Examples with DenseLocalOnHeapVector org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector used on opensource projects

Example 21 with DenseLocalOnHeapVector

use of org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector in project ignite by apache.

the class MnistMLPTestUtil method createDataset.

/**
 */
static IgniteBiTuple<Matrix, Matrix> createDataset(Stream<DenseLocalOnHeapVector> s, int samplesCnt, int featCnt) {
    Matrix vectors = new DenseLocalOnHeapMatrix(featCnt, samplesCnt);
    Matrix labels = new DenseLocalOnHeapMatrix(10, samplesCnt);
    List<DenseLocalOnHeapVector> sc = s.collect(Collectors.toList());
    for (int i = 0; i < samplesCnt; i++) {
        DenseLocalOnHeapVector v = sc.get(i);
        vectors.assignColumn(i, v.viewPart(0, featCnt));
        labels.assignColumn(i, num2Vec((int) v.getX(featCnt), 10));
    }
    return new IgniteBiTuple<>(vectors, labels);
}

Example 22 with DenseLocalOnHeapVector

use of org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector in project ignite by apache.

the class MnistMLPTestUtil method loadMnist.

/**
 */
static IgniteBiTuple<Stream<DenseLocalOnHeapVector>, Stream<DenseLocalOnHeapVector>> loadMnist(int samplesCnt) throws IOException {
    Properties props = loadMNISTProperties();
    Stream<DenseLocalOnHeapVector> trainingMnistStream = MnistUtils.mnist(props.getProperty(PROP_TRAINING_IMAGES), props.getProperty(PROP_TRAINING_LABELS), new Random(123L), samplesCnt);
    Stream<DenseLocalOnHeapVector> testMnistStream = MnistUtils.mnist(props.getProperty(PROP_TEST_IMAGES), props.getProperty(PROP_TEST_LABELS), new Random(123L), 10_000);
    return new IgniteBiTuple<>(trainingMnistStream, testMnistStream);
}

Example 23 with DenseLocalOnHeapVector

use of org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector in project ignite by apache.

the class GradientDescentTest method testOptimize.

/**
 * Test gradient descent optimization on function y = x^2 with gradient function 2 * x.
 */
@Test
public void testOptimize() {
    GradientDescent gradientDescent = new GradientDescent((inputs, groundTruth, point) -> point.times(2), new SimpleUpdater(0.01));
    Vector res = gradientDescent.optimize(new DenseLocalOnHeapMatrix(new double[1][1]), new DenseLocalOnHeapVector(new double[] { 2.0 }));
    TestUtils.assertEquals(0, res.get(0), PRECISION);
}

Example 24 with DenseLocalOnHeapVector

use of org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector in project ignite by apache.

the class SVMModelTest method testPredictOnAnObservationWithWrongCardinality.

/**
 */
@Test(expected = CardinalityException.class)
public void testPredictOnAnObservationWithWrongCardinality() {
    Vector weights = new DenseLocalOnHeapVector(new double[] { 2.0, 3.0 });
    SVMLinearBinaryClassificationModel mdl = new SVMLinearBinaryClassificationModel(weights, 1.0);
    Vector observation = new DenseLocalOnHeapVector(new double[] { 1.0 });
    mdl.apply(observation);
}

Example 25 with DenseLocalOnHeapVector

use of org.apache.ignite.ml.math.impls.vector.DenseLocalOnHeapVector in project ignite by apache.

the class ColumnDecisionTreeTrainerBenchmark method tstMNISTSparseDistributedMatrix.

/**
 * Run decision tree classifier on MNIST using sparse distributed matrix as a storage for dataset.
 * To run this test rename this method so it starts from 'test'.
 *
 * @throws IOException In case of loading MNIST dataset errors.
 */
public void tstMNISTSparseDistributedMatrix() throws IOException {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    int ptsCnt = 30_000;
    int featCnt = 28 * 28;
    Properties props = loadMNISTProperties();
    Stream<DenseLocalOnHeapVector> trainingMnistStream = MnistUtils.mnist(props.getProperty(PROP_TRAINING_IMAGES), props.getProperty(PROP_TRAINING_LABELS), new Random(123L), ptsCnt);
    Stream<DenseLocalOnHeapVector> testMnistStream = MnistUtils.mnist(props.getProperty(PROP_TEST_IMAGES), props.getProperty(PROP_TEST_LABELS), new Random(123L), 10_000);
    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(), trainingMnistStream.iterator(), featCnt + 1);
    ColumnDecisionTreeTrainer<GiniSplitCalculator.GiniData> trainer = new ColumnDecisionTreeTrainer<>(10, ContinuousSplitCalculators.GINI.apply(ignite), RegionCalculators.GINI, RegionCalculators.MOST_COMMON, 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));
    IgniteTriFunction<Model<Vector, Double>, Stream<IgniteBiTuple<Vector, Double>>, Function<Double, Double>, Double> mse = Estimators.errorsPercentage();
    Double accuracy = mse.apply(mdl, testMnistStream.map(v -> new IgniteBiTuple<>(v.viewPart(0, featCnt), v.getX(featCnt))), Function.identity());
    X.println("Errors percentage: " + accuracy);
    Assert.assertEquals(0, SplitCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, FeaturesCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, ContextCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, ProjectionsCache.getOrCreate(ignite).size());
}