readfile.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<string>
#include<iostream>
#include<fstream>
#include<vector>
#include<map>
#include<sstream>
#include<set>
#include "setTemplates.C"
#include "motifDataset.h"
using namespace std;

#ifndef READFILE_MOTIFDATASETGREG
#define READFILE_MOTIFDATASETGREG

class readfile : public motifDataset
{
private:
  
  string filename;
  vector<string> columnToName,rowToName,columnToNameLO;
  map<string,int> nameToColumn,nameToRow,nameToColumnLO;
  vector<vector<double> > data, dataLO;
  vector<vector<bool> > mExists,mExistsLO;
  vector<vector<int> > mClassToExperiments;
  vector<vector<int> > mExperimentsToClass;
  vector<string> classLabels;
  string classString;

  void doRead(string infile);
  void readClasses();
  double atod(string in);

public:
  static const int MISSING_VALUE;

  readfile(set<int>,string,string);
  readfile(const readfile& in);

  virtual void readProbeAliases(string aliasFile);

  virtual void readProbeInfo(string infoFile);


  
  void refactor(set<int> leaveOut);

  virtual bool isProbe(string id) const;
  
  virtual vector<string>* probes();
  virtual vector<string>* samples();
  virtual double operator()(int,int);
  virtual double operator()(string,string);
  virtual bool exists(int,int);
  virtual bool exists(string,string);
  virtual vector<vector<int> >* classToExperiments();
  virtual vector<vector<int> >* experimentsToClass();
//  virtual vector<string>* classes() const;                            

  virtual string computeClassNameForSamples(const set< int > &columnSet, double frac = 1) const;

  virtual int computeClassIndexForSamples(const set< int > &columnSet, double frac = 1) const;

  virtual string getClassNameForSample(unsigned int index) const;

  virtual unsigned int getClassIndexForSample(unsigned int index) const;

  virtual string getClassName(unsigned int index) const;

  virtual unsigned int getClassSize(unsigned int index) const;

  virtual unsigned int getNumClasses() const
    {
      return(classLabels.size());
    }
        
  
  virtual int getColumnIndex(string name) const;

  virtual int getRowIndex(string name) const;

  virtual string getRowName(unsigned int index) const;


};

#endif