Examples with LabeledDatasetPartitionDataBuilderOnHeap org.apache.ignite.ml.structures.partition.LabeledDatasetPartitionDataBuilderOnHeap used on opensource projects

Example 1 with LabeledDatasetPartitionDataBuilderOnHeap

use of org.apache.ignite.ml.structures.partition.LabeledDatasetPartitionDataBuilderOnHeap in project ignite by apache.

the class ANNClassificationTrainer method getCentroidStat.

/**
 */
private <K, V> CentroidStat getCentroidStat(DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> vectorizer, List<Vector> centers) {
    PartitionDataBuilder<K, V, EmptyContext, LabeledVectorSet<LabeledVector>> partDataBuilder = new LabeledDatasetPartitionDataBuilderOnHeap<>(vectorizer);
    try (Dataset<EmptyContext, LabeledVectorSet<LabeledVector>> dataset = datasetBuilder.build(envBuilder, (env, upstream, upstreamSize) -> new EmptyContext(), partDataBuilder, learningEnvironment())) {
        return dataset.compute(data -> {
            CentroidStat res = new CentroidStat();
            for (int i = 0; i < data.rowSize(); i++) {
                final IgniteBiTuple<Integer, Double> closestCentroid = findClosestCentroid(centers, data.getRow(i));
                int centroidIdx = closestCentroid.get1();
                double lb = data.label(i);
                // add new label to label set
                res.labels().add(lb);
                ConcurrentHashMap<Double, Integer> centroidStat = res.centroidStat.get(centroidIdx);
                if (centroidStat == null) {
                    centroidStat = new ConcurrentHashMap<>();
                    centroidStat.put(lb, 1);
                    res.centroidStat.put(centroidIdx, centroidStat);
                } else {
                    int cnt = centroidStat.getOrDefault(lb, 0);
                    centroidStat.put(lb, cnt + 1);
                }
                res.counts.merge(centroidIdx, 1, (IgniteBiFunction<Integer, Integer, Integer>) (i1, i2) -> i1 + i2);
            }
            return res;
        }, (a, b) -> {
            if (a == null)
                return b == null ? new CentroidStat() : b;
            if (b == null)
                return a;
            return a.merge(b);
        });
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

Example 2 with LabeledDatasetPartitionDataBuilderOnHeap

use of org.apache.ignite.ml.structures.partition.LabeledDatasetPartitionDataBuilderOnHeap in project ignite by apache.

the class KNNUtils method buildDataset.

/**
 * Builds dataset.
 *
 * @param envBuilder Learning environment builder.
 * @param datasetBuilder Dataset builder.
 * @param vectorizer Upstream vectorizer.
 * @return Dataset.
 */
@Nullable
public static <K, V, C extends Serializable> Dataset<EmptyContext, LabeledVectorSet<LabeledVector>> buildDataset(LearningEnvironmentBuilder envBuilder, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> vectorizer) {
    LearningEnvironment environment = envBuilder.buildForTrainer();
    environment.initDeployingContext(vectorizer);
    PartitionDataBuilder<K, V, EmptyContext, LabeledVectorSet<LabeledVector>> partDataBuilder = new LabeledDatasetPartitionDataBuilderOnHeap<>(vectorizer);
    Dataset<EmptyContext, LabeledVectorSet<LabeledVector>> dataset = null;
    if (datasetBuilder != null) {
        dataset = datasetBuilder.build(envBuilder, (env, upstream, upstreamSize) -> new EmptyContext(), partDataBuilder, environment);
    }
    return dataset;
}

Example 3 with LabeledDatasetPartitionDataBuilderOnHeap

use of org.apache.ignite.ml.structures.partition.LabeledDatasetPartitionDataBuilderOnHeap in project ignite by apache.

the class KMeansTrainer method updateModel.

/**
 * {@inheritDoc}
 */
@Override
protected <K, V> KMeansModel updateModel(KMeansModel mdl, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> preprocessor) {
    assert datasetBuilder != null;
    PartitionDataBuilder<K, V, EmptyContext, LabeledVectorSet<LabeledVector>> partDataBuilder = new LabeledDatasetPartitionDataBuilderOnHeap<>(preprocessor);
    Vector[] centers;
    try (Dataset<EmptyContext, LabeledVectorSet<LabeledVector>> dataset = datasetBuilder.build(envBuilder, (env, upstream, upstreamSize) -> new EmptyContext(), partDataBuilder, learningEnvironment())) {
        final Integer cols = dataset.compute(org.apache.ignite.ml.structures.Dataset::colSize, (a, b) -> {
            if (a == null)
                return b == null ? 0 : b;
            if (b == null)
                return a;
            return b;
        });
        if (cols == null)
            return getLastTrainedModelOrThrowEmptyDatasetException(mdl);
        centers = Optional.ofNullable(mdl).map(KMeansModel::centers).orElseGet(() -> initClusterCentersRandomly(dataset, k));
        boolean converged = false;
        int iteration = 0;
        while (iteration < maxIterations && !converged) {
            Vector[] newCentroids = new DenseVector[k];
            TotalCostAndCounts totalRes = calcDataForNewCentroids(centers, dataset, cols);
            converged = true;
            for (Map.Entry<Integer, Vector> entry : totalRes.sums.entrySet()) {
                Vector massCenter = entry.getValue().times(1.0 / totalRes.counts.get(entry.getKey()));
                if (converged && distance.compute(massCenter, centers[entry.getKey()]) > epsilon * epsilon)
                    converged = false;
                newCentroids[entry.getKey()] = massCenter;
            }
            iteration++;
            for (int i = 0; i < centers.length; i++) {
                if (newCentroids[i] != null)
                    centers[i] = newCentroids[i];
            }
        }
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
    return new KMeansModel(centers, distance);
}

Example 4 with LabeledDatasetPartitionDataBuilderOnHeap

use of org.apache.ignite.ml.structures.partition.LabeledDatasetPartitionDataBuilderOnHeap in project ignite by apache.

the class Deltas method updateModel.

/**
 * {@inheritDoc}
 */
@Override
protected <K, V> SVMLinearClassificationModel updateModel(SVMLinearClassificationModel mdl, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> preprocessor) {
    assert datasetBuilder != null;
    IgniteFunction<Double, Double> lbTransformer = lb -> {
        if (lb == 0.0)
            return -1.0;
        else
            return lb;
    };
    IgniteFunction<LabeledVector<Double>, LabeledVector<Double>> func = lv -> new LabeledVector<>(lv.features(), lbTransformer.apply(lv.label()));
    PatchedPreprocessor<K, V, Double, Double> patchedPreprocessor = new PatchedPreprocessor<>(func, preprocessor);
    PartitionDataBuilder<K, V, EmptyContext, LabeledVectorSet<LabeledVector>> partDataBuilder = new LabeledDatasetPartitionDataBuilderOnHeap<>(patchedPreprocessor);
    Vector weights;
    try (Dataset<EmptyContext, LabeledVectorSet<LabeledVector>> dataset = datasetBuilder.build(envBuilder, (env, upstream, upstreamSize) -> new EmptyContext(), partDataBuilder, learningEnvironment())) {
        if (mdl == null) {
            final int cols = dataset.compute(org.apache.ignite.ml.structures.Dataset::colSize, (a, b) -> {
                if (a == null)
                    return b == null ? 0 : b;
                if (b == null)
                    return a;
                return b;
            });
            final int weightVectorSizeWithIntercept = cols + 1;
            weights = initializeWeightsWithZeros(weightVectorSizeWithIntercept);
        } else
            weights = getStateVector(mdl);
        for (int i = 0; i < this.getAmountOfIterations(); i++) {
            Vector deltaWeights = calculateUpdates(weights, dataset);
            if (deltaWeights == null)
                return getLastTrainedModelOrThrowEmptyDatasetException(mdl);
            // creates new vector
            weights = weights.plus(deltaWeights);
        }
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
    return new SVMLinearClassificationModel(weights.copyOfRange(1, weights.size()), weights.get(0));
}