Package org.apache.mahout.clustering

Examples of org.apache.mahout.clustering.Cluster

31
32
33
34
35
36
37
38
39
40
41
        .newInstance();
    Writable value = (Writable) reader.getValueClass()
        .newInstance();
   
    while (reader.next(key, value)) {
      Cluster cluster = (Cluster) value;
      clusters.add(cluster);
      value = (Writable) reader.getValueClass()
          .newInstance();
    }
   
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
    int row = 0;
    StringBuilder models = new StringBuilder(100);
    for (Cluster[] r : result) {
      models.append("sample[").append(row++).append("]= ");
      for (int k = 0; k < r.length; k++) {
        Cluster model = r[k];
        if (model.count() > significant) {
          models.append('m').append(k).append(model.asFormatString(null)).append(", ");
        }
      }
      models.append('\n');
    }
    models.append('\n');
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
163
164
  private void pruneInvalidClusters() {
    if (pruned) {
      return;
    }
    for (Iterator<Cluster> it = clusters.iterator(); it.hasNext();) {
      Cluster cluster = it.next();
      if (invalidCluster(cluster)) {
        log.info("Pruning cluster Id={}", cluster.getId());
        it.remove();
        representativePoints.remove(cluster.getId());
      }
    }
    pruned = true;
  }
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
130
131
132
  private void pruneInvalidClusters() {
    if (pruned) {
      return;
    }
    for (Iterator<Cluster> it = clusters.iterator(); it.hasNext();) {
      Cluster cluster = it.next();
      if (invalidCluster(cluster)) {
        log.info("Pruning cluster Id={}", cluster.getId());
        it.remove();
        representativePoints.remove(cluster.getId());
      }
    }
    pruned = true;
  }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
153
154
    double max = 0;
    double min = Double.MAX_VALUE;
    double sum = 0;
    int count = 0;
    for (int i = 0; i < clusters.size(); i++) {
      Cluster clusterI = clusters.get(i);
      for (int j = i + 1; j < clusters.size(); j++) {
        Cluster clusterJ = clusters.get(j);
        double d = measure.distance(clusterI.getCenter(), clusterJ.getCenter());
        min = Math.min(d, min);
        max = Math.max(d, max);
        sum += d;
        count++;
      }
View Full Code Here
98
99
100
101
102
103
104
105
106
  }
 
  /** Reads a typed Model instance from the input stream */
  public static Cluster readModel(DataInput in) throws IOException {
    String modelClassName = in.readUTF();
    Cluster model = ClassUtils.instantiateAs(modelClassName, Cluster.class);
    model.readFields(in);
    return model;
  }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
    int row = 0;
    StringBuilder models = new StringBuilder(100);
    for (Cluster[] r : result) {
      models.append("sample[").append(row++).append("]= ");
      for (int k = 0; k < r.length; k++) {
        Cluster model = r[k];
        if (model.count() > significant) {
          models.append('m').append(k).append(model.asFormatString(null)).append(", ");
        }
      }
      models.append('\n');
    }
    models.append('\n');
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
        SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
        try {
          Writable key = reader.getKeyClass().asSubclass(Writable.class).newInstance();
          Writable value = reader.getValueClass().asSubclass(Writable.class).newInstance();
          while (reader.next(key, value)) {
            Cluster cluster = (Cluster) value;
            String fmtStr = useJSON ? cluster.asJsonString() : cluster.asFormatString(dictionary);
            if (subString > 0 && fmtStr.length() > subString) {
              writer.write(':');
              writer.write(fmtStr, 0, Math.min(subString, fmtStr.length()));
            } else {
              writer.write(fmtStr);
            }

            writer.write('\n');

            if (dictionary != null) {
              String topTerms = getTopFeatures(cluster.getCenter(), dictionary, numTopFeatures);
              writer.write("\tTop Terms: ");
              writer.write(topTerms);
              writer.write('\n');
            }

            List<WeightedVectorWritable> points = clusterIdToPoints.get(cluster.getId());
            if (points != null) {
              writer.write("\tWeight:  Point:\n\t");
              for (Iterator<WeightedVectorWritable> iterator = points.iterator(); iterator.hasNext();) {
                WeightedVectorWritable point = iterator.next();
                writer.write(String.valueOf(point.getWeight()));
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
        Path inPart = part.getPath();
        SequenceFile.Reader reader = new SequenceFile.Reader(fs, inPart, conf);
        Writable key = reader.getKeyClass().asSubclass(Writable.class).newInstance();
        Writable value = reader.getValueClass().asSubclass(Writable.class).newInstance();
        while (reader.next(key, value)) {
          Cluster cluster = (Cluster) value;
          clusters.add(cluster);
          value = reader.getValueClass().asSubclass(Writable.class).newInstance();
        }
        reader.close();
      }
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
179
180
181
  private void pruneInvalidClusters() {
    if (pruned) {
      return;
    }
    for (Iterator<Cluster> it = clusters.iterator(); it.hasNext();) {
      Cluster cluster = it.next();
      if (invalidCluster(cluster)) {
        log.info("Pruning cluster Id=" + cluster.getId());
        it.remove();
        representativePoints.remove(cluster.getId());
      }
    }
    pruned = true;
  }
View Full Code Here
TOP

Related Classes of org.apache.mahout.clustering.Cluster

  • com.ikanow.infinit.e.processing.custom.utils.HadoopUtils
  • mia.clustering.ch10.InterClusterDistances
  • org.apache.mahout.clustering.cdbw.CDbwEvaluator
  • org.apache.mahout.clustering.classify.ClusterClassificationDriver
  • org.apache.mahout.clustering.classify.ClusterClassificationMapper
  • org.apache.mahout.clustering.classify.ClusterClassifier
  • org.apache.mahout.clustering.dirichlet.DirichletCluster
  • org.apache.mahout.clustering.dirichlet.DirichletReducer
  • org.apache.mahout.clustering.dirichlet.JsonClusterAdapter
  • org.apache.mahout.clustering.dirichlet.TestL1ModelClustering
    • 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.