org.apache.mahout.math.jet.random.Gamma.<init>()方法的使用及代码示例

x33g5p2x  于2022-01-20 转载在 其他  
字(7.5k)|赞(0)|评价(0)|浏览(176)

本文整理了Java中org.apache.mahout.math.jet.random.Gamma.<init>()方法的一些代码示例，展示了Gamma.<init>()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。Gamma.<init>()方法的具体详情如下：
包路径：org.apache.mahout.math.jet.random.Gamma
类名称：Gamma
方法名：<init>

Gamma.<init>介绍

[英]Constructs a Gamma distribution with a given shape (alpha) and rate (beta).
[中]构造具有给定形状（alpha）和速率（beta）的Gamma分布。

代码示例

代码示例来源：origin: tdunning/t-digest

  1. @Override
  2.   AbstractDistribution create(Random random) {
  3.     return new Gamma(0.1, 0.1, random);
  4.   }
  5. },

代码示例来源：origin: apache/mahout

  1. /**
  2.  * Constructs a Negative Binomial distribution which describes the probability of getting
  3.  * a particular number of negative trials (k) before getting a fixed number of positive
  4.  * trials (r) where each positive trial has probability (p) of being successful.
  5.  *
  6.  * @param r               the required number of positive trials.
  7.  * @param p               the probability of success.
  8.  * @param randomGenerator a uniform random number generator.
  9.  */
  10. public NegativeBinomial(int r, double p, Random randomGenerator) {
  11.  setRandomGenerator(randomGenerator);
  12.  this.r = r;
  13.  this.p = p;
  14.  this.gamma = new Gamma(r, 1, randomGenerator);
  15.  this.poisson = new Poisson(0.0, randomGenerator);
  16. }

代码示例来源：origin: apache/mahout

  1. private static double[] gamma(int n, double shape) {
  2.   double[] r = new double[n];
  3.   Random gen = RandomUtils.getRandom();
  4.   AbstractContinousDistribution gamma = new Gamma(shape, shape, gen);
  5.   for (int i = 0; i < n; i++) {
  6.    r[i] = gamma.nextDouble();
  7.   }
  8.   return r;
  9.  }
  10. }

代码示例来源：origin: apache/mahout

  1. private static void checkGammaCdf(double alpha, double beta, double... values) {
  2.  Gamma g = new Gamma(alpha, beta, RandomUtils.getRandom());
  3.  int i = 0;
  4.  for (double x : seq(0, 2 * alpha, 2 * alpha / 10)) {
  5.   assertEquals(String.format(Locale.ENGLISH, "alpha=%.2f, i=%d, x=%.2f", alpha, i, x),
  6.                    values[i], g.cdf(x), 1.0e-7);
  7.   i++;
  8.  }
  9. }

代码示例来源：origin: apache/mahout

  1. @Test
  2.  public void testPdf() {
  3.   Random gen = RandomUtils.getRandom();
  4.   for (double alpha : new double[]{0.01, 0.1, 1, 2, 10, 100}) {
  5.    for (double beta : new double[]{0.1, 1, 2, 100}) {
  6.     Gamma g1 = new Gamma(alpha, beta, gen);
  7.     for (double x : seq(0, 0.99, 0.1)) {
  8.      double p = Math.pow(beta, alpha) * Math.pow(x, alpha - 1) *
  9.       Math.exp(-beta * x - org.apache.mahout.math.jet.stat.Gamma.logGamma(alpha));
  10.      assertEquals(String.format(Locale.ENGLISH, "alpha=%.2f, beta=%.2f, x=%.2f\n", alpha, beta, x),
  11.       p, g1.pdf(x), 1.0e-9);
  12.     }
  13.    }
  14.   }
  15.  }
  16. }

代码示例来源：origin: addthis/stream-lib

  1. @Test
  2.   public void testGamma() {
  3.     // this Gamma distribution is very heavily skewed.  The 0.1%-ile is 6.07e-30 while
  4.     // the median is 0.006 and the 99.9th %-ile is 33.6 while the mean is 1.
  5.     // this severe skew means that we have to have positional accuracy that
  6.     // varies by over 11 orders of magnitude.
  7.     Random gen = RandomUtils.getRandom();
  8.     for (int i = 0; i < repeats(); i++) {
  9.       runTest(new Gamma(0.1, 0.1, gen), 100,
  10. //                    new double[]{6.0730483624079e-30, 6.0730483624079e-20, 6.0730483627432e-10, 5.9339110446023e-03,
  11. //                            2.6615455373884e+00, 1.5884778179295e+01, 3.3636770117188e+01},
  12.           new double[]{0.001, 0.01, 0.1, 0.5, 0.9, 0.99, 0.999},
  13.           "gamma", true, gen);
  14.     }
  15.   }

代码示例来源：origin: apache/mahout

  1. @Test
  2. public void testNextDouble() {
  3.  double[] z = new double[100000];
  4.  Random gen = RandomUtils.getRandom();
  5.  for (double alpha : new double[]{1, 2, 10, 0.1, 0.01, 100}) {
  6.   Gamma g = new Gamma(alpha, 1, gen);
  7.   for (int i = 0; i < z.length; i++) {
  8.    z[i] = g.nextDouble();
  9.   }
  10.   Arrays.sort(z);
  11.   // verify that empirical CDF matches theoretical one pretty closely
  12.   for (double q : seq(0.01, 1, 0.01)) {
  13.    double p = z[(int) (q * z.length)];
  14.    assertEquals(q, g.cdf(p), 0.01);
  15.   }
  16.  }
  17. }

代码示例来源：origin: apache/mahout

  1. Gamma g1 = new Gamma(1, beta, gen);
  2. Gamma g2 = new Gamma(1, 1, gen);
  3. for (double x : seq(0, 0.99, 0.1)) {
  4.  assertEquals(String.format(Locale.ENGLISH, "Rate invariance: x = %.4f, alpha = 1, beta = %.1f", x, beta),
  5. Gamma g = new Gamma(alpha, 1, gen);
  6. for (double beta : new double[]{0.1, 1, 2, 100}) {
  7.  Gamma g1 = new Gamma(alpha, beta, gen);
  8.  for (double x : seq(0, 0.9999, 0.001)) {
  9.   assertEquals(

代码示例来源：origin: apache/mahout

  1. @Test(timeout=50000)
  2. public void testTimesSparseEfficiency() {
  3.  Random raw = RandomUtils.getRandom();
  4.  Gamma gen = new Gamma(0.1, 0.1, raw);

代码示例来源：origin: addthis/stream-lib

  1. @Test
  2. public void compareToQDigest() {
  3.   Random rand = RandomUtils.getRandom();
  4.   for (int i = 0; i < repeats(); i++) {
  5.     compare(new Gamma(0.1, 0.1, rand), "gamma", 1L << 48, rand);
  6.     compare(new Uniform(0, 1, rand), "uniform", 1L << 48, rand);
  7.   }
  8. }

代码示例来源：origin: apache/mahout

  1. @Test(timeout=50000)
  2. public void testTimesDenseEfficiency() {
  3.  Random raw = RandomUtils.getRandom();
  4.  Gamma gen = new Gamma(0.1, 0.1, raw);

代码示例来源：origin: apache/mahout

  1. @Test(timeout=50000)
  2. public void testTimesOtherSparseEfficiency() {
  3.  Random raw = RandomUtils.getRandom();
  4.  Gamma gen = new Gamma(0.1, 0.1, raw);
  5.  // build a sequential sparse matrix and a diagonal matrix and multiply them
  6.  Matrix x = new SparseRowMatrix(1000, 2000, false);
  7.  for (int i = 0; i < 1000; i++) {
  8.   int[] values = new int[1000];
  9.   for (int k = 0; k < 1000; k++) {
  10.    int j = (int) Math.min(1000, gen.nextDouble());
  11.    values[j]++;
  12.   }
  13.   for (int j = 0; j < 1000; j++) {
  14.    if (values[j] > 0) {
  15.     x.set(i, j, values[j]);
  16.    }
  17.   }
  18.  }
  19.  Vector d = new DenseVector(2000).assign(Functions.random());
  20.  Matrix y = new DiagonalMatrix(d);
  21.  long t0 = System.nanoTime();
  22.  Matrix z = x.times(y);
  23.  double elapsedTime = (System.nanoTime() - t0) * 1e-6;
  24.  System.out.printf("done in %.1f ms\n", elapsedTime);
  25.  for (MatrixSlice row : z) {
  26.   for (Vector.Element element : row.nonZeroes()) {
  27.    assertEquals(x.get(row.index(), element.index()) * d.get(element.index()), element.get(), 1e-12);
  28.   }
  29.  }
  30. }

代码示例来源：origin: tdunning/bandit-ranking

  1. public BetaDistribution(double alpha, double beta, Random random) {
  2.   this.alpha = alpha;
  3.   this.beta = beta;
  4.   gAlpha = new Gamma(alpha, 1, random);
  5.   gBeta = new Gamma(beta, 1, random);
  6. }

代码示例来源：origin: tdunning/log-synth

  1. @SuppressWarnings("UnusedDeclaration")
  2. public void setSkew(double skew) {
  3.   if (skew < 0) {
  4.     x = new Gamma(skew, 1, gen);
  5.     y = new Gamma(1, 1, gen);
  6.   } else {
  7.     x = new Gamma(1, 1, gen);
  8.     y = new Gamma(skew, 1, gen);
  9.   }
  10. }

代码示例来源：origin: stackoverflow.com

  1. Alpha test1 = new Gamma();
  2. Beta test2 = new Gamma();
  3. Alpha test3 = new Beta();

代码示例来源：origin: tdunning/log-synth

  1. public Changer(@JsonProperty("values") List<FieldSampler> fields) {
  2.   this.fields = fields;
  3.   fieldNames = Lists.newArrayList();
  4.   for (FieldSampler field : fields) {
  5.     fieldNames.add(field.getName());
  6.   }
  7.   x = new Gamma(1, 1, gen);
  8.   y = new Gamma(3, 1, gen);
  9. }

代码示例来源：origin: org.apache.mahout/mahout-math

  1. /**
  2.  * Constructs a Negative Binomial distribution which describes the probability of getting
  3.  * a particular number of negative trials (k) before getting a fixed number of positive
  4.  * trials (r) where each positive trial has probability (p) of being successful.
  5.  *
  6.  * @param r               the required number of positive trials.
  7.  * @param p               the probability of success.
  8.  * @param randomGenerator a uniform random number generator.
  9.  */
  10. public NegativeBinomial(int r, double p, Random randomGenerator) {
  11.  setRandomGenerator(randomGenerator);
  12.  this.r = r;
  13.  this.p = p;
  14.  this.gamma = new Gamma(r, 1, randomGenerator);
  15.  this.poisson = new Poisson(0.0, randomGenerator);
  16. }

代码示例来源：origin: cloudera/mahout

  1. private static void checkGammaCdf(double alpha, double beta, double... values) {
  2.  Gamma g = new Gamma(alpha, beta, RandomUtils.getRandom());
  3.  int i = 0;
  4.  for (double x : seq(0, 2 * alpha, 2 * alpha / 10)) {
  5.   assertEquals(String.format(Locale.ENGLISH, "alpha=%.2f, i=%d, x=%.2f", alpha, i, x),
  6.                    values[i], g.cdf(x), 1.0e-7);
  7.   i++;
  8.  }
  9. }

代码示例来源：origin: cloudera/mahout

  1. @Test
  2.  public void testPdf() {
  3.   Random gen = RandomUtils.getRandom();
  4.   for (double alpha : new double[]{0.01, 0.1, 1, 2, 10, 100}) {
  5.    for (double beta : new double[]{0.1, 1, 2, 100}) {
  6.     Gamma g1 = new Gamma(alpha, beta, gen);
  7.     for (double x : seq(0, 0.99, 0.1)) {
  8.      double p = Math.pow(beta, alpha) * Math.pow(x, alpha - 1) *
  9.       Math.exp(-beta * x - org.apache.mahout.math.jet.stat.Gamma.logGamma(alpha));
  10.      assertEquals(String.format(Locale.ENGLISH, "alpha=%.2f, beta=%.2f, x=%.2f\n", alpha, beta, x),
  11.       p, g1.pdf(x), 1.0e-9);
  12.     }
  13.    }
  14.   }
  15.  }
  16. }

代码示例来源：origin: cloudera/mahout

  1. @Test
  2. public void testNextDouble() {
  3.  double[] z = new double[100000];
  4.  Random gen = RandomUtils.getRandom();
  5.  for (double alpha : new double[]{1, 2, 10, 0.1, 0.01, 100}) {
  6.   Gamma g = new Gamma(alpha, 1, gen);
  7.   for (int i = 0; i < z.length; i++) {
  8.    z[i] = g.nextDouble();
  9.   }
  10.   Arrays.sort(z);
  11.   // verify that empirical CDF matches theoretical one pretty closely
  12.   for (double q : seq(0.01, 1, 0.01)) {
  13.    double p = z[(int) (q * z.length)];
  14.    assertEquals(q, g.cdf(p), 0.01);
  15.   }
  16.  }
  17. }

内容来源于网络，如有侵权，请联系作者删除！

Gamma

相关文章

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新文章

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com