hive影评案例作业

hive影评案例作业

首先将数据文件上传到hdfs上

1.正确建表，导入数据，并且验证
新建moives表，需要进行多字节分隔符处理
create table moives(MovieID BigInt, Title String, Genres String) row format serde ‘org.apache.hadoop.hive.serde2.RegexSerDe’ with serdeproperties (‘input.regex’=’(.):?.):?.*)’,‘output.format.string’=’%1$s$s%3$s’)
stored as textfile location ‘/data/moives’;

show tables;
//查看表的详细信息
desc formatted moives;

hdfs新建三个文件夹
hadoop fs -mkdir /moivesdata
hadoop fs -mkdir /ratingsdata
hadoop fs -mkdir /usersdata

//级联生成文件夹 hadoop fs -mkdir -p /xxx/xx/x

然后将数据文件分别上传
hadoop fs -put ~/files/movies.dat /moivesdata
hadoop fs -put ~/files/ratings.dat /ratingsdata
hadoop fs -put ~/files/users.dat /usersdata

…

load data inpath ‘/moivesdata’ into table moives;

查看一下是否装载成功
select * from moives limit 10;

建剩余的两张表:
创建ratings表
create table ratings(UserID BigInt, MovieID BigInt, Rating Double, Timestamped String) row format serde ‘org.apache.hadoop.hive.serde2.RegexSerDe’ with serdeproperties (‘input.regex’=’(.):?.):?.):?.)’,‘output.format.string’=’%1$s$s%3$s$s’)
stored as textfile location ‘/data/ratings’;

load data inpath ‘/ratingsdata’ into table ratings;

创建users表
create table users(UserID BigInt, Gender String, Age Int, Occupation String, Zipcode String) row format serde ‘org.apache.hadoop.hive.serde2.RegexSerDe’ with serdeproperties (‘input.regex’=’(.):?.):?.):?.):?.*)’,‘output.format.string’&