PLearn 0.1
MeanMedianModeImputationVMatrix.h
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 // Copyright (C) 2003 Olivier Delalleau
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: MeanMedianModeImputationVMatrix.h 3658 2005-07-06 20:30:15  Godbout $
00040    ****************************************************************** */
00041 
00044 #ifndef MeanMedianModeImputationVMatrix_INC
00045 #define MeanMedianModeImputationVMatrix_INC
00046 
00047 #include "ImputationVMatrix.h"
00048 #include <plearn/vmat/FileVMatrix.h>
00049 #include <plearn/io/fileutils.h>                     
00050 #include <plearn/math/BottomNI.h>
00051 
00052 namespace PLearn {
00053 using namespace std;
00054 
00055 class MeanMedianModeImputationVMatrix: public ImputationVMatrix
00056 {
00057   typedef ImputationVMatrix inherited;
00058   
00059 public:
00060 
00061   
00065   VMat                          train_set;
00066   
00071   real                          number_of_train_samples_to_use;
00072   
00074   TVec< pair<string, string> >  imputation_spec;
00075 
00078   bool                          missing_field_error;
00079   string                        default_instruction;
00080 
00081                         MeanMedianModeImputationVMatrix();
00082   virtual               ~MeanMedianModeImputationVMatrix();
00083 
00084   static void           declareOptions(OptionList &ol);
00085 
00086   virtual void          build();
00087   virtual void          makeDeepCopyFromShallowCopy(CopiesMap& copies);
00088 
00089   virtual real         get(int i, int j) const;
00090   virtual void         getSubRow(int i, int j, Vec v) const;
00091   virtual void         getRow(int i, Vec v) const;
00092   virtual void         getColumn(int i, Vec v) const;
00093           VMat         getMeanMedianModeFile();
00094 
00095 private:
00096   
00097   TVec<string>         train_field_names;
00098   VMat                 mean_median_mode_file;
00099 
00100 
00102   Vec                           variable_mean;
00103   
00105   Vec                           variable_median;
00106   
00108   Vec                           variable_mode;
00109   
00111   TVec<int>                     variable_imputation_instruction;
00112   
00113           void         build_();
00114   virtual void setMetaDataDir(const PPath& the_metadatadir);
00115           void         createMeanMedianModeFile(PPath file_name); 
00116           void         loadMeanMedianModeFile(PPath file_name); 
00117           void         computeMeanMedianModeVectors();  
00118   static  void         sortColumn(Vec input_vec, int start, int end);
00119   static  void         sortSmallSubArray(Vec input_vec, int start_index, int end_index);
00120   static  void         swapValues(Vec input_vec, int index_i, int index_j);
00121   static  real         compare(real field1, real field2);
00122   
00123   PLEARN_DECLARE_OBJECT(MeanMedianModeImputationVMatrix);
00124 
00125 };
00126 
00127 DECLARE_OBJECT_PTR(MeanMedianModeImputationVMatrix);
00128 
00129 } // end of namespcae PLearn
00130 #endif
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines