kets
row format delimited
fields terminated by "\t"
stored as textfile;
2)user的創建,文件格式orc,24buckets
create table user(uploader string,買粉絲s int,friends int)
clustered by (uploader) into 24 buckets
row format delimited
fields terminated by "\t"
stored as orc;
user表的數據導入也是同理
數據導入:
1)load data inpath "path" into table user_tmp;
2)由于無法將textfile格式的數據導入到orc格式的表格,所以數據需要從user_tmp導入到user:
insert into table user select * from user_tmp;
1)統計出觀看數最多的10個視頻
2)統計出視頻類別熱度的前10個類型
3)統計出視頻觀看數最高的50個視頻的所屬類別
4)統計出觀看數最多的前N個視頻所關聯的視頻的所屬類別排行
5)篩選出每個類別中熱度最高的前10個視頻
6)篩選出每個類別中評分最高的前10個視頻
7)找出用戶中上傳視頻最多的10個用戶的所有視頻
8)篩選出每個類別中觀看數Top10
select * from youtube3 order by views desc limit 10;
結果如下:
select tagId, 買粉絲unt(a.買粉絲id) as sum from (select 買粉絲id,tagId from youtube3 lateral view explode(category) catetory as tagId) a group by a.tagId order by sum desc limit 10;
結果:
select tagId, 買粉絲unt(a.買粉絲id) as sum from (select 買粉絲id,tagId from (select * from youtube3 order by views desc limit 20) e lateral view explode(category) catetory as tagId) a group by a.tagId order by sum desc;
結果:
思路:
結果:
思路:
結果如下:
select * from youtube_category where categoryId="Music" order by ratings desc limit 10;
結果如下:
思路:
結果如下: