Examples of intern()

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

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

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

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

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

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

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

73
74
75
76
77
78
79
80
81
82
83
    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.println(files.size() + " test files");
    ResultAnalyzer ra = new ResultAnalyzer(newsGroups.values(), "DEFAULT");
View Full Code Here

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

82
83
84
85
86
87
88
89
90
91
92
    System.out.println(files.size() + " test files");
    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();
      //no leak type ensures this is a normal vector
      Vector input = helper.encodeFeatureVector(file, actual, 0, overallCounts);
      Vector result = classifier.classifyFull(input);
      int cat = result.maxValueIndex();
View Full Code Here

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

87
88
89
90
91
92
93
94
95
96
97
                                                          true,
                                                          conf);
    long numItems = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      asfDictionary.intern(next.getFirst().toString());
      numItems++;
    }

    System.out.println(numItems + " training files");
View Full Code Here

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

102
103
104
105
106
107
108
109
110
111
112
            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

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

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

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

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

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

83
84
85
86
87
88
89
90
91
92
93
        null, true, conf);

    long numItems = 0;
    while (iter.hasNext()) {
      Pair<Text, VectorWritable> next = iter.next();
      asfDictionary.intern(next.getFirst().toString());
      numItems++;
    }

    System.out.println(numItems + " test files");
    ResultAnalyzer ra = new ResultAnalyzer(asfDictionary.values(), "DEFAULT");
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.