1 //===----------------------------------------------------------------------===//
2 //
3 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4 // See https://llvm.org/LICENSE.txt for license information.
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6 //
7 //===----------------------------------------------------------------------===//
8 
9 // <random>
10 
11 // class bernoulli_distribution
12 
13 // template<class _URNG> result_type operator()(_URNG& g, const param_type& parm);
14 
15 #include <random>
16 #include <cassert>
17 #include <cmath>
18 #include <cstddef>
19 #include <numeric>
20 #include <vector>
21 
22 #include "test_macros.h"
23 
24 template <class T>
25 inline
26 T
27 sqr(T x)
28 {
29     return x * x;
30 }
31 
32 int main(int, char**)
33 {
34     {
35         typedef std::bernoulli_distribution D;
36         typedef D::param_type P;
37         typedef std::minstd_rand G;
38         G g;
39         D d(.75);
40         P p(.25);
41         const int N = 100000;
42         std::vector<D::result_type> u;
43         for (int i = 0; i < N; ++i)
44             u.push_back(d(g, p));
45         double mean = std::accumulate(u.begin(), u.end(),
46                                               double(0)) / u.size();
47         double var = 0;
48         double skew = 0;
49         double kurtosis = 0;
50         for (std::size_t i = 0; i < u.size(); ++i)
51         {
52             double dbl = (u[i] - mean);
53             double d2 = sqr(dbl);
54             var += d2;
55             skew += dbl * d2;
56             kurtosis += d2 * d2;
57         }
58         var /= u.size();
59         double dev = std::sqrt(var);
60         skew /= u.size() * dev * var;
61         kurtosis /= u.size() * var * var;
62         kurtosis -= 3;
63         double x_mean = p.p();
64         double x_var = p.p()*(1-p.p());
65         double x_skew = (1 - 2 * p.p())/std::sqrt(x_var);
66         double x_kurtosis = (6 * sqr(p.p()) - 6 * p.p() + 1)/x_var;
67         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
68         assert(std::abs((var - x_var) / x_var) < 0.01);
69         assert(std::abs((skew - x_skew) / x_skew) < 0.02);
70         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.05);
71     }
72     {
73         typedef std::bernoulli_distribution D;
74         typedef D::param_type P;
75         typedef std::minstd_rand G;
76         G g;
77         D d(.25);
78         P p(.75);
79         const int N = 100000;
80         std::vector<D::result_type> u;
81         for (int i = 0; i < N; ++i)
82             u.push_back(d(g, p));
83         double mean = std::accumulate(u.begin(), u.end(),
84                                               double(0)) / u.size();
85         double var = 0;
86         double skew = 0;
87         double kurtosis = 0;
88         for (std::size_t i = 0; i < u.size(); ++i)
89         {
90             double dbl = (u[i] - mean);
91             double d2 = sqr(dbl);
92             var += d2;
93             skew += dbl * d2;
94             kurtosis += d2 * d2;
95         }
96         var /= u.size();
97         double dev = std::sqrt(var);
98         skew /= u.size() * dev * var;
99         kurtosis /= u.size() * var * var;
100         kurtosis -= 3;
101         double x_mean = p.p();
102         double x_var = p.p()*(1-p.p());
103         double x_skew = (1 - 2 * p.p())/std::sqrt(x_var);
104         double x_kurtosis = (6 * sqr(p.p()) - 6 * p.p() + 1)/x_var;
105         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
106         assert(std::abs((var - x_var) / x_var) < 0.01);
107         assert(std::abs((skew - x_skew) / x_skew) < 0.02);
108         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.05);
109     }
110 
111   return 0;
112 }
113