def main():
filename = './origin_data/bugreports.xml'
path = './bug_reports'
bugslist = utils.read_xml(filename)
# print(bugslist)
label = utils.read_label('./origin_data/goldset.txt')
# print(label)
samples, ids = utils.get_content(bugslist)
# print(samples)
num_word_list, numword = utils.count_word(samples)
# print(len(num_word_list))
# for i in num_word_list:
# num_sentence.append(len(i))
utils.savefile(samples)
# print(num_sentence)
results = textrank.bugsum(path, numword, num_word_list)
print(len(i) for i in results)
# extra_ids = index2id(results,ids)
# print(len(extra_ids))
pred = eval.index2pred(results, ids)
y = eval.label2y(label, ids)
mean_acc, mean_pr, mean_re, mean_f1 = eval.evaluate(y, pred)
print('mean_acc, mean_pr, mean_re, mean_f1', mean_acc, mean_pr, mean_re,
mean_f1)
def canais():
librtmpwindow()
info_servidores()
nrcanais = 62
canaison = []
empty = 'nada'
#GA("None","listacanais")
if selfAddon.getSetting("prog-lista3") == "true":
mensagemprogresso.create('TV Portuguesa',
'A carregar listas de programação.',
'Por favor aguarde.')
mensagemprogresso.update(0)
if mensagemprogresso.iscanceled(): sys.exit(0)
programas = p_todos()
mensagemprogresso.close()
else:
programas = []
sintomecomsorte()
if activado == True:
addCanal("[B]Lista Completa[/B]", empty, 16,
tvporpath + art + 'gravador-ver1.png', nrcanais, '')
addDir("[B][COLOR white]Informações[/COLOR][/B]", 'nada', 1,
tvporpath + art + 'defs-ver2.png', 1,
'Clique aqui para voltar ao menu principal.', True)
if selfAddon.getSetting("listas-pessoais") == "true":
addDir("[B][COLOR white]Listas Pessoais[/COLOR][/B]", 'nada', 6,
tvporpath + art + 'listas-ver2.png', 1,
'Outras listas de canais criadas pela comunidade.', True)
if selfAddon.getSetting("radios") == "true":
addDir("[B][COLOR white]Radios[/COLOR][/B]", 'nada', 19,
tvporpath + art + 'radios-v1.png', 1,
'Oiça comodamente radios nacionais.', True)
if selfAddon.getSetting("eventos") == "true":
canaison.append('[B][COLOR white]Eventos[/COLOR][/B]')
changeview()
if selfAddon.getSetting("praias") == "true":
addDir("[B][COLOR white]Praias[/COLOR][/B]", 'nada', 26,
tvporpath + art + 'versao-ver2.png', 1,
'Webcams das melhores praias nacionais.', True)
setupCanais(canaison, empty, nrcanais, programas)
try:
canaison = ''.join(canaison)
savefile('canaison', canaison)
except:
pass
vista_canais()
xbmcplugin.setContent(int(sys.argv[1]), 'livetv')
def signal_handler(signal, frame):
"""
Capture Ctrl+C
"""
global crawler_state
global interrupted
print "Saving state Ctrl+C"
interrupted = True
#Serialize
dumped = pickle.dumps(crawler_state)
savefile('state.data', dumped)
sys.exit(0)
def main():
# Arguments logic
parser = argparse.ArgumentParser(description='Web crawler')
parser.add_argument('website', nargs='?', action='store', help='website to crawl')
parser.add_argument('-l', action='store', default=2, help='maximum depth level to crawl')
parser.add_argument('-resume', action='store_const', const=32, help='resume crawler')
global crawler_state
# Arguments parser
args = parser.parse_args()
# Crawler
c = Crawler(args.website, int(args.l))
crawler_state = c
# Register Ctrl+C
signal.signal(signal.SIGINT, signal_handler)
if not args.resume:
info = c.crawl(args.website)
else:
#recover state
print "recovering..."
raw = loadfile('state.data')
data = pickle.loads(raw)
c.output = data.output
c.queue = data.queue
c.queue.append((data.current_url, data.level))
c.visited = data.visited
c.url = data.url
c.maxdepth = data.maxdepth
info = c.crawl(data.url)
print "OK"
# Save data
savefile('structure.txt', info)
def canais():
librtmpwindow()
info_servidores()
nrcanais=62
canaison=[]
empty='nada'
#GA("None","listacanais")
if selfAddon.getSetting("prog-lista3") == "true":
mensagemprogresso.create('TV Portuguesa', 'A carregar listas de programação.','Por favor aguarde.')
mensagemprogresso.update(0)
if mensagemprogresso.iscanceled(): sys.exit(0)
programas=p_todos()
mensagemprogresso.close()
else: programas=[]
sintomecomsorte()
if activado==True: addCanal("[B]Lista Completa[/B]",empty,16,tvporpath + art + 'gravador-ver1.png',nrcanais,'')
addDir("[B][COLOR white]Informações[/COLOR][/B]",'nada',1,tvporpath + art + 'defs-ver2.png',1,'Clique aqui para voltar ao menu principal.',True)
if selfAddon.getSetting("listas-pessoais") == "true":
addDir("[B][COLOR white]Listas Pessoais[/COLOR][/B]",'nada',6,tvporpath + art + 'listas-ver2.png',1,'Outras listas de canais criadas pela comunidade.',True)
if selfAddon.getSetting("radios") == "true": addDir("[B][COLOR white]Radios[/COLOR][/B]",'nada',19,tvporpath + art + 'radios-v1.png',1,'Oiça comodamente radios nacionais.',True)
if selfAddon.getSetting("eventos") == "true": canaison.append('[B][COLOR white]Eventos[/COLOR][/B]'); changeview()
if selfAddon.getSetting("praias") == "true": addDir("[B][COLOR white]Praias[/COLOR][/B]",'nada',26,tvporpath + art + 'versao-ver2.png',1,'Webcams das melhores praias nacionais.',True)
setupCanais(canaison, empty, nrcanais, programas)
try:
canaison=''.join(canaison)
savefile('canaison', canaison)
except: pass
vista_canais()
xbmcplugin.setContent(int(sys.argv[1]), 'livetv')
def train_er_classifier(train_loader, test_loader, encoder, discriminator,
classifier, use_cuda, n_z, sigma, num_epoch, lr,
LAMBDA, LAMBDA0, LAMBDA1, file_name, epsilon, k, a,
delay, print_every, dataset, attack_range):
criterion2 = nn.CrossEntropyLoss()
adversary = LinfPGDAttackOT(epsilon=epsilon, k=k, a=a, data=attack_range)
encoder.train()
discriminator.train()
classifier.train()
# Optimizers
enc_optim = optim.Adam(encoder.parameters(), lr=lr)
dis_optim = optim.Adam(discriminator.parameters(), lr=0.5 * lr)
cla_optim = optim.Adam(classifier.parameters(), lr=0.05 * lr)
enc_scheduler = StepLR(enc_optim, step_size=30, gamma=0.5)
dis_scheduler = StepLR(dis_optim, step_size=30, gamma=0.5)
cla_scheduler = StepLR(cla_optim, step_size=30, gamma=0.5)
if use_cuda:
encoder, discriminator, classifier = encoder.cuda(
), discriminator.cuda(), classifier.cuda()
one = torch.Tensor([1])
mone = one * -1
if use_cuda:
one = one.cuda()
mone = mone.cuda()
for epoch in range(num_epoch):
step = 0
for images, labels in tqdm(train_loader):
if use_cuda:
images, labels = images.cuda(), labels.cuda()
# ======== Training ======== #
batch_size = images.size()[0]
encoder.zero_grad()
discriminator.zero_grad()
classifier.zero_grad()
# ======== Get Adversarial images ======== #
if epoch >= delay:
target_pred = pred_batch_ot(images, classifier, encoder)
images_adv = adv_train_ot(images, target_pred, classifier,
encoder, adversary)
images_adv = to_var(images_adv)
# ======== Train Discriminator ======== #
frozen_params(encoder)
frozen_params(classifier)
free_params(discriminator)
z_fake = torch.randn(batch_size, n_z) * sigma
if use_cuda:
z_fake = z_fake.cuda()
d_fake = discriminator(to_var(z_fake))
z_real = encoder(images)
d_real = discriminator(to_var(z_real))
disc_fake = LAMBDA * d_fake.mean()
disc_real = LAMBDA * d_real.mean()
disc_fake.backward(one)
disc_real.backward(mone)
diss_loss = disc_fake - disc_real
dis_optim.step()
clip_params(discriminator)
if epoch >= delay:
z_fake = torch.randn(batch_size, n_z) * sigma
if use_cuda:
z_fake = z_fake.cuda()
d_fake = discriminator(to_var(z_fake))
z_real = encoder(images_adv)
d_real = discriminator(to_var(z_real))
disc_fake = LAMBDA * d_fake.mean()
disc_real = LAMBDA * d_real.mean()
disc_fake.backward(one)
disc_real.backward(mone)
diss_loss = disc_fake - disc_real
dis_optim.step()
clip_params(discriminator)
# ======== Train Classifier and Encoder======== #
free_params(encoder)
free_params(classifier)
frozen_params(discriminator)
pred_labels = classifier(encoder(to_var(images)))
class_loss = LAMBDA0 * criterion2(pred_labels, labels)
if epoch >= delay:
pred_labels_adv = classifier(encoder(to_var(images_adv)))
class_loss_adv = LAMBDA0 * criterion2(pred_labels_adv, labels)
class_loss = (class_loss + class_loss_adv) / 2
class_loss.backward()
cla_optim.step()
enc_optim.step()
# # ======== Train Encoder ======== #
free_params(encoder)
frozen_params(classifier)
frozen_params(discriminator)
z_real = encoder(images)
d_real = discriminator(encoder(Variable(images.data)))
d_loss = LAMBDA1 * (d_real.mean())
d_loss.backward(one)
enc_optim.step()
if epoch >= delay:
z_real = encoder(images_adv)
d_real = discriminator(encoder(Variable(images_adv.data)))
d_loss = LAMBDA1 * (d_real.mean())
d_loss.backward(one)
enc_optim.step()
step += 1
if (step + 1) % print_every == 0:
print(
"Epoch: [%d/%d], Step: [%d/%d], Discriminative Loss: %.4f, Classification_Loss:%.4f"
% (epoch + 1, num_epoch, step + 1, len(train_loader),
diss_loss.data.item(), class_loss.data.item()))
if (epoch + 1) % 1 == 0:
savefile(file_name,
encoder,
discriminator,
classifier,
dataset=dataset)
test(test_loader, classifier, encoder=encoder, use_cuda=True)
savefile(file_name, encoder, discriminator, classifier, dataset=dataset)
return classifier, encoder