1. 准备表
   

   1.创建原始表:video_ori
   

   点击查看代码

   create table video_ori(
       videoId string, 
       uploader string, 
       age int, 
       category array<string>, 
       length int, 
       views int, 
       rate float, 
       ratings int, 
       comments int,
       relatedId array<string>)
   row format delimited fields terminated by "\t"
   collection items terminated by "&"
   stored as textfile;

   2.创建原始表:user_ori
   

   点击查看代码

   reate table user_ori(
       uploader string,
       videos int,
       friends int)
   row format delimited 
   fields terminated by "\t" 
   stored as textfile;
   

   3.创建orc存储格式带snappy压缩的video_orc
   

   点击查看代码

   create table video_orc(
       videoId string, 
       uploader string, 
       age int, 
       category array<string>, 
       length int, 
       views int, 
       rate float, 
       ratings int, 
       comments int,
       relatedId array<string>)
   stored as orc
   tblproperties("orc.compress"="SNAPPY");

   4.创建orc存储格式带snappy压缩的user_orc
   

   点击查看代码

   create table video_user_orc(
       uploader string,
       videos int,
       friends int)
   row format delimited 
   fields terminated by "\t" 
   stored as orc
   tblproperties("orc.compress"="SNAPPY");
   

    

09Hive_ETL_数据分析