Получение вероятностей прогнозирования для объекта из модели Spacy NER не является тривиальным. Вот решение, адаптированное с здесь :
import spacy
from collections import defaultdict
texts = ['John works at Microsoft.']
# Number of alternate analyses to consider. More is slower, and not necessarily better -- you need to experiment on your problem.
beam_width = 16
# This clips solutions at each step. We multiply the score of the top-ranked action by this value, and use the result as a threshold. This prevents the parser from exploring options that look very unlikely, saving a bit of efficiency. Accuracy may also improve, because we've trained on greedy objective.
beam_density = 0.0001
nlp = spacy.load('en_core_web_md')
docs = list(nlp.pipe(texts, disable=['ner']))
beams = nlp.entity.beam_parse(docs, beam_width=beam_width, beam_density=beam_density)
for doc, beam in zip(docs, beams):
entity_scores = defaultdict(float)
for score, ents in nlp.entity.moves.get_beam_parses(beam):
for start, end, label in ents:
entity_scores[(start, end, label)] += score
l= []
for k, v in entity_scores.items():
l.append({'start': k[0], 'end': k[1], 'label': k[2], 'prob' : v} )
for a in sorted(l, key= lambda x: x['start']):
print(a)
### Output: ####
{'start': 0, 'end': 1, 'label': 'PERSON', 'prob': 0.4054479906820232}
{'start': 0, 'end': 1, 'label': 'ORG', 'prob': 0.01002015005487447}
{'start': 0, 'end': 1, 'label': 'PRODUCT', 'prob': 0.0008592912552754791}
{'start': 0, 'end': 1, 'label': 'WORK_OF_ART', 'prob': 0.0007666755792166002}
{'start': 0, 'end': 1, 'label': 'NORP', 'prob': 0.00034931990870877333}
{'start': 0, 'end': 1, 'label': 'TIME', 'prob': 0.0002786051849320804}
{'start': 3, 'end': 4, 'label': 'ORG', 'prob': 0.9990115861687987}
{'start': 3, 'end': 4, 'label': 'PRODUCT', 'prob': 0.0003378157477046507}
{'start': 3, 'end': 4, 'label': 'FAC', 'prob': 8.249734411749544e-05}