Example usage for weka.filters.unsupervised.attribute StringToWordVector setLowerCaseTokens

Introduction

In this page you can find the example usage for weka.filters.unsupervised.attribute StringToWordVector setLowerCaseTokens.

Prototype

public void setLowerCaseTokens(boolean downCaseTokens) 

Source Link

Document

Sets whether if the tokens are to be downcased or not.

Usage

From source file:com.hack23.cia.service.impl.action.user.wordcount.WordCounterImpl.java

License:Apache License

@Override
public Map<String, Integer> calculateWordCount(final DocumentContentData documentContentData,
        final int maxResult) {

    final String html = documentContentData.getContent();

    final Attribute input = new Attribute("html", (ArrayList<String>) null);

    final ArrayList<Attribute> inputVec = new ArrayList<>();
    inputVec.add(input);// ww w.j ava2s . c  o m

    final Instances htmlInst = new Instances("html", inputVec, 1);

    htmlInst.add(new DenseInstance(1));
    htmlInst.instance(0).setValue(0, html);

    final StopwordsHandler StopwordsHandler = new StopwordsHandler() {

        @Override
        public boolean isStopword(final String word) {

            return word.length() < 5;
        }
    };

    final NGramTokenizer tokenizer = new NGramTokenizer();
    tokenizer.setNGramMinSize(1);
    tokenizer.setNGramMaxSize(1);
    tokenizer.setDelimiters(" \r\n\t.,;:'\"()?!'");

    final StringToWordVector filter = new StringToWordVector();
    filter.setTokenizer(tokenizer);
    filter.setStopwordsHandler(StopwordsHandler);
    filter.setLowerCaseTokens(true);
    filter.setOutputWordCounts(true);
    filter.setWordsToKeep(maxResult);

    final Map<String, Integer> result = new HashMap<>();

    try {
        filter.setInputFormat(htmlInst);
        final Instances dataFiltered = Filter.useFilter(htmlInst, filter);

        final Instance last = dataFiltered.lastInstance();

        final int numAttributes = last.numAttributes();

        for (int i = 0; i < numAttributes; i++) {
            result.put(last.attribute(i).name(), Integer.valueOf(last.toString(i)));
        }
    } catch (final Exception e) {
        LOGGER.warn("Problem calculating wordcount for : {} , exception:{}", documentContentData.getId(), e);
    }

    return result;
}

---

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);
    filter.setWordsToKeep(wordsToKeep);//from  ww w.j  a  v  a  2  s .  c o  m

    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:nl.uva.expose.classification.WekaClassification.java

private void getWordVector(Instances dRaw, Instances dFiltered) throws Exception {
    StringToWordVector filter = new StringToWordVector();
    filter.setAttributeIndices("first-last");
    filter.setIDFTransform(true);/*from ww  w .j a  v a2 s.  co m*/
    filter.setLowerCaseTokens(true);
    filter.setMinTermFreq(2);
    filter.setLowerCaseTokens(true);
    filter.setNormalizeDocLength(
            new SelectedTag(StringToWordVector.FILTER_NORMALIZE_ALL, StringToWordVector.TAGS_FILTER));
    filter.setOutputWordCounts(true);
    //        filter.setTokenizer();
    //        filter.setWordsToKeep();
    filter.setInputFormat(dRaw);
    dFiltered = Filter.useFilter(dRaw, filter);
}

---

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);/*w w  w  .j a  v  a 2s. co  m*/
    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 2  s . c  o  m
    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);/*from   w  ww  .j av a2 s.c  om*/
    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);
}

---