PLearn 0.1
NetflixVMatrix.cc
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // NetflixVMatrix.cc
00004 //
00005 // Copyright (C) 2006 Pierre-Antoine Manzagol
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: Pierre-Antoine Manzagol
00036 
00040 #include "NetflixVMatrix.h"
00041 
00042 namespace PLearn {
00043 using namespace std;
00044 
00045 PLEARN_IMPLEMENT_OBJECT(
00046     NetflixVMatrix,
00047     "Used for holding the netflix data. Minimal implementation.",
00048     "Loads from a text file into a TVec< TVec< int > >.\n"
00049     "A hack for netflix."
00050     );
00051 
00053 // NetflixVMatrix //
00055 NetflixVMatrix::NetflixVMatrix()
00056 /* ### Initialize all fields to their default value here */
00057 {
00058     // ...
00059 
00060     // ### You may (or not) want to call build_() to finish building the object
00061     // ### (doing so assumes the parent classes' build_() have been called too
00062     // ### in the parent classes' constructors, something that you must ensure)
00063 }
00064 
00066 // declareOptions //
00068 void NetflixVMatrix::declareOptions(OptionList& ol)
00069 {
00070     // ### Declare all of this object's options here.
00071     // ### For the "flags" of each option, you should typically specify
00072     // ### one of OptionBase::buildoption, OptionBase::learntoption or
00073     // ### OptionBase::tuningoption. If you don't provide one of these three,
00074     // ### this option will be ignored when loading values from a script.
00075     // ### You can also combine flags, for example with OptionBase::nosave:
00076     // ### (OptionBase::buildoption | OptionBase::nosave)
00077 
00078     // ### ex:
00079     declareOption(ol, "sourceFileName", &NetflixVMatrix::sourceFileName,
00080                    OptionBase::buildoption,
00081                    "Name of the source file - a netflix user profiles file.");
00082 
00083     // Now call the parent class' declareOptions
00084     inherited::declareOptions(ol);
00085 }
00086 
00088 // build //
00090 void NetflixVMatrix::build()
00091 {
00092     inherited::build();
00093     build_();
00094 }
00095 
00097 // build_ //
00099 void NetflixVMatrix::build_()
00100 {
00101 
00102     cout << "NetflixVMatrix::build_()" << endl;
00103 
00104     // ### This method should do the real building of the object,
00105     // ### according to set 'options', in *any* situation.
00106     // ### Typical situations include:
00107     // ###  - Initial building of an object from a few user-specified options
00108     // ###  - Building of a "reloaded" object: i.e. from the complete set of
00109     // ###    all serialised options.
00110     // ###  - Updating or "re-building" of an object after a few "tuning"
00111     // ###    options have been modified.
00112     // ### You should assume that the parent class' build_() has already been
00113     // ### called.
00114 
00115     // Open source file
00116     ifstream input( sourceFileName.c_str() );
00117 
00118     if( ! input.is_open() ) {
00119         PLERROR("Could not open source file %s.", sourceFileName.c_str());
00120     }
00121 
00122     string str_line;
00123     int userIndex = 0;
00124     stringstream ss_tokens;
00125     int dummy;
00126     list< int > l_userProfile;
00127 
00128     // Determine number of users and resize data
00129     while( getline(input, str_line) )  {
00130         userIndex++;
00131     }
00132 
00133     cout << userIndex << " users" << endl;
00134 
00135     length_ = userIndex;
00136 
00137     data.resize(userIndex);
00138     input.clear();
00139     input.seekg(0, ios::beg);
00140     userIndex = 0;
00141 
00142     // Actual loading
00143     while( getline(input, str_line) )  {
00144         ss_tokens.str(str_line);
00145         ss_tokens.clear();
00146 
00147         while(ss_tokens >> dummy) {
00148             l_userProfile.push_back(dummy);
00149         }
00150 
00151         data[userIndex].resize( l_userProfile.size() );
00152 
00153         list< int >::iterator itr_userProfile = l_userProfile.begin();
00154         for(int i=0; itr_userProfile != l_userProfile.end(); itr_userProfile++, i++) {
00155             data[userIndex][i] = (*itr_userProfile);
00156         }
00157         l_userProfile.clear();
00158         userIndex++;
00159     }
00160 
00161 
00162 
00163     cout << "NetflixVMatrix::build_() - DONE!" << endl;
00164 
00165 }
00166 
00168 // get //
00170 real NetflixVMatrix::get(int i, int j) const
00171 {
00172     // get element at i-th row, j-th column
00173     PLERROR("Not implemented!");
00174     return 0.0;
00175 }
00176 
00178 // getExample //
00180 void NetflixVMatrix::getExample(int i, Vec& input, Vec& target, real& weight)
00181 {
00182     input.resize( data[i].length() );
00183     input << data[i];
00184 
00185 }
00186 
00187 /*
00189 // getSubRow //
00191 void NetflixVMatrix::getSubRow(int i, int j, Vec v) const
00192 {
00193     // get part or all of the i-th, starting at the j-th column,
00194     // with v.length() elements; these elements are put in v.
00195     PLERROR("Not implemented!");
00196 }
00197 
00199 // getRow //
00201 void NetflixVMatrix::getRow(int i, Vec v) const
00202 {
00203     PLERROR("Not implemented!");
00204 }
00205 */
00207 // makeDeepCopyFromShallowCopy //
00209 void NetflixVMatrix::makeDeepCopyFromShallowCopy(CopiesMap& copies)
00210 {
00211     inherited::makeDeepCopyFromShallowCopy(copies);
00212 
00213     // ### Call deepCopyField on all "pointer-like" fields
00214     // ### that you wish to be deepCopied rather than
00215     // ### shallow-copied.
00216     // ### ex:
00217     deepCopyField(sourceFileName, copies);
00218     deepCopyField(data, copies);
00219 
00220     // ### Remove this line when you have fully implemented this method.
00221     PLERROR("NetflixVMatrix::makeDeepCopyFromShallowCopy not fully (correctly) implemented yet!");
00222 }
00223 
00224 } // end of namespace PLearn
00225 
00226 
00227 /*
00228   Local Variables:
00229   mode:c++
00230   c-basic-offset:4
00231   c-file-style:"stroustrup"
00232   c-file-offsets:((innamespace . 0)(inline-open . 0))
00233   indent-tabs-mode:nil
00234   fill-column:79
00235   End:
00236 */
00237 // 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