Examples with SparseDistributedMatrix org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix used on opensource projects

Example 26 with SparseDistributedMatrix

use of org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix in project ignite by apache.

the class ColumnDecisionTreeTrainerBenchmark method tstF1.

/**
 * Test decision tree regression.
 * To run this test rename this method so it starts from 'test'.
 */
public void tstF1() {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    int ptsCnt = 10000;
    Map<Integer, double[]> ranges = new HashMap<>();
    ranges.put(0, new double[] { -100.0, 100.0 });
    ranges.put(1, new double[] { -100.0, 100.0 });
    ranges.put(2, new double[] { -100.0, 100.0 });
    int featCnt = 100;
    double[] defRng = { -1.0, 1.0 };
    Vector[] trainVectors = vecsFromRanges(ranges, featCnt, defRng, new Random(123L), ptsCnt, f1);
    SparseDistributedMatrix m = new SparseDistributedMatrix(ptsCnt, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    SparseDistributedMatrixStorage sto = (SparseDistributedMatrixStorage) m.getStorage();
    loadVectorsIntoSparseDistributedMatrixCache(sto.cache().getName(), sto.getUUID(), Arrays.stream(trainVectors).iterator(), featCnt + 1);
    IgniteFunction<DoubleStream, Double> regCalc = s -> s.average().orElse(0.0);
    ColumnDecisionTreeTrainer<VarianceSplitCalculator.VarianceData> trainer = new ColumnDecisionTreeTrainer<>(10, ContinuousSplitCalculators.VARIANCE, RegionCalculators.VARIANCE, regCalc, ignite);
    X.println("Training started.");
    long before = System.currentTimeMillis();
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, new HashMap<>()));
    X.println("Training finished in: " + (System.currentTimeMillis() - before) + " ms.");
    Vector[] testVectors = vecsFromRanges(ranges, featCnt, defRng, new Random(123L), 20, f1);
    IgniteTriFunction<Model<Vector, Double>, Stream<IgniteBiTuple<Vector, Double>>, Function<Double, Double>, Double> mse = Estimators.MSE();
    Double accuracy = mse.apply(mdl, Arrays.stream(testVectors).map(v -> new IgniteBiTuple<>(v.viewPart(0, featCnt), v.getX(featCnt))), Function.identity());
    X.println("MSE: " + accuracy);
}

Example 27 with SparseDistributedMatrix

use of org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix in project ignite by apache.

the class GradientDescent method calculateDistributedGradient.

/**
 * Calculates gradient based in distributed matrix using {@link SparseDistributedMatrixMapReducer}.
 *
 * @param data Distributed matrix
 * @param weights Point to calculate gradient
 * @return Gradient
 */
private Vector calculateDistributedGradient(SparseDistributedMatrix data, Vector weights) {
    SparseDistributedMatrixMapReducer mapReducer = new SparseDistributedMatrixMapReducer(data);
    return mapReducer.mapReduce((matrix, args) -> {
        Matrix inputs = extractInputs(matrix);
        Vector groundTruth = extractGroundTruth(matrix);
        return lossGradient.compute(inputs, groundTruth, args);
    }, gradients -> {
        int cnt = 0;
        Vector resGradient = new DenseLocalOnHeapVector(data.columnSize());
        for (Vector gradient : gradients) {
            if (gradient != null) {
                resGradient = resGradient.plus(gradient);
                cnt++;
            }
        }
        return resGradient.divide(cnt);
    }, weights);
}

Example 28 with SparseDistributedMatrix

use of org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix in project ignite by apache.

the class KMeansDistributedClustererTestMultiNode method testClusterizationOnDatasetWithObviousStructure.

/**
 */
public void testClusterizationOnDatasetWithObviousStructure() throws IOException {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    int ptsCnt = 10000;
    int squareSideLen = 10000;
    Random rnd = new Random(123456L);
    // Let centers be in the vertices of square.
    Map<Integer, Vector> centers = new HashMap<>();
    centers.put(100, new DenseLocalOnHeapVector(new double[] { 0.0, 0.0 }));
    centers.put(900, new DenseLocalOnHeapVector(new double[] { squareSideLen, 0.0 }));
    centers.put(3000, new DenseLocalOnHeapVector(new double[] { 0.0, squareSideLen }));
    centers.put(6000, new DenseLocalOnHeapVector(new double[] { squareSideLen, squareSideLen }));
    SparseDistributedMatrix points = new SparseDistributedMatrix(ptsCnt, 2, StorageConstants.ROW_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    List<Integer> permutation = IntStream.range(0, ptsCnt).boxed().collect(Collectors.toList());
    Collections.shuffle(permutation, rnd);
    int totalCnt = 0;
    for (Integer count : centers.keySet()) {
        for (int i = 0; i < count; i++) {
            Vector pnt = new DenseLocalOnHeapVector(2).assign(centers.get(count));
            // Perturbate point on random value.
            pnt.map(val -> val + rnd.nextDouble() * squareSideLen / 100);
            points.assignRow(permutation.get(totalCnt), pnt);
            totalCnt++;
        }
    }
    EuclideanDistance dist = new EuclideanDistance();
    KMeansDistributedClusterer clusterer = new KMeansDistributedClusterer(dist, 3, 100, 1L);
    clusterer.cluster(points, 4);
    points.destroy();
}

Example 29 with SparseDistributedMatrix

use of org.apache.ignite.ml.math.impls.matrix.SparseDistributedMatrix in project ignite by apache.

the class KMeansDistributedClustererTestMultiNode method testPerformClusterAnalysisDegenerate.

/**
 */
public void testPerformClusterAnalysisDegenerate() {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    KMeansDistributedClusterer clusterer = new KMeansDistributedClusterer(new EuclideanDistance(), 1, 1, 1L);
    double[] v1 = new double[] { 1959, 325100 };
    double[] v2 = new double[] { 1960, 373200 };
    SparseDistributedMatrix points = new SparseDistributedMatrix(2, 2, StorageConstants.ROW_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    points.setRow(0, v1);
    points.setRow(1, v2);
    clusterer.cluster(points, 1);
    points.destroy();
}