PLearn 0.1
NGramDistribution.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // NGramDistribution.h
00004 //
00005 // Copyright (C) 2004 Hugo Larochelle
00006 //
00007 // Redistribution and use in source and binary forms, with or without
00008 // modification, are permitted provided that the following conditions are met:
00009 //
00010 //  1. Redistributions of source code must retain the above copyright
00011 //     notice, this list of conditions and the following disclaimer.
00012 //
00013 //  2. Redistributions in binary form must reproduce the above copyright
00014 //     notice, this list of conditions and the following disclaimer in the
00015 //     documentation and/or other materials provided with the distribution.
00016 //
00017 //  3. The name of the authors may not be used to endorse or promote
00018 //     products derived from this software without specific prior written
00019 //     permission.
00020 //
00021 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00022 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00023 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00024 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00025 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00026 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00027 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00028 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00029 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00030 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00031 //
00032 // This file is part of the PLearn library. For more information on the PLearn
00033 // library, go to the PLearn Web site at www.plearn.org
00034 
00035 /* *******************************************************
00036  * $Id: NGramDistribution.h 8173 2007-10-10 22:43:12Z larocheh $
00037  ******************************************************* */
00038 
00039 // Authors: Hugo Larochelle
00040 
00044 #ifndef NGramDistribution_INC
00045 #define NGramDistribution_INC
00046 
00047 #define THIS_PRECISION 0.0000001
00048 #define EM_PRECISION 0.0001
00049 
00050 #include <plearn_learners/distributions/PDistribution.h>
00051 #include <plearn_learners/distributions/NGramTree.h>
00052 #include <plearn/base/ms_hash_wrapper.h>
00053 
00054 namespace PLearn {
00055 using namespace std;
00056 
00058 class NGramDistribution: public PDistribution
00059 {
00060 
00061 private:
00062 
00063     typedef PDistribution inherited;
00064 
00065 protected:
00066 
00067     // *********************
00068     // * protected options *
00069     // *********************
00070 
00071     int voc_size;
00072 
00073 public:
00074 
00075     // ************************
00076     // * public build options *
00077     // ************************
00078 
00080     bool nan_replace;
00081 
00083     int n;
00084 
00086     real additive_constant;
00087 
00089     real discount_constant;
00090 
00092     string smoothing;
00093 
00095     string lambda_estimation;
00096 
00098     Vec lambdas;
00099 
00101     PP<NGramTree> tree;
00102 
00103 
00104     // ****************
00105     // * Constructors *
00106     // ****************
00107 
00109     NGramDistribution();
00110 
00111     // *************************
00112     // * PDistribution methods *
00113     // *************************
00114 
00115 private:
00116 
00118     void build_();
00119 
00121     void getNGrams(Vec row, TVec<int>& ngram) const;
00122 
00123 protected:
00124 
00126     static void declareOptions(OptionList& ol);
00127 
00128 public:
00129 
00130     // ************************
00131     // **** Object methods ****
00132     // ************************
00133 
00135     virtual void build();
00136 
00138     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);
00139 
00140     // Declare other standard object methods.
00141     PLEARN_DECLARE_OBJECT(NGramDistribution);
00142 
00143     // *******************************
00144     // **** PDistribution methods ****
00145     // *******************************
00146 
00148     virtual real log_density(const Vec& x) const;
00149 
00151     virtual real survival_fn(const Vec& y) const;
00152 
00154     virtual real cdf(const Vec& y) const;
00155 
00157     virtual void expectation(Vec& mu) const;
00158 
00160     virtual void variance(Mat& cov) const;
00161 
00163     virtual void generate(Vec& y) const;
00164 
00166     virtual real density(const Vec& y) const;
00167 
00168     // **************************
00169     // **** PLearner methods ****
00170     // **************************
00171 
00174     virtual void forget();
00175 
00177     virtual void train();
00178 
00179 };
00180 
00181 // Declare a few other classes and functions related to this class.
00182 DECLARE_OBJECT_PTR(NGramDistribution);
00183 
00184 } // end of namespace PLearn
00185 
00186 #endif
00187 
00188 
00189 /*
00190   Local Variables:
00191   mode:c++
00192   c-basic-offset:4
00193   c-file-style:"stroustrup"
00194   c-file-offsets:((innamespace . 0)(inline-open . 0))
00195   indent-tabs-mode:nil
00196   fill-column:79
00197   End:
00198 */
00199 // 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