数据分析案例：商品画像

1.爬取商城数据，并进行分析

具体步骤如下

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';