def load_word2vec_as_vocab_tensor(
path,
delimiter=' ',
cache=True) -> Tuple[Dict[str, int], torch.Tensor]:
realpath = get_resource(path)
vocab_path = replace_ext(realpath, '.vocab')
matrix_path = replace_ext(realpath, '.pt')
if cache:
try:
flash(
'Loading vocab and matrix from cache [blink][yellow]...[/yellow][/blink]'
)
vocab = load_pickle(vocab_path)
matrix = torch.load(matrix_path, map_location='cpu')
flash('')
return vocab, matrix
except IOError:
pass
word2vec, dim = load_word2vec(path, delimiter, cache)
vocab = dict((k, i) for i, k in enumerate(word2vec.keys()))
matrix = torch.Tensor(list(word2vec.values()))
if cache:
flash('Caching vocab and matrix [blink][yellow]...[/yellow][/blink]')
save_pickle(vocab, vocab_path)
torch.save(matrix, matrix_path)
flash('')
return vocab, matrix
def load_word2vec(path, delimiter=' ', cache=True) -> Tuple[Dict[str, np.ndarray], int]:
realpath = get_resource(path)
binpath = replace_ext(realpath, '.pkl')
if cache:
try:
flash('Loading word2vec from cache [blink][yellow]...[/yellow][/blink]')
word2vec, dim = load_pickle(binpath)
flash('')
return word2vec, dim
except IOError:
pass
dim = None
word2vec = dict()
f = TimingFileIterator(realpath)
for idx, line in enumerate(f):
f.log('Loading word2vec from text file [blink][yellow]...[/yellow][/blink]')
line = line.rstrip().split(delimiter)
if len(line) > 2:
if dim is None:
dim = len(line)
else:
if len(line) != dim:
logger.warning('{}#{} length mismatches with {}'.format(path, idx + 1, dim))
continue
word, vec = line[0], line[1:]
word2vec[word] = np.array(vec, dtype=np.float32)
dim -= 1
if cache:
flash('Caching word2vec [blink][yellow]...[/yellow][/blink]')
save_pickle((word2vec, dim), binpath)
flash('')
return word2vec, dim
def batch_remove_empty_category_if_necessary(json_files):
for each in json_files:
src = get_resource(each)
dst = replace_ext(src, '.noempty.txt')
if not os.path.isfile(dst):
remove_all_ec(src)