def do_training(args):
torch.manual_seed(133)
# Set up configuration and output
config = Config(args)
if not os.path.exists(config.output_path):
os.makedirs(config.output_path)
# Set up logging
handler = logging.FileHandler(config.log_output)
handler.setLevel(logging.DEBUG)
handler.setFormatter(
logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logging.getLogger().addHandler(handler)
# Load data
helper, data = load_data(args)
train_examples = data['train_examples']
dev_examples = data['dev_examples']
helper.save(config.output_path)
# Load embeddings
embeddings = load_embeddings(args, helper, config.device)
# Initialize model
logger.info("Initializing model...", )
model = NerBiLstmModel(helper, config, embeddings)
model.to(config.device)
# Preprocess data
data_preprocessor = DataPreprocessor(model, config, helper)
train_examples = data_preprocessor.preprocess_sequence_data(train_examples)
dev_examples = data_preprocessor.preprocess_sequence_data(dev_examples)
# Start training
trainer = Trainer(model, config, helper, logger)
logger.info("Starting training...", )
trainer.train(train_examples, dev_examples)
# Save predictions of the best model
logger.info(
"Training completed, saving predictions of the best model...", )
with torch.no_grad():
model.load_state_dict(torch.load(config.model_output))
model.eval()
predictor = Predictor(model, config)
output = predictor.predict(dev_examples, use_str_labels=True)
sentences, labels, predictions = zip(*output)
predictions = [[LBLS[l] for l in preds] for preds in predictions]
output = list(zip(sentences, labels, predictions))
with open(model.config.conll_output, 'w') as f:
write_conll(f, output)
with open(model.config.eval_output, 'w') as f:
for sentence, labels, predictions in output:
print_sentence(f, sentence, labels, predictions)
def infer(self, conll):
"""
Uses the JAVANLP sentence object to create an appropriate CoNLL formatted input for the CRF
CONLL is a list of arrays.
@param: conll is a set of strings.
"""
with open(self.test_path, "w") as f:
for conll_ in conll:
write_conll(f, conll_)
f.write("\n")
output = check_output([CRF_TEST, "-m", self.model_path, self.test_path], universal_newlines=True)
conll_out = read_conll_doc(output)
assert len(conll_out) == len(conll)
tags = [[tok[-1] for tok in c] for c in conll_out]
return tags
def do_train(args):
# Set up some parameters.
config = Config(args)
helper, train, dev, train_raw, dev_raw = load_and_preprocess_data(args)
embeddings = load_embeddings(args, helper)
#print("**********************Dumping embeddings to a file.***************")
#with open("F:/Jupyter/NLP/assignment3/embeddings.pkl","wb") as f:
#pickle.dump(embeddings, f)
config.embed_size = embeddings.shape[1]
helper.save(config.output_path)
handler = logging.FileHandler(config.log_output)
handler.setLevel(logging.DEBUG)
handler.setFormatter(
logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logging.getLogger().addHandler(handler)
report = None #Report(Config.eval_output)
with tf.Graph().as_default():
logger.info("Building model...", )
start = time.time()
model = RNNModel(helper, config, embeddings)
logger.info("took %.2f seconds", time.time() - start)
init = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as session:
session.run(init)
model.fit(session, saver, train, dev)
if report:
report.log_output(model.output(session, dev_raw))
report.save()
else:
# Save predictions in a text file.
output = model.output(session, dev_raw)
sentences, labels, predictions = zip(*output)
predictions = [[LBLS[l] for l in preds]
for preds in predictions]
output = zip(sentences, labels, predictions)
with open(model.config.conll_output, 'w') as f:
write_conll(f, output)
with open(model.config.eval_output, 'w') as f:
for sentence, labels, predictions in output:
print_sentence(f, sentence, labels, predictions)
def do_train(args):
# Set up some parameters.
config = Config()
helper, train, dev, train_raw, dev_raw = load_and_preprocess_data(args)
embeddings = load_embeddings(args, helper)
config.embed_size = embeddings.shape[1]
helper.save(config.output_path)
handler = logging.FileHandler(config.log_output)
handler.setLevel(logging.DEBUG)
handler.setFormatter(
logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logging.getLogger().addHandler(handler)
report = None #Report(Config.eval_output)
with tf.Graph().as_default():
logger.info("Building model...", )
start = time.time()
model = WindowModel(helper, config, embeddings)
logger.info("took %.2f seconds", time.time() - start)
init = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as session:
#session = tf_debug.LocalCLIDebugWrapperSession(session)
#session.add_tensor_filter("has_inf_or_nan", tf_debug.has_inf_or_nan)
session.run(init)
model.fit(session, saver, train, dev)
if report:
report.log_output(model.output(session, dev_raw))
report.save()
else:
# Save predictions in a text file.
output = model.output(session, dev_raw)
sentences, labels, predictions = zip(*output)
predictions = [[LBLS[l] for l in preds]
for preds in predictions]
output = zip(sentences, labels, predictions)
with open(model.config.conll_output, 'w') as f:
write_conll(f, output)
with open(model.config.eval_output, 'w') as f:
for sentence, labels, predictions in output:
print_sentence(f, sentence, labels, predictions)
def update(self, conll, tags):
"""
Updates labels for the current example.
"""
# Create labelled data
conll_labelled = [feats[:self.TAG_LABEL] + [t] for feats, t in zip(conll, tags)]
# If we've move previous, rewrite the whole labelled set.
if self.cur_index <= len(self.labelled_data):
self.labelled_data[self.cur_index-1] = conll_labelled
self.labelled_data_file.close()
self.labelled_data_file = open(self.train_path,'w')
for conll in self.labelled_data:
write_conll(self.labelled_data_file, conll)
self.labelled_data_file.close()
self.labelled_data_file = open(self.train_path,'a')
else:
self.labelled_data.append(conll_labelled)
write_conll(self.labelled_data_file, conll_labelled)
def do_train(args):
# Set up some parameters.
config = Config()
helper, train, dev, train_raw, dev_raw = load_and_preprocess_data(args)
embeddings = load_embeddings(args, helper)
config.embed_size = embeddings.shape[1]
helper.save(config.output_path)
handler = logging.FileHandler(config.log_output)
handler.setLevel(logging.DEBUG)
handler.setFormatter(logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logging.getLogger().addHandler(handler)
report = None # Report(Config.eval_output)
with tf.Graph().as_default():
logger.info("Building model...", )
start = time.time()
model = WindowModel(helper, config, embeddings)
logger.info("took %.2f seconds", time.time() - start)
init = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as session:
session.run(init)
model.fit(session, saver, train, dev)
if report:
report.log_output(model.output(session, dev_raw))
report.save()
else:
# Save predictions in a text file.
output = model.output(session, dev_raw)
sentences, labels, predictions = zip(*output)
predictions = [[LBLS[l] for l in preds] for preds in predictions]
output = zip(sentences, labels, predictions)
with open(model.config.conll_output, 'w') as f:
write_conll(f, output)
with open(model.config.eval_output, 'w') as f:
for sentence, labels, predictions in output:
print_sentence(f, sentence, labels, predictions)
def do_train(args):
# Set up some parameters.
config = Config()
helper, train, dev, train_raw, dev_raw = load_and_preprocess_data(args)
embeddings = load_embeddings(args, helper)
config.embed_size = embeddings.shape[1]
helper.save(config.output_path)
handler = logging.FileHandler(config.log_output)
handler.setLevel(logging.DEBUG)
handler.setFormatter(
logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
logging.getLogger().addHandler(handler)
report = None #Report(Config.eval_output)
logger.info("Building model...", )
start = time.time()
model = WindowModel(helper, config, embeddings)
logger.info("took %.2f seconds", time.time() - start)
model.apply(init_weights)
model.fit(train, dev)
if report:
report.log_output(model.output(dev_raw))
report.save()
else:
# Save predictions in a text file.
output = model.output(dev_raw)
sentences, labels, predictions = zip(*output)
predictions = [[LBLS[l] for l in preds] for preds in predictions]
output = zip(sentences, labels, predictions)
with open(model.config.conll_output, 'w') as f:
write_conll(f, output)
with open(model.config.eval_output, 'w') as f:
for sentence, labels, predictions in output:
print_sentence(f, sentence, labels, predictions)