PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // PLearn (A C++ Machine Learning Library) 00004 // Copyright (C) 1998 Pascal Vincent 00005 // Copyright (C) 1999-2001 Pascal Vincent, Yoshua Bengio, Rejean Ducharme and University of Montreal 00006 // Copyright (C) 2002 Pascal Vincent, Julien Keable, Xavier Saint-Mleux 00007 // Copyright (C) 2003 Olivier Delalleau 00008 // 00009 // Redistribution and use in source and binary forms, with or without 00010 // modification, are permitted provided that the following conditions are met: 00011 // 00012 // 1. Redistributions of source code must retain the above copyright 00013 // notice, this list of conditions and the following disclaimer. 00014 // 00015 // 2. Redistributions in binary form must reproduce the above copyright 00016 // notice, this list of conditions and the following disclaimer in the 00017 // documentation and/or other materials provided with the distribution. 00018 // 00019 // 3. The name of the authors may not be used to endorse or promote 00020 // products derived from this software without specific prior written 00021 // permission. 00022 // 00023 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR 00024 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 00025 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN 00026 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 00027 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED 00028 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 00029 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 00030 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 00031 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 00032 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 00033 // 00034 // This file is part of the PLearn library. For more information on the PLearn 00035 // library, go to the PLearn Web site at www.plearn.org 00036 00037 00038 /* ******************************************************* 00039 * $Id: SelectColumnsVMatrix.h 9733 2008-12-02 19:53:54Z nouiz $ 00040 ******************************************************* */ 00041 00042 00045 #ifndef SelectColumnsVMatrix_INC 00046 #define SelectColumnsVMatrix_INC 00047 00048 #include "SourceVMatrix.h" 00049 00050 namespace PLearn { 00051 using namespace std; 00052 00056 class SelectColumnsVMatrix: public SourceVMatrix 00057 { 00058 00059 private: 00060 00061 typedef SourceVMatrix inherited; 00062 00064 Vec sinput; 00065 00066 public: 00067 00068 // Public build options. 00069 00070 bool extend_with_missing; 00071 TVec<int> indices; 00072 TVec<string> fields; 00073 PPath save_fields; 00074 bool fields_partial_match; 00075 bool fields_regex; 00076 bool inverse_fields_selection; 00077 bool warn_non_selected_field; 00078 00079 public: 00080 00082 SelectColumnsVMatrix(); 00083 00086 SelectColumnsVMatrix(VMat the_source, TVec<string> the_fields, 00087 bool the_extend_with_missing = false, 00088 bool call_build_ = true); 00089 00092 SelectColumnsVMatrix(VMat the_source, TVec<int> the_indices, 00093 bool call_build_ = true); 00094 00096 SelectColumnsVMatrix(VMat the_source, Vec the_indices); 00097 00098 PLEARN_DECLARE_OBJECT(SelectColumnsVMatrix); 00099 00100 virtual void build(); 00101 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00102 00103 protected: 00104 00106 TVec<int> sel_indices; 00107 00108 static void declareOptions(OptionList &ol); 00109 void getNewRow(int i, const Vec& v) const { getSubRow(i, 0, v); } 00112 void getIndicesFromFields(); 00113 00114 public: 00115 00116 virtual real get(int i, int j) const; 00117 virtual void getSubRow(int i, int j, Vec v) const; 00118 virtual void reset_dimensions() 00119 { 00120 source->reset_dimensions(); length_=source->length(); 00121 for (int i=0;indices.length();i++) 00122 if (indices[i]>=source->width()) 00123 PLERROR("SelectColumnsVMatrix::reset_dimensions, underlying source not wide enough (%d>=%d)", 00124 indices[i],source->width()); 00125 } 00126 00127 virtual const map<string,real>& getStringToRealMapping(int col) const; 00128 virtual const map<real,string>& getRealToStringMapping(int col) const; 00129 00130 virtual real getStringVal(int col, const string & str) const; 00131 virtual string getValString(int col, real val) const; 00132 00135 virtual PP<Dictionary> getDictionary(int col) const; 00136 00138 virtual void getValues(int row, int col, Vec& values) const; 00139 00141 virtual void getValues(const Vec& input, int col, Vec& values) const; 00142 00143 00144 private: 00145 void build_(); 00146 00147 }; 00148 00149 DECLARE_OBJECT_PTR(SelectColumnsVMatrix); 00150 00151 } // end of namespace PLearn 00152 #endif 00153 00154 00155 /* 00156 Local Variables: 00157 mode:c++ 00158 c-basic-offset:4 00159 c-file-style:"stroustrup" 00160 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00161 indent-tabs-mode:nil 00162 fill-column:79 00163 End: 00164 */ 00165 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :