Example usage for weka.core.tokenizers NGramTokenizer NGramTokenizer

List of usage examples for weka.core.tokenizers NGramTokenizer NGramTokenizer

Introduction

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

Prototype

NGramTokenizer

Source Link

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);//from w  w w.j a va2  s. co  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;
}