如何修剪频率设置的数据以符合论文的描述
MovieLens数据集提供了一个包含列的表：
userid | movieid | tag | timestamp
select TMP.userid, count(*) as tagnum
from (select distinct T.userid as userid, T.tag as tag from tags T) AS TMP
group by TMP.userid
having tagnum >= 3;
没有找到相关结果
已邀请:
1 个回复
刷遍派戳
select T1.tag, (select count( distinct T2.movieid ) from tags T2 where T2.tag = T1.tag) as mcount, (select count( distinct T3.userid ) from tags T3 where T3.tag = T1.tag) as ucount from tags T1 having mcount >= 3 and ucount >= 3;select T4.user, count(*) as ucount from (select T1.userid as user, (select count( distinct T2.movieid ) from tags T2 where T2.tag = T1.tag) as mcount, (select count( distinct T3.userid ) from tags T3 where T3.tag = T1.tag) as ucount from tags T1 having mcount >= 3 and ucount >= 3) as T4 group by user having ucount > 3;