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

    assertEquals("[2,2]", "[0.952, 0.047, 0.000]", AbstractCluster.formatVector(pdf, null));
  }
  
  @Test
  public void testDMClassifierSerialization() throws Exception {
    ClusterClassifier classifier = newDMClassifier();
    ClusterClassifier classifierOut = writeAndRead(classifier);
    assertEquals(classifier.getModels().size(), classifierOut.getModels().size());
    assertEquals(classifier.getModels().get(0).getClass().getName(), classifierOut.getModels().get(0).getClass()
        .getName());
  }

View Full Code Here

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

        .getName());
  }
  
  @Test
  public void testClusterClassifierSerialization() throws Exception {
    ClusterClassifier classifier = newKlusterClassifier();
    ClusterClassifier classifierOut = writeAndRead(classifier);
    assertEquals(classifier.getModels().size(), classifierOut.getModels().size());
    assertEquals(classifier.getModels().get(0).getClass().getName(), classifierOut.getModels().get(0).getClass()
        .getName());
  }

View Full Code Here

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

        .getName());
  }
  
  @Test
  public void testSoftClusterClassifierSerialization() throws Exception {
    ClusterClassifier classifier = newSoftClusterClassifier();
    ClusterClassifier classifierOut = writeAndRead(classifier);
    assertEquals(classifier.getModels().size(), classifierOut.getModels().size());
    assertEquals(classifier.getModels().get(0).getClass().getName(), classifierOut.getModels().get(0).getClass()
        .getName());
  }

View Full Code Here

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

        .getName());
  }
  
  @Test
  public void testGaussianClassifierSerialization() throws Exception {
    ClusterClassifier classifier = newGaussianClassifier();
    ClusterClassifier classifierOut = writeAndRead(classifier);
    assertEquals(classifier.getModels().size(), classifierOut.getModels().size());
    assertEquals(classifier.getModels().get(0).getClass().getName(), classifierOut.getModels().get(0).getClass()
        .getName());
  }

View Full Code Here

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

  }
  
  @Test
  public void testClusterIteratorKMeans() {
    List<Vector> data = TestKmeansClustering.getPoints(TestKmeansClustering.REFERENCE);
    ClusterClassifier prior = newKlusterClassifier();
    ClusterClassifier posterior = ClusterIterator.iterate(data, prior, 5);
    assertEquals(3, posterior.getModels().size());
    for (Cluster cluster : posterior.getModels()) {
      System.out.println(cluster.asFormatString(null));
    }
  }

View Full Code Here

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

  }
  
  @Test
  public void testClusterIteratorDirichlet() {
    List<Vector> data = TestKmeansClustering.getPoints(TestKmeansClustering.REFERENCE);
    ClusterClassifier prior = newKlusterClassifier();
    ClusterClassifier posterior = ClusterIterator.iterate(data, prior, 5);
    assertEquals(3, posterior.getModels().size());
    for (Cluster cluster : posterior.getModels()) {
      System.out.println(cluster.asFormatString(null));
    }
  }

View Full Code Here

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

    Configuration conf = getConfiguration();
    FileSystem fs = FileSystem.get(pointsPath.toUri(), conf);
    List<VectorWritable> points = TestKmeansClustering.getPointsWritable(TestKmeansClustering.REFERENCE);
    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file1"), fs, conf);
    Path path = new Path(priorPath, "priorClassifier");
    ClusterClassifier prior = newKlusterClassifier();
    prior.writeToSeqFiles(path);
    assertEquals(3, prior.getModels().size());
    System.out.println("Prior");
    for (Cluster cluster : prior.getModels()) {
      System.out.println(cluster.asFormatString(null));
    }
    ClusterIterator.iterateSeq(conf, pointsPath, path, outPath, 5);
    
    for (int i = 1; i <= 4; i++) {
      System.out.println("Classifier-" + i);
      ClusterClassifier posterior = new ClusterClassifier();
      String name = i == 4 ? "clusters-4-final" : "clusters-" + i;
      posterior.readFromSeqFiles(conf, new Path(outPath, name));
      assertEquals(3, posterior.getModels().size());
      for (Cluster cluster : posterior.getModels()) {
        System.out.println(cluster.asFormatString(null));
      }
      
    }
  }

View Full Code Here

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

    Configuration conf = getConfiguration();
    FileSystem fs = FileSystem.get(pointsPath.toUri(), conf);
    List<VectorWritable> points = TestKmeansClustering.getPointsWritable(TestKmeansClustering.REFERENCE);
    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file1"), fs, conf);
    Path path = new Path(priorPath, "priorClassifier");
    ClusterClassifier prior = newKlusterClassifier();
    prior.writeToSeqFiles(path);
    ClusteringPolicy policy = new KMeansClusteringPolicy();
    ClusterClassifier.writePolicy(policy, path);
    assertEquals(3, prior.getModels().size());
    System.out.println("Prior");
    for (Cluster cluster : prior.getModels()) {
      System.out.println(cluster.asFormatString(null));
    }
    ClusterIterator.iterateMR(conf, pointsPath, path, outPath, 5);
    
    for (int i = 1; i <= 4; i++) {
      System.out.println("Classifier-" + i);
      ClusterClassifier posterior = new ClusterClassifier();
      String name = i == 4 ? "clusters-4-final" : "clusters-" + i;
      posterior.readFromSeqFiles(conf, new Path(outPath, name));
      assertEquals(3, posterior.getModels().size());
      for (Cluster cluster : posterior.getModels()) {
        System.out.println(cluster.asFormatString(null));
      }     
    }
  }

View Full Code Here

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

    }
  }
  
  @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

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

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.