Hive操作无分区

(2) 创建存放info.log数据的表infologback
hive> create table infologback(
> ip string,
> date string,
> traffic string,
> type string,
> id string)
> row format delimited
> fields terminated by ‘,’;
OK

(3) 导入清洗后的数据到infologback表中
load data inpath ‘/output/part-r-00000’ into table infologback;

(4) 查询显示全部内容
select * from infologback;

(5) 查询视频总流量并排序
select traffic,sum(traffic) from infologback sort by traffic;

(6) 查询每个ip地址的同一类型的视频或者文章的访问次数
select ip,count(id) from infologback group by ip;

(7) 查询当天流量最高的文章或者视频的id
select id,max(traffic) from infologback group by id;

(8) 分别统计视频和文章的总数量
select id,count(id) from infologback group by id;

(9)查询每个ip地址的同一类型的视频或者文章的访问次数存放到新表中
create table new_table row format delimited fields terminated by ‘,’ as select ip,count(id) from infologback group by ip;

(10) 使用Sqoop