“数据清洗,抽取”的版本间的差异
第25行: | 第25行: | ||
− | load data | + | load data [local] inpath ‘/root/data’ into table psn; 表示本地而不是Hadoop |
'''创建新表存储''' | '''创建新表存储''' | ||
第48行: | 第48行: | ||
SELECT count(distinct author) FROM data; | SELECT count(distinct author) FROM data; | ||
+ | insert into table test partition(age='xx') select id,name,tel form perop; | ||
+ | '''数据切分''' | ||
− | + | select split(name, '\ ') from data | |
+ | where split(name, '\ ')[0]='Huawei/华为'; |
2020年11月17日 (二) 01:16的版本
上传数据
hadoop fs -mkdir -p /college hadoop fs -put /root/college/loan.csv /college
创建数据库
create database 库名;
create table 表名1(
id int,
name string,
price int,
views int,
sales int,
stock int
)row format delimited
fields terminated by ',';
导入数据-》hive
load data inpath '/college/loan.csv' into table 表名;
load data [local] inpath ‘/root/data’ into table psn; 表示本地而不是Hadoop
创建新表存储
create table 表名2 like 表名2;
数据过滤
insert into 表名2
select * from 表名1
where not id is null and name is null and price is null and views is null and sales is null and stock is null
and name not like '%包包%' and name not like'%衣%' and name not like'%女士%'
group by id,name,price,views,sales,stock;
数据分析并下载
INSERT OVERWRITE LOCAL DIRECTORY '/root/college022/’
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t’
SELECT count(distinct author) FROM data;
insert into table test partition(age='xx') select id,name,tel form perop;
数据切分
select split(name, '\ ') from data where split(name, '\ ')[0]='Huawei/华为';