文本特征提取的方法很多,如基于文本频率的特征提取法、信息增益法、卡方检验法和互信息法等。本文采用基于文本特征频率的提取法,计算文档频率DF,即计算出现某个term在同类文档中的DF。根据计算出来的DF值来选取能代表某类文档的特征词。
直接上代码:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
功能:
时间:
"""
import codecs
import os
import re
# 目录
base = "C:\\Users\\Administrator\\Desktop\\delstopwords3"
for j in range(1, 10):
alltext = []
allwords = []
path = os.path.join(base, str(j))
textnames = os.listdir(path)
for name in textnames:
temp = []
f = codecs.open(os.path.join(path, name), "r")
for line in f:
try:
temp.append(line.strip().decode("utf-8"))
except:
print u"某个词编码有问题..."
continue
alltext.append(temp)
allwords += temp
print u"文本个数:", len(alltext)
print u"词汇个数:", len(allwords)
print u"词汇种数:", len(set(allwords))
word_df = []
for word in set(allwords):
count = 0
for text in alltext:
if word in text:
count += 1
word_df.append([word, str(count)]) # 存储形式[word,DF]
# 输出,之所以不写入文本,是因为总有一些奇怪的字符会报错。。。
word_df.sort(key=lambda x: int(x[1]), reverse=True) # 词频从大到小排序
f_df = codecs.open('%d.txt' % j, "a", encoding="utf-8")
f_df.truncate()
for item in word_df:
f_df.write(item[0] + "\t" + item[1] + "\n")
f_df.close()
print u"程序结束!"