def train_root(topic, group, test_on_annotated_data=False):
args = argparse.ArgumentParser()
args.add_argument('--m', dest='model', default='lstm', help='specify the mode to use (default: lstm)')
args = args.parse_args()
EPOCHS = 1
USE_GPU = torch.cuda.is_available()
EMBEDDING_DIM = 300
HIDDEN_DIM = 150
BATCH_SIZE = 50
timestamp = str(int(time.time()))
best_dev_acc = 0.0
text_field = data.Field(lower=True)
label_field = data.Field(sequential=False)
train_iter, dev_iter, test_iter = load_sst(text_field, label_field, BATCH_SIZE, topic, group, test_on_annotated_data=test_on_annotated_data)
print (text_field.vocab.stoi["zzzzzzlove"])
model = LSTMSentiment(embedding_dim=EMBEDDING_DIM, hidden_dim=HIDDEN_DIM, vocab_size=len(text_field.vocab), label_size=len(label_field.vocab)-1,\
use_gpu=USE_GPU, batch_size=BATCH_SIZE)
if USE_GPU:
model = model.cuda()
print('Load word embeddings...')
# # glove
# text_field.vocab.load_vectors('glove.6B.100d')
# word2vector
word_to_idx = text_field.vocab.stoi
pretrained_embeddings = np.random.uniform(-0.25, 0.25, (len(text_field.vocab), 300))
pretrained_embeddings[0] = 0
word2vec = load_bin_vec('./data/GoogleNews-vectors-negative300-SLIM.bin', word_to_idx)
for word, vector in word2vec.items():
pretrained_embeddings[word_to_idx[word]-1] = vector
# text_field.vocab.load_vectors(wv_type='', wv_dim=300)
model.embeddings.weight.data.copy_(torch.from_numpy(pretrained_embeddings))
# model.embeddings.weight.data = text_field.vocab.vectors
# model.embeddings.embed.weight.requires_grad = False
best_model = model
optimizer = optim.Adam(model.parameters(), lr=1e-3)
loss_function = nn.NLLLoss()
print('Training...')
#out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs"))
print("Writing to {}\n".format(out_dir))
if not os.path.exists(out_dir):
os.makedirs(out_dir)
model_path = out_dir + '/best_model_'+topic+'_'+group + '.pth'
for epoch in range(EPOCHS):
avg_loss, acc = train_epoch_progress(model, train_iter, loss_function, optimizer, text_field, label_field, epoch)
tqdm.write('Train: loss %.2f acc %.1f' % (avg_loss, acc*100))
#if epoch == 1:
# ans = []
# test = doc_complete[:1000]
# for x in test:
# tl = []
# for w in x:
# tl.append(text_field.vocab.stoi[w])
# t = evaluate2(model,torch.Tensor(tl).view(-1,1))
# ans.append(t[0][1])
# sort_idx = [i[0] for i in sorted(enumerate(ans), key= lambda x:x[1], reverse = True)]
# tpo100 = sort_idx[:100]
# pos_tweet = [test[t] for t in tpo100]
# for idx,p in enumerate(pos_tweet):
# p = " ".join(p)
# print (str(idx)+" : "+ p)
# print (" ")
#evaluate1(model,torch.Tensor(tl).view(-1,1))
dev_acc = evaluate(model, dev_iter, loss_function, 'Dev')
test_acc = evaluate(model, test_iter, loss_function, 'Test')
if dev_acc > best_dev_acc:
if best_dev_acc > 0:
os.system('rm '+ model_path)
best_dev_acc = dev_acc
torch.save(model.state_dict(), model_path)
print("Best model is saved.")
model.load_state_dict(torch.load(model_path))
test_acc = evaluate(model, test_iter, loss_function, 'Final Test')
BATCH_SIZE)
# if not args.model:
# print('SALUT!')
model = LSTMSentiment(embedding_dim=EMBEDDING_DIM, hidden_dim=HIDDEN_DIM, vocab_size=len(text_field.vocab), label_size=len(label_field.vocab)-1,\
use_gpu=USE_GPU, batch_size=BATCH_SIZE)
print(model)
model = torch.load('./data/modelLSTM.pt')
# if args.model == 'bilstm':
# model = BiLSTMSentiment(embedding_dim=EMBEDDING_DIM, hidden_dim=HIDDEN_DIM, vocab_size=len(text_field.vocab), label_size=len(label_field.vocab)-1,\
# use_gpu=USE_GPU, batch_size=BATCH_SIZE)
if USE_GPU:
model = model.cuda()
print('Load word embeddings...')
# # glove
# text_field.vocab.load_vectors('glove.6B.100d')
# word2vector
word_to_idx = text_field.vocab.stoi
# print('type(text_field.vocab):', type(text_field.vocab))
# print('type(word_to_idx):', type(word_to_idx))
# print('word_to_idx.keys():', word_to_idx.keys())
keys = word_to_idx.keys()
# print('type(keys):', type(keys))
# print('len(keys):', len(keys))
pretrained_embeddings = np.random.uniform(-0.25, 0.25,