def __init__(self,
np2vec_model_file,
binary=False,
word_ngrams=False,
grouping=False):
"""
Load the np2vec model for set expansion.
Args:
np2vec_model_file (str): the file containing the np2vec model to load
binary (bool): boolean indicating whether the np2vec model to load is in binary format
word_ngrams (int {1,0}): If 1, np2vec model to load uses word vectors with subword (
ngrams) information.
Returns:
np2vec model to load
"""
self.grouping = grouping
if grouping:
# load grouping info
logger.info('loading grouping data')
self.id2rep = load_json_file(path.join(cur_dir, 'id2rep'))
self.np2id = load_json_file(path.join(cur_dir, 'np2id'))
self.id2group = load_json_file(path.join(cur_dir, 'id2group'))
logger.info('loadind model...')
self.np2vec_model = NP2vec.load(np2vec_model_file,
binary=binary,
word_ngrams=word_ngrams)
# extract the first term of the model in order to get the marking character
logger.info('compute L2 norm')
first_term = next(iter(self.np2vec_model.vocab.keys()))
self.mark_char = first_term[-1]
# Precompute L2-normalized vectors.
self.np2vec_model.init_sims()
logger.info('done init')
def __init__(
self,
np2vec_model_file,
binary=False,
word_ngrams=False,
grouping=False,
light_grouping=False,
grouping_map_dir=None,
):
"""
Load the np2vec model for set expansion.
Args:
np2vec_model_file (str): the file containing the np2vec model to load
binary (bool): boolean indicating whether the np2vec model to load is in binary format
word_ngrams (int {1,0}): If 1, np2vec model to load uses word vectors with subword (
ngrams) information.
light_grouping (bool): boolean indicating whether to load all maps for grouping.
grouping_map_dir (str): path to the directory containing maps for grouping.
Returns:
np2vec model to load
"""
self.grouping = grouping
if grouping:
# load grouping info
logger.info("loading grouping data")
if not grouping_map_dir:
grouping_map_dir = path.dirname(np2vec_model_file)
self.np2id = load_json_file(path.join(grouping_map_dir, "np2id"))
if not light_grouping:
self.id2rep = load_json_file(path.join(grouping_map_dir, "id2rep"))
self.id2group = load_json_file(path.join(grouping_map_dir, "id2group"))
logger.info("loadind model...")
self.np2vec_model = NP2vec.load(np2vec_model_file, binary=binary, word_ngrams=word_ngrams)
# extract the first term of the model in order to get the marking character
logger.info("compute L2 norm")
first_term = next(iter(self.np2vec_model.vocab.keys()))
self.mark_char = first_term[-1]
# Precompute L2-normalized vectors.
self.np2vec_model.init_sims()
logger.info("done init")
arg_parser.add_argument(
'--word_ngrams',
default=0,
type=int,
choices=[0, 1],
help=
'If 0, the model to load stores word information. If 1, the model to load stores '
'subword (ngrams) information; note that subword information is relevant only to '
'fasttext models.')
arg_parser.add_argument(
'--mark_char',
default='_',
type=str,
action=check_size(1, 2),
help='special character that marks word separator and NP suffix.')
arg_parser.add_argument('--np',
default='Intel Corp.',
type=str,
action=check_size(min_size=1),
required=True,
help='NP to print its word vector.')
args = arg_parser.parse_args()
np2vec_model = NP2vec.load(args.np2vec_model_file,
binary=args.binary,
word_ngrams=args.word_ngrams)
print("word vector for the NP \'" + args.np + "\':",
np2vec_model[args.mark_char.join(args.np.split()) + args.mark_char])
action='store_true')
arg_parser.add_argument(
'--word_ngrams',
default=0,
type=int,
choices=[0, 1],
help='If 0, the model to load stores word information. If 1, the model to load stores '
'subword (ngrams) information; note that subword information is relevant only to '
'fasttext models.')
arg_parser.add_argument(
'--mark_char',
default='_',
type=str,
action=check_size(1, 2),
help='special character that marks word separator and NP suffix.')
arg_parser.add_argument(
'--np',
default='Intel Corp.',
type=str,
action=check_size(min=1),
help='NP to print its word vector.')
args = arg_parser.parse_args()
np2vec_model = NP2vec.load(
args.np2vec_model_file,
binary=args.binary,
word_ngrams=args.word_ngrams)
print("word vector for the NP \'" + args.np + "\':", np2vec_model[args.mark_char.join(
args.np.split()) + args.mark_char])