(new GaussianCluster(new DenseVector(2), new DenseVector(2).assign(1), 1));
    models.add(new GaussianCluster(new DenseVector(2).assign(-1), new DenseVector(2).assign(1), 2));
    return new ClusterClassifier(models, new DirichletClusteringPolicy(3, 1.0));
  }

View Full Code Here

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

  }
  
  private ClusterClassifier writeAndRead(ClusterClassifier classifier) throws IOException {
    Path path = new Path(getTestTempDirPath(), "output");
    classifier.writeToSeqFiles(path);
    ClusterClassifier newClassifier = new ClusterClassifier();
    newClassifier.readFromSeqFiles(getConfiguration(), path);
    return newClassifier;
  }

View Full Code Here

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

    return newClassifier;
  }
  
  @Test
  public void testDMClusterClassification() {
    ClusterClassifier classifier = newDMClassifier();
    Vector pdf = classifier.classify(new DenseVector(2));
    assertEquals("[0,0]", "[0.200, 0.600, 0.200]", AbstractCluster.formatVector(pdf, null));
    pdf = classifier.classify(new DenseVector(2).assign(2));
    assertEquals("[2,2]", "[0.493, 0.296, 0.211]", AbstractCluster.formatVector(pdf, null));
  }

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.