Example usage for weka.core.tokenizers WordTokenizer setDelimiters

Introduction

In this page you can find the example usage for weka.core.tokenizers WordTokenizer setDelimiters.

Prototype

public void setDelimiters(String value) 

Source Link

Document

Set the value of delimiters.

Usage

From source file:com.ivanrf.smsspam.SpamClassifier.java

License:Apache License

private static FilteredClassifier initFilterClassifier(int wordsToKeep, String tokenizerOp,
        boolean useAttributeSelection, String classifierOp, boolean boosting) throws Exception {
    StringToWordVector filter = new StringToWordVector();
    filter.setDoNotOperateOnPerClassBasis(true);
    filter.setLowerCaseTokens(true);/*from   ww w.jav a  2s  .c  o m*/
    filter.setWordsToKeep(wordsToKeep);

    if (!tokenizerOp.equals(TOKENIZER_DEFAULT)) {
        //Make a tokenizer
        WordTokenizer wt = new WordTokenizer();
        if (tokenizerOp.equals(TOKENIZER_COMPLETE))
            wt.setDelimiters(" \r\n\t.,;:\'\"()?!-+*&#$%/=<>[]_`@\\^{}");
        else //TOKENIZER_COMPLETE_NUMBERS)
            wt.setDelimiters(" \r\n\t.,;:\'\"()?!-+*&#$%/=<>[]_`@\\^{}|~0123456789");
        filter.setTokenizer(wt);
    }

    FilteredClassifier classifier = new FilteredClassifier();
    classifier.setFilter(filter);

    if (useAttributeSelection) {
        AttributeSelection as = new AttributeSelection();
        as.setEvaluator(new InfoGainAttributeEval());
        Ranker r = new Ranker();
        r.setThreshold(0);
        as.setSearch(r);

        MultiFilter mf = new MultiFilter();
        mf.setFilters(new Filter[] { filter, as });

        classifier.setFilter(mf);
    }

    if (classifierOp.equals(CLASSIFIER_SMO))
        classifier.setClassifier(new SMO());
    else if (classifierOp.equals(CLASSIFIER_NB))
        classifier.setClassifier(new NaiveBayes());
    else if (classifierOp.equals(CLASSIFIER_IB1))
        classifier.setClassifier(new IBk(1));
    else if (classifierOp.equals(CLASSIFIER_IB3))
        classifier.setClassifier(new IBk(3));
    else if (classifierOp.equals(CLASSIFIER_IB5))
        classifier.setClassifier(new IBk(5));
    else if (classifierOp.equals(CLASSIFIER_PART))
        classifier.setClassifier(new PART()); //Tarda mucho

    if (boosting) {
        AdaBoostM1 boost = new AdaBoostM1();
        boost.setClassifier(classifier.getClassifier());
        classifier.setClassifier(boost); //Con NB tarda mucho
    }

    return classifier;
}

---

From source file:org.montp2.m1decol.ter.gramms.filters.FilterTokenizerBoolean.java

License:Open Source License

public void indexingToTokenizer(String inPath, String outPath) throws Exception {
    WordTokenizer wordTokenizer = new WordTokenizer();
    wordTokenizer.setDelimiters("\r \t.,;:'\"()?!");

    Instances inputInstances = WekaUtils.loadARFF(inPath);
    StringToWordVector filter = new StringToWordVector();
    filter.setInputFormat(inputInstances);
    filter.setDoNotOperateOnPerClassBasis(false);
    filter.setInvertSelection(false);//from  w  w w .j av  a 2 s  .  c  om
    filter.setLowerCaseTokens(true);
    filter.setOutputWordCounts(false);
    filter.setTokenizer(wordTokenizer);
    filter.setUseStoplist(true);
    filter.setWordsToKeep(wordsTokeep);

    Instances outputInstances = Filter.useFilter(inputInstances, filter);

    OutputStreamUtils.writeSimple(outputInstances.toString(), outPath);
}

---

From source file:org.montp2.m1decol.ter.gramms.filters.FilterTokenizerIDFT.java

License:Open Source License

public void indexingToTokenizer(String inPath, String outPath) throws Exception {

    WordTokenizer wordTokenizer = new WordTokenizer();
    wordTokenizer.setDelimiters("\r \t.,;:'\"()?!");

    Instances inputInstances = WekaUtils.loadARFF(inPath);
    StringToWordVector filter = new StringToWordVector();
    filter.setInputFormat(inputInstances);
    filter.setIDFTransform(true);/*from   ww w. ja v  a  2s. c  om*/
    filter.setTFTransform(true);
    filter.setDoNotOperateOnPerClassBasis(false);
    filter.setInvertSelection(false);
    filter.setLowerCaseTokens(true);
    filter.setMinTermFreq(3);
    filter.setOutputWordCounts(true);
    filter.setTokenizer(wordTokenizer);
    filter.setUseStoplist(true);
    filter.setWordsToKeep(200);

    Instances outputInstances = Filter.useFilter(inputInstances, filter);

    OutputStreamUtils.writeSimple(outputInstances.toString(), outPath);
}

---

From source file:org.montp2.m1decol.ter.gramms.filters.FilterTokenizerVector.java

License:Open Source License

public void indexingToTokenizer(String inPath, String outPath) throws Exception {
    WordTokenizer wordTokenizer = new WordTokenizer();
    wordTokenizer.setDelimiters("\r \t.,;:'\"()?!");

    Instances inputInstances = WekaUtils.loadARFF(inPath);
    StringToWordVector filter = new StringToWordVector();
    filter.setInputFormat(inputInstances);
    filter.setDoNotOperateOnPerClassBasis(false);
    filter.setInvertSelection(false);//  w w  w .ja v a2 s .c o m
    filter.setLowerCaseTokens(true);
    filter.setMinTermFreq(3);
    filter.setOutputWordCounts(true);
    filter.setTokenizer(wordTokenizer);
    filter.setUseStoplist(true);
    filter.setWordsToKeep(200);

    Instances outputInstances = Filter.useFilter(inputInstances, filter);

    OutputStreamUtils.writeSimple(outputInstances.toString(), outPath);
}

---