def test_run(self):
'''
Make sure GA engine can run correctly.
'''
indv_template = GAIndividual(ranges=[(0, 10)],
encoding='binary',
eps=0.001)
population = GAPopulation(indv_template=indv_template, size=50).init()
# Create genetic operators.
selection = RouletteWheelSelection()
crossover = UniformCrossover(pc=0.8, pe=0.5)
mutation = FlipBitMutation(pm=0.1)
# Create genetic algorithm engine.
engine = GAEngine(population=population,
selection=selection,
crossover=crossover,
mutation=mutation)
@engine.fitness_register
def fitness(indv):
x, = indv.variants
return x + 10 * sin(5 * x) + 7 * cos(4 * x)
engine.run(50)
def get_w(alphas, dataset, labels):
''' 通过已知数据点和拉格朗日乘子获得分割超平面参数w
'''
alphas, dataset, labels = np.array(alphas), np.array(dataset), np.array(
labels)
yx = labels.reshape(1, -1).T * np.array([1, 1]) * dataset
w = np.dot(yx.T, alphas)
return w.tolist()
# Population definition.
indv_template = GAIndividual(ranges=[(-2, 2), (-2, 2), (-5, 5)],
encoding='binary',
eps=[0.001, 0.001, 0.005])
population = GAPopulation(indv_template=indv_template, size=600).init()
# Genetic operators.
selection = RouletteWheelSelection()
crossover = UniformCrossover(pc=0.8, pe=0.5)
mutation = FlipBitBigMutation(pm=0.1, pbm=0.55, alpha=0.6)
engine = GAEngine(population=population,
selection=selection,
crossover=crossover,
mutation=mutation,
analysis=[ConsoleOutput, FitnessStore])
# 加载数据
str_PC = float(sys.argv[6])
str_PM = float(sys.argv[7])
str_ng = int(sys.argv[8])
#str_THF_LB = 0.99
#str_THF_HB = 0.999
#str_TOL_LB = 0.90
#str_TOL_HB = 0.99
#str_P = 20
#str_PC = 0.8
#str_PM = 0.1
#str_ng = 2
# Define population.
indv_template = GAIndividual(ranges=[(str_THF_LB, str_THF_HB),
(str_TOL_LB, str_TOL_HB)],
encoding='binary',
eps=0.001)
population = GAPopulation(indv_template=indv_template, size=str_P).init()
# Create genetic operators.
selection = RouletteWheelSelection()
crossover = UniformCrossover(pc=str_PC, pe=0.5)
mutation = FlipBitMutation(pm=str_PM)
# Create genetic algorithm engine.
# Here we pass all built-in analysis to engine constructor.
engine = GAEngine(population=population,
selection=selection,
crossover=crossover,
mutation=mutation,
analysis=[ConsoleOutputAnalysis, FitnessStoreAnalysis])
from gaft import GAEngine
from gaft.components import GAIndividual
from gaft.components import GAPopulation
from gaft.operators import TournamentSelection
from gaft.operators import UniformCrossover
from gaft.operators import FlipBitMutation
# Analysis plugin base class.
from gaft.plugin_interfaces.analysis import OnTheFlyAnalysis
# Built-in best fitness analysis.
from gaft.analysis.fitness_store import FitnessStore
# Define population.
indv_template = GAIndividual(ranges=[(0, 10)], encoding='binary', eps=0.001)
population = GAPopulation(indv_template=indv_template, size=50).init()
# Create genetic operators.
selection = TournamentSelection()
crossover = UniformCrossover(pc=0.8, pe=0.5)
mutation = FlipBitMutation(pm=0.1)
# Create genetic algorithm engine.
engine = GAEngine(population=population, selection=selection,
crossover=crossover, mutation=mutation,
analysis=[FitnessStore])
# Define fitness function.
@engine.fitness_register
def fitness(indv):
length_part1 = int(np.floor(n * 0.5))
maxValue_part1=2**length_part1
length_part2=n-length_part1
maxValue_part2=2**length_part2
print('maxValue part1:',maxValue_part1)
print('maxValue part2:',maxValue_part2)
print('length part1 part2:',length_part1,length_part2)
ranges=[(0, maxValue_part1),(0,maxValue_part2)]
eps = [1, 1]
var1,var2,var_all=greedy_initialize_variants(n,edges,length_part1,length_part2,graph)
vars=[var1,var2]
merge_variants_to_state(vars, length_part1, length_part2, graph=graph, ranges=ranges, eps=eps)
merge_variants_to_state([var_all], n, 0, graph=graph, ranges=[(0,maxValue)], eps=[1])
indv_template = GAIndividual(ranges=ranges, encoding='binary', eps=eps)
indv_template.variants=[var1,var2]
indv_template.chromsome=indv_template.encode()
# var=greedy_initialize_one_variants(n,edges,graph)
# indv_template = GAIndividual(ranges=[(0, maxValue)], encoding='binary', eps=[1])
# indv_template.variants=[var]
# indv_template.chromsome=indv_template.encode()
#####################Initialize approach2##############################
indv_list=[]
for i in range(popsize):
indv_list.append(indv_template.clone())
pc = args.pc
pe = args.pe
pm = args.pm
numEpoch = args.numEpoch
rseed=args.rseed
npseed=args.npseed
tselect=args.tselect
random.seed(rseed)
np.random.seed(npseed)
inputdir= os.path.join(inputpath,filename)
n,edges,graph=construct_graph(inputdir)
maxValue = 2 ** n-1
indv_template = GAIndividual(ranges=[(0, maxValue)], encoding='binary', eps=[1])
population = GAPopulation(indv_template=indv_template, size=popsize).init()
# Create genetic operators.
# selection = TournamentSelection()#RouletteWheelSelection()
if tselect:
print('Tournament selection')
selection = TournamentSelection()
else:
print('RouletteWheelSelection')
selection = RouletteWheelSelection()
crossover = UniformCrossover(pc=pc, pe=pe)
mutation = FlipBitMutation(pm=pm)
# Create genetic algorithm engine.