数据分析 小白笔记
1、文本分词
import jieba
s = "中国新闻网8677条新闻"
cut = jieba.lcut(s)
print(cut)
2、去停用词
下载停用词库
import jieba
stop_words = []
s = "中国0新闻网不问8677条新闻"
def load_stop_words(path = 'stop_words.txt'):
with open(path,'r') as f:
for line in f:
content = line.strip()
stop_words.append(content)
load_stop_words()
lcut = jieba.lcut(s)
cut = [x for x in lcut if x not in stop_words]
print(cut)