Package cc.mallet.cluster

Examples of cc.mallet.cluster.Clustering

46
47
48
49
50
51
52
53
54
55
56
 
  public void testEvaluators ()
  {
    InstanceList instances = new InstanceList(new Randoms(1), 100, 2).subList(0,12);
    System.err.println(instances.size() + " instances");
    Clustering truth = generateTruth(instances);
    System.err.println("truth=" + truth);

    Clustering[] predicted = generatePredicted(instances);
    ClusteringEvaluator pweval = new PairF1Evaluator();
    ClusteringEvaluator bceval = new BCubedEvaluator();
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
   
    public Instance pipe (Instance carrier) {
      boolean mergeFirst = false;
     
      AgglomerativeNeighbor neighbor = (AgglomerativeNeighbor)carrier.getData();
      Clustering original = neighbor.getOriginal();
      InstanceList list = original.getInstances();     
      int[] mergedIndices = neighbor.getNewCluster();
      boolean match = true;
      for (int i = 0; i < mergedIndices.length; i++) {
        for (int j = i + 1; j < mergedIndices.length; j++) {
          if ((original.getLabel(mergedIndices[i]) !=
               original.getLabel(mergedIndices[j])) || mergeFirst) {
            FeatureVector fvi = (FeatureVector)list.get(mergedIndices[i]).getData();
            FeatureVector fvj = (FeatureVector)list.get(mergedIndices[j]).getData();
            if (!(fvi.contains("feature0") && fvj.contains("feature0"))) {
              match = false;
              break;             
            }
          }
        }
      }

      PropertyList pl = null;
      if (match)
        pl = PropertyList.add("Match", 1.0, pl);
      else
        pl = PropertyList.add("NoMatch", 1.0, pl);
     
      FeatureVector fv = new FeatureVector ((Alphabet)getDataAlphabet(),
                                            pl, true);
      carrier.setData(fv);

      boolean positive = true;
      for (int i = 0; i < mergedIndices.length; i++) {
        for (int j = i + 1; j < mergedIndices.length; j++) {
          if (original.getLabel(mergedIndices[i]) != original.getLabel(mergedIndices[j])) {
            positive = false;
            break;
          }
        }
      }
View Full Code Here
29
30
31
32
33
34
35
    super (name);
  }

  private Clustering generateClustering (InstanceList instances) {
    int[] labels = new int[]{0,0,0,1,1,1,2,2,2,2};
    return new Clustering(instances, 3, labels);
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
  public void testEvaluators ()
  {
    Randoms random = new Randoms(1);
    InstanceList instances = new InstanceList(random, 100, 2).subList(0,10);
    System.err.println(instances.size() + " instances");
    Clustering clustering = generateClustering(instances);
    System.err.println("clustering=" + clustering);

    System.err.println("ClusterSampleIterator");
    NeighborIterator iter = new ClusterSampleIterator(clustering,
                                                      random,
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
    logger.info("number clusterings=" + clusterings.size());

    // Prune clusters based on size.
    if (minClusterSize.value > 1) {
      for (int i = 0; i < clusterings.size(); i++) {
        Clustering clustering = clusterings.get(i);
        InstanceList oldInstances = clustering.getInstances();
        Alphabet alph = oldInstances.getDataAlphabet();
        LabelAlphabet lalph = (LabelAlphabet) oldInstances.getTargetAlphabet();
        if (alph == null) alph = new Alphabet();
        if (lalph == null) lalph = new LabelAlphabet();
        Pipe noop = new Noop(alph, lalph);
        InstanceList newInstances = new InstanceList(noop);
        for (int j = 0; j < oldInstances.size(); j++) {
          int label = clustering.getLabel(j);
          Instance instance = oldInstances.get(j);
          if (clustering.size(label) >= minClusterSize.value)
            newInstances.add(noop.pipe(new Instance(instance.getData(), lalph.lookupLabel(new Integer(label)), instance.getName(), instance.getSource())));
        }
        clusterings.set(i, createSmallerClustering(newInstances));
      }
      if (outputPrefixFile.value != null) {
        try {
          ObjectOutputStream oos =
            new ObjectOutputStream(new FileOutputStream(outputPrefixFile.value));
          oos.writeObject(clusterings);
          oos.close();
        } catch (Exception e) {
          logger.warning("Exception writing clustering to file " + outputPrefixFile.value                        + " " + e);
          e.printStackTrace();
        }
      }
    }
   
   
    // Split into training/testing
    if (trainingProportion.value > 0) {
      if (clusterings.size() > 1)
        throw new IllegalArgumentException("Expect one clustering to do train/test split, not " + clusterings.size());
      Clustering clustering = clusterings.get(0);
      int targetTrainSize = (int)(trainingProportion.value * clustering.getNumInstances());
      TIntHashSet clustersSampled = new TIntHashSet();
      Randoms random = new Randoms(123);
      LabelAlphabet lalph = new LabelAlphabet();
      InstanceList trainingInstances = new InstanceList(new Noop(null, lalph));
      while (trainingInstances.size() < targetTrainSize) {
        int cluster = random.nextInt(clustering.getNumClusters());
        if (!clustersSampled.contains(cluster)) {
          clustersSampled.add(cluster);
          InstanceList instances = clustering.getCluster(cluster);
          for (int i = 0; i < instances.size(); i++) {
            Instance inst = instances.get(i);
            trainingInstances.add(new Instance(inst.getData(), lalph.lookupLabel(new Integer(cluster)), inst.getName(), inst.getSource()));
          }
        }
      }
      trainingInstances.shuffle(random);
      Clustering trainingClustering = createSmallerClustering(trainingInstances);
     
      InstanceList testingInstances = new InstanceList(null, lalph);
      for (int i = 0; i < clustering.getNumClusters(); i++) {
        if (!clustersSampled.contains(i)) {
          InstanceList instances = clustering.getCluster(i);
          for (int j = 0; j < instances.size(); j++) {
            Instance inst = instances.get(j);
            testingInstances.add(new Instance(inst.getData(), lalph.lookupLabel(new Integer(i)), inst.getName(), inst.getSource()));
          }         
        }
      }
      testingInstances.shuffle(random);
      Clustering testingClustering = createSmallerClustering(testingInstances);
      logger.info(outputPrefixFile.value + ".train : " + trainingClustering.getNumClusters() + " objects");
      logger.info(outputPrefixFile.value + ".test : " + testingClustering.getNumClusters() + " objects");
      if (outputPrefixFile.value != null) {
        try {
          ObjectOutputStream oos =
            new ObjectOutputStream(new FileOutputStream(new File(outputPrefixFile.value + ".train")));
          oos.writeObject(new Clusterings(new Clustering[]{trainingClustering}));
View Full Code Here
136
137
138
139
140
141
142
143
     
    }
  }

  private static Clustering createSmallerClustering (InstanceList instances) {
    Clustering c = ClusterUtils.createSingletonClustering(instances);
    return ClusterUtils.mergeInstancesWithSameLabel(c);
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
      e.printStackTrace();
    }

    if (printOption.value) {
      for (int i = 0; i < clusterings.size(); i++) {
        Clustering c = clusterings.get(i);
        for (int j = 0; j < c.getNumClusters(); j++) {
          InstanceList cluster = c.getCluster(j);
          for (int k = 0; k < cluster.size(); k++) {
            System.out.println("clustering " + i + " cluster " + j + " element " + k + " " + cluster.get(k).getData());
          }
          System.out.println();
        }
      }
    }
    logger.info("number clusterings=" + clusterings.size());

    int totalInstances = 0;
    int totalClusters = 0;

    for (int i = 0; i < clusterings.size(); i++) {
      Clustering c = clusterings.get(i);
      totalClusters += c.getNumClusters();
      totalInstances += c.getNumInstances();
    }
    logger.info("total instances=" + totalInstances);
    logger.info("total clusters=" + totalClusters);
    logger.info("instances per clustering=" + (double) totalInstances
                / clusterings.size());
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
                        new Integer(label), record.toString(),
                        record.toString()));
        }
      }
      clusterings[i] =
          new Clustering(instances, subdirs.length, labels.toNativeArray());
    }

    logger.info("\nread " + fi + " objects in " + clusterings.length + " clusterings.");
    try {
      ObjectOutputStream oos =
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
114
      evaluator = new ClusteringEvaluators(
          new ClusteringEvaluator[] { new BCubedEvaluator(),
              new PairF1Evaluator(), new MUCEvaluator(), new AccuracyEvaluator() });
    ArrayList<Clustering> predictions = new ArrayList<Clustering>();
    for (int i = 0; i < testing.size(); i++) {
      Clustering clustering = testing.get(i);
      Clustering predicted = clusterer.cluster(clustering.getInstances());
      predictions.add(predicted);
      logger.info(evaluator.evaluate(clustering, predicted));
    }
    logger.info(evaluator.evaluateTotals());
   
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
    }

    public Instance pipe(Instance carrier) {
      AgglomerativeNeighbor neighbor = (AgglomerativeNeighbor) carrier
          .getData();
      Clustering original = neighbor.getOriginal();
      int[] cluster1 = neighbor.getOldClusters()[0];
      int[] cluster2 = neighbor.getOldClusters()[1];
      InstanceList list = original.getInstances();
      int[] mergedIndices = neighbor.getNewCluster();
      Record[] records = array2Records(mergedIndices, list);
      Alphabet fieldAlph = records[0].fieldAlphabet();
      Alphabet valueAlph = records[0].valueAlphabet();

      PropertyList features = null;
      features = addExactMatch(records, fieldAlph, valueAlph, features);
      features = addApproxMatch(records, fieldAlph, valueAlph, features);
      features = addSubstringMatch(records, fieldAlph, valueAlph, features);
      carrier
          .setData(new FeatureVector(getDataAlphabet(), features,
              true));

      LabelAlphabet ldict = (LabelAlphabet) getTargetAlphabet();
      String label = (original.getLabel(cluster1[0]) == original
          .getLabel(cluster2[0])) ? "YES" : "NO";
      carrier.setTarget(ldict.lookupLabel(label));     
      return carrier;
    }
View Full Code Here
TOP

Related Classes of cc.mallet.cluster.Clustering

  • cc.mallet.cluster.clustering_scorer.PairwiseScorer
  • cc.mallet.cluster.evaluate.tests.TestClusteringEvaluators
  • cc.mallet.cluster.examples.FirstOrderClusterExample
  • cc.mallet.cluster.examples.FirstOrderClusterExample$OverlappingFeaturePipe
  • cc.mallet.cluster.iterator.tests.TestIterators
  • cc.mallet.cluster.neighbor_evaluator.MedoidEvaluator
  • cc.mallet.cluster.neighbor_evaluator.PairwiseEvaluator
  • cc.mallet.cluster.tui.Clusterings2Clusterer
  • cc.mallet.cluster.tui.Clusterings2Clusterer$ClusteringPipe
  • cc.mallet.cluster.tui.Clusterings2Clusterings
    • 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.