def main():
# Setup and get current configuration
config = get_configuration()
# Print parameters
print_configuration()
#Initialize class - preprocessing
preprocess = Preprocessing(config=config)
# Perform preprocessing
train_input, train_length_input, train_labels, test_input, test_length_input = preprocess.prepare_data(
)
# Initialize class and select mode and model - embeddings
if config.mode != "infer":
if config.emb_model == "glove":
model_emb = GloVeModel(config=config,
dict_vocab=preprocess.dict_vocab)
else:
model_emb = Word2VecModel(config=config,
dict_vocab=preprocess.dict_vocab)
# Fit corpus
model_emb.fit_to_corpus()
# Train embeddings
model_emb.train()
# Train model
RNN_Model(config, preprocess.dict_vocab_reverse, train_input,
train_length_input, train_labels, test_input, test_length_input)
def main():
# Setup and get current configuration
config = get_configuration()
# Print parameters
print_configuration()
# Perform preprocessing
preprocess = Preprocessing(config=config)
train_input_encoder, train_input_decoder, \
test_input_encoder, test_input_decoder, = preprocess.prepare_data()
# Initialize model class - train or infer: select mode
Seq2seq(config,
train_input_encoder,
train_input_decoder,
test_input_encoder,
test_input_decoder,
preprocess.dict_vocab_reverse,
mode=None)
from utils import generate_batches
from utils import Preprocessing
from configuration import get_configuration
from configuration import print_configuration
from models.basic_model import BasicModel
from models.seq2seq_model import Seq2SeqModel
from models.seq2seq_model import Seq2SeqModelAttention
# Load configuration and create model
config = get_configuration()
model = Seq2SeqModelAttention(config)
# Prepare vocabulary and triples data
preprocess = Preprocessing(config=config)
preprocess.create_vocabulary("Training_Shuffled_Dataset.txt")
preprocess.prepare_data()
# Preprocess Cornell data
preprocess = Preprocessing(train_path_file="cornell_dataset.txt",
test_path_file="Validation_Shuffled_Dataset.txt",
train_path_file_target="input_train_cornell",
test_path_file_target="input_test_triples",
triples=False,
config=config)
preprocess.prepare_data()
# Preprocess Twitter data
preprocess = Preprocessing(train_path_file="twitter_dataset.txt",
test_path_file="Validation_Shuffled_Dataset.txt",
train_path_file_target="input_train_twitter",
test_path_file_target="input_test_triples",
triples=False,
config=config)
