Package cc.mallet.types

Examples of cc.mallet.types.TokenSequence

146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
    return (String[]) wordarray.toArray(new String[]{});
  }
 
  public Instance pipe (Instance carrier)
  {
    TokenSequence ts = (TokenSequence) carrier.getData();
    // xxx This doesn't seem so efficient.  Perhaps have TokenSequence
    // use a LinkedList, and remove Tokens from it? -?
    // But a LinkedList implementation of TokenSequence would be quite inefficient -AKM
    TokenSequence ret = new TokenSequence ();
    Token prevToken = null;
    for (int i = 0; i < ts.size(); i++) {
      Token t = ts.get(i);
      if (! stoplist.contains (caseSensitive ? t.getText() : t.getText().toLowerCase())) {
        // xxx Should we instead make and add a copy of the Token?
        ret.add (t);
        prevToken = t;
      } else if (markDeletions && prevToken != null)
        prevToken.setProperty (FeatureSequenceWithBigrams.deletionMark, t.getText());
    }
    carrier.setData(ret);
View Full Code Here
62
63
64
65
66
67
68
69
70
71
    do {
      count = br.read (buf, 0, BUFSIZE);
      sb.append (buf);
    } while (count == BUFSIZE);
    lexer.setCharSequence ((CharSequence)sb);
    TokenSequence ts = new TokenSequence ();
    while (lexer.hasNext())
      ts.add (new Token ((String) lexer.next()));
    return ts;
  }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
    Transducer model = tt.getTransducer();
    int numCorrectTokens, totalTokens;
    int numTrueSegments, numPredictedSegments, numCorrectSegments;
    int numCorrectSegmentsInAlphabet, numCorrectSegmentsOOV;
    int numIncorrectSegmentsInAlphabet, numIncorrectSegmentsOOV;
    TokenSequence sourceTokenSequence = null;

    totalTokens = numCorrectTokens = 0;
    numTrueSegments = numPredictedSegments = numCorrectSegments = 0;
    numCorrectSegmentsInAlphabet = numCorrectSegmentsOOV = 0;
    numIncorrectSegmentsInAlphabet = numIncorrectSegmentsOOV = 0;
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
    super(new Alphabet(), null);
  }
 
  public Instance pipe (Instance carrier)
  {
    TokenSequence ts = (TokenSequence) carrier.getData();
    FeatureSequence ret =
      new FeatureSequence ((Alphabet)getDataAlphabet(), ts.size());
    for (int i = 0; i < ts.size(); i++) {
      ret.add (ts.get(i).getText());
    }
    carrier.setData(ret);
    return carrier;
  }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
    for (int i = 0; i < instances.size(); i++) {
      if (viterbiOutputStream != null)
        viterbiOutputStream.println ("Viterbi path for "+description+" instance #"+i);
      Instance instance = instances.get(i);
      Sequence input = (Sequence) instance.getData();
      TokenSequence sourceTokenSequence = null;
      if (instance.getSource() instanceof TokenSequence)
        sourceTokenSequence = (TokenSequence) instance.getSource();

      Sequence trueOutput = (Sequence) instance.getTarget();
      assert (input.size() == trueOutput.size());
      Sequence predOutput = transducerTrainer.getTransducer().transduce (input);
      assert (predOutput.size() == trueOutput.size());
     
      for (int j = 0; j < trueOutput.size(); j++) {
        FeatureVector fv = (FeatureVector) input.get(j);
        //viterbiOutputStream.println (tokens.charAt(j)+" "+trueOutput.get(j).toString()+
        //'/'+predOutput.get(j).toString()+"  "+ fv.toString(true));
        if (sourceTokenSequence != null)
          viterbiOutputStream.print (sourceTokenSequence.get(j).getText()+": ");
        viterbiOutputStream.println (trueOutput.get(j).toString()+
            '/'+predOutput.get(j).toString()+"  "+ fv.toString(true));
      }
    }
  }
View Full Code Here
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
    public TestCRFTokenSequenceRemoveSpaces() {
      super(null, new Alphabet());
    }

    public Instance pipe(Instance carrier) {
      TokenSequence ts = (TokenSequence) carrier.getData();
      TokenSequence newTs = new TokenSequence();
      FeatureSequence labelSeq = new FeatureSequence(getTargetAlphabet());
      boolean lastWasSpace = true;
      StringBuffer sb = new StringBuffer();
      for (int i = 0; i < ts.size(); i++) {
        Token t = ts.get(i);
        if (t.getText().equals(" "))
          lastWasSpace = true;
        else {
          sb.append(t.getText());
          newTs.add(t);
          labelSeq.add(lastWasSpace ? "start" : "notstart");
          lastWasSpace = false;
        }
      }
      if (isTargetProcessing())
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
  public Instance pipe (Instance carrier)
  {
    CharSequence string = (CharSequence) carrier.getData();
    lexer.setCharSequence (string);
    TokenSequence ts = new StringTokenization (string);
    while (lexer.hasNext()) {
      lexer.next();
      ts.add (new StringSpan (string, lexer.getStartOffset (), lexer.getEndOffset ()));
    }
    carrier.setData(ts);
    return carrier;
  }
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
89
90
91
        Instance carrier = new Instance (new File(args[i]), null, null, null);
        SerialPipes p = new SerialPipes (new Pipe[] {
          new Input2CharSequence (),
          new CharSequence2TokenSequence(new CharSequenceLexer())});
        carrier = p.newIteratorFrom (new SingleInstanceIterator(carrier)).next();
        TokenSequence ts = (TokenSequence) carrier.getData();
        System.out.println ("===");
        System.out.println (args[i]);
        System.out.println (ts.toString());
      }
    } catch (Exception e) {
      System.out.println (e);
      e.printStackTrace();
    }
View Full Code Here
24
25
26
27
28
29
30
31
32
33
34
35
public class TokenSequenceLowercase extends Pipe implements Serializable
{
 
  public Instance pipe (Instance carrier)
  {
    TokenSequence ts = (TokenSequence) carrier.getData();
    for (int i = 0; i < ts.size(); i++) {
      Token t = ts.get(i);
      t.setText(t.getText().toLowerCase());
    }
    return carrier;
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
    return this;
  }
 
  public Instance pipe (Instance carrier) {
   
    TokenSequence originalSequence = (TokenSequence) carrier.getData();
    TokenSequence newSequence = new TokenSequence();
   
    for (int i = 0; i < originalSequence.size(); i++) {
      Token t = originalSequence.get(i);
     
      boolean passed = true;
      String text = t.getText();
      for (Pattern pattern : stopPatterns) {
        Matcher matcher = pattern.matcher(text);
        if (matcher.matches()) {
          passed = false;
          break;
        }
      }
     
      if (passed) {
        newSequence.add (t);
      }
    }
   
    carrier.setData(newSequence);
    return carrier;
View Full Code Here
TOP

Related Classes of cc.mallet.types.TokenSequence

  • cc.mallet.extract.pipe.TokenSequence2Tokenization
  • cc.mallet.fst.MultiSegmentationEvaluator
  • cc.mallet.fst.SegmentationEvaluator
  • cc.mallet.fst.tests.TestCRF$TestCRFTokenSequenceRemoveSpaces
  • cc.mallet.fst.ViterbiWriter
  • cc.mallet.pipe.CharSequence2CharNGrams
  • cc.mallet.pipe.CharSequence2TokenSequence
  • cc.mallet.pipe.CharSequenceArray2TokenSequence
  • cc.mallet.pipe.iterator.RandomTokenSequenceIterator
  • cc.mallet.pipe.LineGroupString2TokenSequence
    • 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.