Gga4r, General Genetic Algorithms for Ruby

Introduction

General Genetic Algorithms for Ruby is a Ruby Genetic Algorithm so simple to use:

  1. Take a class to evolve it and define fitness, recombine and mutate methods.
    
    	class StringPopulation < Array
    	    def fitness
    	      self.select { |pos| pos == 1 }.size.to_f / self.size.to_f
    	    end
    	
    	    def recombine(c2)
    	      cross_point = (rand * c2.size).to_i
    	      c1_a, c1_b = self.separate(cross_point)
    	      c2_a, c2_b = c2.separate(cross_point)
    	      [StringPopulation.new(c1_a + c2_b),
    	       StringPopulation.new(c2_a + c1_b)]
    	    end
    	
    	    def mutate
    	      mutate_point = (rand * self.size).to_i
    	      self[mutate_point] = 1
    	    end
    	end
    
  2. Create a GeneticAlgorithm object with the population.
    
        def create_population_with_fit_all_1s(s_long = 10, num = 10)
            population = []
            num.times  do
                chromosome = StringPopulation.new( Array.new(s_long).collect \
                                                    { (rand > 0.2) ? 0:1 } )
                population << chromosome
            end
            population
        end
    
        ga = GeneticAlgorithm.new(create_population_with_fit_all_1s)
    
  3. Call evolve method as many times as you want and see the best evolution.
    
    	100.times { |i|  ga.evolve }
    	p ga.best_fit[0]
    

Install

  1. Execute:
    
    	gem install gga4r
    
  2. Add require in your code headers:
    
    	require "rubygems"
    	require "gga4r"
    

Attention

Please note that Gga4r adds shuffle!, each_pair and separate methods to the Array class.

Documentation

Documentation can be readed online in gga4r rdoc or generated using rdoc tool under the source code with:


  rdoc README lib

Contributing

gga4r developer loves beer, if this library has been useful for you or you want to support it, invite him a beer!

Beer 2€

Copying

This work is developed by Sergio Espeja ( sergio.espeja [you_know] gmail.com ) mainly in Institut Universitari de Lingüística Aplicada of Universitat Pompeu Fabra ( www.iula.upf.es ) supported by Núria Bel, and also in bee.com.es ( bee.com.es ).

It is free software, and may be redistributed under GPL license.

validate XHTML