TextBlob(https://textblob.readthedocs.io/en/dev/index.html)是一个用于处理文本数据的Python库。它提供一个简单的API,可用于深入研究常见的NLP任务,如词性标注、名词短语提取、情感分析、文本翻译、分类等。
官方文档:https://textblob.readthedocs.io/en/dev/
目录
情感指的是隐藏在句子中的观点,极性(polarity)定义句子中的消极性或积极性,主观性(subjectivity)暗示句子的表达的含糊的、还是肯定的。
返回一个元组 Sentiment(polarity, subjectivity)
.
polarity: [-1.0, 1.0]. -1.0 消极,1.0积极
subjectivity: [0.0, 1.0] 0.0 表示客观,1.0表示主观.
from textblob import TextBlob
text = "Textblob is amazingly simple to use. What great fun!"
blob = TextBlob(text) # 创建一个textblob对象
from textblob import TextBlob
result = blob.sentiment
# Sentiment(polarity=0.39166666666666666, subjectivity=0.4357142857142857)
polarity = blob.sentiment.polarity # 0.39166666666666666
wiki = TextBlob("Python is a high-level, general-purpose programming language.")
tag = wiki.tags
# [('Python', 'NNP'), ('is', 'VBZ'), ('a', 'DT'), ('high-level', 'JJ'), ('general-purpose', 'JJ'), ('programming', 'NN'), ('language', 'NN')]
blob = TextBlob("Beautiful is better than ugly. "
"Explicit is better than implicit. "
"Simple is better than complex.")
word = blob.words
sentence = blob.sentences
'''
['Beautiful', 'is', 'better', 'than', 'ugly', 'Explicit', 'is', 'better', 'than', 'implicit', 'Simple', 'is', 'better', 'than', 'complex']
[Sentence("Beautiful is better than ugly."),
Sentence("Explicit is better than implicit."),
Sentence("Simple is better than complex.")]
'''
list = wiki.noun_phrases
# ['python']
singularize() 变单数, pluralize()变复数,用在对名词进行处理,且会考虑特殊名词单复数形式
sentence = TextBlob('Use 4 spaces per indentation level.')
word = sentence.words
danshu = word[2].singularize() # space
fushu = word[-1].pluralize() # levels
lemmatize() 方法 对单词进行词形还原,名词找单数,动词找原型。所以需要一次处理名词,一次处理动词。
from textblob import Word
w1 = Word('apples')
result1 = w1.lemmatize() # 默认只处理名词 apple
w2 = Word('went')
result2 = w2.lemmatize("v") # 对动词原型处理 go
# 1.获取近义词
from textblob import Word
from textblob.wordnet import VERB
result1 = Word("hack").synsets
result2 = Word("hack").get_synsets(pos=VERB)
#get_synsets(): 只查找 该词作为 动词 的集合,参数为空时和synsets方法相同
'''
result1:[Synset('hack.n.01'), Synset('machine_politician.n.01'), Synset('hack.n.03'),
Synset('hack.n.04'), Synset('cab.n.03'), Synset('hack.n.06'), Synset('hack.n.07'),
Synset('hack.n.08'), Synset('chop.v.05'), Synset('hack.v.02'), Synset('hack.v.03'),
Synset('hack.v.04'), Synset('hack.v.05'), Synset('hack.v.06'), Synset('hack.v.07'), Synset('hack.v.08')]
result2:[Synset('chop.v.05'), Synset('hack.v.02'), Synset('hack.v.03'), Synset('hack.v.04'),
Synset('hack.v.05'), Synset('hack.v.06'), Synset('hack.v.07'), Synset('hack.v.08')]
'''
2. 获取近义词的定义
defi = result1[1].definition() # 获取定义
#defi结果: a politician who belongs to a small clique that controls a political party for private rather than public ends
3. 获取单词本身的定义
defi = Word("octopus").definitions
# ['tentacles of octopus prepared as food', 'bottom-living cephalopod having a soft oval body with eight long tentacles']
b = TextBlob("I havv goood speling!")
b_corr = b.correct()
print(b_corr) # I have good spelling!
word.spellcheck()方法,返回带有拼写建议的(word,confidence)元组列表
from textblob import Word
w = Word('falibility')
w_ = w.spellcheck()
print(w_) # [('fallibility', 1.0)]
monty = TextBlob("We are no longer the Knights who say Ni. "
"We are now the Knights who say Ekki ekki ekki PTANG.")
#(1)方式1
counts = monty.word_counts['ekki'] # 不区分大小写
print(counts) # 3
#(2)方式2
counts2 = monty.words.count('ekki')
print(counts2) # 3
#(3)方式3
counts3 = monty.words.count('ekki', case_sensitive=True) # 设置大小写敏感,默认不区分
print(counts3) # 2
counts4 = wiki.noun_phrases.count('python') # 短语频次
print(counts4) # 1
en_blob = TextBlob('Simple is better than complex.')
lang = en_blob.translate(to='es') # from_lang默认 en
print(lang)
# TextBlob("Simple es mejor que complejo.")
chinese_blob = TextBlob("美丽优于丑陋")
lang = chinese_blob.translate(from_lang="zh-CN", to='en')
print(lang)
# TextBlob("Beautiful is better than ugly")