def load_model(model_dir):
model_dir = pathlib.Path(model_dir)
nlp = spacy.load('en', parser=False, entity=False, add_vectors=False)
with (model_dir / 'vocab' / 'strings.json').open('r', encoding='utf8') as file_:
nlp.vocab.strings.load(file_)
nlp.vocab.load_lexemes(model_dir / 'vocab' / 'lexemes.bin')
ner = EntityRecognizer.load(model_dir, nlp.vocab, require=True)
return (nlp, ner)
def load_model(model_dir):
model_dir = pathlib.Path(model_dir)
nlp = spacy.load('en', parser=False, entity=False, add_vectors=False)
with (model_dir / 'vocab' / 'strings.json').open('r',
encoding='utf8') as file_:
nlp.vocab.strings.load(file_)
nlp.vocab.load_lexemes(model_dir / 'vocab' / 'lexemes.bin')
ner = EntityRecognizer.load(model_dir, nlp.vocab, require=True)
return (nlp, ner)
def load_model(model_dir):
model_dir = pathlib.Path(model_dir)
nlp = en_core_web_sm.load()
with (model_dir / 'vocab' / 'strings.json').open('r',
encoding='utf8') as file_:
nlp.vocab.strings.load(file_)
nlp.vocab.load_lexemes(model_dir / 'vocab' / 'lexemes.bin')
ner = EntityRecognizer.load(model_dir, nlp.vocab, require=True)
return nlp, ner
def load(cls, model_dir, entity_extractor_spacy, fine_tune_spacy_ner, spacy_nlp):
# type: (Text, Text, bool, Language) -> SpacyEntityExtractor
from spacy.pipeline import EntityRecognizer
if model_dir and entity_extractor_spacy:
ner_dir = os.path.join(model_dir, entity_extractor_spacy)
ner = EntityRecognizer.load(pathlib.Path(ner_dir), spacy_nlp.vocab)
return SpacyEntityExtractor(fine_tune_spacy_ner, ner)
else:
return SpacyEntityExtractor(fine_tune_spacy_ner)
def __init__(self,
nlp=None,
extractor_file=None,
should_fine_tune_spacy_ner=False):
self.nlp = nlp
if extractor_file:
self.ner = EntityRecognizer.load(pathlib.Path(extractor_file),
nlp.vocab)
else:
self.ner = None
self.should_fine_tune_spacy_ner = should_fine_tune_spacy_ner
def predictEnt(query):
nlp = spacy.load('en', parser=False)
doc = nlp.make_doc(query)
vocab_dir = pathlib.Path('ner/vocab')
with (vocab_dir / 'strings.json').open('r', encoding='utf8') as file_:
nlp.vocab.strings.load(file_)
nlp.vocab.load_lexemes(vocab_dir / 'lexemes.bin')
ner = EntityRecognizer.load(pathlib.Path("ner"), nlp.vocab, require=True)
nlp.tagger(doc)
ner(doc)
for word in doc:
if word.ent_type_ == 'PRODUCT':
return word.text
def predict(query):
# Load NER
nlp = spacy.load('en', parser=False, entity=False, add_vectors=False)
vocab_dir = pathlib.Path('ner/vocab')
with (vocab_dir / 'strings.json').open('r',encoding='utf8') as file_:
nlp.vocab.strings.load(file_)
nlp.vocab.load_lexemes(vocab_dir / 'lexemes.bin')
ner = EntityRecognizer.load(pathlib.Path("ner"), nlp.vocab, require=False)
doc = nlp.make_doc(query)
#nlp.tagger(doc)
ner(doc)
for word in doc:
print(word.text, word.orth, word.lower, word.ent_type_)
for word in doc:
if word.ent_type_:
print ('word -> {} and entity-> {}'.format(word.text,word.ent_type_))
def __init__(self, nlp=None, extractor_file=None):
if extractor_file:
self.ner = EntityRecognizer.load(pathlib.Path(extractor_file),
nlp.vocab)
else:
self.ner = None
def load_ner_model(vocab, path):
return EntityRecognizer.load(path, vocab)
def load_ner_model(vocab, path):
return EntityRecognizer.load(path, vocab)
