Example usage for weka.classifiers.misc SerializedClassifier getCurrentModel

Introduction

In this page you can find the example usage for weka.classifiers.misc SerializedClassifier getCurrentModel.

Prototype

public Classifier getCurrentModel() 

Source Link

Document

Gets the currently loaded model (can be null).

Usage

From source file:clasificador.RedNeuronal.java

public void testing() {
    try {//from  ww  w  .  jav  a  2 s .  co  m
        FileReader testReader = new FileReader(
                new File(System.getProperty("user.dir") + "\\src\\clasificador\\archivos\\librotest.arff"));
        Instances testInstance = new Instances(testReader);
        testInstance.setClassIndex(testInstance.numAttributes() - 1);
        Evaluation evalTest = new Evaluation(testInstance);
        SerializedClassifier clasificador = new SerializedClassifier();
        clasificador.setModelFile(new File("TrainMLP.train"));
        //CLASIFICADOR ESTANDAR
        Classifier clasificadorEstandar = clasificador.getCurrentModel();
        evalTest.evaluateModel(clasificadorEstandar, testInstance);

        System.out.println(evalTest.toSummaryString("resultado:", false));
        System.out.println(evalTest.toMatrixString("*****************Matriz de confusion*******"));

        //vamos a predecir el numero q voy a usar       
        // evalTest.toMatrixString();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (Exception ex) {
        Logger.getLogger(RedNeuronal.class.getName()).log(Level.SEVERE, null, ex);
    }
}

---

From source file:clasificador.RedNeuronal.java

public void prediccion() {

    FileReader testReader = null;
    try {/*from   w  w w.j av  a2  s.co m*/
        testReader = new FileReader(
                new File(System.getProperty("user.dir") + "\\src\\clasificador\\archivos\\libro1.arff"));
        Instances testInstance = new Instances(testReader);
        testInstance.setClassIndex(testInstance.numAttributes() - 1);
        Evaluation evalTest = new Evaluation(testInstance);
        SerializedClassifier clasificador = new SerializedClassifier();
        clasificador.setModelFile(new File("TrainMLP.train"));
        //CLASIFICADOR ESTANDAR
        Classifier clasificadorEstandar = clasificador.getCurrentModel();
        evalTest.evaluateModel(clasificadorEstandar, testInstance);

        double[] valores = evalTest.evaluateModel(clasificadorEstandar, testInstance);

        for (int i = 0; i < valores.length; i++) {

            System.out.println("se predice:     " + valores[i] + "\n");
        }
    } catch (FileNotFoundException ex) {
        Logger.getLogger(RedNeuronal.class.getName()).log(Level.SEVERE, null, ex);
    } catch (IOException ex) {
        Logger.getLogger(RedNeuronal.class.getName()).log(Level.SEVERE, null, ex);
    } catch (Exception ex) {
        Logger.getLogger(RedNeuronal.class.getName()).log(Level.SEVERE, null, ex);
    } finally {
        try {
            testReader.close();
        } catch (IOException ex) {
            Logger.getLogger(RedNeuronal.class.getName()).log(Level.SEVERE, null, ex);
        }
    }

}

---