Examples with DenseVector org.apache.ignite.ml.math.primitives.vector.impl.DenseVector used on opensource projects

Example 6 with DenseVector

use of org.apache.ignite.ml.math.primitives.vector.impl.DenseVector in project ignite by apache.

the class MinMaxScalerExample method createCache.

/**
 */
private static IgniteCache<Integer, Vector> createCache(Ignite ignite) {
    CacheConfiguration<Integer, Vector> cacheConfiguration = new CacheConfiguration<>();
    cacheConfiguration.setName("PERSONS");
    cacheConfiguration.setAffinity(new RendezvousAffinityFunction(false, 2));
    IgniteCache<Integer, Vector> persons = ignite.createCache(cacheConfiguration);
    persons.put(1, new DenseVector(new Serializable[] { "Mike", 42, 10000 }));
    persons.put(2, new DenseVector(new Serializable[] { "John", 32, 64000 }));
    persons.put(3, new DenseVector(new Serializable[] { "George", 53, 120000 }));
    persons.put(4, new DenseVector(new Serializable[] { "Karl", 24, 70000 }));
    return persons;
}

Example 7 with DenseVector

use of org.apache.ignite.ml.math.primitives.vector.impl.DenseVector in project ignite by apache.

the class BinarizationExample method createCache.

/**
 */
private static IgniteCache<Integer, Vector> createCache(Ignite ignite) {
    CacheConfiguration<Integer, Vector> cacheConfiguration = new CacheConfiguration<>();
    cacheConfiguration.setName("PERSONS");
    cacheConfiguration.setAffinity(new RendezvousAffinityFunction(false, 2));
    IgniteCache<Integer, Vector> persons = ignite.createCache(cacheConfiguration);
    persons.put(1, new DenseVector(new Serializable[] { "Mike", 42, 10000 }));
    persons.put(2, new DenseVector(new Serializable[] { "John", 32, 64000 }));
    persons.put(3, new DenseVector(new Serializable[] { "George", 53, 120000 }));
    persons.put(4, new DenseVector(new Serializable[] { "Karl", 24, 70000 }));
    return persons;
}

Example 8 with DenseVector

use of org.apache.ignite.ml.math.primitives.vector.impl.DenseVector in project ignite by apache.

the class MaxAbsScalerExample method createCache.

/**
 */
private static IgniteCache<Integer, Vector> createCache(Ignite ignite) {
    CacheConfiguration<Integer, Vector> cacheConfiguration = new CacheConfiguration<>();
    cacheConfiguration.setName("PERSONS");
    cacheConfiguration.setAffinity(new RendezvousAffinityFunction(false, 2));
    IgniteCache<Integer, Vector> persons = ignite.createCache(cacheConfiguration);
    persons.put(1, new DenseVector(new Serializable[] { "Mike", 42, 10000 }));
    persons.put(2, new DenseVector(new Serializable[] { "John", 32, 64000 }));
    persons.put(3, new DenseVector(new Serializable[] { "George", 53, 120000 }));
    persons.put(4, new DenseVector(new Serializable[] { "Karl", 24, 70000 }));
    return persons;
}

Example 9 with DenseVector

use of org.apache.ignite.ml.math.primitives.vector.impl.DenseVector in project ignite by apache.

the class MultilayerPerceptron method initLayers.

/**
 * Init layers parameters with initializer.
 *
 * @param initializer Parameters initializer.
 */
private void initLayers(MLPInitializer initializer) {
    int prevSize = architecture.inputSize();
    for (int i = 1; i < architecture.layersCount(); i++) {
        TransformationLayerArchitecture layerCfg = architecture.transformationLayerArchitecture(i);
        int neuronsCnt = layerCfg.neuronsCount();
        DenseMatrix weights = new DenseMatrix(neuronsCnt, prevSize);
        initializer.initWeights(weights);
        DenseVector biases = null;
        if (layerCfg.hasBias()) {
            biases = new DenseVector(neuronsCnt);
            initializer.initBiases(biases);
        }
        layers.add(new MLPLayer(weights, biases));
        prevSize = layerCfg.neuronsCount();
    }
}

Example 10 with DenseVector

use of org.apache.ignite.ml.math.primitives.vector.impl.DenseVector in project ignite by apache.

the class MultilayerPerceptron method paramsAsVector.

/**
 * Flatten this MLP parameters as vector.
 *
 * @param layersParams List of layers parameters.
 * @return This MLP parameters as vector.
 */
private Vector paramsAsVector(List<MLPLayer> layersParams) {
    int off = 0;
    Vector res = new DenseVector(architecture().parametersCount());
    for (MLPLayer layerParams : layersParams) {
        off = writeToVector(res, layerParams.weights, off);
        if (layerParams.biases != null)
            off = writeToVector(res, layerParams.biases, off);
    }
    return res;
}