paulin/EasyGA
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Initialization for GA with arguments

Browse Source
This commit is contained in:
SimpleArt
2020-10-30 11:52:11 -04:00
parent 2d91037cdf
commit c9d30be1af
3 changed files with 142 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
src/EasyGA.py
View File

@ -22,8 +22,66 @@ from attributes import attributes
class GA(attributes):
# Inhert all the ga attributes from the attributes class.
def __init__(self):
super(GA, self).__init__()
def __init__(self,
chromosome_length = None,
population_size = None,
chromosome_impl = None,
gene_impl = None,
population = None,
target_fitness_type = None,
update_fitness = None,
parent_ratio = None,
selection_probability = None,
tournament_size_ratio = None,
current_generation = None,
current_fitness = None,
generation_goal = None,
fitness_goal = None,
chromosome_mutation_rate = None,
gene_mutation_rate = None,
initialization_impl = None,
fitness_function_impl = None,
make_population = None,
make_chromosome = None,
make_gene = None,
parent_selection_impl = None,
crossover_individual_impl = None,
crossover_population_impl = None,
survivor_selection_impl = None,
mutation_individual_impl = None,
mutation_population_impl = None,
termination_impl = None
):
super(GA, self).__init__(
chromosome_length,
population_size,
chromosome_impl,
gene_impl,
population,
target_fitness_type,
update_fitness,
parent_ratio,
selection_probability,
tournament_size_ratio,
current_generation,
current_fitness,
generation_goal,
fitness_goal,
chromosome_mutation_rate,
gene_mutation_rate,
initialization_impl,
fitness_function_impl,
make_population,
make_chromosome,
make_gene,
parent_selection_impl,
crossover_individual_impl,
crossover_population_impl,
survivor_selection_impl,
mutation_individual_impl,
mutation_population_impl,
termination_impl
)
def evolve_generation(self, number_of_generations = 1, consider_termination = True):

87
src/attributes.py
View File

@ -21,50 +21,79 @@ from crossover import Crossover_Methods
class attributes:
"""SAMPLE TEXT"""
def __init__(self):
def __init__(self,
chromosome_length,
population_size,
chromosome_impl,
gene_impl,
population,
target_fitness_type,
update_fitness,
parent_ratio,
selection_probability,
tournament_size_ratio,
current_generation,
current_fitness,
generation_goal,
fitness_goal,
chromosome_mutation_rate,
gene_mutation_rate,
initialization_impl,
fitness_function_impl,
make_population,
make_chromosome,
make_gene,
parent_selection_impl,
crossover_individual_impl,
crossover_population_impl,
survivor_selection_impl,
mutation_individual_impl,
mutation_population_impl,
termination_impl
):
"""Initialize the GA."""
# Initilization variables
self.chromosome_length = 10
self.population_size = 10
self.chromosome_impl = None
self.gene_impl = lambda: random.randint(1, 10)
self.population = None
self.target_fitness_type = 'max'
self.update_fitness = True
self.chromosome_length = 10 if chromosome_length is None else chromosome_length
self.population_size = 10 if population_size is None else population_size
self.chromosome_impl = chromosome_impl
self.gene_impl = gene_impl
self.population = population
self.target_fitness_type = 'max' if target_fitness_type is None else target_fitness_type
self.update_fitness = True if update_fitness is None else update_fitness
# Selection variables
self.parent_ratio = 0.1
self.selection_probability = 0.75
self.tournament_size_ratio = 0.1
self.parent_ratio = 0.10 if parent_ratio is None else parent_ratio
self.selection_probability = 0.75 if selection_probability is None else selection_probability
self.tournament_size_ratio = 0.10 if tournament_size_ratio is None else tournament_size_ratio
# Termination variables
self.current_generation = 0
self.current_fitness = 0
self.generation_goal = 15
self.fitness_goal = None
self.current_generation = 0 if current_generation is None else current_generation
self.current_fitness = 0 if current_fitness is None else current_fitness
self.generation_goal = 15 if generation_goal is None else generation_goal
self.fitness_goal = fitness_goal
# Mutation variables
self.chromosome_mutation_rate = 0.10
self.gene_mutation_rate = 0.01
self.chromosome_mutation_rate = 0.15 if chromosome_mutation_rate is None else chromosome_mutation_rate
self.gene_mutation_rate = 0.03 if gene_mutation_rate is None else gene_mutation_rate
# Default EasyGA implimentation structure
self.initialization_impl = Initialization_Methods.random_initialization
self.fitness_function_impl = Fitness_Examples.is_it_5
self.make_population = create_population
self.make_chromosome = create_chromosome
self.make_gene = create_gene
self.initialization_impl = Initialization_Methods.random_initialization if initialization_impl is None else initialization_impl
self.fitness_function_impl = Fitness_Examples.is_it_5 if fitness_function_impl is None else fitness_function_impl
self.make_population = create_population if create_population is None else create_population
self.make_chromosome = create_chromosome if create_chromosome is None else create_chromosome
self.make_gene = create_gene if create_gene is None else create_gene
# Methods for accomplishing Parent-Selection -> Crossover -> Survivor_Selection -> Mutation
self.parent_selection_impl = Parent_Selection.Rank.tournament
self.crossover_individual_impl = Crossover_Methods.Individual.single_point
self.crossover_population_impl = Crossover_Methods.Population.sequential_selection
self.survivor_selection_impl = Survivor_Selection.fill_in_best
self.mutation_individual_impl = Mutation_Methods.Individual.single_gene
self.mutation_population_impl = Mutation_Methods.Population.random_selection
self.parent_selection_impl = Parent_Selection.Rank.tournament if parent_selection_impl is None else parent_selection_impl
self.crossover_individual_impl = Crossover_Methods.Individual.single_point if crossover_individual_impl is None else crossover_individual_impl
self.crossover_population_impl = Crossover_Methods.Population.sequential_selection if crossover_population_impl is None else crossover_population_impl
self.survivor_selection_impl = Survivor_Selection.fill_in_best if survivor_selection_impl is None else survivor_selection_impl
self.mutation_individual_impl = Mutation_Methods.Individual.single_gene if mutation_individual_impl is None else mutation_individual_impl
self.mutation_population_impl = Mutation_Methods.Population.random_selection if mutation_population_impl is None else mutation_population_impl
# The type of termination to impliment
self.termination_impl = Termination_Methods.fitness_and_generation_based
self.termination_impl = Termination_Methods.fitness_and_generation_based if termination_impl is None else termination_impl
# Getter and setters for all varibles

47
src/run_testing.py
View File

@ -2,30 +2,31 @@ import random
import EasyGA
# Create the Genetic algorithm
ga = EasyGA.GA()
# Reproduce 30% of the population.
# Mutate 20% of the population.
# Mutate 3% of the genes in each mutated chromosome.
ga.parent_ratio = 0.30
ga.chromosome_mutation_rate = 0.20
ga.gene_mutation_rate = 0.03
# Create 25 chromosomes each with 10 genes
ga.population_size = 100
ga.chromosome_length = 25
# Create random genes from 0 to 10
ga.gene_impl = lambda: random.randint(0, 10)
# Minimize the sum of the genes
ga.fitness_function_impl = lambda chromosome: sum(gene.get_value() for gene in chromosome.get_gene_list())
ga.target_fitness_type = 'min'
# Terminate when a chromosome has all 0's
ga.fitness_goal = 0
ga.generation_goal = 150
# Reproduce 30% of the population.
# Mutate 20% of the population.
# Mutate 3% of the genes in each mutated chromosome.
#
# Create 25 chromosomes each with 10 genes
# Create random genes from 0 to 10
#
# Minimize the sum of the genes
# Terminate when a chromosome has all 0's
# or 150 generations pass
#
ga = EasyGA.GA(
parent_ratio = 0.30,
chromosome_mutation_rate = 0.20,
gene_mutation_rate = 0.03,
population_size = 100,
chromosome_length = 25,
gene_impl = lambda: random.randint(0, 10),
fitness_function_impl = lambda chromosome: sum(gene.get_value() for gene in chromosome.get_gene_list()),
target_fitness_type = 'min',
fitness_goal = 0,
generation_goal = 150
)
# Run 10 generations at a time
while ga.active():
ga.evolve_generation(10)
ga.print_generation()