PLearn 0.1
DistanceKernel.cc
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // PLearn (A C++ Machine Learning Library)
00004 // Copyright (C) 1998 Pascal Vincent
00005 // Copyright (C) 1999-2002 Pascal Vincent, Yoshua Bengio, Rejean Ducharme and University of Montreal
00006 // Copyright (C) 2001-2002 Nicolas Chapados, Ichiro Takeuchi, Jean-Sebastien Senecal
00007 // Copyright (C) 2002 Xiangdong Wang, Christian Dorion
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 /* *******************************************************      
00039  * $Id: DistanceKernel.cc 7675 2007-06-29 19:50:49Z tihocan $
00040  * This file is part of the PLearn library.
00041  ******************************************************* */
00042 
00043 #include "DistanceKernel.h"
00044 #include "SelectedOutputCostFunction.h"
00045 
00046 namespace PLearn {
00047 using namespace std;
00048 
00049 
00050 PLEARN_IMPLEMENT_OBJECT(
00051     DistanceKernel,
00052     "Implements an Ln distance (defaults to L2 i.e. euclidean distance).",
00053     "Output is as follows:\n"
00054     "- If option 'pow_distance' = 1,\n"
00055     "     k(x1,x2) = \\sum_i |x1[i]-x2[i]|^n\n"
00056     "- If option 'pow_distance' = 0,\n"
00057     "     k(x1,x2) = (\\sum_i |x1[i]-x2[i]|^2)^(1/n)");
00058 
00060 // DistanceKernel //
00062 DistanceKernel::DistanceKernel(real the_Ln, bool pd)
00063     : n(the_Ln),
00064       optimized(false),
00065       pow_distance(pd),
00066       ignore_missing(false)
00067 {}
00068 
00070 // declareOptions //
00072 void DistanceKernel::declareOptions(OptionList& ol)
00073 {
00074 
00075     declareOption(ol, "n", &DistanceKernel::n, OptionBase::buildoption, 
00076                   "This class implements a Ln distance (L2, the default is the usual euclidean distance).");
00077 
00078     declareOption(ol, "pow_distance", &DistanceKernel::pow_distance, OptionBase::buildoption, 
00079                   "If set to 1, the distance computed will be elevated to power n.");
00080 
00081     declareOption(ol, "optimized", &DistanceKernel::optimized, OptionBase::buildoption, 
00082                   "If set to 1, the evaluate_i_j method will be faster, at the cost of potential\n"
00083                   "approximations in the result.");
00084 
00085     declareOption(ol, "ignore_missing", &DistanceKernel::ignore_missing, OptionBase::buildoption, 
00086                   "If set to false, nan will be propagated.\n"
00087                   "If set to true, if a value is missing in the matrix of some examples, we will ignore this value for the distance\n"
00088                   "If set to true, work only if pow_distance is set to 1.");
00089 
00090     inherited::declareOptions(ol);
00091 }
00092 
00094 // evaluate //
00096 real DistanceKernel::evaluate(const Vec& x1, const Vec& x2) const {
00097     if (ignore_missing && !pow_distance)
00098         PLERROR("In DistanceKernel::evaluate(int i, int j) - 'ignore_missing' "
00099                 "implemented only if pow_distance is set");
00100 
00101     if (pow_distance) {
00102         return powdistance(x1, x2, n, ignore_missing);
00103     } else {
00104         return dist(x1, x2, n);
00105     }
00106 }
00107 
00109 // evaluate_i_j //
00111 real DistanceKernel::evaluate_i_j(int i, int j) const {
00112     static real d;
00113     if (ignore_missing)
00114         PLERROR("DistanceKernel::evaluate_i_j(int i, int j) not implemented for ignore_missing");
00115 
00116     if (optimized && fast_exact_is_equal(n, 2.0)) {
00117         if (i == j)
00118             // The case 'i == j' can cause precision issues because of the optimized
00119             // formula below. Thus we make sure we always return 0.
00120             return 0;
00121         d = squarednorms[i] + squarednorms[j] - 2 * data->dot(i, j, data_inputsize);
00122         if (d < 0) {
00123             // This can happen (especially when compiled in -opt) if the two points
00124             // are the same, and the distance should be zero.
00125             if (d < -1e-2)
00126                 // That should not happen.
00127                 PLERROR("In DistanceKernel::evaluate_i_j - Found a (significantly) negative distance (%f), "
00128                         "i = %d, j = %d, squarednorms[i] = %f, squarednorms[j] = %f, dot = %f",
00129                         d, i, j, squarednorms[i], squarednorms[j], data->dot(i, j, data_inputsize));
00130             d = 0;
00131         }
00132         if (pow_distance)
00133             return d;
00134         else
00135             return sqrt(d);
00136     } else {
00137         return inherited::evaluate_i_j(i,j);
00138     }
00139 }
00140 
00142 // setDataForKernelMatrix //
00144 void DistanceKernel::setDataForKernelMatrix(VMat the_data)
00145 {
00146     if (ignore_missing)
00147         PLWARNING("DistanceKernel::setDataForKernelMatrix(VMat the_data) not tested for ignore_missing");
00148 
00149     inherited::setDataForKernelMatrix(the_data);
00150     if (fast_exact_is_equal(n, 2.0)) {
00151         squarednorms.resize(data.length());
00152         for(int index=0; index<data.length(); index++) {
00153             squarednorms[index] = data->dot(index, index, data_inputsize);
00154         }
00155     }
00156 }
00157 
00159 // absolute_deviation //
00161 CostFunc absolute_deviation(int singleoutputindex)
00162 { 
00163     if(singleoutputindex>=0)
00164         return new SelectedOutputCostFunction(new DistanceKernel(1.0),singleoutputindex); 
00165     else
00166         return new DistanceKernel(1.0); 
00167 }
00168 
00169 } // end of namespace PLearn
00170 
00171 
00172 /*
00173   Local Variables:
00174   mode:c++
00175   c-basic-offset:4
00176   c-file-style:"stroustrup"
00177   c-file-offsets:((innamespace . 0)(inline-open . 0))
00178   indent-tabs-mode:nil
00179   fill-column:79
00180   End:
00181 */
00182 // 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