Examples with EuclideanDistance smile.math.distance.EuclideanDistance used on opensource projects

Example 26 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class KNNDemo method run.

@Override
public void run() {
    startButton.setEnabled(false);
    logNSlider.setEnabled(false);
    dimensionSlider.setEnabled(false);
    knnField.setEnabled(false);
    logN = logNSlider.getValue();
    dimension = dimensionSlider.getValue();
    System.out.println("Generating dataset...");
    int n = (int) Math.pow(10, logN);
    double[][] data = new double[n][];
    for (int i = 0; i < n; i++) {
        data[i] = new double[dimension];
        for (int j = 0; j < dimension; j++) {
            data[i][j] = Math.random();
        }
    }
    int[] perm = Math.permutate(n);
    System.out.println("Building searching data structure...");
    long time = System.currentTimeMillis();
    LinearSearch<double[]> naive = new LinearSearch<>(data, new EuclideanDistance());
    int naiveBuild = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    KDTree<double[]> kdtree = new KDTree<>(data, data);
    int kdtreeBuild = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    CoverTree<double[]> cover = new CoverTree<>(data, new EuclideanDistance());
    int coverBuild = (int) (System.currentTimeMillis() - time);
    System.out.println("Perform 1000 searches...");
    double radius = 0.0;
    List<Neighbor<double[], double[]>[]> answers = new ArrayList<>(1000);
    time = System.currentTimeMillis();
    for (int i = 0; i < 1000; i++) {
        answers.add(naive.knn(data[perm[i]], knn));
        for (int j = 0; j < answers.get(i).length; j++) {
            radius += answers.get(i)[j].distance;
        }
    }
    int naiveSearch = (int) (System.currentTimeMillis() - time);
    radius /= 1000 * knn;
    time = System.currentTimeMillis();
    for (int i = 0; i < 1000; i++) {
        kdtree.knn(data[perm[i]], knn);
    }
    int kdtreeSearch = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    for (int i = 0; i < 1000; i++) {
        cover.knn(data[perm[i]], knn);
    }
    int coverSearch = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    LSH<double[]> lsh = new LSH<>(dimension, 5, (int) Math.log2(dimension), 4 * radius, 1017881);
    for (int i = 0; i < n; i++) {
        lsh.put(data[i], data[i]);
    }
    int lshBuild = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    MPLSH<double[]> mplsh = new MPLSH<>(dimension, 2, (int) Math.log2(n), 4 * radius, 1017881);
    for (int i = 0; i < n; i++) {
        mplsh.put(data[i], data[i]);
    }
    double[][] train = new double[1000][];
    for (int i = 0; i < train.length; i++) {
        train[i] = data[perm[i]];
    }
    mplsh.learn(kdtree, train, 1.5 * radius);
    int mplshBuild = (int) (System.currentTimeMillis() - time);
    double lshRecall = 0.0;
    time = System.currentTimeMillis();
    for (int i = 0; i < 1000; i++) {
        Neighbor<double[], double[]>[] neighbors = lsh.knn(data[perm[i]], knn);
        int hit = 0;
        for (int p = 0; p < knn && answers.get(i)[p] != null; p++) {
            for (int q = 0; q < knn && neighbors[q] != null; q++) {
                if (answers.get(i)[p].index == neighbors[q].index) {
                    hit++;
                    break;
                }
            }
        }
        lshRecall += 1.0 * hit / knn;
    }
    int lshSearch = (int) (System.currentTimeMillis() - time);
    lshRecall /= 1000;
    System.out.format("The recall of LSH is %.1f%%\n", lshRecall * 100);
    double mplshRecall = 0.0;
    time = System.currentTimeMillis();
    for (int i = 0; i < 1000; i++) {
        Neighbor<double[], double[]>[] neighbors = mplsh.knn(data[perm[i]], knn, 0.95, 10);
        int hit = 0;
        for (int p = 0; p < knn && answers.get(i)[p] != null; p++) {
            for (int q = 0; q < knn && neighbors[q] != null; q++) {
                if (answers.get(i)[p].index == neighbors[q].index) {
                    hit++;
                    break;
                }
            }
        }
        mplshRecall += 1.0 * hit / knn;
    }
    int mplshSearch = (int) (System.currentTimeMillis() - time);
    mplshRecall /= 1000;
    System.out.format("The recall of MPLSH is %.1f%%\n", mplshRecall * 100);
    canvas.removeAll();
    double[] buildTime = { naiveBuild, kdtreeBuild, coverBuild, lshBuild, mplshBuild };
    PlotCanvas build = BarPlot.plot(buildTime, label);
    build.setTitle("Build Time");
    canvas.add(build);
    double[] searchTime = { naiveSearch, kdtreeSearch, coverSearch, lshSearch, mplshSearch };
    PlotCanvas search = BarPlot.plot(searchTime, label);
    search.setTitle("Search Time");
    canvas.add(search);
    validate();
    startButton.setEnabled(true);
    logNSlider.setEnabled(true);
    dimensionSlider.setEnabled(true);
    knnField.setEnabled(true);
}

Example 27 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class MECDemo method learn.

@Override
public JComponent learn() {
    try {
        range = Double.parseDouble(rangeField.getText().trim());
        if (range <= 0) {
            JOptionPane.showMessageDialog(this, "Invalid Range: " + range, "Error", JOptionPane.ERROR_MESSAGE);
            return null;
        }
    } catch (Exception e) {
        JOptionPane.showMessageDialog(this, "Invalid range: " + rangeField.getText(), "Error", JOptionPane.ERROR_MESSAGE);
        return null;
    }
    long clock = System.currentTimeMillis();
    MEC<double[]> mec = new MEC<>(dataset[datasetIndex], new EuclideanDistance(), clusterNumber, range);
    System.out.format("MEC clusterings %d samples in %dms\n", dataset[datasetIndex].length, System.currentTimeMillis() - clock);
    PlotCanvas plot = ScatterPlot.plot(dataset[datasetIndex], pointLegend);
    for (int k = 0; k < mec.getNumClusters(); k++) {
        double[][] cluster = new double[mec.getClusterSize()[k]][];
        for (int i = 0, j = 0; i < dataset[datasetIndex].length; i++) {
            if (mec.getClusterLabel()[i] == k) {
                cluster[j++] = dataset[datasetIndex][i];
            }
        }
        plot.points(cluster, pointLegend, Palette.COLORS[k % Palette.COLORS.length]);
    }
    return plot;
}

Example 28 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class NearestNeighborDemo method run.

@Override
public void run() {
    startButton.setEnabled(false);
    logNSlider.setEnabled(false);
    dimensionSlider.setEnabled(false);
    logN = logNSlider.getValue();
    dimension = dimensionSlider.getValue();
    System.out.println("Generating dataset...");
    int n = (int) Math.pow(10, logN);
    double[][] data = new double[n][];
    for (int i = 0; i < n; i++) {
        data[i] = new double[dimension];
        for (int j = 0; j < dimension; j++) {
            data[i][j] = Math.random();
        }
    }
    int[] perm = Math.permutate(n);
    System.out.println("Building searching data structure...");
    long time = System.currentTimeMillis();
    LinearSearch<double[]> naive = new LinearSearch<>(data, new EuclideanDistance());
    int naiveBuild = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    KDTree<double[]> kdtree = new KDTree<>(data, data);
    int kdtreeBuild = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    CoverTree<double[]> cover = new CoverTree<>(data, new EuclideanDistance());
    int coverBuild = (int) (System.currentTimeMillis() - time);
    System.out.println("Perform 100 searches...");
    int[] answer = new int[100];
    double radius = 0.0;
    time = System.currentTimeMillis();
    for (int i = 0; i < 100; i++) {
        Neighbor<double[], double[]> neighbor = naive.nearest(data[perm[i]]);
        answer[i] = neighbor.index;
        radius += neighbor.distance;
    }
    int naiveSearch = (int) (System.currentTimeMillis() - time);
    radius /= 100;
    time = System.currentTimeMillis();
    for (int i = 0; i < 100; i++) {
        kdtree.nearest(data[perm[i]]);
    }
    int kdtreeSearch = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    for (int i = 0; i < 100; i++) {
        cover.nearest(data[perm[i]]);
    }
    int coverSearch = (int) (System.currentTimeMillis() - time);
    time = System.currentTimeMillis();
    LSH<double[]> lsh = new LSH<>(dimension, 5, (int) Math.ceil(Math.log2(dimension)), 4 * radius, 1017881);
    for (int i = 0; i < n; i++) {
        lsh.put(data[i], data[i]);
    }
    int lshBuild = (int) (System.currentTimeMillis() - time);
    double lshRecall = 0.0;
    time = System.currentTimeMillis();
    for (int i = 0; i < 100; i++) {
        if (lsh.nearest(data[perm[i]]).index == answer[i]) {
            lshRecall++;
        }
    }
    int lshSearch = (int) (System.currentTimeMillis() - time);
    lshRecall /= 100;
    System.out.format("The recall of LSH is %.1f%%\n", lshRecall * 100);
    time = System.currentTimeMillis();
    MPLSH<double[]> mplsh = new MPLSH<>(dimension, 5, (int) Math.ceil(Math.log2(n)), 4 * radius, 1017881);
    for (int i = 0; i < n; i++) {
        mplsh.put(data[i], data[i]);
    }
    double[][] train = new double[1000][];
    for (int i = 0; i < train.length; i++) {
        train[i] = data[perm[i]];
    }
    mplsh.learn(kdtree, train, 1.5 * radius);
    int mplshBuild = (int) (System.currentTimeMillis() - time);
    double mplshRecall = 0.0;
    time = System.currentTimeMillis();
    for (int i = 0; i < 100; i++) {
        if (mplsh.nearest(data[perm[i]], 0.95, 10).index == answer[i]) {
            mplshRecall++;
        }
    }
    int mplshSearch = (int) (System.currentTimeMillis() - time);
    mplshRecall /= 100;
    System.out.format("The recall of MPLSH is %.1f%%\n", mplshRecall * 100);
    canvas.removeAll();
    double[] buildTime = { naiveBuild, kdtreeBuild, coverBuild, lshBuild, mplshBuild };
    PlotCanvas build = BarPlot.plot(buildTime, label);
    build.setTitle("Build Time");
    canvas.add(build);
    double[] searchTime = { naiveSearch, kdtreeSearch, coverSearch, lshSearch, mplshSearch };
    PlotCanvas search = BarPlot.plot(searchTime, label);
    search.setTitle("Search Time");
    canvas.add(search);
    validate();
    startButton.setEnabled(true);
    logNSlider.setEnabled(true);
    dimensionSlider.setEnabled(true);
}

Example 29 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class DBScanDemo method learn.

@Override
public JComponent learn() {
    try {
        minPts = Integer.parseInt(minPtsField.getText().trim());
        if (minPts < 1) {
            JOptionPane.showMessageDialog(this, "Invalid MinPts: " + minPts, "Error", JOptionPane.ERROR_MESSAGE);
            return null;
        }
    } catch (Exception e) {
        JOptionPane.showMessageDialog(this, "Invalid MinPts: " + minPtsField.getText(), "Error", JOptionPane.ERROR_MESSAGE);
        return null;
    }
    try {
        range = Double.parseDouble(rangeField.getText().trim());
        if (range <= 0) {
            JOptionPane.showMessageDialog(this, "Invalid Range: " + range, "Error", JOptionPane.ERROR_MESSAGE);
            return null;
        }
    } catch (Exception e) {
        JOptionPane.showMessageDialog(this, "Invalid range: " + rangeField.getText(), "Error", JOptionPane.ERROR_MESSAGE);
        return null;
    }
    long clock = System.currentTimeMillis();
    DBScan<double[]> dbscan = new DBScan<>(dataset[datasetIndex], new EuclideanDistance(), minPts, range);
    System.out.format("DBSCAN clusterings %d samples in %dms\n", dataset[datasetIndex].length, System.currentTimeMillis() - clock);
    JPanel pane = new JPanel(new GridLayout(1, 2));
    PlotCanvas plot = ScatterPlot.plot(dataset[datasetIndex], pointLegend);
    for (int k = 0; k < dbscan.getNumClusters(); k++) {
        double[][] cluster = new double[dbscan.getClusterSize()[k]][];
        for (int i = 0, j = 0; i < dataset[datasetIndex].length; i++) {
            if (dbscan.getClusterLabel()[i] == k) {
                cluster[j++] = dataset[datasetIndex][i];
            }
        }
        plot.points(cluster, pointLegend, Palette.COLORS[k % Palette.COLORS.length]);
    }
    pane.add(plot);
    return pane;
}