该文描述了如何在Hive中创建一个名为tb_usa_covid的表，存储美国COVID-19数据，包括日期、国家、州、病例和死亡数。接着设置了桶化（bucketing）策略，按州分5个桶，并将数据插入到分桶表tb_usa_covid_buckets中，优化查询效率。
create table tb_usa_covid(
count_date date,
country string,
state string,
flips string,
cases int,
deaths int
)row format delimited
fields terminated by ',';
select * from tb_usa_covid;
set hive.enforce.bucketing = true;
set mapreduce.job.reduces = 5;
create table tb_usa_covid_buckets(
count_date date,
country string,
state string,
flips string,
cases int,
deaths int
)clustered by (state) into 5 buckets
row format delimited
fields terminated by ',';
insert into tb_usa_covid_buckets select * from tb_usa_covid;
626
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
