PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // TrainTestSplitter.h 00004 // 00005 // Copyright (C) 1998 Pascal Vincent 00006 // Copyright (C) 1999,2000 Pascal Vincent, Yoshua Bengio and University of Montreal 00007 // Copyright (C) 2002 Frederic Morin 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 * $Id: TrainTestSplitter.h 7733 2007-07-10 01:19:04Z lamblin $ 00039 ******************************************************* */ 00040 00042 #ifndef TrainTestSplitter_INC 00043 #define TrainTestSplitter_INC 00044 00045 #include "Splitter.h" 00046 00047 namespace PLearn { 00048 using namespace std; 00049 00050 class TrainTestSplitter: public Splitter 00051 { 00052 typedef Splitter inherited; 00053 00054 protected: 00055 // ********************* 00056 // * protected options * 00057 // ********************* 00058 00059 // ### declare protected option fields (such as learnt parameters) here 00060 00061 TVec<int> train_indices, test_indices; 00062 00063 public: 00064 00065 // ************************ 00066 // * public build options * 00067 // ************************ 00068 00069 bool append_train; 00070 real test_fraction; // the fraction of the dataset to be used as test (hese will be the last few samples of the dataset) 00071 bool calc_with_pct; 00072 int test_fraction_abs; 00073 int32_t shuffle_seed; 00074 00075 // **************** 00076 // * Constructors * 00077 // **************** 00078 00079 // Default constructor, make sure the implementation in the .cc 00080 // initializes all fields to reasonable default values. 00081 TrainTestSplitter(real the_test_fraction = 0.0); 00082 TrainTestSplitter(int the_test_fraction); 00083 00084 // ****************** 00085 // * Object methods * 00086 // ****************** 00087 00088 private: 00090 // (Please implement in .cc) 00091 void build_(); 00092 00093 protected: 00095 // (Please implement in .cc) 00096 static void declareOptions(OptionList& ol); 00097 00098 void getRandomSubsets(int train_length, int test_length); 00099 00100 public: 00101 // simply calls inherited::build() then build_() 00102 virtual void build(); 00103 00105 virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00106 00108 PLEARN_DECLARE_OBJECT(TrainTestSplitter); 00109 00110 // ******************************** 00111 // * Splitter methods * 00112 // * (must be implemented in .cc) * 00113 // ******************************** 00114 00116 virtual int nsplits() const; 00117 00119 virtual int nSetsPerSplit() const; 00120 00122 virtual TVec<VMat> getSplit(int i=0); 00123 00124 }; 00125 00126 // Declares a few other classes and functions related to this class 00127 DECLARE_OBJECT_PTR(TrainTestSplitter); 00128 00129 } // end of namespace PLearn 00130 00131 #endif 00132 00133 00134 /* 00135 Local Variables: 00136 mode:c++ 00137 c-basic-offset:4 00138 c-file-style:"stroustrup" 00139 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00140 indent-tabs-mode:nil 00141 fill-column:79 00142 End: 00143 */ 00144 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :