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

Package org.apache.mahout.clustering.classify

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

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.

  }
  
  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

    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

    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
    
    ClusterClassifier classifier = new ClusterClassifier(models, new DirichletClusteringPolicy(15, 1.0));
    ClusterClassifier posterior = ClusterIterator.iterate(sampleData, classifier, 10);
    
    printClusters(posterior.getModels(), DOCS);
  }

View Full Code Here

    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
    
    ClusterClassifier classifier = new ClusterClassifier(models, new DirichletClusteringPolicy(15, 1.0));
    ClusterClassifier posterior = ClusterIterator.iterate(sampleData, classifier, 10);
    
    printClusters(posterior.getModels(), DOCS);
  }

View Full Code Here

    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
    
    ClusterClassifier classifier = new ClusterClassifier(models, new DirichletClusteringPolicy(15, 1.0));
    ClusterClassifier posterior = ClusterIterator.iterate(sampleData, classifier, 10);
    
    printClusters(posterior.getModels(), DOCS2);
  }

View Full Code Here

    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
    
    ClusterClassifier classifier = new ClusterClassifier(models, new DirichletClusteringPolicy(15, 1.0));
    ClusterClassifier posterior = ClusterIterator.iterate(sampleData, classifier, 10);
    
    printClusters(posterior.getModels(), DOCS2);
  }

View Full Code Here

  }
  
  private Iterable<List<Cluster>> getClusters(Path output, int numIterations) throws IOException {
    List<List<Cluster>> result = Lists.newArrayList();
    for (int i = 1; i <= numIterations; i++) {
      ClusterClassifier posterior = new ClusterClassifier();
      String name = i == numIterations ? "clusters-" + i + "-final" : "clusters-" + i;
      posterior.readFromSeqFiles(conf, new Path(output, name));
      List<Cluster> clusters = Lists.newArrayList();
      for (Cluster cluster : posterior.getModels()) {
        clusters.add(cluster);
      }
      result.add(clusters);
    }
    return result;

View Full Code Here

    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

    List<Cluster> initialClusters = Lists.newArrayList();
    int id = 0;
    for (Vector point : points) {
      initialClusters.add(new SoftCluster(point, id++, measure));
    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters, new FuzzyKMeansClusteringPolicy(m, threshold));
    Path priorPath = new Path(output, "classifier-0");
    prior.writeToSeqFiles(priorPath);
    
    ClusterIterator.iterateSeq(conf, samples, priorPath, output, maxIterations);
    loadClustersWritable(output);
  }

View Full Code Here

      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 6 7 8 9

TOP

Related Classes of org.apache.mahout.clustering.classify.ClusterClassifier

org.apache.hadoop.conf.Configuration

org.apache.hadoop.fs.FileSystem

org.apache.hadoop.fs.Path

org.apache.hadoop.io.IntWritable

org.apache.hadoop.io.Text

org.apache.hadoop.io.Writable

org.apache.mahout.clustering.Cluster

org.apache.mahout.clustering.dirichlet.DirichletDriver

org.apache.mahout.clustering.dirichlet.TestL1ModelClustering

org.apache.mahout.clustering.dirichlet.TestMapReduce

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.