PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // MergeDond2Files.h 00004 // 00005 // Copyright (C) 2006 Dan Popovici 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: Dan Popovici 00036 00040 #ifndef MergeDond2Files_INC 00041 #define MergeDond2Files_INC 00042 00043 #include <plearn_learners/generic/PLearner.h> 00044 #include <plearn/vmat/FileVMatrix.h> 00045 00046 namespace PLearn { 00047 00052 class MergeDond2Files : public PLearner 00053 { 00054 typedef PLearner inherited; 00055 00056 public: 00057 00058 //##### Public Build Options ############################################ 00059 00062 00065 VMat external_dataset; 00066 00069 TVec< pair<string, string> > missing_instructions; 00070 00073 TVec< pair<string, string> > merge_instructions; 00074 00076 string merge_path; 00077 00079 int sec_key; 00080 00082 int main_key; 00083 00085 int train_ind; 00086 00088 int test_ind; 00089 00091 VMat train_file; 00092 00094 VMat test_file; 00095 00097 VMat unknown_file; 00098 00099 public: 00100 //##### Public Member Functions ######################################### 00101 00103 // ### Make sure the implementation in the .cc 00104 // ### initializes all fields to reasonable default values. 00105 MergeDond2Files(); 00106 int outputsize() const; 00107 void train(); 00108 void computeOutput(const Vec&, Vec&) const; 00109 void computeCostsFromOutputs(const Vec&, const Vec&, const Vec&, Vec&) const; 00110 TVec<string> getTestCostNames() const; 00111 TVec<string> getTrainCostNames() const; 00112 00113 00114 //##### PLearn::Object Protocol ######################################### 00115 00116 // Declares other standard object methods. 00117 // ### If your class is not instantiatable (it has pure virtual methods) 00118 // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS 00119 PLEARN_DECLARE_OBJECT(MergeDond2Files); 00120 00121 // Simply calls inherited::build() then build_() 00122 virtual void build(); 00123 00125 // (PLEASE IMPLEMENT IN .cc) 00126 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00127 00128 protected: 00129 //##### Protected Member Functions ###################################### 00130 00132 static void declareOptions(OptionList& ol); 00133 00134 private: 00135 //##### Private Member Functions ######################################## 00136 00138 void build_(); 00139 void mergeFiles(); 00140 void accumulateVec(); 00141 void combineAndPut(); 00142 00143 private: 00144 //##### Private Data Members ############################################ 00145 00146 // The rest of the private stuff goes here 00147 // secondary dataset variables 00148 int sec_length; 00149 int sec_width; 00150 int sec_row; 00151 Vec sec_input; 00152 TVec<string> sec_names; 00153 TVec<string> sec_ins; 00154 int extension_width; 00155 int ext_col; 00156 TVec<int> extension_pos; 00157 TVec<string> extension_names; 00158 Mat sec_values; 00159 Mat sec_value_cnt; 00160 TVec<int> sec_value_ind; 00161 bool sec_value_found; 00162 real sec_value_count_max; 00163 00164 // primary dataset variables 00165 int main_length; 00166 int main_width; 00167 int main_row; 00168 Vec main_input; 00169 TVec<string> main_names; 00170 TVec<string> main_ins; 00171 int primary_width; 00172 TVec<string> primary_names; 00173 00174 // merge dataset variables 00175 int train_length; 00176 int test_length; 00177 int unknown_length; 00178 int merge_width; 00179 int train_row; 00180 int test_row; 00181 int unknown_row; 00182 int merge_col; 00183 Vec merge_output; 00184 TVec<string> merge_names; 00185 }; 00186 00187 // Declares a few other classes and functions related to this class 00188 DECLARE_OBJECT_PTR(MergeDond2Files); 00189 00190 } // end of namespace PLearn 00191 00192 #endif 00193 00194 00195 /* 00196 Local Variables: 00197 mode:c++ 00198 c-basic-offset:4 00199 c-file-style:"stroustrup" 00200 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00201 indent-tabs-mode:nil 00202 fill-column:79 00203 End: 00204 */ 00205 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :