Examples with LabelEncoderPreprocessor org.apache.ignite.ml.preprocessing.encoding.label.LabelEncoderPreprocessor used on opensource projects

Example 1 with LabelEncoderPreprocessor

use of org.apache.ignite.ml.preprocessing.encoding.label.LabelEncoderPreprocessor in project ignite by apache.

the class EncoderTrainer method fit.

/**
 * {@inheritDoc}
 */
@Override
public EncoderPreprocessor<K, V> fit(LearningEnvironmentBuilder envBuilder, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> basePreprocessor) {
    if (handledIndices.isEmpty() && encoderType != EncoderType.LABEL_ENCODER)
        throw new RuntimeException("Add indices of handled features");
    try (Dataset<EmptyContext, EncoderPartitionData> dataset = datasetBuilder.build(envBuilder, (env, upstream, upstreamSize) -> new EmptyContext(), (env, upstream, upstreamSize, ctx) -> {
        EncoderPartitionData partData = new EncoderPartitionData();
        if (encoderType == EncoderType.LABEL_ENCODER) {
            Map<String, Integer> lbFrequencies = null;
            while (upstream.hasNext()) {
                UpstreamEntry<K, V> entity = upstream.next();
                LabeledVector<Double> row = basePreprocessor.apply(entity.getKey(), entity.getValue());
                lbFrequencies = updateLabelFrequenciesForNextRow(row, lbFrequencies);
            }
            partData.withLabelFrequencies(lbFrequencies);
        } else if (encoderType == EncoderType.TARGET_ENCODER) {
            TargetCounter[] targetCounter = null;
            while (upstream.hasNext()) {
                UpstreamEntry<K, V> entity = upstream.next();
                LabeledVector<Double> row = basePreprocessor.apply(entity.getKey(), entity.getValue());
                targetCounter = updateTargetCountersForNextRow(row, targetCounter);
            }
            partData.withTargetCounters(targetCounter);
        } else {
            // This array will contain not null values for handled indices
            Map<String, Integer>[] categoryFrequencies = null;
            while (upstream.hasNext()) {
                UpstreamEntry<K, V> entity = upstream.next();
                LabeledVector<Double> row = basePreprocessor.apply(entity.getKey(), entity.getValue());
                categoryFrequencies = updateFeatureFrequenciesForNextRow(row, categoryFrequencies);
            }
            partData.withCategoryFrequencies(categoryFrequencies);
        }
        return partData;
    }, learningEnvironment(basePreprocessor))) {
        switch(encoderType) {
            case ONE_HOT_ENCODER:
                return new OneHotEncoderPreprocessor<>(calculateEncodingValuesByFrequencies(dataset), basePreprocessor, handledIndices);
            case STRING_ENCODER:
                return new StringEncoderPreprocessor<>(calculateEncodingValuesByFrequencies(dataset), basePreprocessor, handledIndices);
            case LABEL_ENCODER:
                return new LabelEncoderPreprocessor<>(calculateEncodingValuesForLabelsByFrequencies(dataset), basePreprocessor);
            case FREQUENCY_ENCODER:
                return new FrequencyEncoderPreprocessor<>(calculateEncodingFrequencies(dataset), basePreprocessor, handledIndices);
            case TARGET_ENCODER:
                return new TargetEncoderPreprocessor<>(calculateTargetEncodingFrequencies(dataset), basePreprocessor, handledIndices);
            default:
                throw new IllegalStateException("Define the type of the resulting prerocessor.");
        }
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

Example 2 with LabelEncoderPreprocessor

use of org.apache.ignite.ml.preprocessing.encoding.label.LabelEncoderPreprocessor in project ignite by apache.

the class LabelEncoderPreprocessorTest method testApply.

/**
 * Tests {@code apply()} method.
 */
@Test
public void testApply() {
    Map<Integer, Object[]> data = new HashMap<>();
    data.put(0, new Object[] { 1, "A" });
    data.put(1, new Object[] { 2, "B" });
    data.put(2, new Object[] { 3, "B" });
    final Vectorizer<Integer, Object[], Integer, Object> vectorizer = new ObjectArrayVectorizer<Integer>(0).labeled(1);
    LabelEncoderPreprocessor<Integer, Object[]> preprocessor = new LabelEncoderPreprocessor<Integer, Object[]>(new HashMap() {

        {
            put("A", 1);
            put("B", 0);
        }
    }, vectorizer);
    double[] postProcessedData = new double[] { 1.0, 0.0, 0.0 };
    for (int i = 0; i < data.size(); i++) assertEquals(postProcessedData[i], (Double) preprocessor.apply(i, data.get(i)).label(), 1e-8);
}