def text_transformer(n_gram, window_size):
"""
Get tweet transformer
:param lang:
:param n_gram:
:return:
"""
if n_gram == 'c1':
return transforms.Compose([
ltransforms.ToLower(),
ltransforms.Character(),
ltransforms.ToIndex(start_ix=0),
ltransforms.ToNGram(n=window_size, overlapse=True),
ltransforms.Reshape((-1, window_size)),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram] - 1)
])
else:
return transforms.Compose([
ltransforms.ToLower(),
ltransforms.Character2Gram(),
ltransforms.ToIndex(start_ix=0),
ltransforms.ToNGram(n=window_size, overlapse=True),
ltransforms.Reshape((-1, window_size)),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram] - 1)
])
def tweet_transformer(lang, n_gram, voc=None):
"""
Get tweet transformer
:param lang:
:param n_gram:
:return:
"""
if voc is None:
token_to_ix = dict()
else:
token_to_ix = voc
# end if
if n_gram == 'c1':
return transforms.Compose([
ltransforms.RemoveRegex(
regex=r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'),
ltransforms.ToLower(),
ltransforms.Character(),
ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
ltransforms.ToLength(length=settings.min_length),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram][lang] - 1)
])
else:
return transforms.Compose([
ltransforms.RemoveRegex(
regex=r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'),
ltransforms.ToLower(),
ltransforms.Character2Gram(),
ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
ltransforms.ToLength(length=settings.min_length),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram][lang] - 1)
])
def text_transformer_cnn(window_size, n_gram, token_to_ix):
"""
Get text transformer for CNNSCD
:param window_size:
:param n_gram:
:return:
"""
if n_gram == 'c1':
return ltransforms.Compose([
ltransforms.ToLower(),
ltransforms.Character(),
ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
ltransforms.ToLength(length=window_size),
ltransforms.Reshape((-1)),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram])
])
else:
return ltransforms.Compose([
ltransforms.ToLower(),
ltransforms.Character2Gram(),
ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
ltransforms.ToLength(length=window_size),
ltransforms.Reshape((-1)),
ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram])
])
# Eval
model.eval()
if args.n_gram == 'c1':
transforms = ltransforms.Compose([
ltransforms.ToLower(),
ltransforms.Character(),
ltransforms.ToIndex(start_ix=1, token_to_ix=voc),
ltransforms.ToLength(length=window_size),
ltransforms.MaxIndex(max_id=settings.voc_sizes[args.n_gram])
])
else:
transforms = ltransforms.Compose([
ltransforms.ToLower(),
ltransforms.Character2Gram(),
ltransforms.ToIndex(start_ix=1, token_to_ix=voc),
ltransforms.ToLength(length=window_size),
ltransforms.MaxIndex(max_id=settings.voc_sizes[args.n_gram])
])
# end if
# Validation losses
validation_total = 0
validation_success = np.zeros((n_levels, n_thresholds))
n_files = 0.0
n_same = 0.0
n_diff = 0.0
# Values
same_distance_values = np.array([])
def train_ccsaa(fold=0,
ccsaa_epoch=100,
text_length=20,
n_gram='c1',
dataset_size=100,
dataset_start=0,
cuda=True,
save=False,
save_dir='.'):
"""
Train CCSAA
:param fold:
:param ccsaa_epoch:
:param text_length:
:param n_gram:
:param dataset_size:
:param dataset_start:
:param cuda:
:return:
"""
# Save path
save_path = os.path.join(save_dir, str(int(dataset_size)),
str(int(dataset_start)))
# Transforms
if n_gram == 'c1':
transform = transforms.Compose([
transforms.Character(),
transforms.ToIndex(start_ix=0),
transforms.ToNGram(n=text_length, overlapse=True),
transforms.Reshape((-1, text_length))
])
else:
transform = transforms.Compose([
transforms.Character2Gram(),
transforms.ToIndex(start_ix=0),
transforms.ToNGram(n=text_length, overlapse=True),
transforms.Reshape((-1, text_length))
])
# end if
# Load from directory
reutersc50_dataset, reuters_loader_train, reuters_loader_test = dataset.load_dataset(
dataset_size=dataset_size, dataset_start=dataset_start)
reutersc50_dataset.transform = transform
# Loss function
loss_function = nn.CrossEntropyLoss()
# Set fold
reuters_loader_train.dataset.set_fold(fold)
reuters_loader_test.dataset.set_fold(fold)
# Model
model = torchlanguage.models.CCSAA(
text_length=text_length,
vocab_size=settings.ccsaa_voc_size,
embedding_dim=settings.ccsaa_embedding_dim,
n_classes=settings.n_authors)
if cuda:
model.cuda()
# end if
# Load
if save and os.path.exists(
os.path.join(save_path,
u"ccsaa." + str(fold) + u".pth")) and os.path.exists(
os.path.join(save_path, u"ccsaa." + str(fold) +
u".voc.pth")):
model.load_state_dict(
torch.load(
open(os.path.join(save_path, u"ccsaa." + str(fold) + u".pth"),
'rb')))
voc = torch.load(
open(os.path.join(save_path, u"ccsaa." + str(fold) + u".voc.pth"),
'rb'))
return model, voc
# end if
# Optimizer
optimizer = optim.SGD(model.parameters(),
lr=settings.ccsaa_lr,
momentum=settings.ccsaa_momentum)
# Best model
best_acc = 0.0
best_model = model.state_dict()
# Fail count
fail_count = 0
# Epoch
for epoch in range(10000):
# Total losses
training_loss = 0.0
training_total = 0.0
test_loss = 0.0
test_total = 0.0
# Get test data for this fold
for i, data in enumerate(reuters_loader_train):
# Inputs and labels
inputs, labels, time_labels = data
# Reshape
inputs = inputs.view(-1, text_length)
# Outputs
outputs = torch.LongTensor(inputs.size(0)).fill_(labels[0])
# To variable
inputs, outputs = Variable(inputs), Variable(outputs)
if cuda:
inputs, outputs = inputs.cuda(), outputs.cuda()
# end if
# Zero grad
model.zero_grad()
# Compute output
log_probs = model(inputs)
# Loss
loss = loss_function(log_probs, outputs)
# Backward and step
loss.backward()
optimizer.step()
# Add
training_loss += loss.data[0]
training_total += 1.0
# end for
# Counters
total = 0.0
success = 0.0
# For each test sample
for i, data in enumerate(reuters_loader_test):
# Inputs and labels
inputs, labels, time_labels = data
# Reshape
inputs = inputs.view(-1, text_length)
# Outputs
outputs = torch.LongTensor(inputs.size(0)).fill_(labels[0])
# To variable
inputs, outputs = Variable(inputs), Variable(outputs)
if cuda:
inputs, outputs = inputs.cuda(), outputs.cuda()
# end if
# Forward
model_outputs = model(inputs)
loss = loss_function(model_outputs, outputs)
# Take the max as predicted
_, predicted = torch.max(model_outputs.data, 1)
# Add to correctly classified word
success += (predicted == outputs.data).sum()
total += predicted.size(0)
# Add loss
test_loss += loss.data[0]
test_total += 1.0
# end for
# Accuracy
accuracy = success / total * 100.0
# print(u"Epoch {}, train loss {}, test loss {}, accuracy {}".format(epoch, training_loss / training_total, test_loss / test_total, accuracy))
# Save if best
if accuracy > best_acc and epoch > 10:
best_acc = accuracy
best_model = model.state_dict()
fail_count = 0
elif epoch > 10:
fail_count += 1
# end if
if fail_count > ccsaa_epoch:
break
# end if
# end for
# Load best
model.load_state_dict(best_model)
# Save
if save:
# Create dir if not exists
if not os.path.exists(save_path):
os.mkdir(save_path)
# end if
# Save
torch.save(
model.state_dict(),
open(os.path.join(save_path, u"ccsaa." + str(fold) + u".pth"),
'wb'))
# Save doc
torch.save(
transform.transforms[1].token_to_ix,
open(os.path.join(save_path, u"ccsaa." + str(fold) + u".voc.pth"),
'wb'))
# end if
return model, transform.transforms[1].token_to_ix
