初学者|一起学学SpaCy

点击上方蓝色字体，关注AI小白入门哟

跟着博主的脚步，每天进步一点点

本文简绍了SpaCy的使用方法，据其官网所言，spaCy是世界上最快的工业级自然语言处理工具。

简介

spaCy是世界上最快的工业级自然语言处理工具。 支持多种自然语言处理基本功能。

spaCy主要功能包括分词、词性标注、词干化、命名实体识别、名词短语提取等等。

官网地址：https://spacy.io/

实战

1.安装

# 安装：pip install spaCy# 国内源安装：pip install spaCy  -i https://pypi.tuna.tsinghua.edu.cn/simpleimport spacynlp = spacy.load('en')doc = nlp(u'This is a sentence.')
# 国内源安装：pip install spaCy  -i https://pypi.tuna.tsinghua.edu.cn/simple
import spacy
nlp = spacy.load('en')
doc = nlp(u'This is a sentence.')

2.tokenize功能

for token in doc:    print(token)Thisisasentence.in doc:
    print(token)

This
is
a
sentence
.

3.词干化（Lemmatize)

for token in doc:    print(token, token.lemma_, token.lemma)This this 1995909169258310477is be 10382539506755952630a a 11901859001352538922sentence sentence 18108853898452662235. . 12646065887601541794in doc:
    print(token, token.lemma_, token.lemma)

This this 1995909169258310477
is be 10382539506755952630
a a 11901859001352538922
sentence sentence 18108853898452662235
. . 12646065887601541794

4.词性标注(POS Tagging)

for token in doc:    print(token, token.pos_, token.pos)This DET 89is VERB 99a DET 89sentence NOUN 91. PUNCT 96in doc:
    print(token, token.pos_, token.pos)

This DET 89
is VERB 99
a DET 89
sentence NOUN 91
. PUNCT 96

5.命名实体识别（NER）

for entity in doc.ents:    print(entity, entity.label_, entity.label)in doc.ents:
    print(entity, entity.label_, entity.label)

6.名词短语提取

for nounc in doc.noun_chunks:    print(nounc)a sentencein doc.noun_chunks:
    print(nounc)

a sentence

代码已上传：https://github.com/yuquanle/StudyForNLP/blob/master/NLPtools/SpacyDemo.ipynb

The End

长按二维码关注
AI小白入门

ID:StudyForAI

学习AI学习ai(爱)

期待与您的相遇~