Example usage for weka.clusterers SimpleKMeans setFastDistanceCalc

Introduction

In this page you can find the example usage for weka.clusterers SimpleKMeans setFastDistanceCalc.

Prototype

public void setFastDistanceCalc(boolean value) 

Source Link

Document

Sets whether to use faster distance calculation.

Usage

From source file:com.edwardraff.WekaMNIST.java

License:Open Source License

public static void main(String[] args) throws IOException, Exception {
    String folder = args[0];/*from   ww  w . ja  va  2s .c o m*/
    String trainPath = folder + "MNISTtrain.arff";
    String testPath = folder + "MNISTtest.arff";

    System.out.println("Weka Timings");
    Instances mnistTrainWeka = new Instances(new BufferedReader(new FileReader(new File(trainPath))));
    mnistTrainWeka.setClassIndex(mnistTrainWeka.numAttributes() - 1);
    Instances mnistTestWeka = new Instances(new BufferedReader(new FileReader(new File(testPath))));
    mnistTestWeka.setClassIndex(mnistTestWeka.numAttributes() - 1);

    //normalize range like into [0, 1]
    Normalize normalizeFilter = new Normalize();
    normalizeFilter.setInputFormat(mnistTrainWeka);

    mnistTestWeka = Normalize.useFilter(mnistTestWeka, normalizeFilter);
    mnistTrainWeka = Normalize.useFilter(mnistTrainWeka, normalizeFilter);

    long start, end;

    System.out.println("RBF SVM (Full Cache)");
    SMO smo = new SMO();
    smo.setKernel(new RBFKernel(mnistTrainWeka, 0/*0 causes Weka to cache the whole matrix...*/, 0.015625));
    smo.setC(8.0);
    smo.setBuildLogisticModels(false);
    evalModel(smo, mnistTrainWeka, mnistTestWeka);

    System.out.println("RBF SVM (No Cache)");
    smo = new SMO();
    smo.setKernel(new RBFKernel(mnistTrainWeka, 1, 0.015625));
    smo.setC(8.0);
    smo.setBuildLogisticModels(false);
    evalModel(smo, mnistTrainWeka, mnistTestWeka);

    System.out.println("Decision Tree C45");
    J48 wekaC45 = new J48();
    wekaC45.setUseLaplace(false);
    wekaC45.setCollapseTree(false);
    wekaC45.setUnpruned(true);
    wekaC45.setMinNumObj(2);
    wekaC45.setUseMDLcorrection(true);

    evalModel(wekaC45, mnistTrainWeka, mnistTestWeka);

    System.out.println("Random Forest 50 trees");
    int featuresToUse = (int) Math.sqrt(28 * 28);//Weka uses different defaults, so lets make sure they both use the published way

    RandomForest wekaRF = new RandomForest();
    wekaRF.setNumExecutionSlots(1);
    wekaRF.setMaxDepth(0/*0 for unlimited*/);
    wekaRF.setNumFeatures(featuresToUse);
    wekaRF.setNumTrees(50);

    evalModel(wekaRF, mnistTrainWeka, mnistTestWeka);

    System.out.println("1-NN (brute)");
    IBk wekaNN = new IBk(1);
    wekaNN.setNearestNeighbourSearchAlgorithm(new LinearNNSearch());
    wekaNN.setCrossValidate(false);

    evalModel(wekaNN, mnistTrainWeka, mnistTestWeka);

    System.out.println("1-NN (Ball Tree)");
    wekaNN = new IBk(1);
    wekaNN.setNearestNeighbourSearchAlgorithm(new BallTree());
    wekaNN.setCrossValidate(false);

    evalModel(wekaNN, mnistTrainWeka, mnistTestWeka);

    System.out.println("1-NN (Cover Tree)");
    wekaNN = new IBk(1);
    wekaNN.setNearestNeighbourSearchAlgorithm(new CoverTree());
    wekaNN.setCrossValidate(false);

    evalModel(wekaNN, mnistTrainWeka, mnistTestWeka);

    System.out.println("Logistic Regression LBFGS lambda = 1e-4");
    Logistic logisticLBFGS = new Logistic();
    logisticLBFGS.setRidge(1e-4);
    logisticLBFGS.setMaxIts(500);

    evalModel(logisticLBFGS, mnistTrainWeka, mnistTestWeka);

    System.out.println("k-means (Loyd)");
    int origClassIndex = mnistTrainWeka.classIndex();
    mnistTrainWeka.setClassIndex(-1);
    mnistTrainWeka.deleteAttributeAt(origClassIndex);
    {
        long totalTime = 0;
        for (int i = 0; i < 10; i++) {
            SimpleKMeans wekaKMeans = new SimpleKMeans();
            wekaKMeans.setNumClusters(10);
            wekaKMeans.setNumExecutionSlots(1);
            wekaKMeans.setFastDistanceCalc(true);

            start = System.currentTimeMillis();
            wekaKMeans.buildClusterer(mnistTrainWeka);
            end = System.currentTimeMillis();
            totalTime += (end - start);
        }
        System.out.println("\tClustering took: " + (totalTime / 10.0) / 1000.0 + " on average");
    }
}

---