'\nDeseja executar diversas vezes com esse parametros para obter estatisticas? (s/n)\n',
's', 'n')
if multipleExecutions:
n = readIntMin('Numero de execucoes do algoritmo: ', 1)
itCountList = []
itFitnnesList = []
itAvgBestFitnessList = []
didtnMakeIt = 0
print('\nExecutando...')
nextPoint = 0
start = time.time()
for i in range(n):
population = []
for j in range(popSize):
population.append(BinaryString.newRandom(zero.size))
[
population, bestGene, bestFitness, lastFitnessList,
lastBestGeneIndex, generationCount, avgFitnessList, bestFitnessList
] = geneticAlgorithm(population, maxIt, rouletteWheelSelection,
crossover2by2, mutate, fitnessCalculation,
equalsZero, newFitnessIsBetter)
if bestFitness != 12:
didtnMakeIt += 1
itAvgBestFitnessList.append(
sum(bestFitnessList) / len(bestFitnessList))
itFitnnesList.append(bestFitness)
itCountList.append(generationCount)
if multipleExecutions:
n = readIntMin('Numero de execucoes do algoritmo: ', 1)
itCountList = []
itAvgBestFitnessList = []
itFitnnesList = []
bestGeneAmongIts = BinaryString([0,1,0,1])
bestFitnessAmongIts = float('inf')
gotToLimitIt = 0
print('\nExecutando...')
start = time.time()
nextPoint = 0
for i in range(n):
population = []
for j in range(popSize):
population.append(BinaryString.newRandom(stringSize))
[population, bestGene, bestFitness, lastFitnessList, lastBestGeneIndex, generationCount, avgFitnessList, bestFitnessList] = geneticAlgorithm(population, maxIt,rouletteWheelSelection, crossover2by2, mutate, populationFitnessCalculation, shouldStop, newFitnessIsBetter, maxItNoImprove)
itCountList.append(generationCount)
itFitnnesList.append(bestFitness)
itAvgBestFitnessList.append(sum(bestFitnessList)/len(bestFitnessList))
if generationCount >= maxIt:
gotToLimitIt += 1
if newFitnessIsBetter(bestFitnessAmongIts, bestFitness):
bestFitnessAmongIts = bestFitness
bestGeneAmongIts = bestGene
prct = float(i)/n
if(prct >= nextPoint):
