PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // TargetEncodingLearner.h 00004 // 00005 // Copyright (C) 2006 Xavier Saint-Mleux 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 // Authors: Xavier Saint-Mleux 00036 00040 #ifndef TargetEncodingLearner_INC 00041 #define TargetEncodingLearner_INC 00042 00043 #include <plearn_learners/generic/PLearner.h> 00044 00045 namespace PLearn { 00046 00057 class TargetEncodingLearner : public PLearner 00058 { 00059 typedef PLearner inherited; 00060 00061 public: 00062 //##### Public Options ############################################ 00063 00066 00067 // Build options 00068 int max_nvals_for_encoding; 00069 00070 PP<PLearner> sublearner; 00071 00072 // Learnt option 00073 TVec<map<real,real> > encodings; 00074 TVec<bool> encode_col; 00075 TVec<real> defaults; 00076 real mean; // weighted mean of targets 00077 00078 bool encodings_learnt; 00079 00080 00081 public: 00082 //##### Public Member Functions ######################################### 00083 00085 // ### Make sure the implementation in the .cc 00086 // ### initializes all fields to reasonable default values. 00087 TargetEncodingLearner(); 00088 00089 00090 //##### PLearner Member Functions ####################################### 00091 00094 // (PLEASE IMPLEMENT IN .cc) 00095 virtual int outputsize() const; 00096 00100 // (PLEASE IMPLEMENT IN .cc) 00101 virtual void forget(); 00102 00106 // (PLEASE IMPLEMENT IN .cc) 00107 virtual void train(); 00108 00110 // (PLEASE IMPLEMENT IN .cc) 00111 virtual void computeOutput(const Vec& input, Vec& output) const; 00112 00114 // (PLEASE IMPLEMENT IN .cc) 00115 virtual void computeCostsFromOutputs(const Vec& input, const Vec& output, 00116 const Vec& target, Vec& costs) const; 00117 00120 // (PLEASE IMPLEMENT IN .cc) 00121 virtual TVec<std::string> getTestCostNames() const; 00122 00125 // (PLEASE IMPLEMENT IN .cc) 00126 virtual TVec<std::string> getTrainCostNames() const; 00127 00129 virtual TVec<string> getOutputNames() const; 00130 00131 // *** SUBCLASS WRITING: *** 00132 // While in general not necessary, in case of particular needs 00133 // (efficiency concerns for ex) you may also want to overload 00134 // some of the following methods: 00135 // virtual void computeOutputAndCosts(const Vec& input, const Vec& target, 00136 // Vec& output, Vec& costs) const; 00137 // virtual void computeCostsOnly(const Vec& input, const Vec& target, 00138 // Vec& costs) const; 00139 // virtual void test(VMat testset, PP<VecStatsCollector> test_stats, 00140 // VMat testoutputs=0, VMat testcosts=0) const; 00141 // virtual int nTestCosts() const; 00142 // virtual int nTrainCosts() const; 00143 // virtual void resetInternalState(); 00144 // virtual bool isStatefulLearner() const; 00145 00146 00147 //##### PLearn::Object Protocol ######################################### 00148 00149 // Declares other standard object methods. 00150 // ### If your class is not instantiatable (it has pure virtual methods) 00151 // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS 00152 PLEARN_DECLARE_OBJECT(TargetEncodingLearner); 00153 00154 // Simply calls inherited::build() then build_() 00155 virtual void build(); 00156 00158 // (PLEASE IMPLEMENT IN .cc) 00159 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00160 00161 virtual void setExperimentDirectory(const PPath& the_expdir); 00162 00163 virtual void setTrainingSet(VMat training_set, bool call_forget=true); 00164 00165 00166 protected: 00167 //##### Protected Options ############################################### 00168 00169 // ### Declare protected option fields (such as learned parameters) here 00170 // ... 00171 00172 void buildEncodingsFromTrainset(); 00173 00174 00175 protected: 00176 //##### Protected Member Functions ###################################### 00177 00179 // (PLEASE IMPLEMENT IN .cc) 00180 static void declareOptions(OptionList& ol); 00181 00182 private: 00183 //##### Private Member Functions ######################################## 00184 00186 // (PLEASE IMPLEMENT IN .cc) 00187 void build_(); 00188 00189 private: 00190 //##### Private Data Members ############################################ 00191 00192 // The rest of the private stuff goes here 00193 }; 00194 00195 // Declares a few other classes and functions related to this class 00196 DECLARE_OBJECT_PTR(TargetEncodingLearner); 00197 00198 } // end of namespace PLearn 00199 00200 #endif 00201 00202 00203 /* 00204 Local Variables: 00205 mode:c++ 00206 c-basic-offset:4 00207 c-file-style:"stroustrup" 00208 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00209 indent-tabs-mode:nil 00210 fill-column:79 00211 End: 00212 */ 00213 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :