class Corpus(object):
def __init__(self, path):
self.dictionary = Dictionary()
self.train = self.tokenize(os.path.join(path, 'train.txt'))
self.valid = self.tokenize(os.path.join(path, 'valid.txt'))
self.test = self.tokenize(os.path.join(path, 'test.txt'))
def tokenize(self, path):
"""Tokenizes a text file."""
assert os.path.exists(path)
# Add words to the dictionary
with open(path, 'r') as f:
tokens = 0
for line in f:
words = line.split() + ['<eos>']
tokens += len(words)
for word in words:
self.dictionary.add_word(word)
# Tokenize file content
with open(path, 'r') as f:
ids = torch.LongTensor(tokens)
token = 0
for line in f:
words = line.split() + ['<eos>']
for word in words:
ids[token] = self.dictionary.word2idx[word]
token += 1
return ids
