博客

我用的是Anaconda3来编译python 代码

# -*- coding: utf-8 -*-
"""
Created on Fri Mar 10 11:02:50 2017

@author: Administrator
"""

#用余弦相似性进行比较
import numpy as np
#Numpy是Python的一个科学计算的库，提供了矩阵运算的功能
import  jieba
#python分词器
import  copy
import codecs,sys
#自然语言编码转换
title2= "张翰怒斥耍大牌被换角谣言"
title1 = "爱剪辑-危机四伏，落水就会被高压电弄死"
#title1 = "王凯《跨界歌王》姗姗来迟“低音炮”开嗓献唱 - 搜狐视频"
#title2  = "《跨界歌王》王凯清唱“好久不见” 低音炮名不虚传_视频在线观看 - 56.com"
#title1 = "王凯《跨界歌王》姗姗来迟“低音炮”开嗓献唱 - 搜狐视频"
#title2 = "范爷维权获赔15万全捐赠"
#sampfn = "C:\\Users\\Administrator\\Desktop\\sample.txt"
#定义了一个余弦相似度函数
def get_cossimi(x,y):
    myx = np.array(x)
    myy = np.array(y)
    cos1 = np.sum(myx * myy)
    cos21 = np.sqrt(sum(myx * myx))
    cos22 = np.sqrt(sum(myy * myy))
    return cos1 / (cos21 * cos22)

if __name__ == '__main__':
    print("loading...")
    print("working...")
#title1进行分词
    f1_seg_list = jieba.cut(title1)#需要添加一个词典，来弥补结巴分词中没有的词语，从而保证更高的正确率
    
#title1进行分词
    ftest1_seg_list = jieba.cut(title2)

    #打开停用词表
    f_stop = codecs.open("C:\\Users\\Administrator\\Desktop\\stopword.txt","r","utf-8")
    try:
        f_stop_text = f_stop.read()
    finally:
        f_stop.close()
    f_stop_seg_list = f_stop_text.split("\n")

    test_words = {}
    all_words = {}

    for myword in f1_seg_list:
        #print(".")
        if not(myword.strip()) in f_stop_seg_list:
            test_words.setdefault(myword, 0)
            all_words.setdefault(myword, 0)
            all_words[myword] += 1

    #read to be tested word
    mytest1_words = copy.deepcopy(test_words)
    for myword in ftest1_seg_list:
       # print(".")
        if not(myword.strip()) in f_stop_seg_list:
            if myword in mytest1_words:
                mytest1_words[myword] += 1

   
    #calculate sample with to be tested text sample
    sampdate = []
    test1data = []
    for key in all_words.keys():
        sampdate.append(all_words[key])
        test1data.append(mytest1_words[key])
test1simi = get_cossimi(sampdate,test1data)

print(u"title1与title2的余弦相似度%f"%(test1simi))





结果为：
runfile('C:/Users/Administrator/Desktop/cosine xiangsi/cosine simlitary.py', wdir='C:/Users/Administrator/Desktop/cosine xiangsi')
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
loading...
working...
Loading model cost 0.658 seconds.
Prefix dict has been built succesfully.
title1与title2的余弦相似度0.301511

我将代码用java进行封装

import org.python.util.PythonInterpreter;  
  

public class juli  
{  
 public static void main(String args[])  
 {  
    
  PythonInterpreter interpreter = new PythonInterpreter();  
  interpreter.execfile("D:\\download\\cosine simlitary.py");  
 }//main  
}  

出现错误：
Exception in thread "main" Traceback (innermost last):

  (no code object) at line 0

SyntaxError: ('Lexical error at line 20, column 35.  Encountered: "\\r" (13), after : ""', ('D:\\download\\cosine simlitary.py', 20, 35, u'title1 = "\u95C4\u5823\u4F46\u741A\uE0A6\u734B\u93C4\uE21C\u5C13 \u8930\u64B3\u6E80\u9359\u6226\uE5DE\u93C6\u5B58\u5F3D\u93CB\u6941\u6D3F\u93C2\uFFFD'))
可能是测试的句子中有空格出现
我进行了一些改正又出现了错误提示：
Exception in thread "main" Traceback (innermost last):

  File "D:\download\cosine simlitary.py", line 9, in ?

ImportError: no module named numpy


仔细想了好久还是不行，看到了一篇博客，运用他的方法最后结果重要正确了   http://blog.csdn.net/ztf312/article/details/51338060


package cos;


import java.io.BufferedReader;  
import java.io.InputStreamReader;  
  
public class juli {  
        public static void main(String[] args){  
                try{  
                        System.out.println("start");  
                        Process pr = Runtime.getRuntime().exec("C:\\ProgramData\\Anaconda3\\python.exe untitled0.py");  
                          
                        BufferedReader in = new BufferedReader(new  
                                InputStreamReader(pr.getInputStream()));  
                        String line;  
                        while ((line = in.readLine()) != null) {  
                            System.out.println(line);  
                        }  
                        in.close();  
                        pr.waitFor();  
                        System.out.println("end");  
                } catch (Exception e){  
                            e.printStackTrace();  
                        }  
                }  
} 


结果如下：
start

loading...

working...

title1与title2的余弦相似度0.301511

end