def create_alphabets(alphabet_directory, train_path, data_paths=None, max_vocabulary_size=100000, embedd_dict=None,
min_occurrence=1, normalize_digits=True):
def expand_vocab():
vocab_set = set(vocab_list)
for data_path in data_paths:
# logger.info("Processing data: %s" % data_path)
with open(data_path, 'r') as file:
for line in file:
line = line.strip()
if len(line) == 0:
continue
tokens = line.split(' ')
word = DIGIT_RE.sub("0", tokens[0]) if normalize_digits else tokens[0]
pos = tokens[1]
chunk = tokens[2]
ner = tokens[3]
pos_alphabet.add(pos)
chunk_alphabet.add(chunk)
ner_alphabet.add(ner)
if word not in vocab_set and (word in embedd_dict or word.lower() in embedd_dict):
vocab_set.add(word)
vocab_list.append(word)
logger = get_logger("Create Alphabets")
word_alphabet = Alphabet('word', default_value=True, singleton=True)
char_alphabet = Alphabet('character', default_value=True)
pos_alphabet = Alphabet('pos')
chunk_alphabet = Alphabet('chunk')
ner_alphabet = Alphabet('ner')
if not os.path.isdir(alphabet_directory):
logger.info("Creating Alphabets: %s" % alphabet_directory)
char_alphabet.add(PAD_CHAR)
pos_alphabet.add(PAD_POS)
chunk_alphabet.add(PAD_CHUNK)
ner_alphabet.add(PAD_NER)
vocab = defaultdict(int)
with open(train_path, 'r') as file:
for line in file:
line = line.strip()
if len(line) == 0:
continue
tokens = line.split(' ')
for char in tokens[0]:
char_alphabet.add(char)
word = DIGIT_RE.sub("0", tokens[0]) if normalize_digits else tokens[0]
vocab[word] += 1
pos = tokens[1]
pos_alphabet.add(pos)
chunk = tokens[2]
chunk_alphabet.add(chunk)
ner = tokens[3]
ner_alphabet.add(ner)
# collect singletons
singletons = set([word for word, count in vocab.items() if count <= min_occurrence])
# if a singleton is in pretrained embedding dict, set the count to min_occur + c
if embedd_dict is not None:
assert isinstance(embedd_dict, OrderedDict)
for word in vocab.keys():
if word in embedd_dict or word.lower() in embedd_dict:
vocab[word] += min_occurrence
vocab_list = _START_VOCAB + sorted(vocab, key=vocab.get, reverse=True)
logger.info("Total Vocabulary Size: %d" % len(vocab_list))
logger.info("Total Singleton Size: %d" % len(singletons))
vocab_list = [word for word in vocab_list if word in _START_VOCAB or vocab[word] > min_occurrence]
logger.info("Total Vocabulary Size (w.o rare words): %d" % len(vocab_list))
if len(vocab_list) > max_vocabulary_size:
vocab_list = vocab_list[:max_vocabulary_size]
if data_paths is not None and embedd_dict is not None:
expand_vocab()
for word in vocab_list:
word_alphabet.add(word)
if word in singletons:
word_alphabet.add_singleton(word_alphabet.get_index(word))
word_alphabet.save(alphabet_directory)
char_alphabet.save(alphabet_directory)
pos_alphabet.save(alphabet_directory)
chunk_alphabet.save(alphabet_directory)
ner_alphabet.save(alphabet_directory)
else:
word_alphabet.load(alphabet_directory)
char_alphabet.load(alphabet_directory)
pos_alphabet.load(alphabet_directory)
chunk_alphabet.load(alphabet_directory)
ner_alphabet.load(alphabet_directory)
word_alphabet.close()
char_alphabet.close()
pos_alphabet.close()
chunk_alphabet.close()
ner_alphabet.close()
logger.info("Word Alphabet Size (Singleton): %d (%d)" % (word_alphabet.size(), word_alphabet.singleton_size()))
logger.info("Character Alphabet Size: %d" % char_alphabet.size())
logger.info("POS Alphabet Size: %d" % pos_alphabet.size())
logger.info("Chunk Alphabet Size: %d" % chunk_alphabet.size())
logger.info("NER Alphabet Size: %d" % ner_alphabet.size())
return word_alphabet, char_alphabet, pos_alphabet, chunk_alphabet, ner_alphabet
def create_alphabets(alphabet_directory, train_path, data_paths=None, max_vocabulary_size=100000, embedd_dict=None,
min_occurrence=1, normalize_digits=True):
def expand_vocab():
vocab_set = set(vocab_list)
for data_path in data_paths:
with open(data_path, 'r') as file:
for line in file:
line = line.strip()
if len(line) == 0:
continue
tokens = line.split('\t')[0].split(' ')
for token in tokens:
word = DIGIT_RE.sub("0", token) if normalize_digits else token
if word not in vocab_set and (word in embedd_dict or word.lower() in embedd_dict):
vocab_set.add(word)
vocab_list.append(word)
logger = get_logger("Create Alphabets")
word_alphabet = Alphabet('word', singleton=True)
if not os.path.isdir(alphabet_directory):
logger.info("Creating Alphabets: %s" % alphabet_directory)
vocab = defaultdict(int)
with open(train_path, 'r') as file:
for line in file:
line = line.strip()
if len(line) == 0:
continue
tokens = line.split('\t')[0].split(' ')
for token in tokens:
word = DIGIT_RE.sub("0", token) if normalize_digits else token
vocab[word] += 1
# collect singletons
singletons = set([word for word, count in vocab.items() if count <= min_occurrence])
# if a singleton is in pretrained embedding dict, set the count to min_occur + c
if embedd_dict is not None:
assert isinstance(embedd_dict, OrderedDict)
for word in vocab.keys():
if word in embedd_dict or word.lower() in embedd_dict:
vocab[word] += min_occurrence
vocab_list = _START_VOCAB + sorted(vocab, key=vocab.get, reverse=True)
logger.info("Total Vocabulary Size: %d" % len(vocab_list))
logger.info("Total Singleton Size: %d" % len(singletons))
multi_vocab = [word for word in vocab_list if word in _START_VOCAB or vocab[word] > min_occurrence]
logger.info("Total Vocabulary Size (w.o rare words): %d" % len(multi_vocab))
if len(vocab_list) > max_vocabulary_size:
vocab_list = vocab_list[:max_vocabulary_size]
if data_paths is not None and embedd_dict is not None:
expand_vocab()
for word in vocab_list:
if word in multi_vocab:
word_alphabet.add(word)
elif word in singletons:
word_alphabet.add_singleton(word_alphabet.get_index(word))
else:
raise ValueError("Error word: " + word)
refiner = UNKRefiner(0, word_alphabet)
# TODO fix the pos here
for word in singletons:
unk_signature = refiner.refine(word, 0)
word_alphabet.add(unk_signature)
word_alphabet.save(alphabet_directory)
else:
word_alphabet.load(alphabet_directory)
word_alphabet.close()
logger.info("Word Alphabet Size (Singleton): %d (%d)" % (word_alphabet.size(), word_alphabet.singleton_size()))
return word_alphabet