Refiner.java

Go to the documentation of this file.

package crowdUser;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;
import java.util.*;

import ipeirotis.gal.scripts.DawidSkene;
import ipeirotis.gal.scripts.Labeling;



public class Refiner {

  00028   // Fields
  00030 
  private String[] columnsCSV;
  private Integer columnAxis;
  private Integer columnMedia1;
  private Integer columnMedia2;
  private Integer columnWorkerId;
  private Integer columnAnswer;
  private Map<String,Integer> compScores ;
  private List<String[]> data;

  
  00067   // Constructors
  00078   public Refiner (List<String> fields)
  {
        this.data = new ArrayList <String[]> ();
        getFields(fields);
  }
  
  00085   // Methods
  00087   
  
  private String signature(String axis, String idMedia1, String idMedia2)
  {
        String sig =  axis + "__" + idMedia1 + "__" + idMedia2;
        return sig;
  }
  

  private void getFields(List<String> csvFields)
  {
       this.columnsCSV = csvFields.toArray(new String[0]) ;
       Integer rank = 0;
       for (String field : csvFields)
            {
              if (field.equals("idMedia1") )
                    this.columnMedia1 = rank ;
              else if (field.equals("idMedia2") )
                    this.columnMedia2 = rank ;
              else if (field.equals("_worker_id") )
                    this.columnWorkerId = rank ;
              else if (field.equals("axis") )
                    this.columnAxis = rank ;
              else if (field.length() > 25 )
                    this.columnAnswer = rank ;
              rank ++ ;
            }
  }

  
 
  public void csv2List( String csvFile )
  {

      this.data.clear();
        try
        {
              // connecting to the .csv "database"
              Class.forName("org.relique.jdbc.csv.CsvDriver");
            Connection conCSV = DriverManager.getConnection("jdbc:relique:csv:" + "../data/HITresults/");
            Statement stmt = conCSV.createStatement();
            // creating and sending the query
            String queryCSV = "SELECT * FROM " + csvFile;
            ResultSet rs = stmt.executeQuery(queryCSV);
            // using the results
            while (rs.next())
            {
              List<String> request = new ArrayList<String>();
              for (int i=1; i<this.columnsCSV.length+1; i++)
                    request.add(rs.getString(i));
              this.data.add(request.toArray(new String[0]));
            }
              // closing everything
              rs.close();
              stmt.close();
              conCSV.close();
        }
        catch(Exception e)  { e.printStackTrace(); }
  }

  
  public void getanotherlabel(  )
  {
        // step 1: creation of the "files"
        String inputFile = generateInputFile() ;
        String correctFile = generateCorrectFile() ;
        String costFile = "1\t1\t0\n2\t2\t0\n1\t2\t1\n2\t1\t1" ;
        Integer iterations = 10 ;
        HashMap<String,String> posterior_voting = new HashMap <String,String>() ;
        List<String[]> newData = new ArrayList <String[]> () ;
        
        // step 2: get another label is called if their is enough HIT results (here, 10).
        if (this.data.size() > 10)
              try
              {   
                    // the content of this block is roughly a copy-pasta from "get another label" main method.
                    String[] lines_input = inputFile.split("\n");
                    Vector<Labeling> labelings = DawidSkene.loadLabels(lines_input);
                    String[] lines_correct = correctFile.split("\n");
                    Vector<Labeling> correct = DawidSkene.loadLabels(lines_correct);
                    String[] lines_cost = costFile.split("\n") ; 
                    Vector<Labeling> costs = DawidSkene.loadLabels(lines_cost);
                    DawidSkene ds = new DawidSkene(labelings, correct, costs);
                    ds.estimate(iterations);
                    ds.updateAnnotatorCosts();
                    posterior_voting = ds.getMajorityVote();
              }
              catch (Exception e) { e.printStackTrace(); }

        // step 2 (again): if their is not enough HIT results, raw results from the "correctFile" String are used directly.
        else
        {
              for (int i=0; i<this.data.size(); i++)
              {
                    String[] dataLine = this.data.get(i);
                    String sig = signature(dataLine[this.columnAxis], dataLine[this.columnMedia1], dataLine[this.columnMedia2]) ;
                    if (  this.compScores.get(sig) > 0)
                          posterior_voting.put(sig, "1");
                    else
                          posterior_voting.put(sig, "2");
              }     
        }
        
        // Step 3: The refined results are put in the "data" attribute
        for (int i=0; i<this.data.size(); i++)
        {
              List<String> newEntry = new ArrayList <String> () ;
              String sigComparisonStudied = signature( this.data.get(i)[this.columnAxis] , 
                              this.data.get(i)[this.columnMedia1] , this.data.get(i)[this.columnMedia2]);
              newEntry.add(this.data.get(i)[this.columnAxis]);
              newEntry.add(this.data.get(i)[this.columnMedia1]);
              newEntry.add(this.data.get(i)[this.columnMedia2]);
              newEntry.add ( posterior_voting.get(sigComparisonStudied) ) ;
              newData.add(newEntry.toArray(new String[0]));
        }
        this.data = newData ;  
  }


  
  private String generateCorrectFile()
  {
        String correctFile = "" ;
        try
        {
              String line;
              for (int i=0; i<this.data.size(); i++)
              {
                    String[] dataLine = this.data.get(i);
                    String sig = signature(dataLine[this.columnAxis], dataLine[this.columnMedia1], dataLine[this.columnMedia2]) ;
                    line = dataLine[this.columnWorkerId] + "\t" + sig + "\t" ;
                    if (  this.compScores.get(sig) > 0)
                          line += "1";
                    else
                          line += "2";
                    correctFile += line+"\n";  
              }
        }
        catch (Exception e) { e.printStackTrace(); }
        return correctFile ;
  }


  private String generateInputFile()
  {
        String inputFile = "";
        this.compScores = new Hashtable <String,Integer> () ;
        try{
              String line;
              for (int i=0; i<this.data.size(); i++)
              {
                    String[] dataLine = this.data.get(i);
                    String sig = signature(dataLine[this.columnAxis], dataLine[this.columnMedia1], dataLine[this.columnMedia2]) ;
                  
                    // storing the results for future retrieval
                    if (dataLine[this.columnAnswer].equals("Media 1"))
                          if (this.compScores.containsKey(sig))
                                this.compScores.put(sig, this.compScores.get(sig) + 1) ;
                          else
                                this.compScores.put(sig, 1);
                    else
                          if (this.compScores.containsKey(sig))
                                this.compScores.put(sig, this.compScores.get(sig) - 1) ;
                          else
                                this.compScores.put(sig, -1);
                    
                    // writing the "input file"
                    line = dataLine[this.columnWorkerId] + "\t" + sig + "\t" ;
                    if (dataLine[this.columnAnswer].equals("Media 1"))
                          line += "1";
                    else
                          line += "2";
                    inputFile += line + "\n";
              }
        }
        catch (Exception e) { e.printStackTrace(); }
        return inputFile ;
  }


  public List<String[]> getData()
  {
        return this.data ;
  }
}