有没有好的SQL PageRank实现呢?我看了http://www.databasedevelop.com/197517/,但是它的可读性和(T-SQL)语法不正确。
顺便问一下,有人知道上面链接中使用的是什么SQL吗?哪种SQL会在随机位置使用"is",在"where"后面什么都不加,还有那个奇怪的AT关键字等等?
顺便问一下,有人知道上面链接中使用的是什么SQL吗?哪种SQL会在随机位置使用"is",在"where"后面什么都不加,还有那个奇怪的AT关键字等等?
我刚刚在SQL中实现了PageRank算法。该算法的工作流程如下:
1.计算PageRank的初始排名值;
2.将PageRank表与Edge表连接,向相邻节点发出排名值,并使用聚合函数sum来“收集”接收到的值。然后,将结果保存到临时表TmpRank中;
以下是代码:
-- The graph data and algorithm source from the book "Mining of Massive Datasets", P175, http://infolab.stanford.edu/~ullman/mmds/book.pdf
-- This script has been verified the correctness in SQL Server 2017 Linux Version.
DROP TABLE Node;
DROP TABLE Edge;
DROP TABLE OutDegree;
DROP TABLE PageRank;
CREATE TABLE Node(id int PRIMARY KEY);
CREATE TABLE Edge(src int,dst int, PRIMARY KEY (src, dst));
CREATE TABLE OutDegree(id int PRIMARY KEY, degree int);
CREATE TABLE PageRank(id int PRIMARY KEY, rank float);
CREATE TABLE TmpRank(id int PRIMARY KEY, rank float);
--delete all records
DELETE FROM Node;
DELETE FROM Edge;
DELETE FROM OutDegree;
DELETE FROM PageRank;
DELETE FROM TmpRank;
--init basic tables
INSERT INTO Node VALUES (0);
INSERT INTO Node VALUES (1);
INSERT INTO Node VALUES (2);
INSERT INTO Node VALUES (3);
INSERT INTO Edge VALUES (0, 1);
INSERT INTO Edge VALUES (0, 2);
INSERT INTO Edge VALUES (0, 3);
INSERT INTO Edge VALUES (1, 0);
INSERT INTO Edge VALUES (1, 3);
INSERT INTO Edge VALUES (2, 2);
INSERT INTO Edge VALUES (3, 1);
INSERT INTO Edge VALUES (3, 2);
--compute out-degree
INSERT INTO OutDegree
SELECT Node.id, COUNT(Edge.src) --Count(Edge.src) instead of Count(*) for count no out-degree edge
FROM Node LEFT OUTER JOIN Edge
ON Node.id = Edge.src
GROUP BY Node.id;
--WARN: There's no special process for node with out-degree, This may cause wrong result
-- Please to make sure every node in graph has out-degree
DECLARE @ALPHA float = 0.8;
DECLARE @Node_Num int;
SELECT @Node_Num = COUNT(*) FROM Node;
--PageRank Init Value
INSERT INTO PageRank
SELECT Node.id, rank = (1 - @ALPHA) / @Node_Num
FROM Node INNER JOIN OutDegree
ON Node.id = OutDegree.id
/*
--For Debugging
SELECT * FROM Node;
SELECT * FROM Edge;
SELECT * FROM OutDegree;
SELECT * FROM PageRank;
SELECT * FROM TmpRank;
*/
DECLARE @Iteration int = 0;
WHILE @Iteration < 50
BEGIN
--Iteration Style
SET @Iteration = @Iteration + 1
INSERT INTO TmpRank
SELECT Edge.dst, rank = SUM(@ALPHA * PageRank.rank / OutDegree.degree) + (1 - @ALPHA) / @Node_Num
FROM PageRank
INNER JOIN Edge ON PageRank.id = Edge.src
INNER JOIN OutDegree ON PageRank.id = OutDegree.id
GROUP BY Edge.dst
DELETE FROM PageRank;
INSERT INTO PageRank
SELECT * FROM TmpRank;
DELETE FROM TmpRank;
END
SELECT * FROM PageRank;