Example usage for opennlp.tools.doccat DocumentCategorizer getNumberOfCategories

Introduction

In this page you can find the example usage for opennlp.tools.doccat DocumentCategorizer getNumberOfCategories.

Prototype

int getNumberOfCategories();

Source Link

Document

get the number of categories

Usage

From source file:com.tamingtext.classifier.maxent.TestMaxent.java

private static void execute(File[] inputFiles, File modelFile) throws IOException, FileNotFoundException {
    //<start id="maxent.examples.test.setup"/> 
    NameFinderFeatureGenerator nffg //<co id="tmx.feature"/>
            = new NameFinderFeatureGenerator();
    BagOfWordsFeatureGenerator bowfg = new BagOfWordsFeatureGenerator();

    InputStream modelStream = //<co id="tmx.modelreader"/>
            new FileInputStream(modelFile);
    DoccatModel model = new DoccatModel(modelStream);
    DocumentCategorizer categorizer //<co id="tmx.categorizer"/>
            = new DocumentCategorizerME(model, nffg, bowfg);
    Tokenizer tokenizer = SimpleTokenizer.INSTANCE;

    int catCount = categorizer.getNumberOfCategories();
    Collection<String> categories = new ArrayList<String>(catCount);
    for (int i = 0; i < catCount; i++) {
        categories.add(categorizer.getCategory(i));
    }// w  w w  .  j  a  va  2  s.com
    ResultAnalyzer resultAnalyzer = //<co id="tmx.results"/>
            new ResultAnalyzer(categories, "unknown");
    runTest(inputFiles, categorizer, tokenizer, resultAnalyzer); //<co id="tmx.run"/>
    /*<calloutlist>
    <callout arearefs="tmx.feature">Setup Feature Generators</callout>
    <callout arearefs="tmx.modelreader">Load Model</callout>
    <callout arearefs="tmx.categorizer">Create Categorizer</callout>
    <callout arearefs="tmx.results">Prepare Result Analyzer</callout>
    <callout arearefs="tmx.run">Execute Test</callout>
    </calloutlist>*/
    //<end id="maxent.examples.test.setup"/>
}

---