Package org.apache.mahout.clustering.classify

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

281
282
283
284
285
286
287
288
289
290
291
    }
  }
 
  @Test
  public void testCosineKlusterClassification() {
    ClusterClassifier classifier = newCosineKlusterClassifier();
    Vector pdf = classifier.classify(new DenseVector(2));
    assertEquals("[0,0]", "[0.333, 0.333, 0.333]", AbstractCluster.formatVector(pdf, null));
    pdf = classifier.classify(new DenseVector(2).assign(2));
    assertEquals("[2,2]", "[0.429, 0.429, 0.143]", AbstractCluster.formatVector(pdf, null));
  }
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
    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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
      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
83
84
85
86
87
88
89
90
91
92
93
    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
78
79
80
81
82
83
84
85
86
87
88
89
    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
49
50
51
52
53
54
55
    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
58
59
60
61
62
63
64
    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
67
68
69
70
71
72
73
    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
76
77
78
79
80
81
82
    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
84
85
86
87
88
89
90
  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
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
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.