PLearn 0.1
FeatureSetNaiveBayesClassifier.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // FeatureSetNaiveBayesClassifier.h
00004 // Copyright (c) 1998-2002 Pascal Vincent
00005 // Copyright (C) 1999-2002 Yoshua Bengio and University of Montreal
00006 // Copyright (c) 2002 Jean-Sebastien Senecal, Xavier Saint-Mleux, Rejean Ducharme
00007 //
00008 // Redistribution and use in source and binary forms, with or without
00009 // modification, are permitted provided that the following conditions are met:
00010 // 
00011 //  1. Redistributions of source code must retain the above copyright
00012 //     notice, this list of conditions and the following disclaimer.
00013 // 
00014 //  2. Redistributions in binary form must reproduce the above copyright
00015 //     notice, this list of conditions and the following disclaimer in the
00016 //     documentation and/or other materials provided with the distribution.
00017 // 
00018 //  3. The name of the authors may not be used to endorse or promote
00019 //     products derived from this software without specific prior written
00020 //     permission.
00021 // 
00022 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00023 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00024 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00025 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00026 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00027 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00028 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00029 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00030 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00031 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00032 // 
00033 // This file is part of the PLearn library. For more information on the PLearn
00034 // library, go to the PLearn Web site at www.plearn.org
00035 
00036 
00037 #ifndef FeatureSetNaiveBayesClassifier_INC
00038 #define FeatureSetNaiveBayesClassifier_INC
00039 
00040 #include <plearn_learners/generic/PLearner.h>
00041 #include <plearn/math/PRandom.h>
00042 #include <plearn/feat/FeatureSet.h>
00043 
00044 namespace PLearn {
00045 using namespace std;
00046 
00050 class FeatureSetNaiveBayesClassifier: public PLearner
00051 {
00052 
00053 private:
00054 
00055     typedef PLearner inherited;
00056     
00058     mutable Vec target_values;
00060     mutable Vec output_comp;
00062     mutable Vec row;
00064     mutable TVec< TVec<int> > feats;
00065 
00069     mutable string str;
00070     mutable int nfeats;
00071 
00072 protected:
00073 
00075     int total_output_size;
00079     int total_feats_per_token;
00081     int n_feat_sets;
00083     mutable Vec feat_input;
00085     mutable VMat val_string_reference_set;
00087     mutable VMat target_values_reference_set;
00089     PP<PRandom> rgen;
00090 
00091 public: 
00093     TVec< TVec< hash_map<int,int> > > feature_class_counts;
00095     TVec< TVec<int> > sum_feature_class_counts;
00097     TVec<int> class_counts;
00098 
00099 public:
00100 
00101     // Build options:
00102 
00105     bool possible_targets_vary;
00107     TVec<PP<FeatureSet> > feat_sets;
00111     bool input_dependent_posterior_estimation;
00113     real smoothing_constant;
00114 
00115 private:
00116     void build_();
00117 
00118     int my_argmax(const Vec& vec, int default_compare=0) const;
00119 
00120 public:
00121 
00122     FeatureSetNaiveBayesClassifier();
00123     virtual ~FeatureSetNaiveBayesClassifier();
00124     PLEARN_DECLARE_OBJECT(FeatureSetNaiveBayesClassifier);
00125 
00126     virtual void build();
00127     virtual void forget(); // simply calls initializeParams()
00128 
00129     virtual int outputsize() const;
00130     virtual TVec<string> getTrainCostNames() const;
00131     virtual TVec<string> getTestCostNames() const;
00132 
00133     virtual void train();
00134 
00135     virtual void computeOutput(const Vec& input, Vec& output) const;
00136 
00137     virtual void computeOutputAndCosts(const Vec& input, const Vec& target,
00138                                        Vec& output, Vec& costs) const;
00139 
00140     virtual void computeCostsFromOutputs(const Vec& input, 
00141                                          const Vec& output, 
00142                                          const Vec& target, 
00143                                          Vec& costs) const;
00144 
00145     virtual void makeDeepCopyFromShallowCopy(CopiesMap &copies);
00146 
00147 protected:
00148     static void declareOptions(OptionList& ol);
00149 
00150     void getProbs(const Vec& inputv, Vec& outputv) const;
00151 
00153     void batchComputeOutputAndConfidence(VMat inputs, real probability,
00154                                          VMat outputs_and_confidence) const;
00156     virtual void use(VMat testset, VMat outputs) const;
00158     virtual void test(VMat testset, PP<VecStatsCollector> test_stats, 
00159                       VMat testoutputs=0, VMat testcosts=0) const;
00161     virtual VMat processDataSet(VMat dataset) const;
00162         
00163 };
00164 
00165 DECLARE_OBJECT_PTR(FeatureSetNaiveBayesClassifier);
00166 
00167 } // end of namespace PLearn
00168 
00169 #endif
00170 
00171 
00172 /*
00173   Local Variables:
00174   mode:c++
00175   c-basic-offset:4
00176   c-file-style:"stroustrup"
00177   c-file-offsets:((innamespace . 0)(inline-open . 0))
00178   indent-tabs-mode:nil
00179   fill-column:79
00180   End:
00181 */
00182 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines