def main(args):
print args
model = None
assert args.embedding, "Pre-trained word embeddings required."
embedding_layer = EmbeddingLayer(
n_d = args.hidden_dim,
vocab = [ "<unk>" ],
embs = load_embedding_iterator(args.embedding)
)
if args.train:
train_x, train_y = read_corpus(args.train)
train_x = [ embedding_layer.map_to_ids(x) for x in train_x ]
if args.dev:
dev_x, dev_y = read_corpus(args.dev)
dev_x = [ embedding_layer.map_to_ids(x) for x in dev_x ]
if args.test:
test_x, test_y = read_corpus(args.test)
test_x = [ embedding_layer.map_to_ids(x) for x in test_x ]
if args.train:
model = Model(
args = args,
embedding_layer = embedding_layer,
nclasses = max(train_y)+1
)
model.ready()
model.train(
(train_x, train_y),
(dev_x, dev_y) if args.dev else None,
(test_x, test_y) if args.test else None,
)
if args.load and args.test and not args.train:
# model.args and model.nclasses will be loaded from file
model = Model(
args = None,
embedding_layer = embedding_layer,
nclasses = -1
)
model.load_model(args.load)
accuracy = model.evaluate_set(test_x, test_y)
print accuracy
def main():
print args
embedding_layer = None
if args.embedding:
assert args.embedding, "Pre-trained word embeddings required."
embedding_layer = myio.create_embedding_layer(args.embedding)
max_len = args.max_len
if args.train:
train_x, train_y = myio.read_annotations(args.train)
train_words = set([word for x in train_x for word in x])
embedding_layer = EmbeddingLayer(n_d=args.hidden_dimension,
vocab=["<unk>", "<padding>"] +
list(train_words),
oov="<unk>",
fix_init_embs=False)
train_x = [embedding_layer.map_to_ids(x)[:max_len] for x in train_x]
if args.dev:
dev_x, dev_y = myio.read_annotations(args.dev)
dev_x = [embedding_layer.map_to_ids(x)[:max_len] for x in dev_x]
if args.load_rationale:
rationale_data = myio.read_rationales(args.load_rationale)
for x in rationale_data:
x["xids"] = embedding_layer.map_to_ids(x["x"])
if args.train:
model = Model(args=args,
embedding_layer=embedding_layer,
nclasses=len(train_y[0]))
model.ready()
#debug_func2 = theano.function(
# inputs = [ model.x, model.z ],
# outputs = model.generator.logpz
# )
#theano.printing.debugprint(debug_func2)
#return
model.train(
(train_x, train_y),
(dev_x, dev_y) if args.dev else None,
None, #(test_x, test_y),
rationale_data if args.load_rationale else None)
def main(args):
print(args)
model = None
assert args.embedding, "Pre-trained word embeddings required."
embedding_layer = EmbeddingLayer(
n_d = args.hidden_dim,
vocab = [ "<unk>" ],
embs = load_embedding_iterator(args.embedding)
)
if args.train:
train_x, train_y = read_corpus(args.train)
train_x = [ embedding_layer.map_to_ids(x) for x in train_x ]
if args.dev:
dev_x, dev_y = read_corpus(args.dev)
dev_x = [ embedding_layer.map_to_ids(x) for x in dev_x ]
if args.test:
test_x, test_y = read_corpus(args.test)
test_x = [ embedding_layer.map_to_ids(x) for x in test_x ]
if args.train:
model = Model(
args = args,
embedding_layer = embedding_layer,
nclasses = max(train_y)+1
)
model.ready()
model.train(
(train_x, train_y),
(dev_x, dev_y) if args.dev else None,
(test_x, test_y) if args.test else None,
)
if args.load and args.test and not args.train:
# model.args and model.nclasses will be loaded from file
model = Model(
args = None,
embedding_layer = embedding_layer,
nclasses = -1
)
model.load_model(args.load)
accuracy = model.evaluate_set(test_x, test_y)
print accuracy
def main(args):
assert args.train, "Training set required"
assert args.dev, "Dev set required"
assert args.test, "Test set required"
assert args.emb, "Pre-trained word embeddings required."
assert args.aspect_seeds, "Aspect seeds required."
print args
seeds = load_lis(args.aspect_seeds)
say("loaded {} aspect seeds\n".format(len(seeds)))
embedding_layer = EmbeddingLayer(
n_d = 100,
vocab = [ "<unk>" ],
pre_embs = load_embedding_iterator(args.emb),
)
seeds_id = np.array(map(lambda seed: embedding_layer.map_to_ids(seed.strip().split()).tolist(), seeds), dtype = np.int32)
if args.train:
train_x, train_y = load_doc_corpus(embedding_layer, args.train)
if args.dev:
dev_x, dev_y = load_doc_corpus(embedding_layer, args.dev)
if args.test:
test_x, test_y = load_doc_corpus(embedding_layer, args.test)
if args.train:
model = Model(
args = args,
embedding_layer = embedding_layer,
num_aspects = len(seeds_id),
query = seeds_id
)
if args.load:
print 'loading model...'
model.load_model(args.load)
else:
model.ready()
print 'training...'
model.train(
(train_x, train_y),
(dev_x, dev_y) if args.dev else None,
(test_x, test_y) if args.test else None
)
