Examples with UPGMALinkage smile.clustering.linkage.UPGMALinkage used on opensource projects

Example 1 with UPGMALinkage

use of smile.clustering.linkage.UPGMALinkage in project smile by haifengl.

the class NeuralMap method partition.

/**
     * Clustering neurons into k clusters.
     * @param k the number of clusters.
     * @param minPts a neuron will be treated as outlier if the number of its
     * points is less than minPts.
     * @return the number of non-outlier leaves.
     */
public int partition(int k, int minPts) {
    List<Neuron> data = new ArrayList<>();
    for (Neuron neuron : neurons) {
        neuron.y = OUTLIER;
        if (neuron.n >= minPts) {
            data.add(neuron);
        }
    }
    double[][] proximity = new double[data.size()][];
    for (int i = 0; i < data.size(); i++) {
        proximity[i] = new double[i + 1];
        for (int j = 0; j < i; j++) {
            proximity[i][j] = Math.distance(data.get(i).w, data.get(j).w);
        }
    }
    Linkage linkage = new UPGMALinkage(proximity);
    HierarchicalClustering hc = new HierarchicalClustering(linkage);
    int[] y = hc.partition(k);
    for (int i = 0; i < data.size(); i++) {
        data.get(i).y = y[i];
    }
    return data.size();
}

Example 2 with UPGMALinkage

use of smile.clustering.linkage.UPGMALinkage in project smile by haifengl.

the class SOM method partition.

/**
     * Clustering the neurons into k groups. And then assigns the samples in
     * each neuron to the corresponding cluster.
     * @param k the number of clusters.
     * @return the cluster label of samples.
     */
public int[] partition(int k) {
    int n = width * height;
    double[][] units = new double[n][d];
    for (int i = 0, l = 0; i < height; i++) {
        for (int j = 0; j < width; j++, l++) {
            units[l] = neurons[i][j];
        }
    }
    double[][] proximity = new double[n][];
    for (int i = 0; i < n; i++) {
        proximity[i] = new double[i + 1];
        for (int j = 0; j < i; j++) {
            proximity[i][j] = Math.distance(units[i], units[j]);
        }
    }
    Linkage linkage = new UPGMALinkage(proximity);
    HierarchicalClustering hc = new HierarchicalClustering(linkage);
    y = hc.partition(k);
    int[] cluster = new int[bmu.length];
    for (int i = 0; i < cluster.length; i++) {
        cluster[i] = y[bmu[i][0] * width + bmu[i][1]];
    }
    return cluster;
}

Example 3 with UPGMALinkage

use of smile.clustering.linkage.UPGMALinkage in project smile by haifengl.

the class GrowingNeuralGas method partition.

/**
     * Clustering neurons into k clusters.
     * @param k the number of clusters.
     */
public void partition(int k) {
    double[][] reps = new double[nodes.size()][];
    int i = 0;
    for (Node neuron : nodes) reps[i++] = neuron.w;
    double[][] proximity = new double[nodes.size()][];
    for (i = 0; i < nodes.size(); i++) {
        proximity[i] = new double[i + 1];
        for (int j = 0; j < i; j++) proximity[i][j] = Math.distance(reps[i], reps[j]);
    }
    Linkage linkage = new UPGMALinkage(proximity);
    HierarchicalClustering hc = new HierarchicalClustering(linkage);
    y = hc.partition(k);
}

Example 4 with UPGMALinkage

use of smile.clustering.linkage.UPGMALinkage in project smile by haifengl.

the class HierarchicalClusteringTest method testUSPS.

/**
     * Test of learn method, of class GMeans.
     */
@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"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        int n = x.length;
        double[][] proximity = new double[n][];
        for (int i = 0; i < n; i++) {
            proximity[i] = new double[i + 1];
            for (int j = 0; j < i; j++) {
                proximity[i][j] = Math.distance(x[i], x[j]);
            }
        }
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        HierarchicalClustering hc = new HierarchicalClustering(new SingleLinkage(proximity));
        int[] label = hc.partition(10);
        double r = rand.measure(y, label);
        double r2 = ari.measure(y, label);
        System.out.format("SingleLinkage rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new CompleteLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("CompleteLinkage rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.75);
        hc = new HierarchicalClustering(new UPGMALinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("UPGMA rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WPGMALinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("WPGMA rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.2);
        hc = new HierarchicalClustering(new UPGMCLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("UPGMC rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WPGMCLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("WPGMC rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WardLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("Ward rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.9);
        assertTrue(r2 > 0.5);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 5 with UPGMALinkage

use of smile.clustering.linkage.UPGMALinkage in project smile by haifengl.

the class HierarchicalClusteringDemo method learn.

@Override
public JComponent learn() {
    long clock = System.currentTimeMillis();
    double[][] data = dataset[datasetIndex];
    int n = data.length;
    double[][] proximity = new double[n][];
    for (int i = 0; i < n; i++) {
        proximity[i] = new double[i + 1];
        for (int j = 0; j < i; j++) proximity[i][j] = Math.distance(data[i], data[j]);
    }
    HierarchicalClustering hac = null;
    switch(linkageBox.getSelectedIndex()) {
        case 0:
            hac = new HierarchicalClustering(new SingleLinkage(proximity));
            break;
        case 1:
            hac = new HierarchicalClustering(new CompleteLinkage(proximity));
            break;
        case 2:
            hac = new HierarchicalClustering(new UPGMALinkage(proximity));
            break;
        case 3:
            hac = new HierarchicalClustering(new WPGMALinkage(proximity));
            break;
        case 4:
            hac = new HierarchicalClustering(new UPGMCLinkage(proximity));
            break;
        case 5:
            hac = new HierarchicalClustering(new WPGMCLinkage(proximity));
            break;
        case 6:
            hac = new HierarchicalClustering(new WardLinkage(proximity));
            break;
        default:
            throw new IllegalStateException("Unsupported Linkage");
    }
    System.out.format("Hierarchical clusterings %d samples in %dms\n", dataset[datasetIndex].length, System.currentTimeMillis() - clock);
    int[] membership = hac.partition(clusterNumber);
    int[] clusterSize = new int[clusterNumber];
    for (int i = 0; i < membership.length; i++) {
        clusterSize[membership[i]]++;
    }
    JPanel pane = new JPanel(new GridLayout(1, 3));
    PlotCanvas plot = ScatterPlot.plot(dataset[datasetIndex], pointLegend);
    plot.setTitle("Data");
    pane.add(plot);
    for (int k = 0; k < clusterNumber; k++) {
        double[][] cluster = new double[clusterSize[k]][];
        for (int i = 0, j = 0; i < dataset[datasetIndex].length; i++) {
            if (membership[i] == k) {
                cluster[j++] = dataset[datasetIndex][i];
            }
        }
        plot.points(cluster, pointLegend, Palette.COLORS[k % Palette.COLORS.length]);
    }
    plot = Dendrogram.plot("Dendrogram", hac.getTree(), hac.getHeight());
    plot.setTitle("Dendrogram");
    pane.add(plot);
    return pane;
}