python TF-IDF算法实现文本关键词提取？相信很多没有经验的人对此束手无策，为此本文总结了问题出现的原因和解决方法，通过这篇文章希望你能解决这个问题。
TF-IDF算法步骤：
（1）、计算词频：
词频 = 某个词在文章中出现的次数
考虑到文章有长短之分，考虑到不同文章之间的比较，将词频进行标准化
词频 = 某个词在文章中出现的次数/文章的总词数
词频 = 某个词在文章中出现的次数/该文出现次数最多的词出现的次数
（2）、计算逆文档频率
需要一个语料库（corpus）来模拟语言的使用环境。
逆文档频率 = log(语料库的文档总数/(包含该词的文档数 + 1))
（3）、计算TF-IDF
TF-IDF = 词频（TF）* 逆文档频率（IDF）
详细代码如下：
#!/usr/bin/env python
#-*- coding:utf-8 -*-
'''
计算文档的TF-IDF
'''
import codecs
import os
import math
import shutil
#读取文本文件
def readtxt(path):
with codecs.open(path,"r",encoding="utf-8") as f:
content = f.read().strip()
return content
#统计词频
def count_word(content):
word_dic ={}
words_list = content.split("/")
del_word = ["\r\n","/s"," ","/n"]
for word in words_list:
if word not in del_word:
if word in word_dic:
word_dic[word] = word_dic[word]+1
else:
word_dic[word] = 1
return word_dic
#遍历文件夹
def funfolder(path):
filesArray = []
for root,dirs,files in os.walk(path):
for file in files:
each_file = str(root+"//"+file)
filesArray.append(each_file)
return filesArray
#计算TF-IDF
def count_tfidf(word_dic,words_dic,files_Array):
word_idf={}
word_tfidf = {}
num_files = len(files_Array)
for word in word_dic:
for words in words_dic:
if word in words:
if word in word_idf:
word_idf[word] = word_idf[word] + 1
else:
word_idf[word] = 1
for key,value in word_dic.items():
if key !=" ":
word_tfidf[key] = value * math.log(num_files/(word_idf[key]+1))
#降序排序
values_list = sorted(word_tfidf.items(),key = lambda item:item[1],reverse=True)
return values_list
#新建文件夹
def buildfolder(path):
if os.path.exists(path):
shutil.rmtree(path)
os.makedirs(path)
print("成功创建文件夹！")
#写入文件
def out_file(path,content_list):
with codecs.open(path,"a",encoding="utf-8") as f:
for content in content_list:
f.write(str(content[0]) + ":" + str(content[1])+"\r\n")
print("well done!")
def main():
#遍历文件夹
folder_path = r"分词结果"
files_array = funfolder(folder_path)
#生成语料库
files_dic = []
for file_path in files_array:
file = readtxt(file_path)
word_dic = count_word(file)
files_dic.append(word_dic)
#新建文件夹
new_folder = r"tfidf计算结果"
buildfolder(new_folder)
#计算tf-idf,并将结果存入txt
i=0
for file in files_dic:
tf_idf = count_tfidf(file,files_dic,files_array)
files_path = files_array[i].split("//")
#print(files_path)
outfile_name = files_path[1]
#print(outfile_name)
out_path = r"%s//%s_tfidf.txt"%(new_folder,outfile_name)
out_file(out_path,tf_idf)
i=i+1
if __name__ == '__main__':
main()看完上述内容，你们掌握python TF-IDF算法实现文本关键词提取的方法了吗？如果还想学到更多技能或想了解更多相关内容，欢迎关注创新互联行业资讯频道，感谢各位的阅读！
