【NLP】NLTK学习笔记

from bs4 import BeautifulSoup
import requests

# 先用爬虫获取一段语料
text = BeautifulSoup(requests.get('https://www.python.org/').text, 'lxml').get_text()


import nltk

freq_dist = nltk.FreqDist(text.split())  # 类似 Counter 的词频统计
freq_dist.plot(50, cumulative=False)  # 画图

from nltk.corpus import wordnet

wordnet.synsets('motorcar')  # 返回一个对象，等同于 wordnet.synset('car.n.01')，含义是 car 的名词释义中的第1个

wordnet.synset('car.n.01').lemma_names()  # 返回同义词：['car', 'auto', 'automobile', 'machine', 'motorcar']


# 有些词是一词多义的，例如 car
wordnet.synsets('car')  # 返回 5 类近义词
# 用一样的方法打印每个类型都有哪些近义词
for i in wordnet.synsets('car'):
    print(i.lemma_names())


# 得到：
# ['car', 'auto', 'automobile', 'machine', 'motorcar']
# ['car', 'railcar', 'railway_car', 'railroad_car']
# ['car', 'gondola']
# ['car', 'elevator_car']
# ['cable_car', 'car']

# 动作的蕴含关系：
wordnet.synset('walk.v.01').entailments()  # [Synset('step.v.01')]
wordnet.synset('eat.v.01').entailments()  # [Synset('chew.v.01'), Synset('swallow.v.01')]
wordnet.synset('tease.v.03').entailments() #[Synset('arouse.v.07'), Synset('disappoint.v.01')]


# 反义词
wordnet.lemma('supply.n.02.supply').antonyms()  # [Lemma('demand.n.02.demand')]