PLearn 0.1
AddBagInformationVMatrix.cc
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // AddBagInformationVMatrix.cc
00004 //
00005 // Copyright (C) 2007 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 // Authors: Olivier Delalleau
00036 
00040 #include "AddBagInformationVMatrix.h"
00041 
00042 namespace PLearn {
00043 using namespace std;
00044 
00045 PLEARN_IMPLEMENT_OBJECT(
00046     AddBagInformationVMatrix,
00047     "Add bag information to an existing VMat.",
00048     "This VMatrix adds an extra target column to its source VMat, that\n"
00049     "contains bag information as follows:\n"
00050     "   - 1 = beginning of bag\n"
00051     "   - 2 = end of bag\n"
00052     "   - 0 = middle of bag\n"
00053     "   - 3 = single-row bag (both beginning and end)\n"
00054     "Bags are found by looking at a specific column of the source (given by\n"
00055     "the 'bag_info_column' option): a new bag is started when this column's\n"
00056     "value changes between two consecutive samples.\n"
00057 );
00058 
00060 // AddBagInformationVMatrix //
00062 AddBagInformationVMatrix::AddBagInformationVMatrix():
00063     remove_bag_info_column(false),
00064     bag_info_idx(-1)
00065 {
00066 }
00067 
00069 // declareOptions //
00071 void AddBagInformationVMatrix::declareOptions(OptionList& ol)
00072 {
00073     declareOption(ol, "bag_info_column",
00074                   &AddBagInformationVMatrix::bag_info_column,
00075                   OptionBase::buildoption,
00076         "The source's column that is used to find bags in the data. It can\n"
00077         "be either a number or a column's name.");
00078 
00079     declareOption(ol, "remove_bag_info_column",
00080                   &AddBagInformationVMatrix::remove_bag_info_column,
00081                   OptionBase::buildoption,
00082         "If true, then the source's column given by bag_info_column is\n"
00083         "removed from the resulting data.");
00084  
00085     // Now call the parent class' declareOptions
00086     inherited::declareOptions(ol);
00087 }
00088 
00090 // build //
00092 void AddBagInformationVMatrix::build()
00093 {
00094     inherited::build();
00095     build_();
00096 }
00097 
00099 // build_ //
00101 void AddBagInformationVMatrix::build_()
00102 {
00103     if (source) {
00104         updateMtime(source);
00105         bag_info_idx = source->getFieldIndex(bag_info_column);
00106         sourcerow.resize(source->width());
00107         int st = source->targetsize();
00108         if (st >= 0)
00109             targetsize_ = st + 1;
00110 
00111         // Set field infos.
00112         Array<VMField> fields = source->getFieldInfos().copy();
00113         fields.append(VMField("bag_info"));
00114 
00115         width_ = source->width() + 1;
00116         inputsize_ = source->inputsize();
00117 
00118         if (remove_bag_info_column) {
00119             // We need to remove a column from the source VMat.
00120             width_--;
00121             if( bag_info_idx < inputsize_ )
00122                 inputsize_--;
00123             Array<VMField> new_fields;
00124             for (int i = 0; i < fields.length(); i++)
00125                 if (i != bag_info_idx)
00126                     new_fields.append(fields[i]);
00127             fields = new_fields;
00128         }
00129 
00130         setFieldInfos(fields);
00131         setMetaInfoFromSource();
00132     }
00133 }
00134 
00136 // getNewRow //
00138 void AddBagInformationVMatrix::getNewRow(int i, const Vec& v) const
00139 {
00140     bool is_beg = false;
00141     bool is_end = false;
00142     // Obtain current bag information.
00143     source->getRow(i, sourcerow);
00144     real cur = sourcerow[bag_info_idx];
00145     if (i == 0)
00146         is_beg = true;
00147     else {
00148         // Compare with previous sample.
00149         real prev = source->get(i - 1, bag_info_idx);
00150         if (!is_equal(cur, prev))
00151             is_beg = true;
00152     }
00153     if (i == length_ - 1)
00154         is_end = true;
00155     else {
00156         // Compare with next sample.
00157         real next = source->get(i + 1, bag_info_idx);
00158         if (!is_equal(cur, next))
00159             is_end = true;
00160     }
00161     real bag_info = is_beg ? is_end ? 3
00162                                     : 1
00163                            : is_end ? 2
00164                                     : 0;
00165     if (remove_bag_info_column) {
00166         v.subVec(0, bag_info_idx) << sourcerow.subVec(0, bag_info_idx);
00167         int n_left = sourcerow.length() - bag_info_idx - 1;
00168         v.subVec(bag_info_idx, n_left) <<
00169             sourcerow.subVec(bag_info_idx + 1, n_left);
00170     } else
00171         v.subVec(0, sourcerow.length()) << sourcerow;
00172     v.lastElement() = bag_info;
00173 }
00174 
00176 // makeDeepCopyFromShallowCopy //
00178 void AddBagInformationVMatrix::makeDeepCopyFromShallowCopy(CopiesMap& copies)
00179 {
00180     inherited::makeDeepCopyFromShallowCopy(copies);
00181 }
00182 
00183 } // end of namespace PLearn
00184 
00185 
00186 /*
00187   Local Variables:
00188   mode:c++
00189   c-basic-offset:4
00190   c-file-style:"stroustrup"
00191   c-file-offsets:((innamespace . 0)(inline-open . 0))
00192   indent-tabs-mode:nil
00193   fill-column:79
00194   End:
00195 */
00196 // 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