1 | #ifndef _theplu_yat_classifier_nbc_ |
---|
2 | #define _theplu_yat_classifier_nbc_ |
---|
3 | |
---|
4 | // $Id: NBC.h 1160 2008-02-26 15:29:50Z markus $ |
---|
5 | |
---|
6 | /* |
---|
7 | Copyright (C) 2006 Jari Häkkinen, Markus Ringnér, Peter Johansson |
---|
8 | Copyright (C) 2007 Peter Johansson |
---|
9 | |
---|
10 | This file is part of the yat library, http://trac.thep.lu.se/yat |
---|
11 | |
---|
12 | The yat library is free software; you can redistribute it and/or |
---|
13 | modify it under the terms of the GNU General Public License as |
---|
14 | published by the Free Software Foundation; either version 2 of the |
---|
15 | License, or (at your option) any later version. |
---|
16 | |
---|
17 | The yat library is distributed in the hope that it will be useful, |
---|
18 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
19 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
---|
20 | General Public License for more details. |
---|
21 | |
---|
22 | You should have received a copy of the GNU General Public License |
---|
23 | along with this program; if not, write to the Free Software |
---|
24 | Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA |
---|
25 | 02111-1307, USA. |
---|
26 | */ |
---|
27 | |
---|
28 | #include "SupervisedClassifier.h" |
---|
29 | #include "yat/utility/Matrix.h" |
---|
30 | |
---|
31 | namespace theplu { |
---|
32 | namespace yat { |
---|
33 | namespace classifier { |
---|
34 | |
---|
35 | class MatrixLookup; |
---|
36 | class MatrixLookupWeighted; |
---|
37 | class Target; |
---|
38 | |
---|
39 | /** |
---|
40 | @brief Naive Bayesian Classifier. |
---|
41 | |
---|
42 | Each class is modelled as a multinormal distribution with |
---|
43 | features being independent: \f$ p(x|c) = \prod |
---|
44 | \frac{1}{\sqrt{2\pi\sigma_i^2}} \exp \left( |
---|
45 | \frac{(x_i-m_i)^2}{2\sigma_i^2)} \right)\f$ |
---|
46 | */ |
---|
47 | class NBC : public SupervisedClassifier |
---|
48 | { |
---|
49 | |
---|
50 | public: |
---|
51 | /// |
---|
52 | /// @brief Constructor |
---|
53 | /// |
---|
54 | NBC(void); |
---|
55 | |
---|
56 | |
---|
57 | /// |
---|
58 | /// @brief Destructor |
---|
59 | /// |
---|
60 | virtual ~NBC(); |
---|
61 | |
---|
62 | |
---|
63 | NBC* make_classifier(void) const; |
---|
64 | |
---|
65 | /// |
---|
66 | /// Train the classifier using training data and targets. |
---|
67 | /// |
---|
68 | /// For each class mean and variance are estimated for each |
---|
69 | /// feature (see Averager and AveragerWeighted for details). |
---|
70 | /// |
---|
71 | /// If variance can not be estimated (only one valid data point) |
---|
72 | /// for a feature and label, then that feature is ignored for that |
---|
73 | /// specific label. |
---|
74 | /// |
---|
75 | void train(const MatrixLookup&, const Target&); |
---|
76 | |
---|
77 | /// |
---|
78 | /// Train the classifier using weighted training data and targets. |
---|
79 | /// |
---|
80 | void train(const MatrixLookupWeighted&, const Target&); |
---|
81 | |
---|
82 | |
---|
83 | |
---|
84 | /** |
---|
85 | Each sample (column) in \a data is predicted and predictions |
---|
86 | are returned in the corresponding column in passed \a res. Each |
---|
87 | row in \a res corresponds to a class. The prediction is the |
---|
88 | estimated probability that sample belong to class \f$ j \f$ |
---|
89 | |
---|
90 | \f$ P_j = \frac{1}{Z}\prod_i{\frac{1}{\sqrt{2\pi\sigma_i^2}}} |
---|
91 | \exp(\frac{w_i(x_i-\mu_i)^2}{\sigma_i^2})\f$, where \f$ \mu_i |
---|
92 | \f$ and \f$ \sigma_i^2 \f$ are the estimated mean and variance, |
---|
93 | respectively. If a \f$ \sigma_i \f$ could not be estimated |
---|
94 | during training, corresponding factor is set to unity, in other |
---|
95 | words, that feature is ignored for the prediction of that |
---|
96 | particular class. Z is chosen such that total probability, \f$ |
---|
97 | \sum P_j \f$, equals unity. If \a data is a MatrixLookup is |
---|
98 | equivalent to using all weight equal to unity. |
---|
99 | */ |
---|
100 | void predict(const MatrixLookup& data, utility::Matrix& res) const; |
---|
101 | |
---|
102 | /** |
---|
103 | @see above |
---|
104 | */ |
---|
105 | void predict(const MatrixLookupWeighted& data, utility::Matrix& res) const; |
---|
106 | |
---|
107 | |
---|
108 | private: |
---|
109 | void standardize_lnP(utility::Matrix& prediction) const; |
---|
110 | |
---|
111 | utility::Matrix centroids_; |
---|
112 | utility::Matrix sigma2_; |
---|
113 | |
---|
114 | double sum_logsigma(size_t i) const; |
---|
115 | |
---|
116 | |
---|
117 | }; |
---|
118 | |
---|
119 | }}} // of namespace classifier, yat, and theplu |
---|
120 | |
---|
121 | #endif |
---|