PageRank计算方法的SQL实现

1、表准备
存储所有网页的基本信息
CREATE TABLE [WebPages] (
 [DOCID] [int] IDENTITY (1, 1) NOT NULL ,
 [URL] [varchar] (900) COLLATE Chinese_PRC_CI_AS NULL ,
 [PAGETEXT] [text] COLLATE Chinese_PRC_CI_AS NULL ,
 [REFCOUNT] [int] NULL ,
 [WEIGHT] [float] NULL ,
 CONSTRAINT [DOCID] PRIMARY KEY  CLUSTERED
 (
  [DOCID]
 )  ON [PRIMARY]
) ON [PRIMARY] TEXTIMAGE_ON [PRIMARY]
GO


存储网页链接关系
CREATE TABLE [PageLinks] (
        [docid] [int] NULL ,
        [url] [varchar] (900) COLLATE Chinese_PRC_CI_AS NULL ,
        [anchordocid] [int] NULL ,
        [anchorurl] [varchar] (900) COLLATE Chinese_PRC_CI_AS NULL
) ON [PRIMARY]
GO


2、执行脚本,填充WebPages中的REFCOUNT,使之成为链出网页的数量
declare cur_webpages cursor
for select docid from webpages

declare @docid int
open cur_webpages
fetch next from cur_webpages into @docid
while (@@fetch_status=0)
begin
        declare @rcount int
        select @rcount=count(*) from pagelinks where docid=@docid
        update webpages set refcount=@rcount WHERE CURRENT OF cur_webpages
        fetch next from cur_webpages into @docid
end
close cur_webpages
deallocate cur_webpages

 

3、填充初始值
update webpages set weight=1.0/(select count(*) from webpages)
update webpages set REVWEIGHT=0

 

4、计算PageRank的SQL脚本
declare @count int
set @count=0

while(@count<=7)
begin
        declare cur_webpages cursor
        for select docid,refcount,weight,revweight from webpages
       
        declare @docid int
        declare @refcount int
        declare @weight float
        declare @revweight float
        if(@count%2=0)
                select docid,weight into pagebak from webpages
        else
                select docid,revweight as weight into pagebak from webpages
        CREATE  INDEX [docid] ON [dbo].[pagebak]([docid])
       
        open cur_webpages
        fetch next from cur_webpages into @docid,@refcount,@weight,@revweight
        while (@@fetch_status=0)
        begin
                if @refcount<>0
                begin
                        if(@count%2=0)
                                update pagebak set weight=weight+(@weight/@refcount) where docid in (select anchordocid from pagelinks where docid=@docid)
                        else
                                update pagebak set weight=weight+(@revweight/@refcount) where docid in (select anchordocid from pagelinks where docid=@docid)
                end
                fetch next from cur_webpages into @docid,@refcount,@weight,@revweight
        end
        close cur_webpages
        deallocate cur_webpages
        if(@count%2=0)
        begin
                update webpages set revweight=0.2+(select weight from pagebak where pagebak.docid=webpages.docid)
                update webpages set revweight=revweight/(select sum(revweight) from webpages)
        end
        else
        begin
                update webpages set weight=0.2+(select weight from pagebak where pagebak.docid=webpages.docid)
                update webpages set weight=weight/(select sum(weight) from webpages)
        end
        drop table pagebak
        select * from webpages
        set @count=@count+1
end

 

 

 

 

 


 

  • 1
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

leeshuqing

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值