Java Code Examples for org.apache.commons.math3.random.RandomDataGenerator#nextUniform()

@Test
public void testSymmetry() {
    Utils.resetRandomGenerator();
    final RandomDataGenerator rdg = Utils.getRandomDataGenerator();

    for (int n = 0; n < 10; n++) {
        final double prior = rdg.nextUniform(0,1);
        final int forwardCount = rdg.nextInt(0, 100);
        final int reverseCount = rdg.nextInt(0, 100);
        final int forwardAltCount = rdg.nextInt(0, forwardCount);
        final int reverseAltCount = rdg.nextInt(0, reverseCount);

        final double prob = new StrandArtifactFilter()
                .strandArtifactProbability(prior, forwardCount, reverseCount, forwardAltCount, reverseAltCount, 0)
                .getArtifactProbability();
        final double flipped = new StrandArtifactFilter()
                .strandArtifactProbability(prior, reverseCount, forwardCount, reverseAltCount, forwardAltCount, 0)
                .getArtifactProbability();

        Assert.assertEquals(prob, flipped, 1.0e-8);
    }
}
 

/**
 * @param rdg random number generator to use
 * @return a hyperparameter value chosen uniformly at random from the range
 */
@Override
public Double getRandomValue(RandomDataGenerator rdg) {
  if (max == min) {
    return min;
  }
  return rdg.nextUniform(min, max, true);
}
 

private static Tuple4<DenseMatrix, DenseMatrix, Long, Long> onlineCorpusUpdate(
    List<Vector> data, DenseMatrix lambda, DenseMatrix alpha, DenseMatrix gammad,
    int vocabularySize, int numTopic, double subSamplingRate) {

    boolean isRandGamma = gammad == null;
    //wordTopicStat is the word topic probability information.
    DenseMatrix wordTopicStat = DenseMatrix.zeros(numTopic, vocabularySize);
    DenseMatrix logPhatPart = new DenseMatrix(numTopic, 1);
    DenseMatrix expELogBeta = LdaUtil.expDirichletExpectation(lambda).transpose();
    long nonEmptyWordCount = 0;
    long nonEmptyDocCount = 0;
    //the online corpus update stage can update the model in two way.
    //if the document order is determined, then it will update in the order.
    //or it will choose documents randomly.
    RandomDataGenerator random = new RandomDataGenerator();
    GammaDistribution distribution = new GammaDistribution(100, 100);
    int dataSize = data.size();
    boolean sampled = false;
    for (int j = 0; j < dataSize; ++j) {
        //if the subSamplingRate is too small and no doc is sampled in one iteration, then will randomly
        //choose one doc to update the model.
        double rate = random.nextUniform(0, 1);
        int index = -1;
        if (rate < subSamplingRate) {
            index = j;
            sampled = true;
        }
        if (j + 1 == dataSize && !sampled) {
            index = random.nextInt(0, dataSize - 1);
        }
        if (index != -1) {
            Vector vec = data.get(index);
            SparseVector sv = (SparseVector) vec;
            sv.setSize(vocabularySize);
            sv.removeZeroValues();
            for (int i = 0; i < sv.numberOfValues(); i++) {
                nonEmptyWordCount += sv.getValues()[i];
            }
            if (isRandGamma) {
                if (gammad == null) {
                    gammad = new DenseMatrix(numTopic, 1);
                }
                for (int i = 0; i < numTopic; i++) {
                    gammad.set(i, 0, distribution.inverseCumulativeProbability(random.nextUniform(0, 1)));
                }
            }
            Tuple2<DenseMatrix, DenseMatrix> topicDistributionTuple =
                LdaUtil.getTopicDistributionMethod(sv, expELogBeta, alpha, gammad, numTopic);

            for (int i = 0; i < sv.getIndices().length; i++) {
                for (int k = 0; k < numTopic; k++) {
                    wordTopicStat.add(k, sv.getIndices()[i], topicDistributionTuple.f1.get(k, i));
                }
            }
            gammad = topicDistributionTuple.f0;
            DenseMatrix deGammad = LdaUtil.dirichletExpectationVec(topicDistributionTuple.f0);
            for (int k = 0; k < numTopic; k++) {
                logPhatPart.add(k, 0, deGammad.get(k, 0));
            }
            nonEmptyDocCount++;
        }
    }
    return new Tuple4<>(wordTopicStat, logPhatPart, nonEmptyWordCount, nonEmptyDocCount);
}
 

private double getRandomInRange(double min, double max) {
    RandomDataGenerator generator = new RandomDataGenerator();
    return generator.nextUniform(min, max);
}