def load_pkuseg_processors(path):
try:
import pkuseg
except ImportError:
if self.use_pkuseg:
raise ImportError(self._pkuseg_install_msg)
if self.pkuseg_seg:
data = srsly.read_msgpack(path)
(user_dict, do_process, common_words, other_words) = data
self.pkuseg_seg.preprocesser = pkuseg.Preprocesser(user_dict)
self.pkuseg_seg.postprocesser.do_process = do_process
self.pkuseg_seg.postprocesser.common_words = set(common_words)
self.pkuseg_seg.postprocesser.other_words = set(other_words)
def from_disk(self, path: Union[Path, str], exclude: Sequence[str] = tuple()):
"""Load a Sense2Vec object from a directory.
path (unicode / Path): The path to load from.
exclude (list): Names of serialization fields to exclude.
RETURNS (Sense2Vec): The loaded object.
"""
path = Path(path)
strings_path = path / "strings.json"
freqs_path = path / "freqs.json"
cache_path = path / "cache"
self.vectors = Vectors().from_disk(path)
self.cfg.update(srsly.read_json(path / "cfg"))
if freqs_path.exists():
self.freqs = dict(srsly.read_json(freqs_path))
if "strings" not in exclude and strings_path.exists():
self.strings = StringStore().from_disk(strings_path)
if "cache" not in exclude and cache_path.exists():
self.cache = srsly.read_msgpack(cache_path)
self._row2key = None
return self
def load_patterns(p):
self.add_patterns(srsly.read_msgpack(p))