文章來自于我的個人部落格:python 分詞計算文檔TF-IDF值并排序
該程式實作的功能是:首先讀取一些文檔,然後通過jieba來分詞,将分詞存入檔案,然後通過sklearn計算每個分詞文檔中的tf-idf值,再将文檔排序輸入一個大檔案中
依賴包:
sklearn
jieba
注:此程式參考了一位同行的程式後進行了修改
# -*- coding: utf-8 -*-
"""
@author: jiangfuqiang
"""
import os
import jieba
import jieba.posseg as pseg
import sys
import re
import time
import string
from sklearn import feature_extraction
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
reload(sys)
sys.setdefaultencoding('utf-8')
def getFileList(path):
filelist = []
files = os.listdir(path)
for f in files:
if f[0] == '.':
pass
else:
filelist.append(f)
return filelist,path
def fenci(filename,path,segPath):
f = open(path +"/" + filename,'r+')
file_list = f.read()
f.close()
#儲存粉刺結果的目錄
if not os.path.exists(segPath):
os.mkdir(segPath)
#對文檔進行分詞處理
seg_list = jieba.cut(file_list,cut_all=True)
#對空格,換行符進行處理
result = []
for seg in seg_list:
seg = ''.join(seg.split())
reg = 'w+'
r = re.search(reg,seg)
if seg != '' and seg != '
' and seg != '
' and seg != '=' and
seg != '[' and seg != ']' and seg != '(' and seg != ')' and not r:
result.append(seg)
#将分詞後的結果用空格隔開,儲存至本地
f = open(segPath+"/"+filename+"-seg.txt","w+")
f.write(' '.join(result))
f.close()
#讀取已經分詞好的文檔,進行TF-IDF計算
def Tfidf(filelist,sFilePath,path):
corpus = []
for ff in filelist:
fname = path + ff
f = open(fname+"-seg.txt",'r+')
content = f.read()
f.close()
corpus.append(content)
vectorizer = CountVectorizer()
transformer = TfidfTransformer()
tfidf = transformer.fit_transform(vectorizer.fit_transform(corpus))
word = vectorizer.get_feature_names() #所有文本的關鍵字
weight = tfidf.toarray()
if not os.path.exists(sFilePath):
os.mkdir(sFilePath)
for i in range(len(weight)):
print u'----------writing all the tf-idf in the ',i,u'file into ', sFilePath+'/' +string.zfill(i,5)+".txt"
f = open(sFilePath+"/"+string.zfill(i,5)+".txt",'w+')
for j in range(len(word)):
f.write(word[j] + " " + str(weight[i][j]) + "
")
f.close()
if __name__ == "__main__":
#儲存tf-idf的計算結果目錄
sFilePath = "/home/lifeix/soft/allfile/tfidffile"+str(time.time())
#儲存分詞的目錄
segPath = '/home/lifeix/soft/allfile/segfile'
(allfile,path) = getFileList('/home/lifeix/soft/allkeyword')
for ff in allfile:
print "Using jieba on " + ff
fenci(ff,path,segPath)
Tfidf(allfile,sFilePath,segPath)
#對整個文檔進行排序
os.system("sort -nrk 2 " + sFilePath+"/*.txt >" + sFilePath + "/sorted.txt")