aGrUM 3.3.2
a C++ library for (probabilistic) graphical models
GibbsSampling_tpl.h
Go to the documentation of this file.
1/****************************************************************************
2 * This file is part of the aGrUM/pyAgrum library. *
3 * *
4 * Copyright (c) 2005-2026 by *
5 * - Pierre-Henri WUILLEMIN(_at_LIP6) *
6 * - Christophe GONZALES(_at_AMU) *
7 * *
8 * The aGrUM/pyAgrum library is free software; you can redistribute it *
9 * and/or modify it under the terms of either : *
10 * *
11 * - the GNU Lesser General Public License as published by *
12 * the Free Software Foundation, either version 3 of the License, *
13 * or (at your option) any later version, *
14 * - the MIT license (MIT), *
15 * - or both in dual license, as here. *
16 * *
17 * (see https://agrum.gitlab.io/articles/dual-licenses-lgplv3mit.html) *
18 * *
19 * This aGrUM/pyAgrum library is distributed in the hope that it will be *
20 * useful, but WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, *
21 * INCLUDING BUT NOT LIMITED TO THE WARRANTIES MERCHANTABILITY or FITNESS *
22 * FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE *
23 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER *
24 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, *
25 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR *
26 * OTHER DEALINGS IN THE SOFTWARE. *
27 * *
28 * See LICENCES for more details. *
29 * *
30 * SPDX-FileCopyrightText: Copyright 2005-2026 *
31 * - Pierre-Henri WUILLEMIN(_at_LIP6) *
32 * - Christophe GONZALES(_at_AMU) *
33 * SPDX-License-Identifier: LGPL-3.0-or-later OR MIT *
34 * *
35 * Contact : info_at_agrum_dot_org *
36 * homepage : http://agrum.gitlab.io *
37 * gitlab : https://gitlab.com/agrumery/agrum *
38 * *
39 ****************************************************************************/
40
41#pragma once
42
43
50
53
54namespace gum {
55
57 template < GUM_Numeric GUM_SCALAR >
59 SamplingInference< GUM_SCALAR >(bn),
60 GibbsOperator< GUM_SCALAR >(*bn, &this->hardEvidence(), "gibbs") {
61 GUM_CONSTRUCTOR(GibbsSampling);
62
63 // the section gibbs only has epsilon, minEpsilonRate and burnIn (the other parameters are those
64 // of the section sampling, read by SamplingInference), so setFromConfiguration_ is not used
65 const auto& conf = Configuration::instance();
66 this->setEpsilon(conf.typed< double >("gibbs", "epsilon"));
67 this->setMinEpsilonRate(conf.typed< double >("gibbs", "minEpsilonRate"));
68 this->setBurnIn(this->sizeFromConfiguration_("gibbs", "burnIn"));
69 }
70
72 template < GUM_Numeric GUM_SCALAR >
76
77 template < GUM_Numeric GUM_SCALAR >
81
82 template < GUM_Numeric GUM_SCALAR >
84 // we initialize the nodes with hard evidence
85 // hypothesis : burnIn_ is called at the beginning of makeInference
87
88 // the chain always starts from a sample, followed by exactly burnIn() transitions
89 GUM_SCALAR w = 1.0f;
91 for (Size i = 0; i < this->burnIn(); i++)
92 Ip = this->draw_(&w, Ip);
93
94 return Ip;
95 }
96
98
99 template < GUM_Numeric GUM_SCALAR >
104
105 template < GUM_Numeric GUM_SCALAR >
109
110 template < GUM_Numeric GUM_SCALAR >
112 return this->burn_in_;
113 }
114
115} // namespace gum
This file contains Gibbs sampling class definition.
static Size sizeFromConfiguration_(const std::string &section, const std::string &key)
Read a non negative integer key of gum::Configuration.
void setMinEpsilonRate(double rate) override
Given that we approximate f(t), stopping criterion on d/dt(|f(t+1)-f(t)|).
Size burn_in_
Number of iterations before checking stopping criteria.
void setEpsilon(double eps) override
Given that we approximate f(t), stopping criterion on |f(t+1)-f(t)|.
static Configuration & instance()
The global configuration.
Instantiation nextSample(Instantiation prev)
draws next sample of Gibbs sampling
Instantiation monteCarloSample()
draws a first sample with a positive probability (starting point of a Gibbs chain)
GibbsOperator(const IBayesNet< GUM_SCALAR > &BN, const NodeProperty< Idx > *hardEv, Size nbr=1, bool atRandom=false)
constructor
~GibbsSampling() override
Destructor.
Instantiation draw_(GUM_SCALAR *w, Instantiation prev) override
draws a sample given previous one according to Gibbs sampling
Instantiation burnIn_() override
draws a defined number of samples without updating the estimators
Instantiation monteCarloSample_()
draws a Monte Carlo sample
void setBurnIn(Size b)
Number of burn in for one iteration.
Size burnIn() const
Returns the number of burn in.
GibbsSampling(const IBayesNet< GUM_SCALAR > *bn)
Default constructor.
const NodeProperty< Idx > & hardEvidence() const
indicate for each node with hard evidence which value it took
Class representing the minimal interface for Bayesian network with no numerical data.
Definition IBayesNet.h:79
Class for assigning/browsing values to tuples of discrete variables.
SamplingInference(const IBayesNet< GUM_SCALAR > *bn)
default constructor
Typed, documented, sectioned configuration singleton read from an .ini content.
std::size_t Size
In aGrUM, hashed values are unsigned long int.
Definition types.h:74
gum is the global namespace for all aGrUM entities
Definition agrum.h:46