Examples of org.apache.mahout.clustering.iterator.ClusterIterator

Package org.apache.mahout.clustering.iterator

Examples of org.apache.mahout.clustering.iterator.ClusterIterator

org.apache.mahout.clustering.iterator.ClusterIterator
This is a clustering iterator which works with a set of Vector data and a prior ClusterClassifier which has been initialized with a set of models. Its implementation is algorithm-neutral and works for any iterative clustering algorithm (currently k-means, fuzzy-k-means and Dirichlet) that processes all the input vectors in each iteration. The cluster classifier is configured with a ClusteringPolicy to select the desired clustering algorithm.

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

View Full Code Here

    
    ClusterClassifier prior = new ClusterClassifier(models, new DirichletClusteringPolicy(numClusters, alpha0));
    prior.writeToSeqFiles(clustersIn);
    
    if (runSequential) {
      new ClusterIterator().iterateSeq(conf, input, clustersIn, output, maxIterations);
    } else {
      new ClusterIterator().iterateMR(conf, input, clustersIn, output, maxIterations);
    }
    return output;
    
  }

View Full Code Here

    ClusteringPolicy policy = new KMeansClusteringPolicy(convergenceDelta);
    ClusterClassifier prior = new ClusterClassifier(clusters, policy);
    prior.writeToSeqFiles(priorClustersPath);
    
    if (runSequential) {
      new ClusterIterator().iterateSeq(conf, input, priorClustersPath, output, maxIterations);
    } else {
      new ClusterIterator().iterateMR(conf, input, priorClustersPath, output, maxIterations);
    }
    return output;
  }

View Full Code Here

    ClusteringPolicy policy = new FuzzyKMeansClusteringPolicy(m, convergenceDelta);
    ClusterClassifier prior = new ClusterClassifier(clusters, policy);
    prior.writeToSeqFiles(priorClustersPath);
    
    if (runSequential) {
      new ClusterIterator().iterateSeq(conf, input, priorClustersPath, output, maxIterations);
    } else {
      new ClusterIterator().iterateMR(conf, input, priorClustersPath, output, maxIterations);
    }
    return output;
  }

View Full Code Here

    }
    ClusterClassifier prior = new ClusterClassifier(initialClusters, new FuzzyKMeansClusteringPolicy(m, threshold));
    Path priorPath = new Path(output, "classifier-0");
    prior.writeToSeqFiles(priorPath);
    
    new ClusterIterator().iterateSeq(conf, samples, priorPath, output, maxIterations);
    loadClustersWritable(output);
  }

View Full Code Here

    }
    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();
    new ClusterIterator().iterateSeq(conf, input, priorPath, output, numIterations);
  }

View Full Code Here

    ClusterClassifier prior = new ClusterClassifier(initialClusters, new KMeansClusteringPolicy(convergenceDelta));
    Path priorPath = new Path(output, Cluster.INITIAL_CLUSTERS_DIR);
    prior.writeToSeqFiles(priorPath);
    
    int maxIter = 10;
    new ClusterIterator().iterateSeq(conf, samples, priorPath, output, maxIter);
    loadClustersWritable(output);
  }

View Full Code Here

TOP

Related Classes of org.apache.mahout.clustering.iterator.ClusterIterator

org.apache.hadoop.fs.FileSystem

org.apache.hadoop.fs.Path

org.apache.hadoop.mapreduce.Job

org.apache.mahout.clustering.classify.ClusterClassifier

org.apache.mahout.clustering.dirichlet.DirichletDriver

org.apache.mahout.clustering.dirichlet.TestL1ModelClustering

org.apache.mahout.clustering.display.DisplayDirichlet

org.apache.mahout.clustering.display.DisplayFuzzyKMeans

org.apache.mahout.clustering.display.DisplayKMeans

org.apache.mahout.clustering.fuzzykmeans.FuzzyKMeansDriver

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.