FitnessMeasuresComp

%%%%%%%%%%%%%%%  COMPUTATION OF FITNESS RELATED MEASURES %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 EXAMPLE 1: From the results of an EDA run with default parameters, different measures describing
            the behavior of the algorithm are computed and graphs are
            displayed

0001 
0002 %%%%%%%%%%%%%%%%  COMPUTATION OF FITNESS RELATED MEASURES %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
0003 % EXAMPLE 1: From the results of an EDA run with default parameters, different measures describing
0004 %            the behavior of the algorithm are computed and graphs are
0005 %            displayed
0006 
0007   PopSize = 300; n = 45; cache  = [1,1,1,1,1]; Card = 2*ones(1,n); edaparams = {};
0008   F = 'sum'; % Onemax function;
0009   ngen = 10;
0010   edaparams{1} = {'stop_cond_method','max_gen',{ngen}};
0011   [AllStat,Cache]=RunEDA(PopSize,n,F,Card,cache,edaparams) 
0012    for i=1:ngen,
0013      auxr{1,i} = Cache{4,i};
0014      auxs{1,i} = Cache{5,i};
0015    end,
0016    
0017   [mean_obj,var_obj] = Mean_Var_Objectives(auxr); % Mean and variance of objectives
0018   [RS] = Response_to_selection(auxr);             % Response to selection
0019   [S] = Amount_of_selection(auxr,auxs);           % Amount of selection
0020   [b] = Realized_heritability(auxr,auxs);         % Realized heritability
0021   ObjectiveDistribution(auxr,1,[1:ngen]);         % Histogram of the objective distribution
0022  
0023   
0024  Inds = Cache{1,1}; 
0025  Inds_sel = Cache{2,1}; 
0026  S_H_pop = Individuals_entropy(Inds,Card,1);      % Accumulated entropy of variables in the first population
0027  S_H_sel = Individuals_entropy(Inds_sel,Card,1);  % Accumulated entropy of variables in the first selected population
0028  for i=1:ngen
0029    inds_gens{i}=Cache{1,i};
0030  end
0031  H_gens = Generations_entropy(inds_gens,Card,1);  % Accumulated entropy of variables at each generation
0032 
0033  X = [1:ngen]
0034  plot(X,H_gens);