目的：从数据库中抽取文章关键词，并统计这些关键词在哪些文章中出现，出现多少次。（算是词袋子模型吧），然后对每篇文章形成形成VSM模型，写成weka的数据格式，然后调用weka对文章聚类。

目前“形成此代码模型一块已经完毕”

其中词袋子的数据结构如下：

map>>&mymap)，

目前已经完成此部分的serilize（save/load)以及print 功能

include "stdafx.h"

#include

#include

形成词袋子模型nt ConstructMap(map<string,vector<pair<int,int>>>&mymap)

{



vector<string>mySplit(strings);

CoInitialize(NULL);

_ConnectionPtr pConn(__uuidof(Connection));

_RecordsetPtr pRst(__uuidof(Recordset));

pConn->ConnectionString="Provider=SQLOLEDB.1;Password=xxx;Persist Security Info=True; User ID=sa;Initial Catalog=ArticleCollection";

pConn->Open("","","",adConnectUnspecified);

pRst=pConn->Execute("select CKeyWord,ArticleId from Article order by ArticleId",NULL,adCmdText);

while(!pRst->rsEOF)

{ vector<string>wordcollection;

stringkeywordstr=(_bstr_t)pRst->GetCollect("CKeyWord");

if(keywordstr!="")

{

wordcollection=mySplit(keywordstr);

stringtempid=(_bstr_t)pRst->GetCollect("ArticleId");

intarticleid=atoi(tempid.c_str());

for(vector<string>::iterator strit=wordcollection.begin();strit!=wordcollection.end();strit++)

{

vector<pair<int,int>>::iterator it;

if(mymap[strit].empty())

{

pair<int,int>mytemppair=make_pair(articleid,1);

mymap[strit].push_back(mytemppair);



}

else

{

for(it=mymap[strit].begin();it!=mymap[strit].end();it++)

{

if(it->first==articleid)

{

it->second=++(it->second);

break;

}



}

if(it==mymap[strit].end())

{

pair<int,int>mytemppair=make_pair(articleid,1);

mymap[strit].push_back(mytemppair);

}



}



}





}





pRst->MoveNext();

wordcollection.clear();

}

pRst->Close();

pConn->Close();

pRst.Release();

pConn.Release();

CoUninitialize();

return0;



}

加载词袋子模型voidload(map<string,vector<pair<int,int>>>&mymap)

{

ifstream infile("c:\mydict.dat",ios::binary);

intlenMyMap;//保存词典长度

intlenVector;//保存每个词出现的文章数目

stringkey;//保存读出的map的键值

intarticleId;//文章标号

intcount;//在该文章中刚出现的数目

stringcomma;

stringsemicolon;



infile>>lenMyMap;

while(!infile.eof())

{

infile>>key;

infile>>lenVector;

vector<pair<int,int>>temp;

for(inti=0;i<lenVector;i++)

{

infile>>articleId>>count>>semicolon;

temp.push_back(make_pair(articleId,count));

}

mymap[key]=temp;





}





infile.close();



}

保存词袋子模型voidsave(map<string,vector<pair<int,int>>>&mymap)

{ ofstream outfile("c:\mydict.dat",ios::binary);

outfile<<mymap.size()<<endl;

map<string,vector<pair<int,int>>>::iterator it;

for(it=mymap.begin();it!=mymap.end();it++)

{ outfile<<it->first<<endl;

vector<pair<int,int>>::iterator subit;

outfile<<it->second.size()<<endl;

for(subit=(it->second).begin();subit!=(it->second).end();++subit)

{

outfile<<subit->first<<""<<subit->second<<""<<";"<<"";

}

outfile<<endl;

}

//outfile.write((char *)&mymap,sizeof(mymap));



outfile.close();

}打印词袋子模型voidprint(map<string,vector<pair<int,int>>>&mymap)

{

cout<<mymap.size()<<endl;

map<string,vector<pair<int,int>>>::iterator it;

for(it=mymap.begin();it!=mymap.end();it++)

{ cout<<it->first<<endl;

vector<pair<int,int>>::iterator subit;

cout<<it->second.size()<<endl;

for(subit=(it->second).begin();subit!=(it->second).end();++subit)

{

cout<<subit->first<<','<<subit->second<<";";

}

cout<<endl;

}



}

原文链接: https://www.cnblogs.com/finallyliuyu/archive/2010/08/25/1808300.html

欢迎关注

微信关注下方公众号，第一时间获取干货硬货；公众号内回复【pdf】免费获取数百本计算机经典书籍