PLearn 0.1
SDBWithStats.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: SDBWithStats.h 8231 2007-11-07 20:50:01Z nouiz $
00041  * AUTHORS: Pascal Vincent
00042  * This file is part of the PLearn library.
00043  ******************************************************* */
00044 
00045 
00048 #ifndef SDBWithStats_INC
00049 #define SDBWithStats_INC
00050 
00051 //#include "general.h"
00052 #include "SimpleDB.h"
00053 #include <map>
00054 
00055 namespace PLearn {
00056 using namespace std;
00057 
00058 class FieldStat
00059 {
00060     friend class SDBWithStats;
00061 
00062 protected:
00063 
00065     int nonmissing_; 
00066     int missing_;    
00067 
00069     double sum_;
00070     double sumsquare_;
00071 
00072     double min_;
00073     double max_;
00074     double mean_;
00075     double stddev_;
00076 
00077 public:
00078 
00080     map<string,int> symbolcount;
00081     mutable map<string,int> symbolid; 
00082     int nsymbols() { return (int)symbolcount.size(); }
00083     static int max_nsymbols; 
00084 
00085     FieldStat()
00086         :nonmissing_(0), missing_(0), 
00087          sum_(0.), sumsquare_(0), min_(FLT_MAX), max_(-FLT_MAX)
00088     {}
00089 
00090     int ntotal() const { return missing_+nonmissing_; }
00091     int missing() const { return missing_; }
00092     int nonmissing() const { return nonmissing_; }
00093     real mean() const { return real(mean_); }
00094     real stddev() const { return real(stddev_); }
00095     real min() const { return real(min_); }
00096     real max() const { return real(max_); }
00097 
00098     void updateString(const string& sym);
00099     void updateNumber(double d);
00100     void updateMissing()  { ++missing_; }
00101 
00102     void clear(); 
00103     void finalize(); 
00104 };
00105 
00106 class SDBWithStats: public SDB
00107 {
00108 public:
00109     vector<FieldStat> fieldstat;
00110     int nfields() { return (int)getSchema().size(); }
00111     string fieldname(int i) { return getSchema()[i].name; }
00112 
00113 public:
00114     SDBWithStats(string basename, string path=".", AccessType access = readwrite,
00115                  bool verbose=true);
00116 
00117     void forgetStats();
00118     void computeStats(unsigned int nrows);
00119     void computeStats() { computeStats(size()); }
00120 
00121     bool hasStats(); 
00122     void saveStats();
00123     void loadStats();
00124 
00125     FieldStat& getStat(int i);
00126     const FieldStat& getStat(int i) const;
00127     FieldStat& getStat(const string& fieldname);
00128     const FieldStat& getStat(const string& fieldname) const;
00129 };
00130 
00131 } // end of namespace PLearn
00132 
00133 #endif
00134 
00135 
00136 /*
00137   Local Variables:
00138   mode:c++
00139   c-basic-offset:4
00140   c-file-style:"stroustrup"
00141   c-file-offsets:((innamespace . 0)(inline-open . 0))
00142   indent-tabs-mode:nil
00143   fill-column:79
00144   End:
00145 */
00146 // 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