Package org.apache.mahout.classifier.df.node

Examples of org.apache.mahout.classifier.df.node.Node

81
82
83
84
85
86
87
88
89
90
91
  @Test
  public void testTreeVisualize() throws Exception {
    // build tree
    DecisionTreeBuilder builder = new DecisionTreeBuilder();
    builder.setM(data.getDataset().nbAttributes() - 1);
    Node tree = builder.build(rng, data);
   
    assertEquals("\noutlook = rainy\n|   windy = FALSE : yes\n|   windy = TRUE : no\n"
            + "outlook = sunny\n|   humidity < 85 : yes\n|   humidity >= 85 : no\n"
            + "outlook = overcast : yes", TreeVisualizer.toString(tree, data.getDataset(), ATTR_NAMES));
  }
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
      partitions.add(partition);

      int nbTrees = Step1Mapper.nbTrees(NUM_MAPS, NUM_TREES, partition);

      for (int treeId = 0; treeId < nbTrees; treeId++) {
        Node tree = new Leaf(rng.nextInt(100));

        keys[index] = new TreeID(partition, treeId);
        values[index] = new MapredOutput(tree, nextIntArray(rng, NUM_INSTANCES));

        index++;
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
      partitions.add(partition);

      int nbTrees = Step1Mapper.nbTrees(NUM_MAPS, NUM_TREES, partition);

      for (int treeId = 0; treeId < nbTrees; treeId++) {
        Node tree = new Leaf(rng.nextInt(100));

        keys[index] = new TreeID(partition, treeId);
        values[index] = new MapredOutput(tree, nextIntArray(rng, NUM_INSTANCES));

        index++;
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
   
    log.debug("Building {} trees", nbTrees);
    for (int treeId = 0; treeId < nbTrees; treeId++) {
      log.debug("Building tree number : {}", treeId);
     
      Node tree = bagging.build(rng);
     
      key.set(partition, firstTreeId + treeId);
     
      if (isOutput()) {
        MapredOutput emOut = new MapredOutput(tree);
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
   
    log.debug("Building {} trees", nbTrees);
    for (int treeId = 0; treeId < nbTrees; treeId++) {
      log.debug("Building tree number : {}", treeId);
     
      Node tree = bagging.build(rng);
     
      key.set(partition, firstTreeId + treeId);
     
      if (!isNoOutput()) {
        MapredOutput emOut = new MapredOutput(tree);
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
  void map(IntWritable key, Context context) throws IOException, InterruptedException {
   
    initRandom((InMemInputSplit) context.getInputSplit());
   
    log.debug("Building...");
    Node tree = bagging.build(rng);
   
    if (!isNoOutput()) {
      log.debug("Outputing...");
      MapredOutput mrOut = new MapredOutput(tree);
     
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
      }
    } else if (node instanceof NumericalNode) {
      NumericalNode nnode = (NumericalNode) node;
      int attr = (Integer) fields.get("NumericalNode.attr").get(nnode);
      double split = (Double) fields.get("NumericalNode.split").get(nnode);
      Node loChild = (Node) fields.get("NumericalNode.loChild").get(nnode);
      Node hiChild = (Node) fields.get("NumericalNode.hiChild").get(nnode);
      buff.append('\n');
      for (int j = 0; j < layer; j++) {
        buff.append("|   ");
      }
      buff.append((attrNames == null ? attr : attrNames[attr]) + " < " + doubleToString(split));
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
      }
    } else if (node instanceof NumericalNode) {
      NumericalNode nnode = (NumericalNode) node;
      int attr = (Integer) fields.get("NumericalNode.attr").get(nnode);
      double split = (Double) fields.get("NumericalNode.split").get(nnode);
      Node loChild = (Node) fields.get("NumericalNode.loChild").get(nnode);
      Node hiChild = (Node) fields.get("NumericalNode.hiChild").get(nnode);

      if (instance.get(attr) < split) {
        buff.append("(" + (attrNames == null ? attr : attrNames[attr]) + " = "
          + doubleToString(instance.get(attr)) + ") < " + doubleToString(split));
        buff.append(" -> ");
View Full Code Here
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
    if (alreadySelected) {
      // attribute already selected
      log.warn("attribute {} already selected in a parent node", best.getAttr());
    }

    Node childNode;
    if (data.getDataset().isNumerical(best.getAttr())) {
      boolean[] temp = null;

      Data loSubset = data.subset(Condition.lesser(best.getAttr(), best.getSplit()));
      Data hiSubset = data.subset(Condition.greaterOrEquals(best.getAttr(), best.getSplit()));

      if (loSubset.isEmpty() || hiSubset.isEmpty()) {
        // the selected attribute did not change the data, avoid using it in the child notes
        selected[best.getAttr()] = true;
      } else {
        // the data changed, so we can unselect all previousely selected NUMERICAL attributes
        temp = selected;
        selected = cloneCategoricalAttributes(data.getDataset(), selected);
      }

      // size of the subset is less than the minSpitNum
      if (loSubset.size() < minSplitNum || hiSubset.size() < minSplitNum) {
        // branch is not split
        double label;
        if (data.getDataset().isNumerical(data.getDataset().getLabelId())) {
          label = sum / data.size();
        } else {
          label = data.majorityLabel(rng);
        }
        log.debug("branch is not split Leaf({})", label);
        return new Leaf(label);
      }

      Node loChild = build(rng, loSubset);
      Node hiChild = build(rng, hiSubset);

      // restore the selection state of the attributes
      if (temp != null) {
        selected = temp;
      } else {
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
  @Test
  public void testTreeVisualize() throws Exception {
    // build tree
    DecisionTreeBuilder builder = new DecisionTreeBuilder();
    builder.setM(data.getDataset().nbAttributes() - 1);
    Node tree = builder.build(rng, data);
   
    assertEquals(TreeVisualizer.toString(tree, data.getDataset(), ATTR_NAMES),
      "\noutlook = rainy\n|   windy = FALSE : yes\n|   windy = TRUE : no\n"
        + "outlook = sunny\n|   humidity < 85 : yes\n|   humidity >= 85 : no\n"
        + "outlook = overcast : yes");
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.df.node.Node

  • org.apache.mahout.classifier.df.builder.DecisionTreeBuilder
  • org.apache.mahout.classifier.df.builder.DefaultTreeBuilder
  • org.apache.mahout.classifier.df.mapreduce.inmem.InMemMapper
  • org.apache.mahout.classifier.df.mapreduce.partial.PartialBuilderTest
  • org.apache.mahout.classifier.df.mapreduce.partial.Step1Mapper
  • org.apache.mahout.classifier.df.tools.TreeVisualizer
  • org.apache.mahout.classifier.df.tools.VisualizerTest
    • 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.