Examples with AttributeDataset smile.data.AttributeDataset used on opensource projects

Example 46 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class RBFNetworkTest method testBank32nh.

/**
     * Test of learn method, of class RBFNetwork.
     */
@Test
public void testBank32nh() {
    System.out.println("bank32nh");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(31);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/bank32nh.arff"));
        double[] datay = data.toArray(new double[data.size()]);
        double[][] datax = data.toArray(new double[data.size()][]);
        Math.standardize(datax);
        int n = datax.length;
        int k = 10;
        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        for (int i = 0; i < k; i++) {
            double[][] trainx = Math.slice(datax, cv.train[i]);
            double[] trainy = Math.slice(datay, cv.train[i]);
            double[][] testx = Math.slice(datax, cv.test[i]);
            double[] testy = Math.slice(datay, cv.test[i]);
            double[][] centers = new double[20][];
            RadialBasisFunction[] basis = SmileUtils.learnGaussianRadialBasis(trainx, centers, 5.0);
            RBFNetwork<double[]> rbf = new RBFNetwork<>(trainx, trainy, new EuclideanDistance(), basis, centers);
            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rbf.predict(testx[j]);
                rss += r * r;
            }
        }
        System.out.println("10-CV MSE = " + rss / n);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 47 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class RandomForestTest method test.

public void test(String dataset, String url, int response) {
    System.out.println(dataset);
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(response);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile(url));
        double[] datay = data.toArray(new double[data.size()]);
        double[][] datax = data.toArray(new double[data.size()][]);
        int n = datax.length;
        int k = 10;
        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double ad = 0.0;
        for (int i = 0; i < k; i++) {
            double[][] trainx = Math.slice(datax, cv.train[i]);
            double[] trainy = Math.slice(datay, cv.train[i]);
            double[][] testx = Math.slice(datax, cv.test[i]);
            double[] testy = Math.slice(datay, cv.test[i]);
            RandomForest forest = new RandomForest(data.attributes(), trainx, trainy, 200, n, 5, trainx[0].length / 3);
            System.out.format("OOB error rate = %.4f%n", forest.error());
            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - forest.predict(testx[j]);
                rss += r * r;
                ad += Math.abs(r);
            }
        }
        System.out.format("10-CV RMSE = %.4f \t AbsoluteDeviation = %.4f%n", Math.sqrt(rss / n), ad / n);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 48 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class NaiveBayesTest method testPredict.

/**
     * Test of predict method, of class NaiveBayes.
     */
@Test
public void testPredict() {
    System.out.println("predict");
    ArffParser arffParser = new ArffParser();
    arffParser.setResponseIndex(4);
    try {
        AttributeDataset iris = arffParser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/iris.arff"));
        double[][] x = iris.toArray(new double[iris.size()][]);
        int[] y = iris.toArray(new int[iris.size()]);
        int n = x.length;
        LOOCV loocv = new LOOCV(n);
        int error = 0;
        for (int l = 0; l < n; l++) {
            double[][] trainx = Math.slice(x, loocv.train[l]);
            int[] trainy = Math.slice(y, loocv.train[l]);
            int p = trainx[0].length;
            int k = Math.max(trainy) + 1;
            double[] priori = new double[k];
            Distribution[][] condprob = new Distribution[k][p];
            for (int i = 0; i < k; i++) {
                priori[i] = 1.0 / k;
                for (int j = 0; j < p; j++) {
                    ArrayList<Double> axi = new ArrayList<>();
                    for (int m = 0; m < trainx.length; m++) {
                        if (trainy[m] == i) {
                            axi.add(trainx[m][j]);
                        }
                    }
                    double[] xi = new double[axi.size()];
                    for (int m = 0; m < xi.length; m++) {
                        xi[m] = axi.get(m);
                    }
                    condprob[i][j] = new GaussianMixture(xi, 3);
                }
            }
            NaiveBayes bayes = new NaiveBayes(priori, condprob);
            if (y[loocv.test[l]] != bayes.predict(x[loocv.test[l]]))
                error++;
        }
        System.out.format("Iris error rate = %.2f%%%n", 100.0 * error / x.length);
        assertEquals(5, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 49 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class NeuralNetworkTest method testUSPS.

/**
     * Test of learn method, of class NeuralNetwork.
     */
@Test
public void testUSPS() {
    System.out.println("USPS");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        AttributeDataset test = parser.parse("USPS Test", smile.data.parser.IOUtils.getTestDataFile("usps/zip.test"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        double[][] testx = test.toArray(new double[test.size()][]);
        int[] testy = test.toArray(new int[test.size()]);
        int p = x[0].length;
        double[] mu = Math.colMean(x);
        double[] sd = Math.colSd(x);
        for (int i = 0; i < x.length; i++) {
            for (int j = 0; j < p; j++) {
                x[i][j] = (x[i][j] - mu[j]) / sd[j];
            }
        }
        for (int i = 0; i < testx.length; i++) {
            for (int j = 0; j < p; j++) {
                testx[i][j] = (testx[i][j] - mu[j]) / sd[j];
            }
        }
        NeuralNetwork net = new NeuralNetwork(NeuralNetwork.ErrorFunction.CROSS_ENTROPY, NeuralNetwork.ActivationFunction.SOFTMAX, x[0].length, 40, Math.max(y) + 1);
        for (int j = 0; j < 30; j++) {
            net.learn(x, y);
        }
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (net.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 50 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class NeuralNetworkTest method testIris2.

/**
     * Test of learn method, of class NeuralNetwork.
     */
@Test
public void testIris2() {
    System.out.println("Iris binary");
    ArffParser arffParser = new ArffParser();
    arffParser.setResponseIndex(4);
    try {
        AttributeDataset iris = arffParser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/iris.arff"));
        double[][] x = iris.toArray(new double[iris.size()][]);
        int[] y = iris.toArray(new int[iris.size()]);
        for (int i = 0; i < y.length; i++) {
            if (y[i] == 2) {
                y[i] = 1;
            } else {
                y[i] = 0;
            }
        }
        int n = x.length;
        int p = x[0].length;
        double[] mu = Math.colMean(x);
        double[] sd = Math.colSd(x);
        for (int i = 0; i < n; i++) {
            for (int j = 0; j < p; j++) {
                x[i][j] = (x[i][j] - mu[j]) / sd[j];
            }
        }
        LOOCV loocv = new LOOCV(n);
        int error = 0;
        for (int i = 0; i < n; i++) {
            double[][] trainx = Math.slice(x, loocv.train[i]);
            int[] trainy = Math.slice(y, loocv.train[i]);
            NeuralNetwork net = new NeuralNetwork(NeuralNetwork.ErrorFunction.CROSS_ENTROPY, NeuralNetwork.ActivationFunction.LOGISTIC_SIGMOID, x[0].length, 10, 1);
            for (int j = 0; j < 30; j++) {
                net.learn(trainx, trainy);
            }
            if (y[loocv.test[i]] != net.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("Neural network error = " + error);
        assertTrue(error <= 8);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}