Examples with TargetEncoderPreprocessor org.apache.ignite.ml.preprocessing.encoding.target.TargetEncoderPreprocessor used on opensource projects

Example 1 with TargetEncoderPreprocessor

use of org.apache.ignite.ml.preprocessing.encoding.target.TargetEncoderPreprocessor 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 TargetEncoderPreprocessor

use of org.apache.ignite.ml.preprocessing.encoding.target.TargetEncoderPreprocessor in project ignite by apache.

the class TargetEncoderPreprocessorTest method testApply.

/**
 * Tests {@code apply()} method.
 */
@Test
public void testApply() {
    Vector[] data = new Vector[] { new DenseVector(new Serializable[] { "1", "Moscow", "A" }), new DenseVector(new Serializable[] { "2", "Moscow", "B" }), new DenseVector(new Serializable[] { "3", "Moscow", "B" }) };
    Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<>(0, 1, 2);
    TargetEncoderPreprocessor<Integer, Vector> preprocessor = new TargetEncoderPreprocessor<>(new TargetEncodingMeta[] { // feature 0
    new TargetEncodingMeta().withGlobalMean(0.5).withCategoryMean(new HashMap<String, Double>() {

        {
            // category "1" avg mean = 1.0
            put("1", 1.0);
            // category "2" avg mean = 0.0
            put("2", 0.0);
        }
    }), // feature 1
    new TargetEncodingMeta().withGlobalMean(0.1).withCategoryMean(new HashMap<String, Double>() {
    }), // feature 2
    new TargetEncodingMeta().withGlobalMean(0.1).withCategoryMean(new HashMap<String, Double>() {

        {
            // category "A" avg mean 1.0
            put("A", 1.0);
            // category "B" avg mean 2.0
            put("B", 2.0);
        }
    }) }, vectorizer, new HashSet<Integer>() {

        {
            add(0);
            add(1);
            add(2);
        }
    });
    double[][] postProcessedData = new double[][] { { // "1" contains in dict => use category mean 1.0
    1.0, // "Moscow" not contains in dict => use global 0.1
    0.1, // "A" contains in dict => use category mean 1.0
    1.0 }, { // "2" contains in dict => use category mean 0.0
    0.0, // "Moscow" not contains in dict => use global 0.1
    0.1, // "B" contains in dict => use category mean 2.0
    2.0 }, { // "3" not contains in dict => use global mean 0.5
    0.5, // "Moscow" not contains in dict => use global 0.1
    0.1, // "B" contains in dict => use category mean 2.0
    2.0 } };
    for (int i = 0; i < data.length; i++) assertArrayEquals(postProcessedData[i], preprocessor.apply(i, data[i]).features().asArray(), 1e-8);
}