import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
@Override
public RandomNumberDistribution<Double> getCauchy(
		final RandomNumberStream rng, final Number median,
		final Number scale)
{
	final RealDistribution dist = new CauchyDistribution(
			RandomNumberStream.Util.asCommonsRandomGenerator(rng),
			median.doubleValue(), scale.doubleValue());
	return new RandomNumberDistribution<Double>()
	{
		@Override
		public Double draw()
		{
			return dist.sample();
		}
	};
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
@Test
public void testNextCauchy() {
    double[] quartiles = TestUtils.getDistributionQuartiles(new CauchyDistribution(1.2, 2.1));
    long[] counts = new long[4];
    randomData.reSeed(1000);
    for (int i = 0; i < 1000; i++) {
        double value = randomData.nextCauchy(1.2, 2.1);
        TestUtils.updateCounts(value, counts, quartiles);
    }
    TestUtils.assertChiSquareAccept(expected, counts, 0.001);
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
/**
 * Visible for the segmenter
 */
public static double logEmissionProbability(final Double data, final double log2CopyRatio, final double cauchyWidth) {
    return new CauchyDistribution(null, log2CopyRatio, cauchyWidth).logDensity(data);
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
/**
 * @param log2CopyRatios array of log-2 copy ratios corresponding to the hidden states
 * @param weights array of (real-space, not log) prior probabilities of each hidden state
 *                when memory of the previous state is lost.  These may be unnormalized relative
 *                probabilities, which is useful when using variational Bayes.
 * @param memoryLength when consecutive SNPs are a distance d bases apart, the prior probability
 *                     for memory of the CNV state to be kept is exp(-d/memoryLength)
 */
public CopyRatioHMM(final List<Double> log2CopyRatios, final List<Double> weights,
                    final double memoryLength, final double logCoverageCauchyWidth) {
    super(log2CopyRatios, weights, memoryLength);
    this.logCoverageCauchyWidth = logCoverageCauchyWidth;
    emissionDistributions = hiddenStates().stream()
            .map(n -> new CauchyDistribution(null, log2CopyRatios.get(n), logCoverageCauchyWidth)).collect(Collectors.toList());
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
/**
 * Generates a random value from the {@link CauchyDistribution Cauchy Distribution}.
 *
 * @param median the median of the Cauchy distribution
 * @param scale the scale parameter of the Cauchy distribution
 * @return random value sampled from the Cauchy(median, scale) distribution
 */
public double nextCauchy(double median, double scale) {
    return new CauchyDistribution(getRandomGenerator(), median, scale,
            CauchyDistribution.DEFAULT_INVERSE_ABSOLUTE_ACCURACY).sample();
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
/**
 * Generates a random value from the {@link CauchyDistribution Cauchy Distribution}.
 * This implementation uses {@link #nextInversionDeviate(RealDistribution) inversion}
 * to generate random values.
 *
 * @param median the median of the Cauchy distribution
 * @param scale the scale parameter of the Cauchy distribution
 * @return random value sampled from the Cauchy(median, scale) distribution
 * @since 2.2
 */
public double nextCauchy(double median, double scale) {
    return nextInversionDeviate(new CauchyDistribution(median, scale));
}
 

import org.apache.commons.math3.distribution.CauchyDistribution; //导入依赖的package包/类
/**
 * Generates a random value from the {@link CauchyDistribution Cauchy Distribution}.
 *
 * @param median the median of the Cauchy distribution
 * @param scale the scale parameter of the Cauchy distribution
 * @return random value sampled from the Cauchy(median, scale) distribution
 */
public double nextCauchy(double median, double scale) {
    return new CauchyDistribution(getRan(), median, scale,
            CauchyDistribution.DEFAULT_INVERSE_ABSOLUTE_ACCURACY).sample();
}