1.上传tar包
2.解压
tar -zxvf hive-0.9.0.tar.gz -C /usr/local
3.配置mysql metastore(切换到root用户)
配置HIVE_HOME环境变量
rpm -qa | grep mysql
rpm -e mysql-libs-5.1.66-2.el6_3.i686 --nodeps
rpm -ivh MySQL-server-5.1.73-1.glibc23.i386.rpm
rpm -ivh MySQL-client-5.1.73-1.glibc23.i386.rpm
修改mysql的密码
/usr/bin/mysql_secure_installation
(注意:删除匿名用户,允许用户远程连接)
登陆mysql
mysql -u root -p
4.配置hive
cp hive-default.xml.template hive-site.xml
修改hive-site.xml(删除所有内容,只留一个<property></property>)
添加如下内容:
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://hadoop00:3306/hive?createDatabaseIfNotExist=true</value>
<description>JDBC connect string for a JDBC metastore</description>
</property>
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.jdbc.Driver</value>
<description>Driver class name for a JDBC metastore</description>
</property>
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
<description>username to use against metastore database</description>
</property>
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>123</value>
<description>password to use against metastore database</description>
</property>
5.安装hive和mysq完成后,将mysql的连接jar包拷贝到$HIVE_HOME/lib目录下
如果出现没有权限的问题,在mysql授权(在安装mysql的机器上执行)
mysql -uroot -p
#(执行下面的语句 *.*:所有库下的所有表 %:任何IP地址或主机都可以连接)
GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY '123' WITH GRANT OPTION;
FLUSH PRIVILEGES;
6.建表(默认是内部表)
create table trade_detail(id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t';
建分区表
create table td_part(id bigint, account string, income double, expenses double, time string) partitioned by (logdate string) row format delimited fields terminated by '\t';
建外部表
create external table td_ext(id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t' location '/td_ext';
7.创建分区表
普通表和分区表区别:有大量数据增加的需要建分区表
create table book (id bigint, name string) partitioned by (pubdate string) row format delimited fields terminated by '\t';
分区表加载数据
load data local inpath './book.txt' overwrite into table book partition (pubdate='2010-08-22');
load data local inpath '/root/data.am' into table beauty partition (nation="USA");
create table trade_detail(id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t';
create table user_info(id bigint, account string, name string, age int) row format delimited fields terminated by '\t';
load data local inpath '/home/hadoop/data/trade_detail' overwrite into table trade_detail;
load data local inpath '/home/hadoop/data/user_info' overwrite into table user_info;
create table result row format delimited fields terminated by '\t' as select t1.account, t1.income, t1.expenses, t1.surplus, t2.name from user_info t2 join (select account, sum(income) as income, sum(expenses) as expenses, sum(income-expenses) as surplus from trade_detail group by account) t1 on(t1.account = t2.account);
创建外部表
create external table t_detail(id bigint, account string, income double, expenses double, time string) partitioned by (logdate string) row format delimited fields terminated by '\t' location '/hive/td_partition';
create temporary function AreaUDF as 'cn.itcast.hive.udf.AreaUDF';
load data inpath '/apache_cleaned/2013-05-31/part-r-00000' into table hmbbs partition (logdate='2018-05-31');
8、hive的UDF的使用
要继承org.apache.hadoop.hive.ql.exec.UDF类实现evaluate
自定义函数调用过程:
1.添加jar包(在hive命令行里面执行)
hive> add jar /root/NUDF.jar;
2.创建临时函数
hive> create temporary function getNation as 'cn.yy.hive.udf.NationUDF';
3.调用
hive> select id, name, getNation(nation) from usertable;
4.将查询结果保存到HDFS中
hive> create table result row format delimited fields terminated by '\t' as select * from usertable order by id desc;
hive> select id, getAreaName(id) as name from tel_rec;
create table result row format delimited fields terminated by '\t' as select id, getNation(nation) from usertable;