• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1 //===----------------------------------------------------------------------===//
2 //
3 //                     The LLVM Compiler Infrastructure
4 //
5 // This file is dual licensed under the MIT and the University of Illinois Open
6 // Source Licenses. See LICENSE.TXT for details.
7 //
8 //===----------------------------------------------------------------------===//
9 
10 // <random>
11 
12 // template<class IntType = int>
13 // class binomial_distribution
14 
15 // template<class _URNG> result_type operator()(_URNG& g);
16 
17 #include <random>
18 #include <numeric>
19 #include <vector>
20 #include <cassert>
21 
22 template <class T>
23 inline
24 T
sqr(T x)25 sqr(T x)
26 {
27     return x * x;
28 }
29 
main()30 int main()
31 {
32     {
33         typedef std::binomial_distribution<> D;
34         typedef std::mt19937_64 G;
35         G g;
36         D d(5, .75);
37         const int N = 1000000;
38         std::vector<D::result_type> u;
39         for (int i = 0; i < N; ++i)
40         {
41             D::result_type v = d(g);
42             assert(d.min() <= v && v <= d.max());
43             u.push_back(v);
44         }
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 (int i = 0; i < u.size(); ++i)
51         {
52             double d = (u[i] - mean);
53             double d2 = sqr(d);
54             var += d2;
55             skew += d * 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 = d.t() * d.p();
64         double x_var = x_mean*(1-d.p());
65         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
66         double x_kurtosis = (1-6*d.p()*(1-d.p())) / 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) < 0.01);
70         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.04);
71     }
72     {
73         typedef std::binomial_distribution<> D;
74         typedef std::mt19937 G;
75         G g;
76         D d(30, .03125);
77         const int N = 100000;
78         std::vector<D::result_type> u;
79         for (int i = 0; i < N; ++i)
80         {
81             D::result_type v = d(g);
82             assert(d.min() <= v && v <= d.max());
83             u.push_back(v);
84         }
85         double mean = std::accumulate(u.begin(), u.end(),
86                                               double(0)) / u.size();
87         double var = 0;
88         double skew = 0;
89         double kurtosis = 0;
90         for (int i = 0; i < u.size(); ++i)
91         {
92             double d = (u[i] - mean);
93             double d2 = sqr(d);
94             var += d2;
95             skew += d * d2;
96             kurtosis += d2 * d2;
97         }
98         var /= u.size();
99         double dev = std::sqrt(var);
100         skew /= u.size() * dev * var;
101         kurtosis /= u.size() * var * var;
102         kurtosis -= 3;
103         double x_mean = d.t() * d.p();
104         double x_var = x_mean*(1-d.p());
105         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
106         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
107         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
108         assert(std::abs((var - x_var) / x_var) < 0.01);
109         assert(std::abs((skew - x_skew) / x_skew) < 0.01);
110         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.01);
111     }
112     {
113         typedef std::binomial_distribution<> D;
114         typedef std::mt19937 G;
115         G g;
116         D d(40, .25);
117         const int N = 100000;
118         std::vector<D::result_type> u;
119         for (int i = 0; i < N; ++i)
120         {
121             D::result_type v = d(g);
122             assert(d.min() <= v && v <= d.max());
123             u.push_back(v);
124         }
125         double mean = std::accumulate(u.begin(), u.end(),
126                                               double(0)) / u.size();
127         double var = 0;
128         double skew = 0;
129         double kurtosis = 0;
130         for (int i = 0; i < u.size(); ++i)
131         {
132             double d = (u[i] - mean);
133             double d2 = sqr(d);
134             var += d2;
135             skew += d * d2;
136             kurtosis += d2 * d2;
137         }
138         var /= u.size();
139         double dev = std::sqrt(var);
140         skew /= u.size() * dev * var;
141         kurtosis /= u.size() * var * var;
142         kurtosis -= 3;
143         double x_mean = d.t() * d.p();
144         double x_var = x_mean*(1-d.p());
145         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
146         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
147         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
148         assert(std::abs((var - x_var) / x_var) < 0.01);
149         assert(std::abs((skew - x_skew) / x_skew) < 0.03);
150         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.3);
151     }
152     {
153         typedef std::binomial_distribution<> D;
154         typedef std::mt19937 G;
155         G g;
156         D d(40, 0);
157         const int N = 100000;
158         std::vector<D::result_type> u;
159         for (int i = 0; i < N; ++i)
160         {
161             D::result_type v = d(g);
162             assert(d.min() <= v && v <= d.max());
163             u.push_back(v);
164         }
165         double mean = std::accumulate(u.begin(), u.end(),
166                                               double(0)) / u.size();
167         double var = 0;
168         double skew = 0;
169         double kurtosis = 0;
170         for (int i = 0; i < u.size(); ++i)
171         {
172             double d = (u[i] - mean);
173             double d2 = sqr(d);
174             var += d2;
175             skew += d * d2;
176             kurtosis += d2 * d2;
177         }
178         var /= u.size();
179         double dev = std::sqrt(var);
180         skew /= u.size() * dev * var;
181         kurtosis /= u.size() * var * var;
182         kurtosis -= 3;
183         double x_mean = d.t() * d.p();
184         double x_var = x_mean*(1-d.p());
185         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
186         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
187         assert(mean == x_mean);
188         assert(var == x_var);
189     }
190     {
191         typedef std::binomial_distribution<> D;
192         typedef std::mt19937 G;
193         G g;
194         D d(40, 1);
195         const int N = 100000;
196         std::vector<D::result_type> u;
197         for (int i = 0; i < N; ++i)
198         {
199             D::result_type v = d(g);
200             assert(d.min() <= v && v <= d.max());
201             u.push_back(v);
202         }
203         double mean = std::accumulate(u.begin(), u.end(),
204                                               double(0)) / u.size();
205         double var = 0;
206         double skew = 0;
207         double kurtosis = 0;
208         for (int i = 0; i < u.size(); ++i)
209         {
210             double d = (u[i] - mean);
211             double d2 = sqr(d);
212             var += d2;
213             skew += d * d2;
214             kurtosis += d2 * d2;
215         }
216         var /= u.size();
217         double dev = std::sqrt(var);
218         skew /= u.size() * dev * var;
219         kurtosis /= u.size() * var * var;
220         kurtosis -= 3;
221         double x_mean = d.t() * d.p();
222         double x_var = x_mean*(1-d.p());
223         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
224         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
225         assert(mean == x_mean);
226         assert(var == x_var);
227     }
228     {
229         typedef std::binomial_distribution<> D;
230         typedef std::mt19937 G;
231         G g;
232         D d(400, 0.5);
233         const int N = 100000;
234         std::vector<D::result_type> u;
235         for (int i = 0; i < N; ++i)
236         {
237             D::result_type v = d(g);
238             assert(d.min() <= v && v <= d.max());
239             u.push_back(v);
240         }
241         double mean = std::accumulate(u.begin(), u.end(),
242                                               double(0)) / u.size();
243         double var = 0;
244         double skew = 0;
245         double kurtosis = 0;
246         for (int i = 0; i < u.size(); ++i)
247         {
248             double d = (u[i] - mean);
249             double d2 = sqr(d);
250             var += d2;
251             skew += d * d2;
252             kurtosis += d2 * d2;
253         }
254         var /= u.size();
255         double dev = std::sqrt(var);
256         skew /= u.size() * dev * var;
257         kurtosis /= u.size() * var * var;
258         kurtosis -= 3;
259         double x_mean = d.t() * d.p();
260         double x_var = x_mean*(1-d.p());
261         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
262         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
263         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
264         assert(std::abs((var - x_var) / x_var) < 0.01);
265         assert(std::abs(skew - x_skew) < 0.01);
266         assert(std::abs(kurtosis - x_kurtosis) < 0.01);
267     }
268     {
269         typedef std::binomial_distribution<> D;
270         typedef std::mt19937 G;
271         G g;
272         D d(1, 0.5);
273         const int N = 100000;
274         std::vector<D::result_type> u;
275         for (int i = 0; i < N; ++i)
276         {
277             D::result_type v = d(g);
278             assert(d.min() <= v && v <= d.max());
279             u.push_back(v);
280         }
281         double mean = std::accumulate(u.begin(), u.end(),
282                                               double(0)) / u.size();
283         double var = 0;
284         double skew = 0;
285         double kurtosis = 0;
286         for (int i = 0; i < u.size(); ++i)
287         {
288             double d = (u[i] - mean);
289             double d2 = sqr(d);
290             var += d2;
291             skew += d * d2;
292             kurtosis += d2 * d2;
293         }
294         var /= u.size();
295         double dev = std::sqrt(var);
296         skew /= u.size() * dev * var;
297         kurtosis /= u.size() * var * var;
298         kurtosis -= 3;
299         double x_mean = d.t() * d.p();
300         double x_var = x_mean*(1-d.p());
301         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
302         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
303         assert(std::abs((mean - x_mean) / x_mean) < 0.01);
304         assert(std::abs((var - x_var) / x_var) < 0.01);
305         assert(std::abs(skew - x_skew) < 0.01);
306         assert(std::abs((kurtosis - x_kurtosis) / x_kurtosis) < 0.01);
307     }
308     {
309         typedef std::binomial_distribution<> D;
310         typedef std::mt19937 G;
311         G g;
312         D d(0, 0.005);
313         const int N = 100000;
314         std::vector<D::result_type> u;
315         for (int i = 0; i < N; ++i)
316         {
317             D::result_type v = d(g);
318             assert(d.min() <= v && v <= d.max());
319             u.push_back(v);
320         }
321         double mean = std::accumulate(u.begin(), u.end(),
322                                               double(0)) / u.size();
323         double var = 0;
324         double skew = 0;
325         double kurtosis = 0;
326         for (int i = 0; i < u.size(); ++i)
327         {
328             double d = (u[i] - mean);
329             double d2 = sqr(d);
330             var += d2;
331             skew += d * d2;
332             kurtosis += d2 * d2;
333         }
334         var /= u.size();
335         double dev = std::sqrt(var);
336         skew /= u.size() * dev * var;
337         kurtosis /= u.size() * var * var;
338         kurtosis -= 3;
339         double x_mean = d.t() * d.p();
340         double x_var = x_mean*(1-d.p());
341         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
342         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
343         assert(mean == x_mean);
344         assert(var == x_var);
345     }
346     {
347         typedef std::binomial_distribution<> D;
348         typedef std::mt19937 G;
349         G g;
350         D d(0, 0);
351         const int N = 100000;
352         std::vector<D::result_type> u;
353         for (int i = 0; i < N; ++i)
354         {
355             D::result_type v = d(g);
356             assert(d.min() <= v && v <= d.max());
357             u.push_back(v);
358         }
359         double mean = std::accumulate(u.begin(), u.end(),
360                                               double(0)) / u.size();
361         double var = 0;
362         double skew = 0;
363         double kurtosis = 0;
364         for (int i = 0; i < u.size(); ++i)
365         {
366             double d = (u[i] - mean);
367             double d2 = sqr(d);
368             var += d2;
369             skew += d * d2;
370             kurtosis += d2 * d2;
371         }
372         var /= u.size();
373         double dev = std::sqrt(var);
374         skew /= u.size() * dev * var;
375         kurtosis /= u.size() * var * var;
376         kurtosis -= 3;
377         double x_mean = d.t() * d.p();
378         double x_var = x_mean*(1-d.p());
379         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
380         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
381         assert(mean == x_mean);
382         assert(var == x_var);
383     }
384     {
385         typedef std::binomial_distribution<> D;
386         typedef std::mt19937 G;
387         G g;
388         D d(0, 1);
389         const int N = 100000;
390         std::vector<D::result_type> u;
391         for (int i = 0; i < N; ++i)
392         {
393             D::result_type v = d(g);
394             assert(d.min() <= v && v <= d.max());
395             u.push_back(v);
396         }
397         double mean = std::accumulate(u.begin(), u.end(),
398                                               double(0)) / u.size();
399         double var = 0;
400         double skew = 0;
401         double kurtosis = 0;
402         for (int i = 0; i < u.size(); ++i)
403         {
404             double d = (u[i] - mean);
405             double d2 = sqr(d);
406             var += d2;
407             skew += d * d2;
408             kurtosis += d2 * d2;
409         }
410         var /= u.size();
411         double dev = std::sqrt(var);
412         skew /= u.size() * dev * var;
413         kurtosis /= u.size() * var * var;
414         kurtosis -= 3;
415         double x_mean = d.t() * d.p();
416         double x_var = x_mean*(1-d.p());
417         double x_skew = (1-2*d.p()) / std::sqrt(x_var);
418         double x_kurtosis = (1-6*d.p()*(1-d.p())) / x_var;
419         assert(mean == x_mean);
420         assert(var == x_var);
421     }
422 }
423