itemset.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<map>
#include<vector>
#include<string>
#include<iostream>
#include<sstream>

#include "motifDataset.h"
using namespace std;

#ifndef ITEMSET
#define ITEMSET

struct ItemsetRange
{
  set<int> probes;
  map<int,double> high;
  map<int,double>       low;
  double pval;
};

class itemset
{
  friend class xmotif;
  friend class greedySetCover;
  friend class classifier;
  friend class itemsetEnrichment;

private:
  
  int id; // Used to identify this itemset.

  //stores the indices of columns and rows
  //so we dont have to work with strings
  vector<int> columns;
  vector<int> rows;
  
  vector<vector<double> > rowValues;
  // an itemset keeps track of whether it is in the classifier or not. 
  // this variable is useful when processing enrichments and building
  // the navigation HTML file.
  bool _inClassifier;

  bool _getInClassifier() const
    {
      return(_inClassifier);
    }
  void _setInClassifier()
    {
      _inClassifier = true;
    }
  void _unsetInClassifier()
    {
      _inClassifier = false;
    }
  
  const bool consumes(const itemset&) const;
  string mClass;
  vector<double> _mean;
  vector<double> _stddev;
  double pOfZ(double) const;
  int requiredIterations;
  double pval;


  //converts a T to a string
  template <class T> string toa(T in) const
    {
      stringstream ss;
      ss<<in;
      string out;
      ss>>out;
      return out;
    }
  
  
  
public:
  
  itemset()
    {
      _inClassifier = false;
          id = -1;
    }

  //  itemset(const itemset &itm);
  
  itemset(string line, const motifDataset* data);

  virtual ~itemset()
    {}

  void build(set<int> &D, ItemsetRange &G, motifDataset *dataset,
             int chosenClass);

  int size() const;
  bool operator<(const itemset &a) const;
  bool operator==(const itemset &a) const;

  string getClass() const {return mClass; };

  void getColumnSet(set< int > &columnSet) const;
  
  void getRowSet(set< int > &rowSet) const;

  void getRowNames(const motifDataset *data, set<string>& itemsetRows) const;
  

  //prints the itemset in Murali's standard format to standard out
  void print(const int itemsetnum,vector<string> probes,vector<string> samples, ostream*) const;        
  

  void save(ostream *out) const;
  void load(istream *in);
  
  vector<double> classify(motifDataset*) const;
  vector<double> classifyMedian(motifDataset*) const;

  int getId() const;
  void setId(int id);
};

#endif