PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // NGramTree.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: NGramTree.h 5865 2006-06-14 18:13:50Z larocheh $ 00037 ******************************************************* */ 00038 00039 // Authors: Hugo Larochelle 00040 00044 #ifndef NGramTree_INC 00045 #define NGramTree_INC 00046 00047 #include <plearn/base/Object.h> 00048 #include <plearn_learners/distributions/SymbolNode.h> 00049 00050 namespace PLearn { 00051 using namespace std; 00052 00053 class NGramTree: public Object 00054 { 00055 00056 private: 00057 00058 typedef Object inherited; 00059 00060 protected: 00061 // ********************* 00062 // * protected options * 00063 // ********************* 00064 00065 PP<SymbolNode> root; 00066 00067 public: 00068 00069 // ************************ 00070 // * public build options * 00071 // ************************ 00072 00073 // **************** 00074 // * Constructors * 00075 // **************** 00076 00078 NGramTree(); 00079 00081 NGramTree(PP<SymbolNode> root_); 00082 00083 // ****************** 00084 // * Object methods * 00085 // ****************** 00086 00087 private: 00089 void build_(); 00090 00091 protected: 00093 static void declareOptions(OptionList& ol); 00094 00095 public: 00096 // Declares other standard object methods. 00097 PLEARN_DECLARE_OBJECT(NGramTree); 00098 00099 // simply calls inherited::build() then build_() 00100 virtual void build(); 00101 00103 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00104 00106 void add(TVec<int> ngram); 00107 00109 TVec<int> freq(TVec<int> ngram); 00110 00114 TVec<map<int,int>*> freqs(TVec<int> ngram); 00115 00117 TVec<int> normalization(TVec<int> ngram); 00118 00121 int n_children(TVec<int> sequence); 00122 00126 TVec<int> n_freq(TVec<int> sequence); 00127 00128 /* Hugo: not useful 00130 // WARNING: the frequency counts don't mean anything then... 00131 // the tree can only be usefull for counting the number of nodes 00132 // for example... 00133 TVec<PP<NGramTree> > getSubTrees(TVec<int> sequence); 00134 */ 00135 00137 void setRoot(PP<SymbolNode> root_){root = root_;} 00138 00140 void forget(); 00141 00142 }; 00143 00144 // Declares a few other classes and functions related to this class 00145 DECLARE_OBJECT_PTR(NGramTree); 00146 00147 } // end of namespace PLearn 00148 00149 #endif 00150 00151 00152 /* 00153 Local Variables: 00154 mode:c++ 00155 c-basic-offset:4 00156 c-file-style:"stroustrup" 00157 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00158 indent-tabs-mode:nil 00159 fill-column:79 00160 End: 00161 */ 00162 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :