# Get arguments
print('Getting arguments...')
args = get_args()
# make a dataset
print('Importing dataset...')
data = SentimentDataset(data=args.train_path)
# preprocess and save word encodings
preprocessor = Preprocessor(max_vocab=args.max_vocab)
data = preprocessor.fit_transform(dataset=data)
preprocessor.save(args.prepro_save_path)
# validation split
data.split_data(validation_count=args.validation_count)
train_ds, val_ds = data.to_dataset()
# to dataLoaders
train_set = DataLoader(train_ds, batch_size=args.batch_size, shuffle=True)
val_set = DataLoader(val_ds, batch_size=args.batch_size, shuffle=False)
print('Initializing model...')
mod = SentimentModel(
len(preprocessor.vocab2enc) + 3, args.embedding_dim, args.hidden_dim)
opt = Adam(mod.parameters(), lr=args.lr)
print('Training...')
fit(training=train_set,
model=mod,
validation=val_set,
optimizer=opt,
return parser.parse_args()
if __name__ == '__main__':
# Get arguments
print('Getting arguments...')
args = get_args()
# make a dataset
print('Importing dataset...')
data = SentimentDataset(data=args.test_path)
# preprocess and save word encodings
preprocessor = Preprocessor(max_vocab=args.max_vocab)
preprocessor.load()
data = preprocessor.transform(dataset=data)
# validation split
test_ds, _ = data.to_dataset()
# to dataLoaders
test_set = DataLoader(test_ds, batch_size=16, shuffle=False)
# load saved model
print('Loading trained model...')
model = torch.load(args.model_path)
model.eval()
test(test_set, model, val=False)