Package org.apache.mahout.classifier

Examples of org.apache.mahout.classifier.NewsgroupHelper

51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
    model.close();

    Map<String, Set<Integer>> traceDictionary = Maps.newTreeMap();
    ModelDissector md = new ModelDissector();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setTraceDictionary(traceDictionary);
    helper.getBias().setTraceDictionary(traceDictionary);

    for (File file : permute(files, helper.getRandom()).subList(0, 500)) {
      String ng = file.getParentFile().getName();
      int actual = dictionary.intern(ng);

      traceDictionary.clear();
      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      md.update(v, traceDictionary, model);
    }

    List<String> ngNames = Lists.newArrayList(dictionary.values());
    List<ModelDissector.Weight> weights = md.summary(100);
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
    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();
      double score = result.maxValue();
      double ll = classifier.logLikelihood(actual, input);
      ClassifierResult cr = new ClassifierResult(newsGroups.values().get(cat), score, ll);
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
      leakType = Integer.parseInt(args[1]);
    }

    Dictionary newsGroups = new Dictionary();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setProbes(2);
    AdaptiveLogisticRegression learningAlgorithm =
        new AdaptiveLogisticRegression(20, NewsgroupHelper.FEATURES, new L1());
    learningAlgorithm.setInterval(800);
    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");
    SGDInfo info = new SGDInfo();

    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++;
      State<AdaptiveLogisticRegression.Wrapper, CrossFoldLearner> best = learningAlgorithm.getBest();
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
    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();
      double ll = classifier.logLikelihood(actual, input);
      ClassifierResult cr = new ClassifierResult(newsGroups.values().get(cat), score, ll);
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
      leakType = Integer.parseInt(args[1]);
    }

    Dictionary newsGroups = new Dictionary();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setProbes(2);
    AdaptiveLogisticRegression learningAlgorithm = new AdaptiveLogisticRegression(20, NewsgroupHelper.FEATURES, new L1());
    learningAlgorithm.setInterval(800);
    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());
    SGDInfo info = new SGDInfo();

    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++;
      State<AdaptiveLogisticRegression.Wrapper, CrossFoldLearner> best = learningAlgorithm.getBest();
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
    model.close();

    Map<String, Set<Integer>> traceDictionary = Maps.newTreeMap();
    ModelDissector md = new ModelDissector();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setTraceDictionary(traceDictionary);
    helper.getBias().setTraceDictionary(traceDictionary);

    for (File file : permute(files, helper.getRandom()).subList(0, 500)) {
      String ng = file.getParentFile().getName();
      int actual = dictionary.intern(ng);

      traceDictionary.clear();
      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      md.update(v, traceDictionary, model);
    }

    List<String> ngNames = Lists.newArrayList(dictionary.values());
    List<ModelDissector.Weight> weights = md.summary(100);
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
      leakType = Integer.parseInt(args[1]);
    }

    Dictionary newsGroups = new Dictionary();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setProbes(2);
    AdaptiveLogisticRegression learningAlgorithm =
        new AdaptiveLogisticRegression(20, NewsgroupHelper.FEATURES, new L1());
    learningAlgorithm.setInterval(800);
    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");
    SGDInfo info = new SGDInfo();

    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++;
      State<AdaptiveLogisticRegression.Wrapper, CrossFoldLearner> best = learningAlgorithm.getBest();
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
    model.close();

    Map<String, Set<Integer>> traceDictionary = Maps.newTreeMap();
    ModelDissector md = new ModelDissector();

    NewsgroupHelper helper = new NewsgroupHelper();
    helper.getEncoder().setTraceDictionary(traceDictionary);
    helper.getBias().setTraceDictionary(traceDictionary);

    for (File file : permute(files, helper.getRandom()).subList(0, 500)) {
      String ng = file.getParentFile().getName();
      int actual = dictionary.intern(ng);

      traceDictionary.clear();
      Vector v = helper.encodeFeatureVector(file, actual, leakType, overallCounts);
      md.update(v, traceDictionary, model);
    }

    List<String> ngNames = Lists.newArrayList(dictionary.values());
    List<ModelDissector.Weight> weights = md.summary(100);
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.NewsgroupHelper

  • org.apache.lucene.analysis.TokenStream
  • org.apache.mahout.classifier.sgd.SGDHelper
  • org.apache.mahout.classifier.sgd.TestNewsGroups
  • org.apache.mahout.classifier.sgd.TrainNewsGroups
  • org.apache.mahout.math.RandomAccessSparseVector
  • org.apache.mahout.math.Vector
  • java.io.Reader
  • java.io.BufferedReader
  • java.util.Date
  • java.io.StringReader
    • 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.