Package org.apache.mahout.vectorizer.encoders

Examples of org.apache.mahout.vectorizer.encoders.Dictionary.intern()

99
100
101
102
103
104
105
106
107
108
109
            null, true, conf);
    int k = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      String ng = next.getFirst().toString();
      int actual = asfDictionary.intern(ng);
      //we already have encoded
      learningAlgorithm.train(actual, next.getSecond().get());
      k++;
      State<AdaptiveLogisticRegression.Wrapper, CrossFoldLearner> best = learningAlgorithm.getBest();
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
    learningAlgorithm.setAveragingWindow(500);

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    Collections.shuffle(files);
    System.out.printf("%d training files\n", files.size());
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
    int k = 0;


    for (File file : files) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      learningAlgorithm.train(actual, v);

      k++;
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
    learningAlgorithm.setAveragingWindow(500);

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    Collections.shuffle(files);
    System.out.println(files.size() + " training files");
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
    int k = 0;


    for (File file : files) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      learningAlgorithm.train(actual, v);

      k++;
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.