mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
62 lines
1.9 KiB
Python
62 lines
1.9 KiB
Python
#!/usr/bin/env python
|
||
# coding: utf8
|
||
"""A simple example of extracting relations between phrases and entities using
|
||
spaCy's named entity recognizer and the dependency parse. Here, we extract
|
||
money and currency values (entities labelled as MONEY) and then check the
|
||
dependency tree to find the noun phrase they are referring to – for example:
|
||
$9.4 million --> Net income.
|
||
|
||
Last updated for: spaCy 2.0.0a18
|
||
"""
|
||
from __future__ import unicode_literals, print_function
|
||
|
||
import plac
|
||
import spacy
|
||
|
||
|
||
TEXTS = [
|
||
'Net income was $9.4 million compared to the prior year of $2.7 million.',
|
||
'Revenue exceeded twelve billion dollars, with a loss of $1b.',
|
||
]
|
||
|
||
|
||
@plac.annotations(
|
||
model=("Model to load (needs parser and NER)", "positional", None, str))
|
||
def main(model='en_core_web_sm'):
|
||
nlp = spacy.load(model)
|
||
print("Loaded model '%s'" % model)
|
||
print("Processing %d texts" % len(TEXTS))
|
||
|
||
for text in TEXTS:
|
||
doc = nlp(text)
|
||
relations = extract_currency_relations(doc)
|
||
for r1, r2 in relations:
|
||
print('{:<10}\t{}\t{}'.format(r1.text, r2.ent_type_, r2.text))
|
||
|
||
|
||
def extract_currency_relations(doc):
|
||
# merge entities and noun chunks into one token
|
||
for span in [*list(doc.ents), *list(doc.noun_chunks)]:
|
||
span.merge()
|
||
|
||
relations = []
|
||
for money in filter(lambda w: w.ent_type_ == 'MONEY', doc):
|
||
if money.dep_ in ('attr', 'dobj'):
|
||
subject = [w for w in money.head.lefts if w.dep_ == 'nsubj']
|
||
if subject:
|
||
subject = subject[0]
|
||
relations.append((subject, money))
|
||
elif money.dep_ == 'pobj' and money.head.dep_ == 'prep':
|
||
relations.append((money.head.head, money))
|
||
return relations
|
||
|
||
|
||
if __name__ == '__main__':
|
||
plac.call(main)
|
||
|
||
# Expected output:
|
||
# Net income MONEY $9.4 million
|
||
# the prior year MONEY $2.7 million
|
||
# Revenue MONEY twelve billion dollars
|
||
# a loss MONEY 1b
|