chavalitros
/
MH-P2
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix uniform crossover function

This commit is contained in:
coolneng 2021-06-20 18:04:23 +02:00
parent 046b1a043a
commit 5f89731f77
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 22 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
src/genetic_algorithm.py
View File

@ -5,6 +5,7 @@ from math import ceil
from functools import partial from functools import partial
from multiprocessing import Pool from multiprocessing import Pool
from copy import deepcopy from copy import deepcopy
from itertools import chain, repeat
from preprocessing import parse_file from preprocessing import parse_file
@ -130,12 +131,15 @@ def position_crossover(parents, m):
def crossover(mode, parents, m): def crossover(mode, parents, m):
split_parents = zip(*[iter(parents)] * 2) split_parents = list(zip(*[iter(parents)] * 2))
offspring = []
if mode == "uniform": if mode == "uniform":
crossover_func = partial(uniform_crossover, m=m) for i in range(len(split_parents)):
offspring.append(uniform_crossover(split_parents[i], m))
offspring.append(uniform_crossover(split_parents[i], m))
else: else:
crossover_func = partial(position_crossover, m=m) crossover_func = partial(position_crossover, m=m)
offspring = [*map(crossover_func, split_parents)] offspring = [*map(crossover_func, split_parents)]
return offspring return offspring
@ -211,18 +215,26 @@ def get_best_elements(population):
def get_worst_elements(population): def get_worst_elements(population):
first_index = population.index(min(population, key=lambda x: all(x.fitness))) select_population = deepcopy(population)
population.pop(first_index) first_element = min(select_population, key=lambda x: x.fitness.values[0])
second_index = population.index(min(population, key=lambda x: all(x.fitness))) first_index = get_individual_index(first_element, select_population)
select_population.pop(first_index)
second_element = min(select_population, key=lambda x: x.fitness.values[0])
second_index = get_individual_index(second_element, select_population)
return first_index, second_index return first_index, second_index
def stationary_replacement(prev_population, current_population): def stationary_replacement(prev_population, current_population):
new_population = prev_population new_population = prev_population
worst_indexes = get_worst_elements(prev_population) first_worst, second_worst = get_worst_elements(prev_population)
best_indexes = get_best_elements(current_population) first_best, second_best = get_best_elements(current_population)
worst_indexes = [first_worst, second_worst]
best_indexes = [first_best, second_best]
for worst, best in zip(worst_indexes, best_indexes): for worst, best in zip(worst_indexes, best_indexes):
if current_population[best].fitness > prev_population[worst].fitness: if (
current_population[best].fitness.values[0]
> prev_population[worst].fitness.values[0]
):
new_population[worst] = current_population[best] new_population[worst] = current_population[best]
return new_population return new_population
@ -276,5 +288,5 @@ genetic_algorithm(
data=data, data=data,
select_mode="generational", select_mode="generational",
crossover_mode="uniform", crossover_mode="uniform",
max_iterations=1, max_iterations=10,
) )