Example usage for weka.classifiers.bayes NaiveBayesSimple NaiveBayesSimple

Introduction

In this page you can find the example usage for weka.classifiers.bayes NaiveBayesSimple NaiveBayesSimple.

Prototype

NaiveBayesSimple

Source Link

Usage

From source file:kea.KEAFilter.java

License:Open Source License

/**
 * Builds the classifier./*ww  w . ja  v  a  2 s.c  o  m*/
 */
private void buildClassifier() throws Exception {

    // Generate input format for classifier
    FastVector atts = new FastVector();
    for (int i = 0; i < getInputFormat().numAttributes(); i++) {
        if (i == m_DocumentAtt) {
            atts.addElement(new Attribute("TFxIDF"));
            atts.addElement(new Attribute("First_occurrence"));
            if (m_KFused) {
                atts.addElement(new Attribute("Keyphrase_frequency"));
            }
        } else if (i == m_KeyphrasesAtt) {
            FastVector vals = new FastVector(2);
            vals.addElement("False");
            vals.addElement("True");
            atts.addElement(new Attribute("Keyphrase?", vals));
        }
    }
    m_ClassifierData = new Instances("ClassifierData", atts, 0);
    m_ClassifierData.setClassIndex(m_NumFeatures);

    if (m_Debug) {
        System.err.println("--- Converting instances for classifier");
    }

    // Convert pending input instances into data for classifier
    for (int i = 0; i < getInputFormat().numInstances(); i++) {
        Instance current = getInputFormat().instance(i);

        // Get the key phrases for the document
        String keyphrases = current.stringValue(m_KeyphrasesAtt);
        HashMap hashKeyphrases = getGivenKeyphrases(keyphrases, false);
        HashMap hashKeysEval = getGivenKeyphrases(keyphrases, true);

        // Get the phrases for the document
        HashMap hash = new HashMap();
        int length = getPhrases(hash, current.stringValue(m_DocumentAtt));

        // Compute the feature values for each phrase and
        // add the instance to the data for the classifier
        Iterator it = hash.keySet().iterator();
        while (it.hasNext()) {
            String phrase = (String) it.next();
            FastVector phraseInfo = (FastVector) hash.get(phrase);
            double[] vals = featVals(phrase, phraseInfo, true, hashKeysEval, hashKeyphrases, length);
            Instance inst = new Instance(current.weight(), vals);
            m_ClassifierData.add(inst);
        }
    }

    if (m_Debug) {
        System.err.println("--- Building classifier");
    }

    // Build classifier
    FilteredClassifier fclass = new FilteredClassifier();
    fclass.setClassifier(new NaiveBayesSimple());
    fclass.setFilter(new Discretize());
    m_Classifier = fclass;
    m_Classifier.buildClassifier(m_ClassifierData);

    if (m_Debug) {
        System.err.println(m_Classifier);
    }

    // Save space
    m_ClassifierData = new Instances(m_ClassifierData, 0);
}

---