数据分析之图算法: 基于Spark和Neo4j

使用图算法增强机器学习

｜

163

ON CREATE SET a += apoc.map.clean(value,["id","authors","references"],[0])

WITH a,value.authors as authors

UNWIND authors as author

MERGE (b:Author{name:author})

MERGE (b)<-[:AUTHOR]-(a)'

, {batchSize: 10000, iterateList: true});

这段代码将产生图

8-4

所示的图模式。

图 8-4：引用图

由于连接论文和作者的图还比较简单，因此要添加更多从关系中推断出的信息来辅助预测。

8.3.3

　合著者关系图

要预测作者之间未来的合作，首先要创建合著者关系图。下面的

Neo4j Cypher

查询将为合

著论文的每对作者创建

CO_AUTHOR

关系。

MATCH

(a1)<-[:AUTHOR]-(paper)-[:AUTHOR]->(a2:Author)

WITH

a1, a2, paper

ORDER BY

a1, paper.year

WITH

a1, a2, collect(paper)[0].year

AS

year, count(*)

AS

collaborations

MERGE (a1)-[coauthor:CO_AUTHOR {year: year}]-(a2)

SET

coauthor.collaborations = collaborations; ...