classifier.h

/**************************************************************************
 * Copyright (c) 2005-2011 T. M. Murali                                   *
 * Copyright (c) 2008-2011 Naveed Massjouni                               *
 * Copyright (c) 2004 Greg Grothaus                                       *
 *                                                                        *
 * This file is part of Biorithm.                                         *
 *                                                                        *
 * Biorithm is free software: you can redistribute it and/or modify       *
 * it under the terms of the GNU General Public License as published by   *
 * the Free Software Foundation, either version 3 of the License, or      *
 * (at your option) any later version.                                    *
 *                                                                        *
 * Biorithm is distributed in the hope that it will be useful,            *
 * but WITHOUT ANY WARRANTY; without even the implied warranty of         *
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the          *
 * GNU General Public License for more details.                           *
 *                                                                        *
 * You should have received a copy of the GNU General Public License      *
 * along with Biorithm.  If not, see <http://www.gnu.org/licenses/>.      *
 *                                                                        *
 **************************************************************************/

#include<set>
#include<string>
#include<iostream>
#include<algorithm>
#include<vector>
#include<cmath>

#include "motifDataset.h"
#include "setTemplates.C"
#include "readfile.h"
#include "xmotif.h"
#include "greedySetCover.h"

using namespace std;

#ifndef CLASSIFIERGREG
#define CLASSIFIERGREG

class classifier
{
private:
  static const double BIG_DBL;
  set<itemset> _classifierMotifs;
  set<itemset> _unprunedMotifs;
  void pruneItemsets(motifDataset*);
  double cosine(vector<double> a,vector<double> b);
  double distnce(vector<double> &a,vector<double> &b);
  vector<double> normalize(vector<double> in);
  double randDouble(double min,double max);
  double zprob(int dimensions,double dist);
  map<int,double> dimmean,dimdev;
  vector<string> probes,samples;
  void normalizeValues(vector<double>& values);
  double multivariatePValue(const vector<double> testData,
    const vector<double>& means, const vector<double>& stdDevs, int totalRows);
  double stouffersZ(const vector<double> testData,
    const vector<double>& means, const vector<double>& stdDevs, int totalRows);
                
public:
  
  void processItemset(const itemset &);
  classifier();
  void train(double pVal, motifDataset*,int, XMotifMethods& methods,
             void (*)(const itemset&) = NULL, string xmotifFile = NULL);
  void print(ostream*);
  void load(string,motifDataset*);
  void save(string filename);
  classifier(string);
  vector<string> classify(motifDataset*);
  vector<string> classifyUsingUnitHypercube(motifDataset*);
  vector<string> classifyUsingMultivariateNormal(motifDataset*);
  vector<string> classifyUsingStouffers(motifDataset*);
  set<itemset> getMotifs();
};
#endif