Displacy for Custom NER

23 Aug 2020

import spacy
nlp = spacy.load('en')

from spacy import displacy
def explain_text_entities(text):
    doc = nlp(text)
    for ent in doc.ents:
        print(f'Entity: {ent}, Label: {ent.label_}, {spacy.explain(ent.label_)}')
    displacy.render(doc, style='ent', jupyter=True)

t = 'No different than Apple ORG . To play a specific list of music you must have an Amazon of Spotify PRODUCT “plus/prime/etc” account. So you must pay to play “your” music. 3 CARDINAL stars for that reason. Everything else is great .'

explain_text_entities(t)

Entity: Apple ORG, Label: ORG, Companies, agencies, institutions, etc.
Entity: 3, Label: CARDINAL, Numerals that do not fall under another type

No different than Apple ORG ORG . To play a specific list of music you must have an Amazon of Spotify PRODUCT “plus/prime/etc” account. So you must pay to play “your” music. 3 CARDINAL CARDINAL stars for that reason. Everything else is great .