def evaluate(particle):
# Find all selected features
indices = [index for index, entry in enumerate(particle) if entry == 1.0]
# Build new dataset with selected features
src_feature = Core.src_feature[:, indices]
tarU_feature = Core.tarU_feature[:, indices]
tarL_feature = Core.tarL_feature[:, indices]
if SUPERVISED:
return FitnessFunction.fitness_function(src_feature=src_feature, src_label=Core.src_label,
tarU_feature=tarU_feature,
classifier=Core.classifier,
tarL_feature=tarL_feature, tarL_label=Core.tarL_label)
else:
return FitnessFunction.fitness_function(src_feature=src_feature, src_label=Core.src_label,
tarU_feature=tarU_feature,
classifier=Core.classifier)
def evaluate(individual):
for sub_ind in individual:
if sub_ind.height > MAX_DEPTH:
print("Too high in GP: "+individual.height)
funcs = [toolbox.compile(expr=tree) for tree in individual]
src_feature = GPUtility.buildNewFeatures(Core.src_feature, funcs)
tarU_feature = GPUtility.buildNewFeatures(Core.tarU_feature, funcs)
tarL_feature = GPUtility.buildNewFeatures(Core.tarL_feature, funcs)
if SUPERVISED:
return FitnessFunction.fitness_function(src_feature=src_feature, src_label=Core.src_label,
tarU_feature=tarU_feature, tarU_soft_label= Core.tarU_soft_label,
classifier=Core.classifier,
tarL_feature=tarL_feature, tarL_label=Core.tarL_label),
else:
return FitnessFunction.fitness_function(src_feature=src_feature, src_label=Core.src_label,
tarU_feature=tarU_feature, tarU_soft_label=Core.tarU_soft_label,
classifier=Core.classifier),
def evaluate(particle):
A = np.copy(particle)
A = np.reshape(A, (Core.A_row, Core.A_col))
return Fitness.fitness_function(A),
def evaluate(particle):
beta = np.copy(particle)
beta = np.reshape(beta, (len(Core.Xs) + len(Core.Xt), Core.C))
fitness = FitnessFunction.fitness_function(beta)
return fitness,
def main(args):
global i_stick, i_pbest, i_gbest, ustks, SUPERVISED
run_index = int(args[0])
random.seed(1617 ** 2 * run_index)
filename = "iteration"+str(args[0])+".txt"
file = open(filename, 'w+')
time_start = time.clock()
SUPERVISED = False
#supervised = int(args[1])
#if supervised == 0:
# SUPERVISED = False
#else:
# SUPERVISED = True
cond_index = int(args[1])
FitnessFunction.tarVersion = cond_index
#setWeight()
#FitnessFunction.setWeight(Core.src_feature, Core.src_label, Core.tarU_feature, Core.tarU_soft_label)
# Set the weight for each components in the fitness function
#FitnessFunction.setWeight(src_feature=Core.src_feature, src_label=Core.src_label,
# tarU_feature=Core.tarU_feature, tarU_label=Core.tarU_soft_label)
FitnessFunction.srcWeight = 0.0
FitnessFunction.margWeight = 1.0
FitnessFunction.tarWeight = 0.0
# Initialize population and the gbest
pop = toolbox.population(n=NPART)
best = None
toWrite = ("Supervised: %r \n" \
"Source weight: %f\n" \
"Diff source and target weight: %f\n" \
"Target weight: %g\n" \
"Conditional version: %d\n" % (SUPERVISED,
FitnessFunction.srcWeight,
FitnessFunction.margWeight,
FitnessFunction.tarWeight,
FitnessFunction.tarVersion))
for g in range(NGEN):
print(g)
toWrite += ("=====Gen %d=====\n" % g)
for part in pop:
# Evaluate all particles
part.fitness.values = toolbox.evaluate(part)
if part.best is None or part.best.fitness < part.fitness:
part.best = creator.Particle(part)
part.best.fitness.values = part.fitness.values
# update gbest
if best is None or best.fitness < part.fitness:
best = creator.Particle(part)
best.fitness.values = part.fitness.values
if TEST:
print("is=", i_stick, "ip=", i_pbest, "ig=", i_gbest, "ustks=", ustks )
print("best=", best)
print(best.fitness.values)
print("\n")
for i, part in enumerate(pop):
print("Particle %d: " % i)
print("Particle position:",part)
print("Particle pbest:",part.best)
print("Particle stickiness:",part.stk)
print("\n")
# now update the position of each particle
for part in pop:
toolbox.update(part, best)
# Gather all the fitness components of the gbest and print the stats
indices = [index for index, entry in enumerate(best) if entry == 1.0]
src_feature = Core.src_feature[:, indices]
tarU_feature = Core.tarU_feature[:, indices]
tarL_feature = Core.tarL_feature[:, indices]
if SUPERVISED:
src_err, diff_marg, tar_err = FitnessFunction.domain_differece(src_feature=src_feature, src_label=Core.src_label,
classifier=Core.classifier,
tarU_feature=tarU_feature,
tarL_feature=tarL_feature, tarL_label=Core.tarL_label)
else:
src_err, diff_marg, tar_err = FitnessFunction.domain_differece(src_feature=src_feature, src_label=Core.src_label,
classifier=Core.classifier,
tarU_feature=tarU_feature)
toWrite += (" Source Error: %f \n Diff Marg: %f \n Target Error: %f \n" %(src_err, diff_marg, tar_err))
toWrite += (" Fitness function of real best: %f\n" % best.fitness.values[0])
acc = 1.0 - FitnessFunction.classification_error(training_feature=src_feature, training_label=Core.src_label,
classifier=Core.classifier,
testing_feature=tarU_feature, testing_label=Core.tarU_label)
toWrite += (" Accuracy on unlabel target: " + str(acc) + "\n")
toWrite += " Position:"+str(best)+"\n"
# update the parameters
i_stick = is_up - (is_up - is_low)*(g+1)/NGEN
i_gbest = (1-i_stick)/(pg_rate+1)
i_pbest = pg_rate*i_gbest
ustks = ustks_low + (ustks_up-ustks_low)*(g+1)/NGEN
# Update the pseudo label (only when the cond_index is equal to 2)
if cond_index == 3 & g % 10==0:
Core.classifier.fit(src_feature, Core.src_label)
Core.tarU_soft_label = Core.classifier.predict(tarU_feature)
FitnessFunction.set_weight(src_feature, Core.src_label, tarU_feature, Core.tarU_soft_label)
# Need to update the fitness value of best and pbest again
best.fitness.values = FitnessFunction.fitness_function(src_feature, Core.src_label,
tarU_feature, Core.tarU_soft_label,
Core.classifier),
for part in pop:
indices = [index for index, entry in enumerate(part.best) if entry == 1.0]
p_src_feature = Core.src_feature[:, indices]
p_tarU_feature = Core.tarU_feature[:, indices]
part.best.fitness.values = FitnessFunction.fitness_function(p_src_feature, Core.src_label,
p_tarU_feature, Core.tarU_soft_label,
Core.classifier),
time_elapsed = (time.clock() - time_start)
toWrite += "----Final -----\n"
indices = [index for index, entry in enumerate(best) if entry == 1.0]
src_feature = Core.src_feature[:, indices]
tarU_feature = Core.tarU_feature[:, indices]
acc = 1.0 - FitnessFunction.classification_error(training_feature=src_feature, training_label=Core.src_label,
classifier=Core.classifier,
testing_feature=tarU_feature, testing_label=Core.tarU_label)
toWrite += ("Accuracy on unlabel target: " + str(acc) + "\n")
toWrite += ("Accuracy on the target (No TL): %f\n" % (
1.0 - FitnessFunction.classification_error(training_feature=Core.src_feature, training_label=Core.src_label,
classifier=Core.classifier,
testing_feature=Core.tarU_feature, testing_label=Core.tarU_label)))
toWrite += ("Computation time: %f\n" % time_elapsed)
toWrite += ("Number of features: %d\n" % len(indices))
toWrite += str(best)
file.write(toWrite)
file.close()
