def gaVRPTW(pop,
instName,
unitCost,
initCost,
waitCost,
delayCost,
indSize,
popSize,
cxPb,
mutPb,
NGen,
exportCSV=False,
customizeData=False):
if customizeData:
jsonDataDir = os.path.join('data', 'json_customize')
else:
jsonDataDir = os.path.join('data', 'json')
jsonFile = os.path.join(jsonDataDir, '%s.json' % instName)
with open(jsonFile) as f:
instance = load(f)
# Operator registering
toolbox.register('evaluate',
core.evalVRPTW,
instance=instance,
unitCost=unitCost,
initCost=initCost,
waitCost=waitCost,
delayCost=delayCost)
toolbox.register('select', tools.selRoulette)
toolbox.register('mate', core.cxPartialyMatched)
toolbox.register('mutate', core.mutInverseIndexes)
pop = pop
print pop
# Results holders for exporting results to CSV file
csvData = []
print 'Start of evolution'
# Evaluate the entire population
fitnesses = list(toolbox.map(toolbox.evaluate, pop))
for ind, fit in zip(pop, fitnesses):
ind.fitness.values = fit
# Debug, suppress print()
# print ' Evaluated %d individuals' % len(pop)
# Begin the evolution
for g in range(NGen):
# print '-- Generation %d --' % g
# Select the next generation individuals
# Select elite - the best offspring, keep this past crossover/mutate
elite = tools.selBest(pop, 1)
# Keep top 10% of all offspring
# Roulette select the rest 90% of offsprings
offspring = tools.selBest(pop, int(numpy.ceil(len(pop) * 0.1)))
offspringRoulette = toolbox.select(
pop,
int(numpy.floor(len(pop) * 0.9)) - 1)
offspring.extend(offspringRoulette)
# Clone the selected individuals
offspring = list(toolbox.map(toolbox.clone, offspring))
# Apply crossover and mutation on the offspring
for child1, child2 in zip(offspring[::2], offspring[1::2]):
if random.random() < cxPb:
toolbox.mate(child1, child2)
del child1.fitness.values
del child2.fitness.values
for mutant in offspring:
if random.random() < mutPb:
toolbox.mutate(mutant)
del mutant.fitness.values
# Evaluate the individuals with an invalid fitness
invalidInd = [ind for ind in offspring if not ind.fitness.valid]
fitnesses = toolbox.map(toolbox.evaluate, invalidInd)
for ind, fit in zip(invalidInd, fitnesses):
ind.fitness.values = fit
# Debug, suppress print()
# print ' Evaluated %d individuals' % len(invalidInd)
# The population is entirely replaced by the offspring
offspring.extend(elite)
pop[:] = offspring
# Gather all the fitnesses in one list and print the stats
fits = [ind.fitness.values[0] for ind in pop]
length = len(pop)
mean = sum(fits) / length
sum2 = sum(x * x for x in fits)
std = abs(sum2 / length - mean**2)**0.5
# Debug, suppress print()
# print ' Min %s' % min(fits)
# print ' Max %s' % max(fits)
# print ' Avg %s' % mean
# print ' Std %s' % std
# Write data to holders for exporting results to CSV file
if exportCSV:
csvRow = {
'generation': g,
'evaluated_individuals': len(invalidInd),
'min_fitness': min(fits),
'max_fitness': max(fits),
'avg_fitness': mean,
'std_fitness': std,
'avg_cost': 1 / mean,
}
csvData.append(csvRow)
print '-- End of (successful) evolution --'
bestInd = tools.selBest(pop, 1)[0]
print 'Best individual: %s' % bestInd
print 'Fitness: %s' % bestInd.fitness.values[0]
core.printRoute(core.ind2route(bestInd, instance))
print 'Total cost: %s' % (1 / bestInd.fitness.values[0])
if exportCSV:
csvFilename = '%s_uC%s_iC%s_wC%s_dC%s_iS%s_pS%s_cP%s_mP%s_nG%s.csv' % (
instName, unitCost, initCost, waitCost, delayCost, indSize,
popSize, cxPb, mutPb, NGen)
csvPathname = os.path.join('results', csvFilename)
print 'Write to file: %s' % csvPathname
utils.makeDirsForFile(pathname=csvPathname)
if not utils.exist(pathname=csvPathname, overwrite=True):
with open(csvPathname, 'w') as f:
fieldnames = [
'generation', 'evaluated_individuals', 'min_fitness',
'max_fitness', 'avg_fitness', 'std_fitness', 'avg_cost'
]
writer = DictWriter(f, fieldnames=fieldnames, dialect='excel')
writer.writeheader()
for csvRow in csvData:
writer.writerow(csvRow)
return core.ind2route(bestInd, instance)
toolbox.register('population', tools.initRepeat, list, toolbox.individual)
toolbox.register('select', tools.selRoulette)
toolbox.register('evaluate',
evalVRPTW,
instance=instance,
unitCost=1.0,
initCost=0)
optimalRoute = [[21, 31, 19, 17, 13, 7, 26], [12, 1, 16, 30], [27, 24],
[29, 18, 8, 9, 22, 15, 10, 25, 5, 20],
[14, 28, 11, 4, 23, 3, 2, 6]]
individual2 = [
5, 10, 15, 22, 9, 11, 28, 18, 6, 3, 2, 17, 19, 31, 21, 13, 23, 4, 8, 29,
27, 14, 24, 30, 16, 12, 1, 7, 26, 25, 20
]
route2 = ind2route(individual2, instance)
individual = [
21, 31, 19, 17, 13, 7, 26, 12, 1, 16, 30, 27, 24, 29, 18, 8, 9, 22, 15, 10,
25, 5, 20, 14, 28, 11, 4, 23, 3, 2, 6
]
route = ind2route(individual, instance)
utils.visualizeRoutes(instName, instance, optimalRoute)
# Due to the way EvalVRP is written, a vehicle needs to exceed max capacity before
# starting a new vehicle. The optimal route leaves certain vehicles below capacity
# and therefore gives even more optimal (smaller) costs
# The optimal cost of this route in literature is 784
# My evalVRP code reads this route's cost as 1030