Search in sources :

Example 6 with EnumeratedDistribution

use of org.apache.commons.math3.distribution.EnumeratedDistribution in project druid by druid-io.

the class BenchmarkColumnValueGenerator method initDistribution.

private void initDistribution() {
    BenchmarkColumnSchema.ValueDistribution distributionType = schema.getDistributionType();
    ValueType type = schema.getType();
    List<Object> enumeratedValues = schema.getEnumeratedValues();
    List<Double> enumeratedProbabilities = schema.getEnumeratedProbabilities();
    List<Pair<Object, Double>> probabilities = new ArrayList<>();
    switch(distributionType) {
        case SEQUENTIAL:
            // not random, just cycle through numbers from start to end, or cycle through enumerated values if provided
            distribution = new SequentialDistribution(schema.getStartInt(), schema.getEndInt(), schema.getEnumeratedValues());
            break;
        case UNIFORM:
            distribution = new UniformRealDistribution(schema.getStartDouble(), schema.getEndDouble());
            break;
        case DISCRETE_UNIFORM:
            if (enumeratedValues == null) {
                enumeratedValues = new ArrayList<>();
                for (int i = schema.getStartInt(); i < schema.getEndInt(); i++) {
                    Object val = convertType(i, type);
                    enumeratedValues.add(val);
                }
            }
            // give them all equal probability, the library will normalize probabilities to sum to 1.0
            for (int i = 0; i < enumeratedValues.size(); i++) {
                probabilities.add(new Pair<>(enumeratedValues.get(i), 0.1));
            }
            distribution = new EnumeratedTreeDistribution<>(probabilities);
            break;
        case NORMAL:
            distribution = new NormalDistribution(schema.getMean(), schema.getStandardDeviation());
            break;
        case ROUNDED_NORMAL:
            NormalDistribution normalDist = new NormalDistribution(schema.getMean(), schema.getStandardDeviation());
            distribution = new RealRoundingDistribution(normalDist);
            break;
        case ZIPF:
            int cardinality;
            if (enumeratedValues == null) {
                Integer startInt = schema.getStartInt();
                cardinality = schema.getEndInt() - startInt;
                ZipfDistribution zipf = new ZipfDistribution(cardinality, schema.getZipfExponent());
                for (int i = 0; i < cardinality; i++) {
                    probabilities.add(new Pair<>((Object) (i + startInt), zipf.probability(i)));
                }
            } else {
                cardinality = enumeratedValues.size();
                ZipfDistribution zipf = new ZipfDistribution(enumeratedValues.size(), schema.getZipfExponent());
                for (int i = 0; i < cardinality; i++) {
                    probabilities.add(new Pair<>(enumeratedValues.get(i), zipf.probability(i)));
                }
            }
            distribution = new EnumeratedTreeDistribution<>(probabilities);
            break;
        case ENUMERATED:
            for (int i = 0; i < enumeratedValues.size(); i++) {
                probabilities.add(new Pair<>(enumeratedValues.get(i), enumeratedProbabilities.get(i)));
            }
            distribution = new EnumeratedTreeDistribution<>(probabilities);
            break;
        default:
            throw new UnsupportedOperationException("Unknown distribution type: " + distributionType);
    }
    if (distribution instanceof AbstractIntegerDistribution) {
        ((AbstractIntegerDistribution) distribution).reseedRandomGenerator(seed);
    } else if (distribution instanceof AbstractRealDistribution) {
        ((AbstractRealDistribution) distribution).reseedRandomGenerator(seed);
    } else if (distribution instanceof EnumeratedDistribution) {
        ((EnumeratedDistribution) distribution).reseedRandomGenerator(seed);
    }
}
Also used : ValueType(io.druid.segment.column.ValueType) ArrayList(java.util.ArrayList) UniformRealDistribution(org.apache.commons.math3.distribution.UniformRealDistribution) EnumeratedDistribution(org.apache.commons.math3.distribution.EnumeratedDistribution) AbstractIntegerDistribution(org.apache.commons.math3.distribution.AbstractIntegerDistribution) AbstractRealDistribution(org.apache.commons.math3.distribution.AbstractRealDistribution) NormalDistribution(org.apache.commons.math3.distribution.NormalDistribution) ZipfDistribution(org.apache.commons.math3.distribution.ZipfDistribution) Pair(org.apache.commons.math3.util.Pair)

Aggregations

AbstractIntegerDistribution (org.apache.commons.math3.distribution.AbstractIntegerDistribution)4 AbstractRealDistribution (org.apache.commons.math3.distribution.AbstractRealDistribution)4 EnumeratedDistribution (org.apache.commons.math3.distribution.EnumeratedDistribution)4 Pair (org.apache.commons.math3.util.Pair)4 ArrayList (java.util.ArrayList)3 ValueType (io.druid.segment.column.ValueType)2 NormalDistribution (org.apache.commons.math3.distribution.NormalDistribution)2 UniformRealDistribution (org.apache.commons.math3.distribution.UniformRealDistribution)2 ZipfDistribution (org.apache.commons.math3.distribution.ZipfDistribution)2 ValueType (org.apache.druid.segment.column.ValueType)2 Range (com.milaboratory.core.Range)1 ReferencePoint (io.repseq.core.ReferencePoint)1 GGene (io.repseq.gen.GGene)1 Map (java.util.Map)1 Operation (org.apache.cassandra.stress.Operation)1 PartitionGenerator (org.apache.cassandra.stress.generate.PartitionGenerator)1 Timer (org.apache.cassandra.stress.report.Timer)1 UniformIntegerDistribution (org.apache.commons.math3.distribution.UniformIntegerDistribution)1