Package cc.mallet.types

Examples of cc.mallet.types.TokenSequence

68
69
70
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
  public Instance pipe (Instance carrier)
  {
    CharSequence string = (CharSequence) carrier.getData();
    StringTokenization dataTokens = new StringTokenization (string);
    TokenSequence targetTokens = new TokenSequence ();
    String tag = backgroundTag;
    String nextTag = backgroundTag;
    Matcher m = sgmlPattern.matcher (string);
    int textStart = 0;
    int textEnd = 0;
    int nextStart = 0;
    boolean done = false;

    logger.fine(sgmlPattern.pattern());
    logger.finer(string.toString());

    while (!done) {
      done = !(m.find());
      if (done)
        textEnd = string.length(); // culotta: changed from string.length()-1
      else {
        String sgml = m.group();
        logger.finer ("SGML = "+sgml);

        int groupCount = m.groupCount();
        logger.finer(Integer.toString (groupCount));

        if (sgml.charAt(1) == '/')
          nextTag = backgroundTag;
        else{
          //nextTag = m.group(0);
          nextTag = sgml.substring(1, sgml.length()-1);
        }
        logger.finer("nextTag: " + nextTag);

        nextStart = m.end();  // m.end returns one beyond index of last match char
        textEnd = m.start();  // String.subtring does not include index end
        logger.finer ("Text start/end "+textStart+" "+textEnd);
      }
      if (textEnd - textStart > 0) {
        logger.finer ("Tag = "+tag);
        logger.finer ("Target = "+string.subSequence (textStart, textEnd));
        lexer.setCharSequence (string.subSequence (textStart, textEnd));
        while (lexer.hasNext()) {
          lexer.next ();
          int tokStart = textStart + lexer.getStartOffset ();
          int tokEnd = textStart + lexer.getEndOffset ();
          dataTokens.add (new StringSpan (string, tokStart, tokEnd));
          targetTokens.add (new Token (tag));
        }
      }
      textStart = nextStart;
      tag = nextTag;
    }
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
//        new SGML2TokenSequence (new CharSequenceLexer (Pattern.compile (".")), "O")
        });

      for (int i = 0; i < args.length; i++) {
        Instance carrier = p.instanceFrom(new Instance (new File(args[i]), null, null, null));
        TokenSequence data = (TokenSequence) carrier.getData();
        TokenSequence target = (TokenSequence) carrier.getTarget();
        logger.finer ("===");
        logger.info (args[i]);
        for (int j = 0; j < data.size(); j++)
          logger.info (target.get(j).getText()+" "+data.get(j).getText());
      }
    } catch (Exception e) {
      System.out.println (e);
      e.printStackTrace();
    }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
public class TokenSequenceDocHeader extends Pipe implements Serializable
{
 
  public Instance pipe (Instance carrier)
  {
    TokenSequence ts = (TokenSequence) carrier.getData();
    if (ts.size() > 3
        && (ts.get(2).getText().equals("-") || ts.get(3).getText().equals("-"))
        && ts.get(1).getText().matches("[A-Z]+")) {
      String header = ts.get(1).getText();
      if (header.equals("PRESS"))        // Don't bother with "PRESS DIGEST" headers
        return carrier;
      String featureName = "HEADER="+header;
      for (int i = 0; i < ts.size(); i++) {
        Token t = ts.get(i);
        // Only apply this feature to capitalized words, because if we apply it to everything
        // we easily get an immense number of possible feature conjunctions, (e.g. every word
        // with each of these HEADER= features.
        if (t.getText().matches("^[A-Z].*"))
          t.setFeatureValue (featureName, 1.0);
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
  }

  public Instance pipe (Instance carrier)
  {
    if (carrier.getData() instanceof CharSequence)
      carrier.setData(new TokenSequence (ngramify ((CharSequence)carrier.getData())));
    else if (carrier.getData() instanceof TokenSequence) {
      TokenSequence ts = (TokenSequence) carrier.getData();
      TokenSequence ret = new TokenSequence ();
      for (int i = 0; i < ts.size(); i++)
        ret.add (ngramify (ts.get(i).getText()).toString());
      carrier.setData(ret);
    } else
      throw new IllegalArgumentException ("Unhandled type "+carrier.getData().getClass());
    return carrier;
  }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
    Object data = carrier.getData ();
    if (data instanceof Tokenization) {
      // we're done
    } else if (data instanceof TokenSequence) {
      StringBuffer buf = new StringBuffer ();
      TokenSequence ts = (TokenSequence) data;
      StringTokenization spans = new StringTokenization (buf);  // I can use a StringBuffer as the doc! Awesome!

      for (int i = 0; i < ts.size(); i++) {
        Token token = ts.get(i);

        int start = buf.length ();
        buf.append (token.getText());
        int end = buf.length();
View Full Code Here
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
    int[] numTrueSegments, numPredictedSegments, numCorrectSegments;
    int allIndex = segmentStartTags.length;
    numTrueSegments = new int[allIndex+1];
    numPredictedSegments = new int[allIndex+1];
    numCorrectSegments = new int[allIndex+1];
    TokenSequence sourceTokenSequence = null;

    totalTokens = numCorrectTokens = 0;
    for (int n = 0; n < numTrueSegments.length; n++)
      numTrueSegments[n] = numPredictedSegments[n] = numCorrectSegments[n] = 0;
    for (int i = 0; i < data.size(); i++) {
      if (viterbiOutputStream != null)
        viterbiOutputStream.println ("Viterbi path for "+description+" instance #"+i);
      Instance instance = data.get(i);
      Sequence input = (Sequence) instance.getData();     
      //String tokens = null;
      //if (instance.getSource() != null)
      //tokens = (String) instance.getSource().toString();
      Sequence trueOutput = (Sequence) instance.getTarget();
      assert (input.size() == trueOutput.size());
      Sequence predOutput = (Sequence) predictedSequences.get (i);
      if (predOutput == null) // skip this instance
        continue;
      assert (predOutput.size() == trueOutput.size());
      int trueStart, predStart;        // -1 for non-start, otherwise index into segmentStartTag
      for (int j = 0; j < trueOutput.size(); j++) {
        totalTokens++;
        if (trueOutput.get(j).equals(predOutput.get(j)))
          numCorrectTokens++;
        trueStart = predStart = -1;
        // Count true segment starts
        for (int n = 0; n < segmentStartTags.length; n++) {
          if (segmentStartTags[n].equals(trueOutput.get(j))) {
            numTrueSegments[n]++;
            numTrueSegments[allIndex]++;
            trueStart = n;
            break;
          }
        }
        // Count predicted segment starts
        for (int n = 0; n < segmentStartTags.length; n++) {
          if (segmentStartTags[n].equals(predOutput.get(j))) {
            numPredictedSegments[n]++;
            numPredictedSegments[allIndex]++;
            predStart = n;
          }
        }
        if (trueStart != -1 && trueStart == predStart) {
          // Truth and Prediction both agree that the same segment tag-type is starting now
          int m;
          boolean trueContinue = false;
          boolean predContinue = false;
          for (m = j+1; m < trueOutput.size(); m++) {
            trueContinue = segmentContinueTags[predStart].equals (trueOutput.get(m));
            predContinue = segmentContinueTags[predStart].equals (predOutput.get(m));
            if (!trueContinue || !predContinue) {
              if (trueContinue == predContinue) {
                // They agree about a segment is ending somehow
                numCorrectSegments[predStart]++;
                numCorrectSegments[allIndex]++;
              }
              break;
            }
          }
          // for the case of the end of the sequence
          if (m == trueOutput.size()) {
            if (trueContinue == predContinue) {
              numCorrectSegments[predStart]++;
              numCorrectSegments[allIndex]++;
            }
          }
        }

        if (viterbiOutputStream != null) {
          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
51
52
53
54
55
56
57
58
   
    if (!(carrier.getData() instanceof CharSequence))
      throw new IllegalArgumentException ();
    String s = carrier.getData().toString();
    String[] lines = s.split (System.getProperty ("line.separator"));
    carrier.setData (new TokenSequence (lines));
    return carrier;
  }
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
  }
 
  public Instance pipe (Instance carrier)
  {
    String newTerm = null;
    TokenSequence tmpTS = new TokenSequence();
    TokenSequence ts = (TokenSequence) carrier.getData();

    for (int i = 0; i < ts.size(); i++) {
      Token t = ts.get(i);
      for(int j = 0; j < gramSizes.length; j++) {
        int len = gramSizes[j];
        if (len <= 0 || len > (i+1)) continue;
        if (len == 1) { tmpTS.add(t); continue; }
        newTerm = new String(t.getText());
        for(int k = 1; k < len; k++)
          newTerm = ts.get(i-k).getText() + "_" + newTerm;
        tmpTS.add(newTerm);
      }
    }

    carrier.setData(tmpTS);
View Full Code Here
66
67
68
69
70
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
99
100
101
102
103
104
105
106
107
  public Instance pipe (Instance carrier)
  {
    if (!(carrier.getData() instanceof CharSequence))
      throw new ClassCastException ("carrier.data is a " + carrier.getData().getClass().getName() +
                                   " not a CharSequence");
    TokenSequence dataTokens = new TokenSequence ();
     TokenSequence targetTokens = new TokenSequence ();
    CharSequence string = (CharSequence) carrier.getData();
    String tag = backgroundTag;
    String nextTag = backgroundTag;
    Matcher m = sgmlPattern.matcher (string);
    int textStart = 0;
    int textEnd = 0;
    int nextStart = 0;
    boolean done = false;

    while (!done) {
      done = !findNextValidMatch (m);
      if (done)
        textEnd = string.length()-1;
      else {
        String sgml = m.group();
        int groupCount = m.groupCount();
        if (sgml.charAt(1) == '/')
          nextTag = backgroundTag;
        else{
          nextTag = m.group(0);
          nextTag = sgml.substring(1, sgml.length()-1);
        }
        nextStart = m.end();
        textEnd = m.start();
      }
      if (textEnd - textStart > 0) {
        lexer.setCharSequence (string.subSequence (textStart, textEnd));
        while (lexer.hasNext()) {
          dataTokens.add (new Token ((String) lexer.next()));
          targetTokens.add (new Token (tag));
        }
      }
      textStart = nextStart;
      tag = nextTag;
    }
View Full Code Here
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
129
130
131
132
133
    this (namePrefix, leftBoundaryOffset, rightBoundaryOffset, null, true);
  }
 
  public Instance pipe (Instance carrier)
  {
    TokenSequence ts = (TokenSequence) carrier.getData();
    int tsSize = ts.size();
    PropertyList[] newFeatures = new PropertyList[tsSize];
    for (int i = 0; i < tsSize; i++) {
      Token t = ts.get (i);
      PropertyList pl = t.getFeatures();
      newFeatures[i] = pl;
      for (int position = i + leftBoundary; position < i + rightBoundary; position++) {
        if (position == i && !includeCurrentToken)
          continue;
        PropertyList pl2;
        if (position < 0)
          pl2 = startfs[-position];
        else if (position >= tsSize)
          pl2 = endfs[position-tsSize];
        else
          pl2 = ts.get(position).getFeatures ();
        PropertyList.Iterator pl2i = pl2.iterator();
        while (pl2i.hasNext()) {
          pl2i.next();
          String key = pl2i.getKey();
          if (featureRegex == null || featureRegex.matcher(key).matches()) {
            newFeatures[i] = PropertyList.add ((namePrefixLeft == null || position-i>0 ? namePrefix : namePrefixLeft)+key,
                                               pl2i.getNumericValue(), newFeatures[i]);
          }
        }
      }
    }
    for (int i = 0; i < tsSize; i++) {
      // Put the new PropertyLists in place
      ts.get (i).setFeatures (newFeatures[i]);
    }
    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.