PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // TestImputations.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 TestImputations_INC 00041 #define TestImputations_INC 00042 00043 #include <cstdarg> 00044 00045 #include <plearn_learners/generic/PLearner.h> 00046 #include <plearn_learners/testers/PTester.h> 00047 #include <plearn/vmat/FileVMatrix.h> 00048 #include <plearn/vmat/MemoryVMatrix.h> 00049 #include <plearn/io/load_and_save.h> 00050 #include <plearn/io/fileutils.h> 00051 #include <plearn/math/random.h> 00052 #include <plearn/vmat/ExplicitSplitter.h> 00053 #include <plearn_learners/nearest_neighbors/BallTreeNearestNeighbors.h> 00054 #include <plearn_learners/nearest_neighbors/ExhaustiveNearestNeighbors.h> 00055 #include <plearn_learners/cgi/CovariancePreservationImputationVMatrix.h> 00056 #include <plearn_learners/cgi/NeighborhoodImputationVMatrix.h> 00057 #include <plearn_learners/cgi/WeightedDistance.h> 00058 00059 namespace PLearn { 00060 00065 class TestImputations : public PLearner 00066 { 00067 typedef PLearner inherited; 00068 00069 public: 00070 00071 //##### Public Build Options ############################################ 00072 00075 00077 int min_number_of_samples; 00079 int max_number_of_samples; 00081 PPath mean_median_mode_file_name; 00083 PPath tree_conditional_mean_directory; 00085 PPath covariance_preservation_file_name; 00087 VMat reference_set_with_covpres; 00089 VMat reference_set_with_missing; 00091 TVec<string> missing_indicators; 00092 00093 public: 00094 //##### Public Member Functions ######################################### 00095 00097 // ### Make sure the implementation in the .cc 00098 // ### initializes all fields to reasonable default values. 00099 TestImputations(); 00100 int outputsize() const; 00101 void train(); 00102 void computeOutput(const Vec&, Vec&) const; 00103 void computeCostsFromOutputs(const Vec&, const Vec&, const Vec&, Vec&) const; 00104 TVec<string> getTestCostNames() const; 00105 TVec<string> getTrainCostNames() const; 00106 00107 00108 //##### PLearn::Object Protocol ######################################### 00109 00110 // Declares other standard object methods. 00111 // ### If your class is not instantiatable (it has pure virtual methods) 00112 // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS 00113 PLEARN_DECLARE_OBJECT(TestImputations); 00114 00115 // Simply calls inherited::build() then build_() 00116 virtual void build(); 00117 00119 // (PLEASE IMPLEMENT IN .cc) 00120 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00121 00122 protected: 00123 //##### Protected Member Functions ###################################### 00124 00126 static void declareOptions(OptionList& ol); 00127 00128 private: 00129 //##### Private Member Functions ######################################## 00130 00132 void build_(); 00133 void build_ball_tree(int nb_neighbors); 00134 void initialize(); 00135 void computeMeanMedianModeStats(); 00136 void computeTreeCondMeanStats(); 00137 void computeCovPresStats(); 00138 real covariancePreservationValue(int col); 00139 void computeNeighborhoodStats(int nb_neighbors,int max_miss_neigbors); 00140 void createHeaderFile(); 00141 void getHeaderRecord(); 00142 void updateHeaderRecord(int var_col); 00143 void createOutputFile(); 00144 void getOutputRecord(int var_col); 00145 void updateOutputRecord(int var_col); 00146 void endtestimputation(const char* msg, ...); 00147 private: 00148 //##### Private Data Members ############################################ 00149 00150 // The rest of the private stuff goes here 00151 ExhaustiveNearestNeighbors* ball_tree; 00152 Mat ref_cov; 00153 Mat ref_mis; 00154 int train_length; 00155 int train_width; 00156 Vec train_input; 00157 TVec<string> train_names; 00158 PPath train_metadata; 00159 StatsCollector train_stats; 00160 int train_total; 00161 int train_missing; 00162 int train_present; 00163 PPath header_file_name; 00164 VMat header_file; 00165 Vec header_record; 00166 int to_deal_with_total; 00167 int to_deal_with_next; 00168 string to_deal_with_name; 00169 real to_deal_with_value; 00170 VMat test_samples_set; 00171 TVec<int> indices; 00172 int test_length; 00173 int test_width; 00174 real mmmf_mean_err; 00175 real mmmf_median_err; 00176 real mmmf_mode_err; 00177 PPath tcmf_file_name; 00178 VMat tcmf_file; 00179 real tcmf_mean_err; 00180 Mat cvpf_cov; 00181 Vec cvpf_mu; 00182 real cvpf_mean_err; 00183 Vec knnf_input; 00184 Vec knnf_neighbors; 00185 Vec knnf_mean_cov_err; 00186 Vec knnf_mean_miss_err; 00187 Vec knnf_nmiss_value_count; 00188 Vec weights; 00189 WeightedDistance* weighted_distance_kernel; 00190 PPath output_file_name; 00191 VMat output_file; 00192 Vec output_record; 00193 TVec<string> output_names; 00194 }; 00195 00196 // Declares a few other classes and functions related to this class 00197 DECLARE_OBJECT_PTR(TestImputations); 00198 00199 } // end of namespace PLearn 00200 00201 #endif 00202 00203 00204 /* 00205 Local Variables: 00206 mode:c++ 00207 c-basic-offset:4 00208 c-file-style:"stroustrup" 00209 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00210 indent-tabs-mode:nil 00211 fill-column:79 00212 End: 00213 */ 00214 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :