Package dk.alexandra.fresco.stat

Interface Sampler

All Known Implementing Classes:
DefaultSampler
public interface Sampler
This computation library contains functions which samples random values from various distributions.

  • Method Summary

    Modifier and Type Method Description
    DRes<SInt> sampleBernoulliDistribution​(double p)
    Draw a sample from a Bernoulli distribution with parameter p with 0 ≤ p ≤ 1.
    DRes<SInt> sampleBernoulliDistribution​(DRes<SFixed> p)
    Draw a sample from a Bernoulli distribution with parameter p with 0 ≤ p ≤ 1.
    DRes<SInt> sampleCategoricalDistribution​(double[] probabilities)
    Draw a sample from the set {0, ..., probabilities.length - 1} with probabilities[i] indicating the probability of drawing i.
    DRes<SInt> sampleCategoricalDistribution​(List<DRes<SFixed>> probabilities)
    Draw a sample from the set {0, ..., probabilities.size() - 1} with probabilities.get(i) indicating the probability of drawing i.
    DRes<SInt> sampleCategoricalDistribution​(List<DRes<SFixed>> probabilities, boolean normalized)
    Draw a sample from the set {0, ..., probabilities.size() - 1} with probabilities.get(i) indicating the probability of drawing i.
    DRes<SFixed> sampleExponentialDistribution​(double b)
    Draw a sample from an exponential distribution with parameter λ = 1 / b with b gt; 0.
    DRes<SFixed> sampleExponentialDistribution​(DRes<SFixed> b)
    Draw a sample from an exponential distribution with parameter λ = 1 / b with b gt; 0.
    DRes<SFixed> sampleLaplaceDistribution​(double b)
    Draw a sample from a Laplace distribution with location 0 and scale b > 0.
    DRes<SFixed> sampleLaplaceDistribution​(DRes<SFixed> b)
    Draw a sample from a Laplace distribution with location 0 and scale b gt; 0.
    DRes<SFixed> sampleNormalDistribution()
    Draw a sample from a normal distribution with mean 0 and variance 1.
    DRes<SInt> sampleRademacherDistribution()
    Draw a sample from a Rademacher distribution.
    DRes<SFixed> sampleUniformDistribution()
    Draw a sample form a uniform distribution on [0, 1).
    static Sampler using​(ProtocolBuilderNumeric builder)  

  • Method Details

    • using

      static Sampler using​(ProtocolBuilderNumeric builder)

    • sampleBernoulliDistribution

      DRes<SInt> sampleBernoulliDistribution​(DRes<SFixed> p)
      Draw a sample from a Bernoulli distribution with parameter p with 0 ≤ p ≤ 1.

    • sampleBernoulliDistribution

      DRes<SInt> sampleBernoulliDistribution​(double p)
      Draw a sample from a Bernoulli distribution with parameter p with 0 ≤ p ≤ 1.

    • sampleCategoricalDistribution

      DRes<SInt> sampleCategoricalDistribution​(List<DRes<SFixed>> probabilities)
      Draw a sample from the set {0, ..., probabilities.size() - 1} with probabilities.get(i) indicating the probability of drawing i. Note that the sum of probabilities should be equal to 1.

    • sampleCategoricalDistribution

      DRes<SInt> sampleCategoricalDistribution​(double[] probabilities)
      Draw a sample from the set {0, ..., probabilities.length - 1} with probabilities[i] indicating the probability of drawing i. Note that the sum of probabilities should be equal to 1.

    • sampleCategoricalDistribution

      DRes<SInt> sampleCategoricalDistribution​(List<DRes<SFixed>> probabilities, boolean normalized)
      Draw a sample from the set {0, ..., probabilities.size() - 1} with probabilities.get(i) indicating the probability of drawing i. If it is not known whether the sum of the probabilities is equal to 1, the normalized parameter should be set to false.

    • sampleExponentialDistribution

      DRes<SFixed> sampleExponentialDistribution​(DRes<SFixed> b)
      Draw a sample from an exponential distribution with parameter λ = 1 / b with b gt; 0.

    • sampleExponentialDistribution

      DRes<SFixed> sampleExponentialDistribution​(double b)
      Draw a sample from an exponential distribution with parameter λ = 1 / b with b gt; 0.

    • sampleLaplaceDistribution

      DRes<SFixed> sampleLaplaceDistribution​(double b)
      Draw a sample from a Laplace distribution with location 0 and scale b > 0.

    • sampleLaplaceDistribution

      DRes<SFixed> sampleLaplaceDistribution​(DRes<SFixed> b)
      Draw a sample from a Laplace distribution with location 0 and scale b gt; 0.

    • sampleNormalDistribution

      DRes<SFixed> sampleNormalDistribution()
      Draw a sample from a normal distribution with mean 0 and variance 1.

    • sampleRademacherDistribution

      DRes<SInt> sampleRademacherDistribution()
      Draw a sample from a Rademacher distribution.

    • sampleUniformDistribution

      DRes<SFixed> sampleUniformDistribution()
      Draw a sample form a uniform distribution on [0, 1).