Examples with EnumeratedDistribution org.apache.commons.math3.distribution.EnumeratedDistribution used on opensource projects

Example 1 with EnumeratedDistribution

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

the class BenchmarkColumnValueGenerator method generateSingleRowValue.

private Object generateSingleRowValue() {
    Object ret = null;
    ValueType type = schema.getType();
    if (distribution instanceof AbstractIntegerDistribution) {
        ret = ((AbstractIntegerDistribution) distribution).sample();
    } else if (distribution instanceof AbstractRealDistribution) {
        ret = ((AbstractRealDistribution) distribution).sample();
    } else if (distribution instanceof EnumeratedDistribution) {
        ret = ((EnumeratedDistribution) distribution).sample();
    }
    ret = convertType(ret, type);
    return ret;
}

Example 2 with EnumeratedDistribution

use of org.apache.commons.math3.distribution.EnumeratedDistribution in project cassandra by apache.

the class SampledOpDistributionFactory method get.

public OpDistribution get(boolean isWarmup, MeasurementSink sink) {
    PartitionGenerator generator = newGenerator();
    List<Pair<Operation, Double>> operations = new ArrayList<>();
    for (Map.Entry<T, Double> ratio : ratios.entrySet()) {
        List<? extends Operation> ops = get(new Timer(ratio.getKey().toString(), sink), generator, ratio.getKey(), isWarmup);
        for (Operation op : ops) operations.add(new Pair<>(op, ratio.getValue() / ops.size()));
    }
    return new SampledOpDistribution(new EnumeratedDistribution<>(operations), clustering.get());
}

Example 3 with EnumeratedDistribution

use of org.apache.commons.math3.distribution.EnumeratedDistribution in project repseqio by repseqio.

the class MarkovInsertModel method create.

@Override
public InsertGenerator create(RandomGenerator random, final boolean v, List<VDJCGene> vGenes, List<VDJCGene> dGenes, List<VDJCGene> jGenes, List<VDJCGene> cGenes) {
    Map<Byte, List<Pair<Byte, Double>>> distParams = new HashMap<>();
    for (Map.Entry<String, Double> s : distribution.entrySet()) {
        String[] split = s.getKey().split(">");
        if (split.length != 2 || split[0].length() != 1 || split[1].length() != 1)
            throw new IllegalArgumentException("Illegal distribution key: " + s.getKey() + ". " + "Expected something like \"A>C\"");
        byte codeFrom = NucleotideSequence.ALPHABET.symbolToCode(split[0].charAt(0));
        byte codeTo = NucleotideSequence.ALPHABET.symbolToCode(split[1].charAt(0));
        if (codeFrom == -1 || codeTo == -1)
            throw new IllegalArgumentException("Illegal nucleotide in: " + s.getKey() + ".");
        List<Pair<Byte, Double>> pairs = distParams.get(codeFrom);
        if (pairs == null)
            distParams.put(codeFrom, pairs = new ArrayList<>());
        pairs.add(new Pair<>(codeTo, s.getValue()));
    }
    final Map<Byte, EnumeratedDistribution<Byte>> dists = new HashMap<>();
    for (byte from = 0; from < NucleotideSequence.ALPHABET.basicSize(); from++) {
        List<Pair<Byte, Double>> d = distParams.get(from);
        if (d == null)
            throw new IllegalArgumentException("No distribution for letter: " + NucleotideSequence.ALPHABET.codeToSymbol(from));
        dists.put(from, new EnumeratedDistribution<>(random, d));
    }
    final IndependentIntGenerator lengthDist = lengthDistribution.create(random);
    return new InsertGenerator() {

        @Override
        public NucleotideSequence generate(GGene gene) {
            ReferencePoint point = beginPoint(fromLeft, v);
            int pointPosition = gene.getPartitioning().getPosition(point);
            if (pointPosition == -1)
                throw new RuntimeException("Point " + point + " is not available for gene " + gene);
            byte letter = gene.getSequence(new Range(pointPosition, pointPosition + 1)).codeAt(0);
            int length = lengthDist.sample();
            byte[] array = new byte[length];
            for (int i = 0; i < length; i++) {
                byte cLetter = dists.get(letter).sample();
                array[i] = cLetter;
                letter = cLetter;
            }
            if (!fromLeft)
                ArraysUtils.reverse(array);
            return NucleotideSequence.ALPHABET.createBuilder().ensureCapacity(length).append(array).createAndDestroy();
        }
    };
}

Example 4 with EnumeratedDistribution

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

the class ColumnValueGenerator method initDistribution.

private void initDistribution() {
    GeneratorColumnSchema.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 (Object enumeratedValue : enumeratedValues) {
                probabilities.add(new Pair<>(enumeratedValue, 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 LAZY_ZIPF:
            int lazyCardinality;
            Integer startInt = schema.getStartInt();
            lazyCardinality = schema.getEndInt() - startInt;
            distribution = new ZipfDistribution(lazyCardinality, schema.getZipfExponent());
            break;
        case LAZY_DISCRETE_UNIFORM:
            distribution = new UniformIntegerDistribution(schema.getStartInt(), schema.getEndInt());
            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 {
        ((EnumeratedDistribution) distribution).reseedRandomGenerator(seed);
    }
}

Example 5 with EnumeratedDistribution

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

the class ColumnValueGenerator method generateSingleRowValue.

private Object generateSingleRowValue() {
    Object ret = null;
    ValueType type = schema.getType();
    if (distribution instanceof AbstractIntegerDistribution) {
        ret = ((AbstractIntegerDistribution) distribution).sample();
    } else if (distribution instanceof AbstractRealDistribution) {
        ret = ((AbstractRealDistribution) distribution).sample();
    } else if (distribution instanceof EnumeratedDistribution) {
        ret = ((EnumeratedDistribution) distribution).sample();
    }
    ret = convertType(ret, type);
    return ret;
}