spaCy/spacy/sandbox_test_sofie/testing_el.py

# coding: utf-8
import spacy
from spacy.kb import KnowledgeBase


def create_kb():
    mykb = KnowledgeBase()

    print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
    print()

    # adding entities
    entity_0 = "Q0"  # douglas adams
    print(" adding entity", entity_0)
    mykb.add_entity(entity_id=entity_0, prob=0.5)

    entity_42 = "Q42"   # douglas adams
    print(" adding entity", entity_42)
    mykb.add_entity(entity_id=entity_42, prob=0.5)

    entity_5301561 = "Q5301561"
    print(" adding entity", entity_5301561)
    mykb.add_entity(entity_id=entity_5301561, prob=0.5)

    print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
    print()

    # adding aliases
    alias1 = "douglassss"
    print(" adding alias", alias1, "to Q42 and Q5301561")
    mykb.add_alias(alias=alias1, entities=["Q42", "Q5301561"], probabilities=[0.8, 0.2])

    alias3 = "adam"
    print(" adding alias", alias3, "to Q42")
    mykb.add_alias(alias=alias3, entities=["Q42"], probabilities=[0.9])

    print("kb size", len(mykb), mykb.get_size_entities(), mykb.get_size_aliases())
    print()

    return mykb


def add_el(kb):
    nlp = spacy.load('en_core_web_sm')
    print("pipes before:", nlp.pipe_names)

    el_pipe = nlp.create_pipe(name='el', config={"kb": kb})
    nlp.add_pipe(el_pipe, last=True)

    print("pipes after:", nlp.pipe_names)
    print()

    text = "The Hitchhiker's Guide to the Galaxy, written by Douglas Adams, reminds us to always bring our towel."
    doc = nlp(text)

    for token in doc:
        print("token", token.text, token.ent_type_, token.ent_kb_id_)

    print()
    for ent in doc.ents:
        print("ent", ent.text, ent.label_, ent.kb_id_)

    print()
    for alias in ["douglassss", "rubbish", "adam"]:
        candidates = nlp.linker.kb.get_candidates(alias)
        print(len(candidates), "candidates for", alias)


if __name__ == "__main__":
    mykb = create_kb()
    add_el(mykb)