Package org.apache.mahout.vectorizer.encoders

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

61
62
63
64
65
66
67
68
69
70
71
            .lambda(3.0e-5)
            .learningRate(20);
   
    List<File> files = new ArrayList<File>();
    for (File newsgroup : base.listFiles()) {
      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
142
143
144
145
146
147
148
149
150
151
152
    List<File> files = Lists.newArrayList();
    File[] directories = base.listFiles();
    Arrays.sort(directories, Ordering.usingToString());
    for (File newsgroup : directories) {
      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
158
159
160
161
162
163
164
165
166
167
168
    int k = 0;
    double step = 0;
    int[] bumps = {1, 2, 5};
    for (File file : files) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

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

      k++;
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
    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
156
157
158
159
160
161
162
163
164
165
166
    int k = 0;
    double step = 0;
    int[] bumps = {1, 2, 5};
    for (File file : files.subList(0, 10000)) {
      String ng = file.getParentFile().getName();
      int actual = newsGroups.intern(ng);

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

      k++;
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
    Multiset<String> overallCounts = HashMultiset.create();

    List<File> files = Lists.newArrayList();
    for (File newsgroup : base.listFiles()) {
      if (newsgroup.isDirectory()) {
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    System.out.printf("%d test files\n", files.size());
    ResultAnalyzer ra = new ResultAnalyzer(newsGroups.values(), "DEFAULT");
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
    System.out.printf("%d test files\n", files.size());
    ResultAnalyzer ra = new ResultAnalyzer(newsGroups.values(), "DEFAULT");
    for (File file : files) {
      String ng = file.getParentFile().getName();

      int actual = newsGroups.intern(ng);
      NewsgroupHelper helper = new NewsgroupHelper();
      Vector input = helper.encodeFeatureVector(file, actual, 0, overallCounts);//no leak type ensures this is a normal vector
      Vector result = classifier.classifyFull(input);
      int cat = result.maxValueIndex();
      double score = result.maxValue();
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
    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
113
114
115
116
117
118
119
120
121
122
123
    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
205
206
207
208
209
210
211
212
213
214
215
        v.set(i++, Double.parseDouble(value));
      }
      data.add(v);

      // and the target
      target.add(dict.intern(Iterables.get(values, 4)));
    }

    // randomize the order ... original data has each species all together
    // note that this randomization is deterministic
    Random random = RandomUtils.getRandom();
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.