PLearn 0.1
VVMatrix.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // VVMatrix.h
00004 // Copyright (C) 2002 Pascal Vincent and Julien Keable
00005 //
00006 // Redistribution and use in source and binary forms, with or without
00007 // modification, are permitted provided that the following conditions are met:
00008 //
00009 //  1. Redistributions of source code must retain the above copyright
00010 //     notice, this list of conditions and the following disclaimer.
00011 //
00012 //  2. Redistributions in binary form must reproduce the above copyright
00013 //     notice, this list of conditions and the following disclaimer in the
00014 //     documentation and/or other materials provided with the distribution.
00015 //
00016 //  3. The name of the authors may not be used to endorse or promote
00017 //     products derived from this software without specific prior written
00018 //     permission.
00019 //
00020 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR
00021 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
00022 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
00023 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
00024 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
00025 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
00026 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
00027 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
00028 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
00029 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
00030 //
00031 // This file is part of the PLearn library. For more information on the PLearn
00032 // library, go to the PLearn Web site at www.plearn.org
00033 
00034 /* *******************************************************
00035  * $Id: VVMatrix.h 5557 2006-05-10 20:36:58Z lamblin $
00036  * This file is part of the PLearn library.
00037  ******************************************************* */
00038 
00039 #ifndef VVMatrix_INC
00040 #define VVMatrix_INC
00041 
00042 #include "VMat.h"
00043 
00044 namespace PLearn {
00045 using namespace std;
00046 
00048 class VVMatrix: public VMatrix
00049 {
00050 
00051 private:
00052 
00053     typedef VMatrix inherited;
00054 
00055 protected:
00056 
00057     string code;
00058     VMat the_mat;
00059 
00060     static void declareOptions(OptionList& ol);
00061 
00063     // returns the precomputed version if it can
00064     static VMat createPreproVMat(const string & filename);
00065 
00066     // generate a file (ivfname) containing indexes of rows of 'source' that remain after filtering with
00067     // the *every* possible step that changes the index of rows (i.e : prefilter, shuffle.. postfiltering)
00068     // -- Not optimal, since it will first *precompute* if any postfilter is required
00069     static void generateVMatIndex(VMat source, const string& meta_data_dir,
00070                                   const string & filename, time_t date_of_code,const string & in,
00071                                   size_t idx_prefilter, size_t cidx_prefilter,
00072                                   size_t idx_postfilter, size_t cidx_postfilter,
00073                                   size_t idx_process, size_t cidx_process,
00074                                   size_t idx_shuffle, size_t cidx_shuffle,
00075                                   size_t idx_join, size_t cidx_join);
00076 // returns the result from the join operation
00077     static void processJoinSection(const vector<string> & code, VMat & tmpsource);
00078     // returns a 2d-array that contains the structure of the source datasets that will be concatenated
00079     static vector<vector<string> > extractSourceMatrix(const string & str,const string& filename);
00080     // generate a file (ivfname) containing indexes of rows of 'source' that remain after filtering with 'code'
00081     static void generateFilterIndexFile(VMat source, const string & code, const string& ivfname);
00082 
00083 public:
00084 
00085     // public build options
00086     string the_filename;
00087 
00088 public:
00089 
00090     PLEARN_DECLARE_OBJECT(VVMatrix);
00091 
00092     virtual void build();
00093 
00094     const string & getCode(){return code;}
00095 
00097     static time_t getDateOfVMat(const string& filename);
00098 
00102     static VMat buildFilteredVMatFromVPL(VMat source, const string & code, const string& ivfname, time_t date_of_code);
00103 
00105     bool isPrecomputedAndUpToDate();
00106 
00107     // returns a filename for the precomputed dataset (which you could load for example with getDataSet)
00108     string getPrecomputedDataName();
00109 
00110     VVMatrix(const string& filename_):the_filename(filename_){build_();}
00111     VVMatrix(){};
00112 
00113     // ****************************************************
00114     // POSSIBLE "cache" IMPROVEMENT.. need to check it out with pascal
00115     // would it be a good idea to systematically wrap "the_mat" with a RowBufferedVMatrix  ?
00116 
00117 // string maps are those loaded from the .vmat metadatadir, not those of the source vmatrix anymore
00118 // could be changed..
00119 
00120 //   virtual string getValString(int col, real val) const;
00121 //   virtual real getStringVal(int col, const string & str) const;
00122 //   virtual string getString(int row,int col) const;
00123 //   virtual const hash_map<string,real>& getStringToRealMapping(int col) const;
00124 
00125     virtual real get(int i, int j) const {return the_mat->get(i,j);}
00126     virtual void getSubRow(int i, int j, Vec v) const {the_mat->getSubRow(i,j,v);}
00127 
00129     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);
00130 
00131 private:
00132 
00133     void build_();
00134 
00135 };
00136 
00137 DECLARE_OBJECT_PTR(VVMatrix);
00138 
00139 } // end of namespace PLearn
00140 
00141 
00142 #endif // VVMatrix_INC
00143 
00144 
00145 /*
00146   Local Variables:
00147   mode:c++
00148   c-basic-offset:4
00149   c-file-style:"stroustrup"
00150   c-file-offsets:((innamespace . 0)(inline-open . 0))
00151   indent-tabs-mode:nil
00152   fill-column:79
00153   End:
00154 */
00155 // 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