PLearn 0.1
Splitter.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // Splitter.h
00004 //
00005 // Copyright (C) 2002 Pascal Vincent, Frederic Morin
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: Splitter.h 8122 2007-09-27 19:21:10Z nouiz $
00037  ******************************************************* */
00038 
00040 #ifndef Splitter_INC
00041 #define Splitter_INC
00042 
00043 #include <plearn/base/Object.h>
00044 #include <plearn/base/Array.h>
00045 #include "VMat.h"
00046 
00047 namespace PLearn {
00048 using namespace std;
00049 
00061 class Splitter : public Object
00062 {
00063     typedef Object inherited;
00064 
00065 protected:
00066     // *********************
00067     // * protected options *
00068     // *********************
00069 
00070     VMat dataset;
00071 
00072 public:
00073     // ****************
00074     // * Constructors *
00075     // ****************
00076 
00077     PLEARN_DECLARE_ABSTRACT_OBJECT(Splitter);
00078 
00079     Splitter() {};
00080 
00082     virtual void setDataSet(VMat the_dataset);
00083 
00085     VMat getDataSet()
00086     { return dataset; }
00087 
00089     virtual int nsplits() const = 0;
00090 
00092     virtual int nSetsPerSplit() const = 0;
00093 
00095     virtual TVec<VMat> getSplit(int i=0) = 0;
00096 
00098     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);
00099 
00100 protected:    
00102     static void declareOptions(OptionList& ol);
00103 
00105     static void declareMethods(RemoteMethodMap& rmm);
00106 };
00107 
00108 // Declares a few other classes and functions related to this class
00109 DECLARE_OBJECT_PTR(Splitter);
00110 
00111 
00112 // A few useful function for splitting the datasets... (can be called in Splitter subclasses
00113 
00123 void split(VMat d, real test_fraction, VMat& train, VMat& test, int i = 0, bool use_all = false);
00124 
00126 void split(VMat d, real validation_fraction, real test_fraction, VMat& train, VMat& valid, VMat& test,bool do_shuffle=false);
00127 
00134 Vec randomSplit(VMat d, real test_fraction, VMat& train, VMat& test);
00135 
00137 void randomSplit(VMat d, real validation_fraction, real test_fraction, VMat& train, VMat& valid, VMat& test);
00138 
00139 
00140 } // end of namespace PLearn
00141 
00142 #endif
00143 
00144 
00145 /*
00146   Local Variables:
00147   mode:c++
00148   c-basic-offset:4
00149   c-file-style:"stroustrup"
00150   c-file-offsets:((innamespace . 0)(inline-open . 0))
00151   indent-tabs-mode:nil
00152   fill-column:79
00153   End:
00154 */
00155 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines