NLTK 数据清洗示例

目录

• 数据清洗

---

数据清洗

• 去掉多余空格
• 去掉不需要特殊字符
• 去掉一些网站等没用的东西

使用正则，stopwords

import re
from nltk.corpus import stopwords
# 输入数据
s = '    RT @Amila #Test\nTom\'s newly listed Co  & Mary\'s unlisted     Group to supply tech for nlTK.\nh $TSLA $AAPL https:// t.co/x34afsfQsh'

#指定停用词
cache_english_stopwords = stopwords.words('english')

def text_clean(text):
    print('原始数据:', text, '\n')
    
    # 去掉HTML标签(e.g. &)
    text_no_special_entities = re.sub(r'\&\w*;|#\w*|@\w*', '', text)
    print('去掉特殊标签后的:', text_no_special_entities, '\n')
    
    # 去掉一些价值符号
    text_no_tickers = re.sub(r'\$\w*', '', text_no_special_entities) 
    print('去掉价值符号后的:', text_no_tickers, '\n')
    
    # 去掉超链接
    text_no_hyperlinks = re.sub(r'https?:\/\/.*\/\w*', '', text_no_tickers)
    print('去掉超链接后的:', text_no_hyperlinks, '\n')

    # 去掉一些专门名词缩写，简单来说就是字母比较少的词
    text_no_small_words = re.sub(r'\b\w{1,2}\b', '', text_no_hyperlinks) 
    print('去掉专门名词缩写后:', text_no_small_words, '\n')
    
    # 去掉多余的空格
    text_no_whitespace = re.sub(r'\s\s+', ' ', text_no_small_words)
    text_no_whitespace = text_no_whitespace.lstrip(' ') 
    print('去掉空格后的:', text_no_whitespace, '\n')
    
    # 分词
    tokens = word_tokenize(text_no_whitespace)
    print('分词结果:', tokens, '\n')    
          
    # 去停用词
    list_no_stopwords = [i for i in tokens if i not in cache_english_stopwords]
    print('去停用词后结果:', list_no_stopwords, '\n')
    # 过滤后结果
    text_filtered =' '.join(list_no_stopwords) # ''.join() would join without spaces between words.
    print('过滤后:', text_filtered)

text_clean(s)

---