PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // AnalyzeFieldStats.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 AnalyzeFieldStats_INC 00041 #define AnalyzeFieldStats_INC 00042 00043 #include <plearn_learners/generic/PLearner.h> 00044 #include <plearn_learners/testers/PTester.h> 00045 #include <plearn/vmat/FileVMatrix.h> 00046 #include <plearn/vmat/MemoryVMatrix.h> 00047 00048 namespace PLearn { 00049 00054 class AnalyzeFieldStats : public PLearner 00055 { 00056 typedef PLearner inherited; 00057 00058 public: 00059 00060 //##### Public Build Options ############################################ 00061 00064 00066 int min_number_of_samples; 00068 int max_number_of_samples; 00070 VMat targeted_set; 00072 PP<PTester> cond_mean_template; 00074 TVec<string> fields; 00075 00076 public: 00077 //##### Public Member Functions ######################################### 00078 00080 // ### Make sure the implementation in the .cc 00081 // ### initializes all fields to reasonable default values. 00082 AnalyzeFieldStats(); 00083 int outputsize() const; 00084 void train(); 00085 void computeOutput(const Vec&, Vec&) const; 00086 void computeCostsFromOutputs(const Vec&, const Vec&, const Vec&, Vec&) const; 00087 TVec<string> getTestCostNames() const; 00088 TVec<string> getTrainCostNames() const; 00089 00090 00091 //##### PLearn::Object Protocol ######################################### 00092 00093 // Declares other standard object methods. 00094 // ### If your class is not instantiatable (it has pure virtual methods) 00095 // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS 00096 PLEARN_DECLARE_OBJECT(AnalyzeFieldStats); 00097 00098 // Simply calls inherited::build() then build_() 00099 virtual void build(); 00100 00102 // (PLEASE IMPLEMENT IN .cc) 00103 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00104 00105 protected: 00106 //##### Protected Member Functions ###################################### 00107 00109 static void declareOptions(OptionList& ol); 00110 00111 private: 00112 //##### Private Member Functions ######################################## 00113 00115 void build_(); 00116 void analyzeVariableStats(); 00117 void createHeaderFile(); 00118 void getHeaderRecord(); 00119 void updateHeaderRecord(int var_col); 00120 void reviewGlobalStats(); 00121 00122 private: 00123 //##### Private Data Members ############################################ 00124 00125 // The rest of the private stuff goes here 00126 00127 int main_width; 00128 TVec<string> main_names; 00129 StatsCollector main_stats; 00130 PPath main_metadata; 00131 TVec<int> main_ins; 00132 real main_total; 00133 real main_missing; 00134 real main_present; 00135 int targeted_length; 00136 int targeted_width; 00137 Vec targeted_input; 00138 TVec<string> targeted_names; 00139 StatsCollector targeted_stats; 00140 PPath targeted_metadata; 00141 real targeted_missing; 00142 PPath header_file_name; 00143 VMat header_file; 00144 Vec header_record; 00145 int fields_col; 00146 int fields_width; 00147 TVec<int> fields_selected; 00148 int to_deal_with_total; 00149 int to_deal_with_next; 00150 real to_deal_with_value; 00151 string to_deal_with_name; 00152 int ind_next; 00153 int output_length; 00154 int output_width; 00155 int output_col; 00156 string output_path; 00157 TVec<string> output_names; 00158 Vec output_vec; 00159 TVec<int> output_variable_src; 00160 VMat output_file; 00161 int train_test_length; 00162 string train_test_path; 00163 TVec<int> train_test_variable_src; 00164 VMat train_test_file; 00165 PPath results_file_name; 00166 VMat results_file; 00167 int results_length; 00168 real results_nstages; 00169 real results_mse; 00170 real results_std_err; 00171 PPath test_output_file_name; 00172 VMat test_output_file; 00173 int test_output_length; 00174 00175 }; 00176 00177 // Declares a few other classes and functions related to this class 00178 DECLARE_OBJECT_PTR(AnalyzeFieldStats); 00179 00180 } // end of namespace PLearn 00181 00182 #endif 00183 00184 00185 /* 00186 Local Variables: 00187 mode:c++ 00188 c-basic-offset:4 00189 c-file-style:"stroustrup" 00190 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00191 indent-tabs-mode:nil 00192 fill-column:79 00193 End: 00194 */ 00195 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :