def train_and_eval(embeddings_name, fold_count, use_ELMo=False):
batch_size = 256
if use_ELMo:
batch_size = 20
model = Classifier('citations',
"gru",
list_classes=list_classes,
max_epoch=70,
fold_number=fold_count,
use_roc_auc=True,
embeddings_name=embeddings_name,
use_ELMo=use_ELMo,
batch_size=batch_size,
class_weights=class_weights)
print('loading citation sentiment corpus...')
xtr, y = load_citation_sentiment_corpus(
"data/textClassification/citations/citation_sentiment_corpus.txt")
# segment train and eval sets
x_train, y_train, x_test, y_test = split_data_and_labels(xtr, y, 0.9)
if fold_count == 1:
model.train(x_train, y_train)
else:
model.train_nfold(x_train, y_train)
model.eval(x_test, y_test)
# saving the model
model.save()
def train(embeddings_name, fold_count, use_ELMo=False):
batch_size = 256
if use_ELMo:
batch_size = 20
model = Classifier('citations',
"gru",
list_classes=list_classes,
max_epoch=70,
fold_number=fold_count,
use_roc_auc=True,
embeddings_name=embeddings_name,
use_ELMo=use_ELMo,
batch_size=batch_size,
class_weights=class_weights)
print('loading citation sentiment corpus...')
xtr, y = load_citation_sentiment_corpus(
"data/textClassification/citations/citation_sentiment_corpus.txt")
if fold_count == 1:
model.train(xtr, y)
else:
model.train_nfold(xtr, y)
# saving the model
model.save()
def train(embeddings_name,
fold_count,
use_ELMo=False,
use_BERT=False,
architecture="gru"):
batch_size, maxlen = configure(architecture, use_BERT, use_ELMo)
model = Classifier('citations',
model_type=architecture,
list_classes=list_classes,
max_epoch=100,
fold_number=fold_count,
patience=10,
use_roc_auc=True,
embeddings_name=embeddings_name,
use_ELMo=use_ELMo,
use_BERT=use_BERT,
batch_size=batch_size,
maxlen=maxlen,
class_weights=class_weights)
print('loading citation sentiment corpus...')
xtr, y = load_citation_sentiment_corpus(
"data/textClassification/citations/citation_sentiment_corpus.txt")
if fold_count == 1:
model.train(xtr, y)
else:
model.train_nfold(xtr, y)
# saving the model
model.save()
def train(embeddings_name, fold_count, architecture="gru", transformer=None):
batch_size, maxlen, patience, early_stop, max_epoch = configure(
architecture)
model = Classifier('citations_' + architecture,
architecture=architecture,
list_classes=list_classes,
max_epoch=max_epoch,
fold_number=fold_count,
use_roc_auc=True,
embeddings_name=embeddings_name,
batch_size=batch_size,
maxlen=maxlen,
patience=patience,
early_stop=early_stop,
class_weights=class_weights,
transformer_name=transformer)
print('loading citation sentiment corpus...')
xtr, y = load_citation_sentiment_corpus(
"data/textClassification/citations/citation_sentiment_corpus.txt")
if fold_count == 1:
model.train(xtr, y)
else:
model.train_nfold(xtr, y)
# saving the model
model.save()
def train(embeddings_name, fold_count):
model = Classifier('citations',
"gru",
list_classes=list_classes,
max_epoch=70,
fold_number=fold_count,
use_roc_auc=True,
embeddings_name=embeddings_name)
print('loading citation sentiment corpus...')
xtr, y = load_citation_sentiment_corpus(
"data/textClassification/citations/citation_sentiment_corpus.txt")
if fold_count == 1:
model.train(xtr, y)
else:
model.train_nfold(xtr, y)
# saving the model
model.save()