PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // DictionaryVMatrix.h 00004 // 00005 // Copyright (C) 2004 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 /* ******************************************************* 00036 * $Id: DictionaryVMatrix.h 9436 2008-09-04 18:48:55Z nouiz $ 00037 ******************************************************* */ 00038 00039 // Authors: Hugo Larochelle 00040 00044 #ifndef DictionaryVMatrix_INC 00045 #define DictionaryVMatrix_INC 00046 00047 #include <plearn/python/PythonCodeSnippet.h> 00048 00049 #include <plearn/base/stringutils.h> 00050 #include <plearn/vmat/RowBufferedVMatrix.h> 00051 #include <plearn/dict/Dictionary.h> 00052 00053 // number of attributes of dictionary specifications 00054 #define DIC_SPECIFICATION_SIZE 3 00055 00056 namespace PLearn { 00057 using namespace std; 00058 00080 00081 class DictionaryVMatrix: public RowBufferedVMatrix 00082 { 00083 00084 private: 00085 00086 00087 typedef RowBufferedVMatrix inherited; 00088 00089 Mat data; 00090 00091 protected: 00092 00093 // ********************* 00094 // * protected options * 00095 // ********************* 00096 00098 int n_attributes; 00099 00101 PP<PythonCodeSnippet> python; 00102 00103 public: 00104 00105 // ************************ 00106 // * public build options * 00107 // ************************ 00108 00110 TVec<PPath> file_names; 00111 00113 TVec< PP<Dictionary> > dictionaries; 00114 00116 TVec< TVec <int> > option_fields; 00117 00119 string delimiters; 00120 00122 string code; 00123 00126 TVec<int> minimum_frequencies; 00127 00129 TVec< TVec<string> >symbols_to_ignore; 00130 00133 bool remove_rows_with_oov; 00134 00135 // **************** 00136 // * Constructors * 00137 // **************** 00138 00139 // Default constructor, make sure the implementation in the .cc 00140 // initializes all fields to reasonable default values. 00141 DictionaryVMatrix(); 00142 00143 private: 00144 00146 // (Please implement in .cc) 00147 void build_(); 00148 00149 protected: 00150 00152 // (Please implement in .cc) 00153 static void declareOptions(OptionList& ol); 00154 00157 virtual void getNewRow(int i, const Vec& v) const; 00158 00159 public: 00160 00162 virtual real getStringVal(int col, const string & str) const; 00163 00164 virtual string getValString(int col, real val) const; 00165 00166 virtual void getValues(int row, int col, Vec& values) const; 00167 00169 virtual void getValues(const Vec& input, int col, Vec& values) const; 00170 00171 // Simply call inherited::build() then build_(). 00172 virtual void build(); 00173 00175 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00176 00178 virtual PP<Dictionary> getDictionary(int col) const; 00179 00180 // virtual void save(const string& filename) ; 00182 PLEARN_DECLARE_OBJECT(DictionaryVMatrix); 00183 00184 }; 00185 00186 DECLARE_OBJECT_PTR(DictionaryVMatrix); 00187 00188 } // end of namespace PLearn 00189 #endif 00190 00191 00192 /* 00193 Local Variables: 00194 mode:c++ 00195 c-basic-offset:4 00196 c-file-style:"stroustrup" 00197 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00198 indent-tabs-mode:nil 00199 fill-column:79 00200 End: 00201 */ 00202 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :