Java KMeans類代碼示例

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Learns Gaussian RBF function and centers from data. The centers are
 * chosen as the centroids of K-Means. Let d<sub>max</sub> be the maximum
 * distance between the chosen centers, the standard deviation (i.e. width)
 * of Gaussian radial basis function is d<sub>max</sub> / sqrt(2*k), where
 * k is number of centers. This choice would be close to the optimal
 * solution if the data were uniformly distributed in the input space,
 * leading to a uniform distribution of centroids.
 * @param x the training dataset.
 * @param centers an array to store centers on output. Its length is used as k of k-means.
 * @return a Gaussian RBF function with parameter learned from data.
 */
public static GaussianRadialBasis learnGaussianRadialBasis(double[][] x, double[][] centers) {
    int k = centers.length;
    KMeans kmeans = new KMeans(x, k, 10);
    System.arraycopy(kmeans.centroids(), 0, centers, 0, k);

    double r0 = 0.0;
    for (int i = 0; i < k; i++) {
        for (int j = 0; j < i; j++) {
            double d = Math.distance(centers[i], centers[j]);
            if (r0 < d) {
                r0 = d;
            }
        }
    }

    r0 /= Math.sqrt(2*k);
    return new GaussianRadialBasis(r0);
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
@Override
public JComponent learn() {
    long clock = System.currentTimeMillis();
    KMeans kmeans = new KMeans(dataset[datasetIndex], clusterNumber, 100, 4);
    System.out.format("K-Means clusterings %d samples in %dms\n", dataset[datasetIndex].length, System.currentTimeMillis()-clock);

    PlotCanvas plot = ScatterPlot.plot(dataset[datasetIndex], kmeans.getClusterLabel(), pointLegend, Palette.COLORS);
    plot.points(kmeans.centroids(), '@');
    return plot;
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
@Override
public void impute(double[][] data) throws MissingValueImputationException {
    int[] count = new int[data[0].length];
    for (int i = 0; i < data.length; i++) {
        int n = 0;
        for (int j = 0; j < data[i].length; j++) {
            if (Double.isNaN(data[i][j])) {
                n++;
                count[j]++;
            }
        }

        if (n == data[i].length) {
            throw new MissingValueImputationException("The whole row " + i + " is missing");
        }
    }

    for (int i = 0; i < data[0].length; i++) {
        if (count[i] == data.length) {
            throw new MissingValueImputationException("The whole column " + i + " is missing");
        }
    }

    KMeans kmeans = KMeans.lloyd(data, k, Integer.MAX_VALUE, runs);

    for (int i = 0; i < k; i++) {
        if (kmeans.getClusterSize()[i] > 0) {
            double[][] d = new double[kmeans.getClusterSize()[i]][];
            for (int j = 0, m = 0; j < data.length; j++) {
                if (kmeans.getClusterLabel()[j] == i) {
                    d[m++] = data[j];
                }
            }

            columnAverageImpute(d);
        }
    }

    // In case of some clusters miss all values in some columns.
    columnAverageImpute(data);
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void testCPU() {
    System.out.println("CPU");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(6);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/cpu.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;
        double sparseRSS30 = 0.0;
        double nystromRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(47.02), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);
            GaussianProcessRegression<double[]> nystrom30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1, true);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;

                r = testy[j] - nystrom30.predict(testx[j]);
                nystromRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
        System.out.println("Nystrom (30) 10-CV MSE = " + nystromRSS30 / n);
     } catch (Exception ex) {
        ex.printStackTrace();
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void test2DPlanes() {
    System.out.println("2dplanes");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(10);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/2dplanes.arff"));
        double[][] x = data.toArray(new double[data.size()][]);
        double[] y = data.toArray(new double[data.size()]);

        int[] perm = Math.permutate(x.length);
        double[][] datax = new double[4000][];
        double[] datay = new double[datax.length];
        for (int i = 0; i < datax.length; i++) {
            datax[i] = x[perm[i]];
            datay[i] = y[perm[i]];
        }

        int n = datax.length;
        int k = 10;

        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double sparseRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(34.866), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
     } catch (Exception ex) {
         System.err.println(ex);
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void testAilerons() {
    System.out.println("ailerons");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(40);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/ailerons.arff"));
        double[][] x = data.toArray(new double[data.size()][]);
        Math.standardize(x);

        double[] y = data.toArray(new double[data.size()]);
        for (int i = 0; i < y.length; i++) {
            y[i] *= 10000;
        }

        int[] perm = Math.permutate(x.length);
        double[][] datax = new double[4000][];
        double[] datay = new double[datax.length];
        for (int i = 0; i < datax.length; i++) {
            datax[i] = x[perm[i]];
            datay[i] = y[perm[i]];
        }

        int n = datax.length;
        int k = 10;

        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double sparseRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(183.96), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
     } catch (Exception ex) {
         System.err.println(ex);
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void testBank32nh() {
    System.out.println("bank32nh");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(32);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/bank32nh.arff"));
        double[] y = data.toArray(new double[data.size()]);
        double[][] x = data.toArray(new double[data.size()][]);
        Math.standardize(x);

        int[] perm = Math.permutate(x.length);
        double[][] datax = new double[4000][];
        double[] datay = new double[datax.length];
        for (int i = 0; i < datax.length; i++) {
            datax[i] = x[perm[i]];
            datay[i] = y[perm[i]];
        }

        int n = datax.length;
        int k = 10;

        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double sparseRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(55.3), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
     } catch (Exception ex) {
         System.err.println(ex);
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void testPuma8nh() {
    System.out.println("puma8nh");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(8);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/puma8nh.arff"));
        double[] y = data.toArray(new double[data.size()]);
        double[][] x = data.toArray(new double[data.size()][]);

        int[] perm = Math.permutate(x.length);
        double[][] datax = new double[4000][];
        double[] datay = new double[datax.length];
        for (int i = 0; i < datax.length; i++) {
            datax[i] = x[perm[i]];
            datay[i] = y[perm[i]];
        }

        int n = datax.length;
        int k = 10;

        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double sparseRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(38.63), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
     } catch (Exception ex) {
         System.err.println(ex);
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
/**
 * Test of learn method, of class GaussianProcessRegression.
 */
@Test
public void testKin8nm() {
    System.out.println("kin8nm");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(8);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/regression/kin8nm.arff"));
        double[] y = data.toArray(new double[data.size()]);
        double[][] x = data.toArray(new double[data.size()][]);

        int[] perm = Math.permutate(x.length);
        double[][] datax = new double[4000][];
        double[] datay = new double[datax.length];
        for (int i = 0; i < datax.length; i++) {
            datax[i] = x[perm[i]];
            datay[i] = y[perm[i]];
        }

        int n = datax.length;
        int k = 10;

        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double sparseRSS30 = 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]);

            GaussianProcessRegression<double[]> rkhs = new GaussianProcessRegression<>(trainx, trainy, new GaussianKernel(34.97), 0.1);

            KMeans kmeans = new KMeans(trainx, 30, 10);
            double[][] centers = kmeans.centroids();
            double r0 = 0.0;
            for (int l = 0; l < centers.length; l++) {
                for (int j = 0; j < l; j++) {
                    r0 += Math.distance(centers[l], centers[j]);
                }
            }
            r0 /= (2 * centers.length);
            System.out.println("Kernel width = " + r0);
            GaussianProcessRegression<double[]> sparse30 = new GaussianProcessRegression<>(trainx, trainy, centers, new GaussianKernel(r0), 0.1);

            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - rkhs.predict(testx[j]);
                rss += r * r;
                
                r = testy[j] - sparse30.predict(testx[j]);
                sparseRSS30 += r * r;
            }
        }

        System.out.println("Regular 10-CV MSE = " + rss / n);
        System.out.println("Sparse (30) 10-CV MSE = " + sparseRSS30 / n);
     } catch (Exception ex) {
         System.err.println(ex);
     }
}
 

import smile.clustering.KMeans; //導入依賴的package包/類
public Kmeans(int k, NumericColumn... columns) {
    double[][] input = DoubleArrays.to2dArray(columns);
    this.kMeans = new KMeans(input, k);
    this.inputColumns = columns;
}