PLearn 0.1
SentencesBlocks.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) 1999-2001 Pascal Vincent, Yoshua Bengio, Rejean Ducharme and University of Montreal
00006 // Copyright (C) 2002 Pascal Vincent, Julien Keable, Xavier Saint-Mleux
00007 //
00008 // Redistribution and use in source and binary forms, with or without
00009 // modification, are permitted provided that the following conditions are met:
00010 //
00011 //  1. Redistributions of source code must retain the above copyright
00012 //     notice, this list of conditions and the following disclaimer.
00013 //
00014 //  2. Redistributions in binary form must reproduce the above copyright
00015 //     notice, this list of conditions and the following disclaimer in the
00016 //     documentation and/or other materials provided with the distribution.
00017 //
00018 //  3. The name of the authors may not be used to endorse or promote
00019 //     products derived from this software without specific prior written
00020 //     permission.
00021 //
00022 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00023 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00024 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00025 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00026 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00027 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00028 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00029 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00030 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00031 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00032 //
00033 // This file is part of the PLearn library. For more information on the PLearn
00034 // library, go to the PLearn Web site at www.plearn.org
00035 
00036 
00037 /* *******************************************************
00038  * $Id: SentencesBlocks.cc 5557 2006-05-10 20:36:58Z lamblin $
00039  ******************************************************* */
00040 
00041 #include "SentencesBlocks.h"
00042 
00043 namespace PLearn {
00044 using namespace std;
00045 
00048 SentencesBlocks::SentencesBlocks(int n_blocks, VMat d, Vec separator)
00049     : TVec<VMat>(n_blocks)
00050 {
00051     if (n_blocks==1)
00052     {
00053         (*this)[0]=d;
00054         return;
00055     }
00056     int total_size = d->length();
00057     if (total_size < n_blocks * 2)
00058         PLERROR("SentencesBlocks: can't have blocks of size < 2 in average");
00059     Vec v(d->width());
00060     int b=0;
00061     int previous_previous_block=0,previous_beginning_of_block = 0, previous_beginning_of_sentence=0;
00062     int next_target = (int)(total_size / (real)n_blocks);
00063     for (int i=0;i<total_size && b<n_blocks-1;i++)
00064     {
00065         d->getRow(i,v);
00066         if (v==separator)
00067         {
00068             if (i>=next_target)
00069             {
00070                 int cut=0;
00071                 if (i-next_target < next_target-previous_beginning_of_sentence ||
00072                     previous_beginning_of_sentence < previous_beginning_of_block)
00073                     cut=i+1;
00074                 else
00075                 {
00076                     cut=previous_beginning_of_sentence;
00077                     previous_beginning_of_sentence = i+1;
00078                 }
00079                 (*this)[b++] = d.subMatRows(previous_beginning_of_block,
00080                                             cut-previous_beginning_of_block);
00081                 previous_previous_block = previous_beginning_of_block;
00082                 previous_beginning_of_block=cut;
00083                 if (b<n_blocks)
00084                 {
00085                     if (b>n_blocks-3)
00086                         next_target = (int)((total_size - cut) / (real)(n_blocks-b));
00087                     else
00088                         next_target = (int)(total_size * (real)(b+1.0) / n_blocks);
00089                 }
00090             }
00091             else
00092                 previous_beginning_of_sentence=i+1;
00093         }
00094     }
00095     if (b==n_blocks-1)
00096         (*this)[b++] = d.subMatRows(previous_beginning_of_block,
00097                                     total_size-previous_beginning_of_block);
00098     if (b<n_blocks-1) // we have to backtrack, split previous block in two
00099     {
00100         if (b<n_blocks-2)
00101             PLERROR("SentencesBlocks: blocks are too small!");
00102         if (previous_beginning_of_sentence<previous_beginning_of_block)
00103             PLERROR("SentencesBlocks: Blocks are too small!");
00104         int cut = previous_beginning_of_sentence;
00105         (*this)[b++] = d.subMatRows(previous_beginning_of_block,
00106                                     cut-previous_beginning_of_block);
00107         previous_beginning_of_block=cut;
00108         (*this)[b++] = d.subMatRows(previous_beginning_of_block,
00109                                     total_size-previous_beginning_of_block);
00110     }
00111 }
00112 
00113 } // end of namespace PLearn
00114 
00115 
00116 /*
00117   Local Variables:
00118   mode:c++
00119   c-basic-offset:4
00120   c-file-style:"stroustrup"
00121   c-file-offsets:((innamespace . 0)(inline-open . 0))
00122   indent-tabs-mode:nil
00123   fill-column:79
00124   End:
00125 */
00126 // 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