def __init__(self, opt):
self.opt = opt
absa_dataset = ABSADatesetReader(dataset=opt.dataset,
embed_dim=opt.embed_dim)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(opt.device)
self._print_args()
self.global_f1 = 0.
if torch.cuda.is_available():
print('cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))
def __init__(self, opt):
self.opt = opt
# absa_dataset = ABSADatesetReader(dataset=opt.dataset, embed_dim=opt.embed_dim)
absa_dataset = pickle.load(open(opt.dataset + '_datas.pkl', 'rb'))
absa_other = pickle.load(open('other' + '_datas.pkl', 'rb'))
opt.edge_size = len(absa_dataset.edgevocab)
# self.train_data_loader = BucketIterator(data=absa_dataset.train_data, other=absa_other.train_data, batch_size=opt.batch_size, shuffle=True)
self.train_data_loader = BucketIterator(data=absa_dataset.train_data,
batch_size=opt.batch_size,
shuffle=True)
self.test_data_loader = BucketIterator(data=absa_dataset.test_data,
batch_size=opt.batch_size,
shuffle=False)
self.model = opt.model_class(absa_dataset.embedding_matrix,
opt).to(opt.device)
self._print_args()
self.global_f1 = 0.
if torch.cuda.is_available():
print('cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))
def _train(self, optimizer, fold_i):
max_test_precision = 0
max_test_recall = 0
max_test_f1 = 0
max_test_precision_e = 0
max_test_recall_e = 0
max_test_f1_e = 0
max_test_precision_c = 0
max_test_recall_c = 0
max_test_f1_c = 0
max_pair_matrix_len = 20
global_step = 0
continue_not_increase = 0
train_data_loader = BucketIterator(
data=self.dataset.train_data[fold_i],
batch_size=opt.batch_size,
shuffle=True)
test_data_loader = BucketIterator(data=self.dataset.test_data[fold_i],
batch_size=opt.batch_size,
shuffle=False)
for epoch in range(self.opt.num_epoch):
print('>' * 100)
print('epoch: ', epoch)
increase_flag = False
for i_batch, sample_batched in enumerate(train_data_loader):
global_step += 1
# switch model to training mode, clear gradient accumulators
self.model.train()
optimizer.zero_grad()
inputs = [
sample_batched[col].to(self.opt.device)
for col in self.opt.inputs_cols
]
targets = [
sample_batched[col].to(self.opt.device)
for col in self.opt.targets_cols
]
outputs = self.model(inputs)
loss = self.model.calc_loss(outputs, targets)
loss.backward()
optimizer.step()
if global_step % self.opt.log_step == 0:
output_emotion, output_cause, output_pair = outputs
target_emotion, target_cause, target_pair = targets
output_pairs = torch.nonzero(
output_pair > 0.3).cpu().numpy().tolist()
target_pairs = torch.nonzero(
target_pair > 0.3).cpu().numpy().tolist()
n_TP = 0
for i_pair in output_pairs:
if i_pair in target_pairs:
n_TP += 1
n_FP = (len(output_pairs) - n_TP)
n_FN = (len(target_pairs) - n_TP)
precision = float(n_TP) / float(n_TP + n_FP + 1e-5)
recall = float(n_TP) / float(n_TP + n_FN + 1e-5)
f1 = 2 * precision * recall / (precision + recall + 1e-5)
test_precision, test_recall, test_f1, test_precision_e, test_recall_e, test_f1_e, test_precision_c, test_recall_c, test_f1_c = self._evaluate(
test_data_loader)
if test_f1 > max_test_f1:
increase_flag = True
max_test_precision = test_precision
max_test_recall = test_recall
max_test_f1 = test_f1
if self.opt.save:
if not os.path.exists('state_dict'):
os.mkdir('state_dict')
torch.save(
self.model.state_dict(),
'state_dict/' + self.opt.model_name + '_' +
str(fold_i) + self.opt.dataset + '.pkl')
print('>> model saved.')
print(
'loss: {:.4f}, train_f1: {:.4f}, test_precision: {:.4f}, test_recall: {:.4f}, test_f1: {:.4f}'
.format(loss.item(), f1, test_precision, test_recall,
test_f1))
if test_f1_e > max_test_f1_e:
increase_flag = True
max_test_precision_e = test_precision_e
max_test_recall_e = test_recall_e
max_test_f1_e = test_f1_e
print(
'test_precision_e: {:.4f}, test_recall_e: {:.4f}, test_f1_e: {:.4f}'
.format(test_precision_e, test_recall_e, test_f1_e))
if test_f1_c > max_test_f1_c:
increase_flag = True
max_test_precision_c = test_precision_c
max_test_recall_c = test_recall_c
max_test_f1_c = test_f1_c
print(
'test_precision_c: {:.4f}, test_recall_c: {:.4f}, test_f1_c: {:.4f}'
.format(test_precision_c, test_recall_c, test_f1_c))
if increase_flag == False:
continue_not_increase += 1
if continue_not_increase >= self.opt.patience:
print('>> early stop.')
break
else:
continue_not_increase = 0
return max_test_precision, max_test_recall, max_test_f1, max_test_precision_e, max_test_recall_e, max_test_f1_e, max_test_precision_c, max_test_recall_c, max_test_f1_c
def __init__(self, opt):
self.opt = opt
if opt.model in [
'bote', 'bote_v0_ablation', 'bote_v1_ablation',
'bote_v2_ablation', 'bote_v3_ablation', 'bote_v4'
]:
absa_data_reader = ABSADataReaderBERT(data_dir=opt.data_dir)
tokenizer = BertTokenizer(opt.bert_model, opt.case, opt.spacy_lang,
opt.lang)
embedding_matrix = []
self.train_data_loader = BucketIteratorBert(
data=absa_data_reader.get_train(tokenizer),
batch_size=opt.batch_size,
shuffle=True)
self.dev_data_loader = BucketIteratorBert(
data=absa_data_reader.get_dev(tokenizer),
batch_size=opt.batch_size,
shuffle=False)
self.test_data_loader = BucketIteratorBert(
data=absa_data_reader.get_test(tokenizer),
batch_size=opt.batch_size,
shuffle=False)
else:
absa_data_reader = ABSADataReader(data_dir=opt.data_dir)
tokenizer = build_tokenizer(data_dir=opt.data_dir)
embedding_matrix = build_embedding_matrix(opt.data_dir,
tokenizer.word2idx,
opt.embed_dim,
opt.dataset,
opt.glove_fname)
self.train_data_loader = BucketIterator(
data=absa_data_reader.get_train(tokenizer),
batch_size=opt.batch_size,
shuffle=True)
self.dev_data_loader = BucketIterator(
data=absa_data_reader.get_dev(tokenizer),
batch_size=opt.batch_size,
shuffle=False)
self.test_data_loader = BucketIterator(
data=absa_data_reader.get_test(tokenizer),
batch_size=opt.batch_size,
shuffle=False)
self.idx2tag, self.idx2polarity = absa_data_reader.reverse_tag_map, absa_data_reader.reverse_polarity_map
self.model = opt.model_class(embedding_matrix, opt, self.idx2tag,
self.idx2polarity).to(opt.device)
self.history_metrics = {
'epoch': [],
'step': [],
'train_ap_precision': [],
'train_ap_recall': [],
'train_ap_f1': [],
'train_op_precision': [],
'train_op_recall': [],
'train_op_f1': [],
'train_triplet_precision': [],
'train_triplet_recall': [],
'train_triplet_f1': [],
'dev_ap_precision': [],
'dev_ap_recall': [],
'dev_ap_f1': [],
'dev_op_precision': [],
'dev_op_recall': [],
'dev_op_f1': [],
'dev_triplet_precision': [],
'dev_triplet_recall': [],
'dev_triplet_f1': []
}
self.results = {
'aspect_extraction': {
'precision': [],
'recall': [],
'f1': []
},
'opinion_extraction': {
'precision': [],
'recall': [],
'f1': []
},
'triplet_extraction': {
'precision': [],
'recall': [],
'f1': []
}
}
self._print_args()
if torch.cuda.is_available():
print('>>> cuda memory allocated:',
torch.cuda.memory_allocated(device=opt.device.index))