def __init__(self,
model,
optimizer,
train_dataset,
test_dataset,
num_folds=config.num_folds,
loss_function=None):
self.num_folds = num_folds
assert num_folds >= 1
self.use_crf = config.use_crf
vocab = Vocab.from_files(
[config.dataset_path, config.test_dataset_path],
store=config.mapping_file)
#self.train_dataset = ReviewDataset(config.dataset_path, preprocessed= False, vocab= vocab)
#self.test_dataset = ReviewDataset(config.test_dataset_path, preprocessed= False, vocab= vocab)
#self.model = model( vocab, embedding_path= config.word_embedding_path, use_crf= config.use_crf ).to(config.device)
self.train_dataset = train_dataset
self.test_dataset = test_dataset
self.model = model
self.optimizer = optimizer(self.model.parameters())
if not self.use_crf and loss_function is None:
raise Exception(
' Loss function must be specified when crf is not being used ')
self.device = torch.device(
config.device if torch.cuda.is_available() else 'cpu')
self.model.to(self.device)
print('using device: ', self.device)
'adam': torch.optim.Adam, # default lr=0.001
'adamax': torch.optim.Adamax, # default lr=0.002
'asgd': torch.optim.ASGD, # default lr=0.01
'rmsprop': torch.optim.RMSprop, # default lr=0.01
'sgd': torch.optim.SGD,
}
models = {
'lstm': LSTM,
'attention_lstm': AttentionAspectExtraction,
'global_attention_lstm': GlobalAttentionAspectExtraction,
'hsan': HSAN,
'decnn': DECNN
}
vocab = Vocab.from_files([config.dataset_path, config.test_dataset_path],
store=config.mapping_file)
train_dataset = ReviewDataset(config.dataset_path,
preprocessed=False,
vocab=vocab)
test_dataset = ReviewDataset(config.test_dataset_path,
preprocessed=False,
vocab=vocab)
network = models[config.model](vocab,
embedding_path=config.word_embedding_path,
lambda1=config.lambda1,
use_crf=config.use_crf).to(config.device)
trainer = Trainer(network,
optimizers[config.optimizer],
train_dataset,
test_dataset,
import numpy as np
import json
from data_utils import Vocab
vocab = {}
vectors = []
index = 0
train_dataset = './datasets/Restaurants_Train.xml'
test_dataset = './datasets/Restaurants_Test.xml'
mapping_file = './embeddings/restaurant_mapping.json'
vocab = Vocab.from_files([train_dataset, test_dataset],
store=mapping_file).get_vocab()
embedding = np.zeros((len(vocab), 200))
with open('embeddings/glove/glove.6B.100d.txt', 'r', encoding='utf-8') as f:
for line in f:
values = line.split()
word = values[0]
if word in vocab:
vector = np.asarray(values[1:])
embedding[vocab[word], :100] = vector
print('glove done')
with open('embeddings/domain_embedding/restaurant_emb.vec',
'r',
encoding='utf-8') as f:
for line in f:
