PLearn 0.1
Preprocessing.h
Go to the documentation of this file.
00001 // -*- C++ -*-
00002 
00003 // Preprocessing.h
00004 //
00005 // Copyright (C) 2006 Dan Popovici
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: Dan Popovici
00036 
00040 #ifndef Preprocessing_INC
00041 #define Preprocessing_INC
00042 
00043 #include <plearn_learners/second_iteration/ComputeDond2Target.h>
00044 #include <plearn_learners/second_iteration/FixDond2BinaryVariables.h>
00045 #include <plearn_learners/second_iteration/DichotomizeDond2DiscreteVariables.h>
00046 #include <plearn_learners/second_iteration/MeanMedianModeImputationVMatrix.h>
00047 #include <plearn_learners/second_iteration/GaussianizeVMatrix.h>
00048 #include <plearn_learners/second_iteration/MissingIndicatorVMatrix.h>     
00049 #include <plearn_learners/generic/PLearner.h>
00050 #include <plearn_learners/testers/PTester.h>
00051 #include <plearn/vmat/FileVMatrix.h>
00052 #include <plearn/vmat/MemoryVMatrix.h>
00053 
00054 namespace PLearn {
00055 
00060 class Preprocessing : public PLearner
00061 {
00062     typedef PLearner inherited;
00063 
00064 public:
00065 
00066     //#####  Public Build Options  ############################################
00067 
00070 
00072     VMat test_set;
00074     VMat unknown_set;
00076     PP<ComputeDond2Target> compute_target_learner_template;
00078     PP<FixDond2BinaryVariables> fix_binary_variables_template;
00080     TVec< pair<string, string> >  imputation_spec;
00084     TVec< pair<string, TVec< pair<real, real> > > > discrete_variable_instructions;
00086     TVec< string > selected_variables_for_input;
00088     TVec< string > selected_variables_for_target;
00090     TVec< string > inputs_excluded_from_gaussianization;
00092     TVec< string > targets_excluded_from_gaussianization;
00093 
00094 public:
00095     //#####  Public Member Functions  #########################################
00096 
00098     // ### Make sure the implementation in the .cc
00099     // ### initializes all fields to reasonable default values.
00100     Preprocessing();
00101     int outputsize() const;
00102     void train();
00103     void computeOutput(const Vec&, Vec&) const;
00104     void computeCostsFromOutputs(const Vec&, const Vec&, const Vec&, Vec&) const;
00105     TVec<string> getTestCostNames() const;
00106     TVec<string> getTrainCostNames() const;
00107 
00108 
00109     //#####  PLearn::Object Protocol  #########################################
00110 
00111     // Declares other standard object methods.
00112     // ### If your class is not instantiatable (it has pure virtual methods)
00113     // ### you should replace this by PLEARN_DECLARE_ABSTRACT_OBJECT_METHODS
00114     PLEARN_DECLARE_OBJECT(Preprocessing);
00115 
00116     // Simply calls inherited::build() then build_()
00117     virtual void build();
00118 
00120     // (PLEASE IMPLEMENT IN .cc)
00121     virtual void makeDeepCopyFromShallowCopy(CopiesMap& copies);    
00122 
00123 protected:
00124     //#####  Protected Member Functions  ######################################
00125 
00127     static void declareOptions(OptionList& ol);
00128 
00129 private:
00130     //#####  Private Member Functions  ########################################
00131 
00133     void build_();
00134     void manageTrainTestUnknownSets();
00135 
00136 private:
00137     //#####  Private Data Members  ############################################
00138 
00139     // The rest of the private stuff goes here
00140     
00141 };
00142 
00143 // Declares a few other classes and functions related to this class
00144 DECLARE_OBJECT_PTR(Preprocessing);
00145 
00146 } // end of namespace PLearn
00147 
00148 #endif
00149 
00150 
00151 /*
00152   Local Variables:
00153   mode:c++
00154   c-basic-offset:4
00155   c-file-style:"stroustrup"
00156   c-file-offsets:((innamespace . 0)(inline-open . 0))
00157   indent-tabs-mode:nil
00158   fill-column:79
00159   End:
00160 */
00161 // 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