def load_data(data_dir, task, cv, training_data_size=None):
# Load data from file
if task == "trec":
train_x, train_y, test_x, test_y = load_dataset[task](data_dir)
data = train_x + test_x
label = None
elif task == "sst":
train_x, train_y, valid_x, valid_y, test_x, test_y = load_dataset[
task](data_dir)
data = train_x + valid_x + test_x
label = None
else:
data, label = load_dataset[task](data_dir)
if task == "trec":
train_x, train_y, valid_x, valid_y = cv_split2(train_x,
train_y,
nfold=10,
valid_id=cv)
elif task != "sst":
train_x, train_y, valid_x, valid_y, test_x, test_y = cv_split(
data, label, nfold=10, test_id=cv)
nclasses = max(train_y) + 1
# Set the training dataset size
if training_data_size:
train_x = train_x[:training_data_size]
train_y = train_y[:training_data_size]
train_y = torch.LongTensor(train_y)
valid_y = torch.LongTensor(valid_y)
test_y = torch.LongTensor(test_y)
dataset = {
"train": (train_x, train_y),
"valid": (valid_x, valid_y),
"test": (test_x, test_y),
"nclasses": nclasses,
}
return dataset, data
def main(args):
if args.dataset == 'mr':
data, label = dataloader.read_MR(args.path)
elif args.dataset == 'subj':
data, label = dataloader.read_SUBJ(args.path)
elif args.dataset == 'cr':
data, label = dataloader.read_CR(args.path)
elif args.dataset == 'mpqa':
data, label = dataloader.read_MPQA(args.path)
elif args.dataset == 'trec':
train_x, train_y, test_x, test_y = dataloader.read_TREC(args.path)
data = train_x + test_x
label = None
elif args.dataset == 'sst':
train_x, train_y, valid_x, valid_y, test_x, test_y = dataloader.read_SST(args.path)
data = train_x + valid_x + test_x
label = None
else:
raise Exception("unknown dataset: {}".format(args.dataset))
emb_layer = modules.EmbeddingLayer(
args.d, data,
embs = dataloader.load_embedding(args.embedding)
)
if args.dataset == 'trec':
train_x, train_y, valid_x, valid_y = dataloader.cv_split2(
train_x, train_y,
nfold = 10,
valid_id = args.cv
)
elif args.dataset != 'sst':
train_x, train_y, valid_x, valid_y, test_x, test_y = dataloader.cv_split(
data, label,
nfold = 10,
test_id = args.cv
)
nclasses = max(train_y)+1
train_x, train_y = dataloader.create_batches(
train_x, train_y,
args.batch_size,
emb_layer.word2id,
sort = args.dataset == 'sst'
)
valid_x, valid_y = dataloader.create_batches(
valid_x, valid_y,
args.batch_size,
emb_layer.word2id,
sort = args.dataset == 'sst'
)
test_x, test_y = dataloader.create_batches(
test_x, test_y,
args.batch_size,
emb_layer.word2id,
sort = args.dataset == 'sst'
)
model = Model(args, emb_layer, nclasses).cuda()
need_grad = lambda x: x.requires_grad
optimizer = optim.Adam(
filter(need_grad, model.parameters()),
lr = args.lr
)
best_valid = 1e+8
test_err = 1e+8
for epoch in range(args.max_epoch):
best_valid, test_err = train_model(epoch, model, optimizer,
train_x, train_y,
valid_x, valid_y,
test_x, test_y,
best_valid, test_err
)
if args.lr_decay>0:
optimizer.param_groups[0]['lr'] *= args.lr_decay
sys.stdout.write("best_valid: {:.6f}\n".format(
best_valid
))
sys.stdout.write("test_err: {:.6f}\n".format(
test_err
))
def main(args):
datasetList = ['mr', 'subj', 'cr', 'mpqa', 'trec', 'sst']
numberOfTest = 5
args.max_epoch = 100
for dset in datasetList:
if dset == 'mr':
data, label = dataloader.read_MR(args.path)
elif dset == 'subj':
data, label = dataloader.read_SUBJ(args.path)
elif dset == 'cr':
data, label = dataloader.read_CR(args.path)
elif dset == 'mpqa':
data, label = dataloader.read_MPQA(args.path)
elif dset == 'trec':
train_x, train_y, test_x, test_y = dataloader.read_TREC(args.path)
data = train_x + test_x
label = None
elif dset == 'sst':
train_x, train_y, valid_x, valid_y, test_x, test_y = dataloader.read_SST(args.path)
data = train_x + valid_x + test_x
label = None
else:
raise Exception("unknown dataset: {}".format(dset))
emb_layer = modules.EmbeddingLayer(
args.d, data,
embs = dataloader.load_embedding(args.embedding)
)
if dset == 'trec':
train_x, train_y, valid_x, valid_y = dataloader.cv_split2(
train_x, train_y,
nfold = 10,
valid_id = args.cv
)
elif dset != 'sst':
train_x, train_y, valid_x, valid_y, test_x, test_y = dataloader.cv_split(
data, label,
nfold = 10,
test_id = args.cv
)
nclasses = max(train_y)+1
train_x, train_y = dataloader.create_batches(train_x, train_y, args.batch_size, emb_layer.word2id, sort = dset == 'sst')
valid_x, valid_y = dataloader.create_batches(valid_x, valid_y, args.batch_size, emb_layer.word2id, sort = dset == 'sst')
test_x, test_y = dataloader.create_batches(test_x, test_y, args.batch_size, emb_layer.word2id, sort = dset == 'sst')
for models in range(3):
if models == 1:
args.cnn = True
modelName = 'CNN'
elif models == 2:
args.cnn = False
args.lstm = True
modelName = 'LSTM'
else:
args.lstm = False
modelName = 'SRU'
sys.stdout.write("Training {} with {} architecture: \n".format(dset,modelName))
args.dropout = 0.5
for testNo in range(numberOfTest):
model = Model(args, emb_layer, nclasses).cuda()
need_grad = lambda x: x.requires_grad
optimizer = optim.Adam(filter(need_grad, model.parameters()), lr = args.lr)
best_valid = 1e+8
test_err = 1e+8
results = []
for epoch in range(args.max_epoch):
results.append(train_model(epoch, model, optimizer, train_x, train_y, valid_x, valid_y, test_x, test_y, best_valid, test_err))
with open('results_{d}_{m}_{i}.csv'.format(d=dset, m=modelName, i=(testNo+1)), 'wb') as dump:
wr = csv.writer(dump, delimiter=',')
wr.writerow(['Epoch','Training Loss', 'Validation Error', 'Test Error', 'Duration'])
for idx, value in enumerate(results):
wr.writerow(value)