PLearn 0.1
BinSplitter.cc
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // BinSplitter.cc
00004 //
00005 // Copyright (C) 2004 Olivier Delalleau
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: BinSplitter.cc 6861 2007-04-09 19:04:15Z saintmlx $
00037  ******************************************************* */
00038 
00039 // Authors: Olivier Delalleau
00040 
00044 #include "BinSplitter.h"
00045 #include <plearn/vmat/SelectRowsVMatrix.h>
00046 
00047 namespace PLearn {
00048 using namespace std;
00049 
00051 // BinSplitter //
00053 BinSplitter::BinSplitter()
00054     : column(0),
00055       column_spec("")
00056 {
00057 }
00058 
00059 PLEARN_IMPLEMENT_OBJECT(BinSplitter,
00060                         "Split a dataset into bins given by a Binner object.",
00061                         ""
00062     );
00063 
00065 // declareOptions //
00067 void BinSplitter::declareOptions(OptionList& ol)
00068 {
00069     declareOption(ol, "binner", &BinSplitter::binner, OptionBase::buildoption,
00070                   "The binner used to create the bins.");
00071 
00072     declareOption(ol, "column", &BinSplitter::column, OptionBase::buildoption,
00073                   "The column used to defined the bins.");
00074 
00075     declareOption(ol, "column_spec", &BinSplitter::column_spec, OptionBase::buildoption,
00076                   "Alternatively, this option can be used to override the 'column' option:\n"
00077                   " - 'first_input' : the first input column\n"
00078                   " - 'last_input'  : the last input column\n"
00079                   " - 'first_target': the first target column\n"
00080                   " - 'last_target' : the last target column");
00081 
00082     // Now call the parent class' declareOptions
00083     inherited::declareOptions(ol);
00084 }
00085 
00087 // build_ //
00089 void BinSplitter::build_()
00090 {
00091 }
00092 
00094 // build //
00096 void BinSplitter::build()
00097 {
00098     inherited::build();
00099     build_();
00100 }
00101 
00102 void BinSplitter::makeDeepCopyFromShallowCopy(CopiesMap& copies)
00103 {
00104     inherited::makeDeepCopyFromShallowCopy(copies);
00105 
00106     // ### Call deepCopyField on all "pointer-like" fields
00107     // ### that you wish to be deepCopied rather than
00108     // ### shallow-copied.
00109     // ### ex:
00110     // deepCopyField(trainvec, copies);
00111 
00112     // ### Remove this line when you have fully implemented this method.
00113     PLERROR("BinSplitter::makeDeepCopyFromShallowCopy not fully (correctly) implemented yet!");
00114 }
00115 
00117 // nsplits //
00119 int BinSplitter::nsplits() const
00120 {
00121     return 1;
00122 }
00123 
00125 // nSetsPerSplit //
00127 int BinSplitter::nSetsPerSplit() const
00128 {
00129     return binner->nBins();
00130 }
00131 
00133 // getSplit //
00135 TVec<VMat> BinSplitter::getSplit(int k)
00136 {
00137     TVec<VMat> sets(nSetsPerSplit());
00138     for (int i = 0; i < sets.length(); i++) {
00139         sets[i] = new SelectRowsVMatrix(dataset, bins[i]);
00140     }
00141     return sets;
00142 }
00143 
00145 // setDataSet //
00147 void BinSplitter::setDataSet(VMat the_dataset) {
00148     inherited::setDataSet(the_dataset);
00149     int col = column;
00150     if (column_spec != "") {
00151         if (column_spec == "first_input")
00152             col = 0;
00153         else if (column_spec == "last_input")
00154             col = the_dataset->inputsize() - 1;
00155         else if (column_spec == "first_target")
00156             col = the_dataset->inputsize();
00157         else if (column_spec == "last_target")
00158             col = the_dataset->inputsize() + the_dataset->targetsize() - 1;
00159         else
00160             PLERROR("In BinSplitter::setDataSet - Wrong value for 'column_spec'");
00161         if (col < 0)
00162             PLERROR("In BinSplitter::setDataSet - Found a negative column, check the dataset sizes are correctly defined");
00163     }
00164     else if (column >= the_dataset->width())
00165         PLERROR("In BinSplitter::setDataSet - The column number is higher than available");
00166     Vec col_vec = the_dataset.column(col)->toMat().toVec();
00167     if (!binner)
00168         PLERROR("In BinSplitter::setDataSet - You must provide a binner first.");
00169     bins = binner->getBins(col_vec);
00170 }
00171 
00172 } // end of namespace PLearn
00173 
00174 
00175 /*
00176   Local Variables:
00177   mode:c++
00178   c-basic-offset:4
00179   c-file-style:"stroustrup"
00180   c-file-offsets:((innamespace . 0)(inline-open . 0))
00181   indent-tabs-mode:nil
00182   fill-column:79
00183   End:
00184 */
00185 // 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