neo4jでsandbox その12

#概要

neo4jでsandboxやってみた。
movielens、やってみた。
レコメンドしてみた。

#jaccardで映画をお勧め。

MATCH (m:Movie {title:"Short Circuit (1986)"})-[:GENRE]->(g:Genre)<-[:GENRE]-(other:Movie)
WITH m,
	other,
	COUNT(g) AS intersection,
	COLLECT(g.name) AS i
MATCH (m)-[:GENRE]->(mg:Genre)
WITH m,
	other,
	intersection,
	i,
	COLLECT(mg.name) AS s1
MATCH (other)-[:GENRE]->(og:Genre)
WITH m,
	other,
	intersection,
	i,
	s1,
	COLLECT(og.name) AS s2
WITH m,
	other,
	intersection,
	s1,
	s2
WITH m,
	other,
	intersection,
	s1 + filter(x IN s2 WHERE NOT x IN s1) AS union,
	s1,
	s2
RETURN m.title,
	other.title,
	s1,
	s2,
	((1.0 * intersection) / SIZE(union)) AS jaccard
ORDER BY jaccard DESC
LIMIT 5

#python実行結果

title   jaccard
Cocoon: The Return (1988)  1.0
Evolution (2001)  1.0
Hot Tub Time Machine (2010)  1.0
Cocoon (1985)  1.0
Americathon (1979)  1.0

以上。