PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // OutputFeaturesCommand.cc 00004 // 00005 // Copyright (C) 2006 Hugo Larochelle 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: Hugo Larochelle 00036 00040 #include "OutputFeaturesCommand.h" 00041 #include <plearn/feat/FeatureSet.h> 00042 #include <plearn/vmat/VMatrix.h> 00043 #include <plearn/vmat/SubVMatrix.h> 00044 #include <plearn/db/getDataSet.h> 00045 #include <plearn/io/load_and_save.h> 00046 #include <plearn/feat/HashMapFeatureSet.h> 00047 #include <plearn/feat/CachedFeatureSet.h> 00048 00049 namespace PLearn { 00050 using namespace std; 00051 00053 PLearnCommandRegistry OutputFeaturesCommand::reg_(new OutputFeaturesCommand); 00054 00055 OutputFeaturesCommand::OutputFeaturesCommand() 00056 : PLearnCommand( 00057 "output-features", 00058 "PLearn command that outputs the features found in a VMatrix input fields", 00059 "Usage: output-features <dataset> <feat_set> <output_string> [used_feat_set]\n" 00060 " Will use feat_set to obtain the features from dataset and output\n" 00061 " them. If output_string == 1, the features will be in string \n" 00062 " format and if output_string == 0, the feature IDs will be given.\n" 00063 " Optionaly, feat_set can be saved in a new file (used_feat_set)\n" 00064 " after it has been used. This can be useful when the feature set\n" 00065 " maintains a cache of the previously requested features of tokens.\n" 00066 " Only the input fields' features are output, with the features of\n" 00067 " a single token separated with by ' ' and the features from \n" 00068 " different fields separated by '\\t'." 00069 ) 00070 {} 00071 00073 void OutputFeaturesCommand::run(const vector<string>& args) 00074 { 00075 if(args.size() != 3 && args.size() != 4) 00076 { 00077 cerr << helpmsg << endl; 00078 return; 00079 } 00080 string vmat_file = args[0]; 00081 string feat_file = args[1]; 00082 string output_string = args[2]; 00083 if(args[2] != "0" && args[2] != "1") 00084 PLERROR("In OutputFeaturesCommand::run(): output_string should be 0 or 1"); 00085 bool bool_output_string = tobool(output_string); 00086 string used_feat_file = ""; 00087 if(args.size() == 4) used_feat_file = args[3]; 00088 00089 VMat vmat = getDataSet(vmat_file); 00090 VMat get_input_vmat; 00091 get_input_vmat = 00092 new SubVMatrix(vmat,0,0,vmat->length(), 00093 vmat->inputsize()); 00094 00095 PP<FeatureSet> feat; 00096 load(feat_file,feat); 00097 00098 Vec row(get_input_vmat->width()); 00099 string token; 00100 TVec<int> features; 00101 TVec<string> f_str; 00102 int l = get_input_vmat->length(); 00103 int w = get_input_vmat->width(); 00104 for(int i=0; i<l; i++) 00105 { 00106 get_input_vmat->getRow(i,row); 00107 for(int j=0; j<w; j++) 00108 { 00109 token = get_input_vmat->getValString(j,row[j]); 00110 feat->getFeatures(token, features); 00111 if(bool_output_string) 00112 for(int k=0; k<features.length(); k++) 00113 { 00114 cout << feat->getStringFeature(features[k]); 00115 if( k < features.length()-1) 00116 cout << " "; 00117 } 00118 else 00119 for(int k=0; k<features.length(); k++) 00120 { 00121 cout << features[k]; 00122 if( k < features.length()-1) 00123 cout << " "; 00124 00125 } 00126 if(j < l-1) 00127 cout << "\t"; 00128 } 00129 cout << endl; 00130 } 00131 00132 if(used_feat_file != "") 00133 save(used_feat_file,feat); 00134 } 00135 00136 } // end of namespace PLearn 00137 00138 00139 /* 00140 Local Variables: 00141 mode:c++ 00142 c-basic-offset:4 00143 c-file-style:"stroustrup" 00144 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00145 indent-tabs-mode:nil 00146 fill-column:79 00147 End: 00148 */ 00149 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :