PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // UniformizeLearner.h 00004 // 00005 // Copyright (C) 2004 ApSTAT Technologies Inc. 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: UniformizeLearner.h 6007 2006-07-11 21:39:12Z saintmlx $ 00037 ******************************************************* */ 00038 00039 // Authors: Pascal Vincent 00040 00043 #ifndef UniformizeLearner_INC 00044 #define UniformizeLearner_INC 00045 00046 #include <plearn_learners/generic/PLearner.h> 00047 00048 namespace PLearn { 00049 using namespace std; 00050 00051 class UniformizeLearner: public PLearner 00052 { 00053 private: 00054 typedef PLearner inherited; 00055 00056 protected: 00057 00059 static Vec v_no_missing; 00060 00061 int weight_field_index; 00062 TVec<string> input_field_names; 00063 00064 // ** learnt options ** 00065 00066 TVec< map<real,real> > val_to_rank; 00067 00068 public: 00069 00070 // ************************ 00071 // * public build options * 00072 // ************************ 00073 00074 TVec<string> which_fieldnames; 00075 TVec<int> which_fieldnums; 00076 int nquantiles; 00077 00078 bool raw_inputs_as_output; 00079 00080 // **************** 00081 // * Constructors * 00082 // **************** 00083 00084 // Default constructor, make sure the implementation in the .cc 00085 // initializes all fields to reasonable default values. 00086 UniformizeLearner(); 00087 00088 00089 // ****************** 00090 // * PLearner methods * 00091 // ****************** 00092 00093 private: 00095 // (Please implement in .cc) 00096 void build_(); 00097 00098 protected: 00100 // (Please implement in .cc) 00101 static void declareOptions(OptionList& ol); 00102 00103 public: 00104 00105 // ************************ 00106 // **** Object methods **** 00107 // ************************ 00108 00110 virtual void build(); 00111 00113 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00114 00115 // Declares other standard object methods 00116 // If your class is not instantiatable (it has pure virtual methods) 00117 // you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS 00118 PLEARN_DECLARE_OBJECT(UniformizeLearner); 00119 00120 00121 // ************************** 00122 // **** PLearner methods **** 00123 // ************************** 00124 00127 // (PLEASE IMPLEMENT IN .cc) 00128 virtual int outputsize() const; 00129 00132 virtual void forget(); 00133 00134 00137 virtual void train(); 00138 00139 00141 virtual void computeOutput(const Vec& input, Vec& output) const; 00142 00144 virtual void computeCostsFromOutputs(const Vec& input, const Vec& output, 00145 const Vec& target, Vec& costs) const; 00146 00147 00149 virtual TVec<string> getTestCostNames() const; 00150 00153 virtual TVec<string> getTrainCostNames() const; 00154 00155 00156 virtual void setTrainingSet(VMat training_set, bool call_forget=true); 00157 00158 virtual TVec<string> getOutputNames() const; 00159 00160 00161 // *** SUBCLASS WRITING: *** 00162 // While in general not necessary, in case of particular needs 00163 // (efficiency concerns for ex) you may also want to overload 00164 // some of the following methods: 00165 // virtual void computeOutputAndCosts(const Vec& input, const Vec& target, Vec& output, Vec& costs) const; 00166 // virtual void computeCostsOnly(const Vec& input, const Vec& target, Vec& costs) const; 00167 // virtual void test(VMat testset, PP<VecStatsCollector> test_stats, VMat testoutputs=0, VMat testcosts=0) const; 00168 // virtual int nTestCosts() const; 00169 // virtual int nTrainCosts() const; 00170 00171 // ** UniformizeLearner methods ** 00172 00175 static void computeRankMap(const Vec& v, int nquantiles, 00176 map<real,real>& rankmap); 00177 00178 00179 static void computeWeightedRankMap(const Vec& v, int nquantiles, map<real,real>& rankmap, const Vec& weights); 00180 00182 static real mapToRank(real val, const map<real,real>& rankmap); 00183 00184 }; 00185 00186 // Declares a few other classes and functions related to this class 00187 DECLARE_OBJECT_PTR(UniformizeLearner); 00188 00189 } // end of namespace PLearn 00190 00191 #endif 00192 00193 00194 /* 00195 Local Variables: 00196 mode:c++ 00197 c-basic-offset:4 00198 c-file-style:"stroustrup" 00199 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00200 indent-tabs-mode:nil 00201 fill-column:79 00202 End: 00203 */ 00204 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :