利用tf-idf提取关键词_analyse.tfidf

##读取.txt并保存为.txt

from jieba import analyse

f = open("result.txt", "w", encoding="utf-8")
for line in open("text.txt",encoding="utf-8"):
    tfidf = analyse.extract_tags
    text = line
    keywords = tfidf(text, topK=4, withWeight=False, allowPOS=())
    content_text = ' '.join(keywords)
    print(content_text)
    f.write(text)
    f.write(content_text)
    f.write("\n")
f.close()

1
2
3
4
5
6
7
8
9
10
11
12
13
14

##读取.xlsx并保存为.xlsx

from jieba import analyse
from openpyxl import load_workbook   #导入模块
wb = load_workbook(filename="data.xlsx")    # 打开文件, 默认可读写, 若有需要可以指定 write_only和read_only 为True
sheet = wb["Sheet1"]   # 找到工作表
for i in range(3,sheet.max_row+1):
    text = sheet.cell(row=i, column=2).value
    tfidf = analyse.extract_tags
    keywords = tfidf(text, topK=4, withWeight=False, allowPOS=())
    content_text = " ".join(keywords)
    sheet.cell(row=i, column=3, value=content_text)
wb.save('test1.xlsx')
1
2
3
4
5
6
7
8
9
10
11