weka.classifiers.bayes.NaiveBayes Java Examples

public static void main(String[] args) throws Exception {
//        ConverterUtils.DataSource source = new ConverterUtils.DataSource("data/AnonFruit.arff");
        DataSource source = new DataSource("data/AnonFruit.arff");
        Instances train = source.getDataSet();
        train.setClassIndex(3);  // target attribute: (Sweet)
        //build model
        NaiveBayes model=new NaiveBayes();
        model.buildClassifier(train);

        //use
        Instances test = train;
        Evaluation eval = new Evaluation(test);
        eval.evaluateModel(model,test);
        List <Prediction> predictions = eval.predictions();
        int k = 0;
        for (Instance instance : test) {
            double actual = instance.classValue();
            double prediction = eval.evaluateModelOnce(model, instance);
            System.out.printf("%2d.%4.0f%4.0f", ++k, actual, prediction);
            System.out.println(prediction != actual? " *": "");
        }
    }
 

/**
 * @param args the command line arguments
 */
public static void main(String[] args) {
    // TODO code application logic here
    try{
        DataSource src = new DataSource("/Users/admin/Documents/NetBeansProjects/DevelopClassifier/vote.arff");
        Instances dt = src.getDataSet();
        dt.setClassIndex(dt.numAttributes()-1);
        
        String[] options = new String[4];
        options[0] = "-C";
        options[1] = "0.1";
        options[2] = "-M";
        options[3] = "2";
        J48 tree = new J48();
        tree.setOptions(options);
        tree.buildClassifier(dt);
        System.out.println(tree.getCapabilities().toString());
        System.out.println(tree.graph());
        
        //uncomment the following three lines of code for Naive Bayes 
        NaiveBayes nb = new NaiveBayes();
        nb.buildClassifier(dt);
        System.out.println(nb.getCapabilities().toString());
        
        }        
    catch(Exception e){
        System.out.println("Error!!!!\n" + e.getMessage());
    }
}
 

public void generateModel(){
	nb = new NaiveBayes();
	try {
		nb.buildClassifier(iris);
	} catch (Exception e) {

	}
}
 

/**
 * Classifiers used in the HIVE COTE paper
 */    
    public void configureDefaultEnsemble(){
//HIVE_SHAPELET_SVMQ    HIVE_SHAPELET_RandF    HIVE_SHAPELET_RotF    
//HIVE_SHAPELET_NN    HIVE_SHAPELET_NB    HIVE_SHAPELET_C45    HIVE_SHAPELET_SVML   
        ensemble=new CAWPE();
        ensemble.setWeightingScheme(new TrainAcc(4));
        ensemble.setVotingScheme(new MajorityConfidence());
        Classifier[] classifiers = new Classifier[7];
        String[] classifierNames = new String[7];
        
        SMO smo = new SMO();
        smo.turnChecksOff();
        smo.setBuildLogisticModels(true);
        PolyKernel kl = new PolyKernel();
        kl.setExponent(2);
        smo.setKernel(kl);
        if (seedClassifier)
            smo.setRandomSeed((int)seed);
        classifiers[0] = smo;
        classifierNames[0] = "SVMQ";

        RandomForest r=new RandomForest();
        r.setNumTrees(500);
        if(seedClassifier)
           r.setSeed((int)seed);            
        classifiers[1] = r;
        classifierNames[1] = "RandF";
            
            
        RotationForest rf=new RotationForest();
        rf.setNumIterations(100);
        if(seedClassifier)
           rf.setSeed((int)seed);
        classifiers[2] = rf;
        classifierNames[2] = "RotF";
        IBk nn=new IBk();
        classifiers[3] = nn;
        classifierNames[3] = "NN";
        NaiveBayes nb=new NaiveBayes();
        classifiers[4] = nb;
        classifierNames[4] = "NB";
        J48 c45=new J48();
        classifiers[5] = c45;
        classifierNames[5] = "C45";
        SMO svml = new SMO();
        svml.turnChecksOff();
        svml.setBuildLogisticModels(true);
        PolyKernel k2 = new PolyKernel();
        k2.setExponent(1);
        smo.setKernel(k2);
        classifiers[6] = svml;
        classifierNames[6] = "SVML";
        ensemble.setClassifiers(classifiers, classifierNames, null);
    }
 

/**
     * Comps: NN, SVML, SVMQ, C4.5, NB,  RotF, RandF, BN,
     * Weight: TrainAcc
     * Vote: MajorityVote
     *
     * As used originally in ST_HESCA, COTE.
     * NOTE the original also contained Bayes Net (BN). We have removed it because the classifier crashes
     * unpredictably when discretising features (due to lack of variance in the feature, but not easily detected and
     * dealt with
     *
     */
    public final void setupOriginalHESCASettings() {
        this.ensembleName = "HESCA";
        
        this.weightingScheme = new TrainAcc();
        this.votingScheme = new MajorityVote();
        
        CrossValidationEvaluator cv = new CrossValidationEvaluator(seed, false, false, false, false); 
        cv.setNumFolds(10);
        this.trainEstimator = cv; 
        int numClassifiers=7;
        Classifier[] classifiers = new Classifier[numClassifiers];
        String[] classifierNames = new String[numClassifiers];

        kNN k=new kNN(100);
        k.setCrossValidate(true);
        k.normalise(false);
        k.setDistanceFunction(new EuclideanDistance());
        classifiers[0] = k;
        classifierNames[0] = "NN";

        classifiers[1] = new NaiveBayes();
        classifierNames[1] = "NB";

        classifiers[2] = new J48();
        classifierNames[2] = "C45";

        SMO svml = new SMO();
        svml.turnChecksOff();
        PolyKernel kl = new PolyKernel();
        kl.setExponent(1);
        svml.setKernel(kl);
        svml.setRandomSeed(seed);
        classifiers[3] = svml;
        classifierNames[3] = "SVML";

        SMO svmq =new SMO();
//Assumes no missing, all real valued and a discrete class variable
        svmq.turnChecksOff();
        PolyKernel kq = new PolyKernel();
        kq.setExponent(2);
        svmq.setKernel(kq);
        svmq.setRandomSeed(seed);
        classifiers[4] =svmq;
        classifierNames[4] = "SVMQ";

        RandomForest r=new RandomForest();
        r.setNumTrees(500);
        r.setSeed(seed);
        classifiers[5] = r;
        classifierNames[5] = "RandF";

        RotationForest rf=new RotationForest();
        rf.setNumIterations(50);
        rf.setSeed(seed);
        classifiers[6] = rf;
        classifierNames[6] = "RotF";

//        classifiers[7] = new BayesNet();
//        classifierNames[7] = "bayesNet";

        setClassifiers(classifiers, classifierNames, null);
    }
 

public void loadModel(String modelPath){
	try {
		nb = (NaiveBayes) weka.core.SerializationHelper.read(modelPath);
	} catch (Exception e) {
	}
}
 

/**
 * Initializes the HIVE COTE ensemble consisting of 7 classifiers using a
 * majority voting strategy as described in J. Lines, S. Taylor and A. Bagnall,
 * "HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based
 * Ensembles for Time Series Classification," 2016 IEEE 16th International
 * Conference on Data Mining (ICDM), Barcelona, 2016, pp. 1041-1046. doi:
 * 10.1109/ICDM.2016.0133.
 *
 * @param seed
 *            Seed used within the classifiers and the majority confidence
 *            voting scheme
 * @param numFolds
 *            Number of folds used within the determination of the classifier
 *            weights for the {@link MajorityConfidenceVote}
 * @return Returns the initialized (but untrained) HIVE COTE ensemble model.
 */
public static Classifier provideHIVECOTEEnsembleModel(final long seed) {
	Classifier[] classifier = new Classifier[7];

	Vote voter = new MajorityConfidenceVote(5, seed);

	// SMO poly2
	SMO smop = new SMO();
	smop.turnChecksOff();
	smop.setBuildCalibrationModels(true);
	PolyKernel kernel = new PolyKernel();
	kernel.setExponent(2);
	smop.setKernel(kernel);
	smop.setRandomSeed((int)seed);
	classifier[0] = smop;

	// Random Forest
	RandomForest rf = new RandomForest();
	rf.setSeed((int)seed);
	rf.setNumIterations(500);
	classifier[1] = rf;

	// Rotation forest
	RotationForest rotF = new RotationForest();
	rotF.setSeed((int)seed);
	rotF.setNumIterations(100);
	classifier[2] = rotF;

	// NN
	IBk nn = new IBk();
	classifier[3] = nn;

	// Naive Bayes
	NaiveBayes nb = new NaiveBayes();
	classifier[4] = nb;

	// C45
	J48 c45 = new J48();
	c45.setSeed((int)seed);
	classifier[5] = c45;

	// SMO linear
	SMO smol = new SMO();
	smol.turnChecksOff();
	smol.setBuildCalibrationModels(true);
	PolyKernel linearKernel = new PolyKernel();
	linearKernel.setExponent(1);
	smol.setKernel(linearKernel);
	classifier[6] = smol;

	voter.setClassifiers(classifier);
	return voter;
}
 

/**
 * Get classifier's class name by a short name
 * */
public static String getClassifierClassName(String classifierName) {
	String className = "";
	switch (classifierName) {
	case "SGD":
		className = SGD.class.toString();
		break;
	case "SGDText":
		className = SGDText.class.toString();
		break;
	case "J48":
		className = J48.class.toString();
		break;
	case "PART":
		className = PART.class.toString();
		break;
	case "NaiveBayes":
		className = NaiveBayes.class.toString();
		break;
	case "NBUpdateable":
		className = NaiveBayesUpdateable.class.toString();
		break;
	case "AdaBoostM1":
		className = AdaBoostM1.class.toString();
		break;
	case "LogitBoost":
		className = LogitBoost.class.toString();
		break;
	case "Bagging":
		className = Bagging.class.toString();
		break;
	case "Stacking":
		className = Stacking.class.toString();
		break;
	case "AdditiveRegression":
		className = AdditiveRegression.class.toString();
		break;
	case "Apriori":
		className = Apriori.class.toString();
		break;
	default:
		className = SGD.class.toString();
	}
	className = className.substring(6);
	return className;
}
 

public static void main(String args[]) throws Exception {
	
	/*
	 * Build Naive Bayes baseline
	 */


	Classifier baselineNB = new NaiveBayes();

	double resNB[] = evaluate(baselineNB);
	System.out.println("Naive Bayes\n" + 
						"\tchurn:     " + resNB[0] + "\n" + 
						"\tappetency: " + resNB[1] + "\n" + 
						"\tup-sell:   " + resNB[2] + "\n" + 
						"\toverall:   " + resNB[3] + "\n");


	
	/*
	 * Ensemble method
	 */
	
	EnsembleLibrary ensembleLib = new EnsembleLibrary();
	
	// Decision trees
	ensembleLib.addModel("weka.classifiers.trees.J48 -S -C 0.25 -B -M 2");
	ensembleLib.addModel("weka.classifiers.trees.J48 -S -C 0.25 -B -M 2 -A");
	
	// naive Bayes
	ensembleLib.addModel("weka.classifiers.bayes.NaiveBayes");
	
	// k-nn
	ensembleLib.addModel("weka.classifiers.lazy.IBk");

	// AdaBoost
	ensembleLib.addModel("weka.classifiers.meta.AdaBoostM1");
	
	// LogitBoost
	ensembleLib.addModel("weka.classifiers.meta.LogitBoost");

	// SVM
	ensembleLib.addModel("weka.classifiers.functions.SMO");

	// Logistic regression
	ensembleLib.addModel("weka.classifiers.functions.Logistic");
	
	// Simple logistic regression
	ensembleLib.addModel("weka.classifiers.functions.SimpleLogistic");

	
	EnsembleLibrary.saveLibrary(new File("data/ensembleLib.model.xml"), ensembleLib, null);
	System.out.println(ensembleLib.getModels());
	
	EnsembleSelection ensambleSel = new EnsembleSelection();
	ensambleSel.setOptions(new String[]{
			 "-L", "data/ensembleLib.model.xml", // </path/to/modelLibrary> - Specifies the Model Library File, continuing the list of all models.
			 "-W", "data/esTmp", // </path/to/working/directory> - Specifies the Working Directory, where all models will be stored.
			 "-B", "10", // <numModelBags> - Set the number of bags, i.e., number of iterations to run the ensemble selection algorithm.
			 "-E", "1.0", // <modelRatio> - Set the ratio of library models that will be randomly chosen  to populate each bag of models.
			 "-V", "0.25", // <validationRatio> - Set the ratio of the training data set that will be reserved for validation.
			 "-H", "100", // <hillClimbIterations> - Set the number of hillclimbing iterations to be performed on each model bag.
			 "-I", "1.0", // <sortInitialization> - Set the the ratio of the ensemble library that the sort initialization algorithm will be able to choose from while initializing the ensemble for each model bag
			 "-X", "2", // <numFolds> - Sets the number of cross-validation folds.
			 "-P", "roc", // <hillclimbMettric> - Specify the metric that will be used for model selection during the hillclimbing algorithm.
			 "-A", "forward", // <algorithm> - Specifies the algorithm to be used for ensemble selection. 
			 "-R", "true", // - Flag whether or not models can be selected more than once for an ensemble.
			 "-G", "true", // - Whether sort initialization greedily stops adding models when performance degrades.
			 "-O", "true", // - Flag for verbose output. Prints out performance of all selected models.
			 "-S", "1", // <num> - Random number seed.
			 "-D", "true" // - If set, classifier is run in debug mode and may output additional info to the console
	});
	
	double resES[] = evaluate(ensambleSel);
	System.out.println("Ensemble\n" + "\tchurn:     " + resES[0] + "\n"
			+ "\tappetency: " + resES[1] + "\n" + "\tup-sell:   "
			+ resES[2] + "\n" + "\toverall:   " + resES[3] + "\n");
	

}