vsm向量空间模型实现

妖狐艹你老母 2022-06-08 13:35 193阅读 0赞

1.  简介
2.  代码实现
3.  总结

一.简介  
在检索当中，主要涉及了两个核心问题:  
I.相似度计算  
II.索引的建立  
索引建立参考链接：

[http://blog.csdn.net/malefactor/article/details/7256305][http_blog.csdn.net_malefactor_article_details_7256305]

这里我们重点讲解第一个问题  
1.1整体流程如图：  
![这里写图片描述][20160326112649722]  
1.2在整个流程当中，第二步骤和第三步骤对于效果影响很多，故此很关键  
相似度的vsm经典模型流程如图：  
![这里写图片描述][20160326112937259]  
经过第三步骤处理后，文档在词典当中均有唯一的表示-表示为一个长向量的形式  
第四步骤参考链接：

> [http://blog.csdn.net/u010598982/article/details/50876831][http_blog.csdn.net_u010598982_article_details_50876831]

二.代码实现

# !usr/bin/python
    # copyright(c) youfuwen
    # Date:2016.03.26
    # E-Mail:yfwen@bjtu.edu.cn
    # first: cipintongji
    import math
    import ast
    from collections import Counter
    wordsCount=0#variable for wordsfrequency
    def CountKeyByWen(fileName1):
        global wordsCount
        f1=open(fileName1,'r')
        f2=open(fileName2,'r')
        table={}
        for lines in f1:
            for line in lines.split(' '):
                if line!=' ' and table.has_key(line):
                    table[line]+=1
                    wordsCount+=1
                elif line!=' ':
                    wordsCount+=1
                    table[line]=1
        dic = sorted(table.iteritems(),key= lambda asd:asd[1], reverse=True)
        # print len(dic) code for testing
        return dic
    # seconde:create vocabulary
    def CreateVocabulary(dic1=None, dic2=None):
        vocabulary=[]
        for dicEle in dic1:
            if dicEle[0] not in vocabulary:
                vocabulary.append(dicEle[0])
        for dicEle in dic2:
            if dicEle[0] not in vocabulary:
                vocabulary.append(dicEle[0])
        # print len(vocabulary) code for testing
        return vocabulary
    # third:compute TF-IDF output: a vector
    # In this code we just use TF for computing similarity
    def ComputeVector(dic1=None,vocabulary=None):
        # 3.1compute cipin global wordscount wordsCount
        # 3.2create vector
        dicVector = {}
        for elem in vocabulary:
            dicVector[elem]=0
        # dicVector = sorted(dicVector.iteritems(),key= lambda asd:asd[1], reverse=True)
        dicTemp1,dicTemp2=Counter(dicVector), Counter(dic1)
        dicTemp=dict(dicTemp1+dicTemp2)
        # dicTemp = sorted(dicTemp.iteritems(),key= lambda asd:asd[1], reverse=True)
        return  dicTemp
    # fourth: compute TF-IDF
    def ComputeSimlirity(dic1Vector=None,dic2Vector=None):
        x=0.0 #fenzi
        #fenmu
        y1=0.0
        y2=0.0
        for k in dic1Vector:# because of the element of dic1 and dic2 are the same
            temp1=(float)(float(dic1Vector[k])/float(wordsCount))
            temp2=(float)(float(dic2Vector[k])/float(wordsCount))
            x=x+ (temp1*temp2)
            y1+=pow(temp1,2)
            y2+=pow(temp2,2)
        return x/math.sqrt(y1*y2)
    
    if __name__=='__main__':
        fileName1='amanda_all.txt';
        fileName2='amanda_all.txt';
        dic1 = CountKeyByWen(fileName1)
        dic2 = CountKeyByWen(fileName2)
        vocabulary = CreateVocabulary(dic1, dic2)
        dic1Vector = ComputeVector(dic1, vocabulary)
        dic2Vector = ComputeVector(dic2, vocabulary)
        for elem in dic1Vector:
            print "<"+elem[0],',',str(elem[1])+">"
        sim=ComputeSimlirity(dic1Vector,dic2Vector)
        print sim
       
        
         1 
         2 
         3 
         4 
         5 
         6 
         7 
         8 
         9 
         10 
         11 
         12 
         13 
         14 
         15 
         16 
         17 
         18 
         19 
         20 
         21 
         22 
         23 
         24 
         25 
         26 
         27 
         28 
         29 
         30 
         31 
         32 
         33 
         34 
         35 
         36 
         37 
         38 
         39 
         40 
         41 
         42 
         43 
         44 
         45 
         46 
         47 
         48 
         49 
         50 
         51 
         52 
         53 
         54 
         55 
         56 
         57 
         58 
         59 
         60 
         61 
         62 
         63 
         64 
         65 
         66 
         67 
         68 
         69 
         70 
         71 
         72 
         73 
         74 
         75

tips:上面的code有人提示楼主有问题，遂做修改，欢迎大家批评指正哈！修改代码如下：

# !usr/bin/python
    # copyright(c) youfuwen
    # Date:2016.03.29revised version
    # E-Mail:yfwen@bjtu.edu.cn
    # first: count words frequency
    import math
    import ast
    from collections import Counter
    wordsCount=0#variable for wordsfrequency
    def CountKeyByWen(fileName1):
        global wordsCount
        f1=open(fileName1,'r')
        f2=open(fileName2,'r')
        table={}
        for lines in f1:
            for line in lines.split(' '):
                if line!=' ' and table.has_key(line):
                    table[line]+=1
                    wordsCount+=1
                elif line!=' ':
                    wordsCount+=1
                    table[line]=1
        #dic = sorted(table.iteritems(),key= lambda asd:asd[1], reverse=True)
        # print len(dic) code for testing
        return table
    # seconde:create vocabulary
    def CreateVocabulary(dic1=None, dic2=None):
        vocabulary=[]
        for dicEle in dic1:
            if dicEle not in vocabulary:
                vocabulary.append(dicEle)
        for dicEle in dic2:
            if dicEle not in vocabulary:
                vocabulary.append(dicEle)
        # print len(vocabulary) code for testing
        return vocabulary
    # third:compute TF-IDF output: a vector
    # In this code we just use TF for computing similarity
    def union_dict(*objs):
        _keys = set(sum([obj.keys() for obj in objs],[]))
        _total = {}
        for _key in _keys:
            _total[_key] = sum([obj.get(_key,0) for obj in objs])
        return _total
    def ComputeVector(dic1=None,vocabulary=None):
        # 3.1compute cipin global wordscount wordsCount
        # 3.2create vector
        dicVector = {}
        for elem in vocabulary:
            dicVector[elem]=0
        # dicVector = sorted(dicVector.iteritems(),key= lambda asd:asd[1], reverse=True)
        # U"vocabulary --->dicVector"
        # U"dic1->vector"
        dicTemp=union_dict(dicVector,dic1);
        # dicTemp1,dicTemp2=Counter(dicVector), Counter(dic1)
        # dicTemp=dict(dicTemp1+dicTemp2)
        # dicTemp = sorted(dicTemp.iteritems(),key= lambda asd:asd[1], reverse=True)
        return  dicTemp
    # fourth: compute TF-IDF
    def ComputeSimlirity(dic1Vector=None,dic2Vector=None):
        x=0.0 #fenzi
        #fenmu
        y1=0.0
        y2=0.0
        for k in dic1Vector:# because of the element of dic1 and dic2 are the same
            temp1=(float)(float(dic1Vector[k])/float(wordsCount))
            temp2=(float)(float(dic2Vector[k])/float(wordsCount))
            x=x+ (temp1*temp2)
            y1+=pow(temp1,2)
            y2+=pow(temp2,2)
        return x/math.sqrt(y1*y2)
    
    if __name__=='__main__':
        fileName1='a.txt';
        fileName2='b.txt';
        dic1 = CountKeyByWen(fileName1)
        dic2 = CountKeyByWen(fileName2)
        vocabulary = CreateVocabulary(dic1, dic2)
        dic1Vector = ComputeVector(dic1, vocabulary)
        dic2Vector = ComputeVector(dic2, vocabulary)
        for elem in dic1Vector:
            print "<"+elem,',',str(dic1Vector[elem])+">"
        sim=ComputeSimlirity(dic1Vector,dic2Vector)
        print "similarity="+str(sim)
        #####################################
       
        
         1 
         2 
         3 
         4 
         5 
         6 
         7 
         8 
         9 
         10 
         11 
         12 
         13 
         14 
         15 
         16 
         17 
         18 
         19 
         20 
         21 
         22 
         23 
         24 
         25 
         26 
         27 
         28 
         29 
         30 
         31 
         32 
         33 
         34 
         35 
         36 
         37 
         38 
         39 
         40 
         41 
         42 
         43 
         44 
         45 
         46 
         47 
         48 
         49 
         50 
         51 
         52 
         53 
         54 
         55 
         56 
         57 
         58 
         59 
         60 
         61 
         62 
         63 
         64 
         65 
         66 
         67 
         68 
         69 
         70 
         71 
         72 
         73 
         74 
         75 
         76 
         77 
         78 
         79 
         80 
         81 
         82 
         83 
         84 
         85

三.总结  
I.任何事情均通于天道地道，都有一个积累的过程，努力是成功的必要前提条件II.让我们一同努力，明天会更好！

[转载地址][Link 1]

顶

踩

[http_blog.csdn.net_malefactor_article_details_7256305]: http://blog.csdn.net/malefactor/article/details/7256305
[20160326112649722]: /images/20220608/a5202a3e22344b00b7b1e14a0111466d.png
[20160326112937259]: /images/20220608/e8137fdff01d4055bf7a51104d0a2d03.png
[http_blog.csdn.net_u010598982_article_details_50876831]: http://blog.csdn.net/u010598982/article/details/50876831
[Link 1]: http://blog.csdn.net/u010598982/article/details/50985994