spaCy是一个Python自然语言处理工具包,诞生于2014年年中,号称“Industrial-Strength Natural Language Processing in Python”,是具有工业级强度的Python NLP工具包。spaCy里大量使用了 Cython 来提高相关模块的性能,这个区别于学术性质更浓的Python NLTK,因此具有了业界应用的实际价值。
加载模型
# 导入工具包和英文模型
# python -m spacy download en 用管理员身份打开CMD
import spacy
nlp = spacy.load('en')
文本处理
doc = nlp('Weather is good, very windy and sunny. We have no classes in the afternoon.')
# 分词
for token in doc:
print (token)
OUT:
Weather
is
good
,
very
windy
and
sunny
.
We
have
no
classes
in
the
afternoon
---------------------------------
#分句
for sent in doc.sents:
print (sent)
OUT:
Weather is good, very windy and sunny.
We have no classes in the afternoon.
词性 参考 https://www.winwaed.com/blog/2011/11/08/part-of-speech-tags/
for token in doc:
print ('{}-{}'.format(token,token.pos_))
OUT:
Weather-PROPN
is-VERB
good-ADJ
,-PUNCT
very-ADV
windy-ADJ
and-CCONJ
sunny-ADJ
.-PUNCT
We-PRON
have-VERB
no-DET
classes-NOUN
in-ADP
the-DET
afternoon-NOUN
.-PUNCT
命名体识别
doc_2 = nlp("I went to Paris where I met my old friend Jack from uni.")
for ent in doc_2.ents:
print ('{}-{}'.format(ent,ent.label_))
OUT:
Paris-GPE
Jack-PERSON
----
from spacy import displacy
doc = nlp('I went to Paris where I met my old friend Jack from uni.')
displacy.render(doc,style='ent',jupyter=True)
练习 : 找到书中所有人物名字
def read_file(file_name):
with open(file_name, 'r') as file:
return file.read()
# 加载文本数据
text = read_file('./data/pride_and_prejudice.txt')
processed_text = nlp(text)
sentences = [s for s in processed_text.sents]
print (len(sentences))
OUT:
6469
一共有6469个句子
from collections import Counter,defaultdict
def find_person(doc):
c = Counter()
for ent in processed_text.ents:
if ent.label_ == 'PERSON':
c[ent.lemma_]+=1
return c.most_common(10)
print (find_person(processed_text))
OUT:
[('elizabeth', 604), ('darcy', 276), ('jane', 274), ('bennet', 233), ('bingley', 189), ('collins', 179), ('wickham', 170), ('gardiner', 95), ('lizzy', 94), ('lady catherine', 77)]
搞定