Examples of RAMTrainingCorpus

Examples of com.digitalpebble.classification.RAMTrainingCorpus

51
52
53
54
55
56
57
58
59
60
61
62
    }   
    Learner creator = Learner.getLearner("./temp",Learner.LibSVMModelCreator,true);
    creator.setParameters(parameters);
    creator.setMethod(Parameters.WeightingMethod.BOOLEAN);

    RAMTrainingCorpus subjectiveCorpus = getCorpus(fileSubj,"subjective",creator);
    RAMTrainingCorpus objectiveCorpus = getCorpus(fileObj,"objective",creator);
    subjectiveCorpus.addAll(objectiveCorpus);
   
    // filter some of the attributes out based on their LLR score
    creator.keepTopNAttributesLLR(2000);
   
View Full Code Here

Examples of com.digitalpebble.classification.RAMTrainingCorpus

131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
  
  private RAMTrainingCorpus getCorpus(String file, String label, Object operator) throws IOException{
    File original = new File(file);
    BufferedReader reader = new BufferedReader(new FileReader(original));
    String line;
    RAMTrainingCorpus corpusList = new RAMTrainingCorpus();
    while ((line=reader.readLine())!=null)
    {
      String[] tokens = line.split("\\W");
      // lower case
      for (int i=0;i<tokens.length;i++){
        tokens[i]=tokens[i].toLowerCase();
      }     
     
      Document doc = null;
      if (operator instanceof Learner)
      doc = ((Learner)operator).createDocument(tokens,label);
      else
        doc = ((TextClassifier)operator).createDocument(tokens);
      corpusList.add(doc);
    }
    reader.close();
    return corpusList;
  }
View Full Code Here

Examples of com.digitalpebble.classification.RAMTrainingCorpus

56
57
58
59
60
61
62
63
64
65
66
67
68
    fields3[2] = new Field("title", new String[] { "some", "different",
        "content" });
    learner.setMethod(Parameters.WeightingMethod.TFIDF);
    Document doc3 = learner.createDocument(fields3, "small");

    RAMTrainingCorpus corpus = new RAMTrainingCorpus();
    corpus.add(doc);
    corpus.add(doc2);
    learner.learn(corpus);

    TextClassifier classi = TextClassifier.getClassifier(tempFile);
    double[] scores = classi.classify(doc);
    assertEquals("large", classi.getBestLabel(scores));
View Full Code Here

Examples of com.digitalpebble.classification.RAMTrainingCorpus

37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
        "this", "will", "have", "a", "small", "value" };
    Document doc2 = learner.createDocument(simplecontent, "small");

    // com.digitalpebble.classification.TrainingCorpus tc =
    // learner.getFileTrainingCorpus();
    com.digitalpebble.classification.TrainingCorpus tc = new RAMTrainingCorpus();
    tc.addDocument(doc);
    tc.addDocument(doc2);
    tc.close();

    int numDoc = 0;

    Iterator iter = tc.iterator();
    while (iter.hasNext()) {
      numDoc++;
      iter.next();
    }

    assertEquals(2, numDoc);

    tc = learner.getFileTrainingCorpus();
    tc.addDocument(doc);
    tc.addDocument(doc2);
    tc.close();

    numDoc = 0;

    iter = tc.iterator();
    while (iter.hasNext()) {
      numDoc++;
      iter.next();
    }
View Full Code Here

Examples of com.digitalpebble.classification.RAMTrainingCorpus

172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
    evaluateWeightingSchemes(Parameters.WeightingMethod.TFIDF);
  }

  private void evaluateWeightingSchemes(WeightingMethod method) {

    RAMTrainingCorpus corpus = new RAMTrainingCorpus();

    learner.setMethod(method);

    for (String[] content : docs) {
      Document doc = learner.createDocument(content);
      corpus.add(doc);
    }

    Iterator<Document> corpusIter = corpus.iterator();

    Map<Integer, String> invertedIndex = learner.getLexicon()
        .getInvertedIndex();

    List<Map> expectedset = references.get(method);

    // check that we have the same number of docs in the corpus
    // and in the ref

    assertEquals(expectedset.size(), corpus.size());

    for (Map<String, Double> ref : expectedset) {
      Document doc = corpusIter.next();
      Vector vector = doc.getFeatureVector(learner.getLexicon());
      // now let's compare what we wanted to have with the content of the
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.