PLearn 0.1
VMField.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) 1999-2002 Pascal Vincent, Yoshua Bengio and University of Montreal
00006 //
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 
00039 /* *******************************************************
00040  * $Id: VMField.h 9227 2008-07-10 18:53:55Z saintmlx $
00041  * This file is part of the PLearn library.
00042  ******************************************************* */
00043 
00044 
00047 #ifndef VMField_INC
00048 #define VMField_INC
00049 
00050 #include <plearn/base/general.h>
00051 #include <plearn/io/PStream.h>
00052 
00053 namespace PLearn {
00054 using namespace std;
00055 
00057 class VMField
00058 {
00059 public:
00060 
00061     enum FieldType
00062     {
00063         UnknownType = 0,
00064         Continuous,
00065         DiscrGeneral,
00066         DiscrMonotonic,
00067         DiscrFloat,
00068         Date
00069     };
00070 
00071     string name;
00072     FieldType fieldtype;
00073 
00074     VMField(const string& the_name="", FieldType the_fieldtype=UnknownType);
00075 
00076     bool operator==(const VMField& other) const;
00077     bool operator!=(const VMField& other) const;
00078 
00079 };
00080 
00081 PStream& operator>>(PStream& in, VMField::FieldType& x); // dummy placeholder; do not call
00082 
00083 PStream& operator>>(PStream& in, VMField& x);
00084 PStream& operator<<(PStream& out, const VMField& x);
00085 
00087 class VMFieldStat
00088 {
00089 protected:
00090     int nmissing_;  
00091     int nnonmissing_;  
00092     int npositive_; 
00093     int nnegative_; 
00094     double sum_;    
00095     double sumsquare_; 
00096     real min_;       
00097     real max_;       
00098 
00100     int maxndiscrete;
00101 
00102 public:
00103 
00106     map<real,int> counts;
00107 
00108     VMFieldStat(int the_maxndiscrete=255);
00109 
00110     int count() const { return nmissing_ + nnonmissing_; } 
00111     int nmissing() const { return nmissing_; }
00112     int nnonmissing() const { return nnonmissing_; }
00113     int npositive() const { return npositive_; }
00114     int nnegative() const { return nnegative_; }
00115     int nzero() const { return nnonmissing_ - (npositive_+nnegative_); }
00116     real sum() const { return real(sum_); }
00117     real sumsquare() const { return real(sumsquare_); }
00118     real min() const { return min_; }
00119     real max() const { return max_; }
00120     real mean() const { return real(sum_/nnonmissing_); }
00121     real variance() const { return real((sumsquare_ - square(sum_)/nnonmissing_)/(nnonmissing_-1)); }
00122     real stddev() const { return sqrt(variance()); }
00123 
00124     real prob(real value) { return counts[value]/real(nnonmissing()); }
00125 
00126     void update(real val);
00127 
00128     void write(PStream& out) const;
00129     void read(PStream& in);
00130 };
00131 
00132 } // end of namespace PLearn
00133 
00134 #endif
00135 
00136 
00137 /*
00138   Local Variables:
00139   mode:c++
00140   c-basic-offset:4
00141   c-file-style:"stroustrup"
00142   c-file-offsets:((innamespace . 0)(inline-open . 0))
00143   indent-tabs-mode:nil
00144   fill-column:79
00145   End:
00146 */
00147 // 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