hive HQL

set hive.cli.print.header=true;

CREATE TABLE page_view(viewTime INT, userid BIGINT,

page_url STRING, referrer_url STRING,

ip STRING COMMENT 'IP Address of the User')

COMMENT 'This is the page view table'

PARTITIONED BY(dt STRING, country STRING)

ROW FORMAT DELIMITED

FIELDS TERMINATED BY '\001'

STORED AS SEQUENCEFILE; TEXTFILE

//sequencefile

create table tab_ip_seq(id int,name string,ip string,country string)

row format delimited

fields terminated by ','

stored as sequencefile;

insert overwrite table tab_ip_seq select * from tab_ext;

//create & load

create table tab_ip(id int,name string,ip string,country string)

row format delimited

fields terminated by ','

stored as textfile;

load data local inpath '/home/hadoop/ip.txt' into table tab_ext;

//external

CREATE EXTERNAL TABLE tab_ip_ext(id int, name string,

ip STRING,

country STRING)

ROW FORMAT DELIMITED FIELDS TERMINATED BY ','

STORED AS TEXTFILE

LOCATION '/external/hive';

// CTAS 用于创建一些临时表存储中间结果

CREATE TABLE tab_ip_ctas

AS

SELECT id new_id, name new_name, ip new_ip,country new_country

FROM tab_ip_ext

SORT BY new_id;

//insert from select 用于向临时表中追加中间结果数据

create table tab_ip_like like tab_ip;

insert overwrite table tab_ip_like

select * from tab_ip;

//CLUSTER <--相对高级一点,你可以放在有精力的时候才去学习>

create table tab_ip_cluster(id int,name string,ip string,country string)

clustered by(id) into 3 buckets;

load data local inpath '/home/hadoop/ip.txt' overwrite into table tab_ip_cluster;

set hive.enforce.bucketing=true;

insert into table tab_ip_cluster select * from tab_ip;

select * from tab_ip_cluster tablesample(bucket 2 out of 3 on id);

//PARTITION

create table tab_ip_part(id int,name string,ip string,country string)

partitioned by (part_flag string)

row format delimited fields terminated by ',';

load data local inpath '/home/hadoop/ip.txt' overwrite into table tab_ip_part

partition(part_flag='part1');

load data local inpath '/home/hadoop/ip_part2.txt' overwrite into table tab_ip_part

partition(part_flag='part2');

select * from tab_ip_part;

select * from tab_ip_part where part_flag='part2';

select count(*) from tab_ip_part where part_flag='part2';

alter table tab_ip change id id_alter string;

ALTER TABLE tab_cts ADD PARTITION (partCol = 'dt') location '/external/hive/dt';

show partitions tab_ip_part;

//write to hdfs

insert overwrite local directory '/home/hadoop/hivetemp/test.txt' select * from tab_ip_part where part_flag='part1';

insert overwrite directory '/hiveout.txt' select * from tab_ip_part where part_flag='part1';

//array

create table tab_array(a array<int>,b array<string>)

row format delimited

fields terminated by '\t'

collection items terminated by ',';

示例数据

tobenbrone,laihama,woshishui 13866987898,13287654321

abc,iloveyou,itcast 13866987898,13287654321

select a[0] from tab_array;

select * from tab_array where array_contains(b,'word');

insert into table tab_array select array(0),array(name,ip) from tab_ext t;

//map

create table tab_map(name string,info map<string,string>)

row format delimited

fields terminated by '\t'

collection items terminated by ';'

map keys terminated by ':';

示例数据:

fengjie age:18;size:36A;addr:usa

furong age:28;size:39C;addr:beijing;weight:180KG

load data local inpath '/home/hadoop/hivetemp/tab_map.txt' overwrite into table tab_map;

insert into table tab_map select name,map('name',name,'ip',ip) from tab_ext;

//struct

create table tab_struct(name string,info struct<age:int,tel:string,addr:string>)

row format delimited

fields terminated by '\t'

collection items terminated by ','

load data local inpath '/home/hadoop/hivetemp/tab_st.txt' overwrite into table tab_struct;

insert into table tab_struct select name,named_struct('age',id,'tel',name,'addr',country) from tab_ext;

//cli shell

hive -S -e 'select country,count(*) from tab_ext' > /home/hadoop/hivetemp/e.txt

有了这种执行机制,就使得我们可以利用脚本语言(bash shell,python)进行hql语句的批量执行

select * from tab_ext sort by id desc limit 5;

select a.ip,b.book from tab_ext a join tab_ip_book b on(a.name=b.name);

//UDF

0.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.itcast.hive.udf.NationUDF';

3.调用

hive> select id, name, getNation(nation) from beauty;

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 beauty order by id desc;

hive> select id, getAreaName(id) as name from tel_rec;

hive>create table result row format delimited fields terminated by '\t' as select id, getNation(nation) from beauties;

hive>select if(id=1,first,no-first),name from tab_ext;

hive>add jar /home/hadoop/myudf.jar;

hive>CREATE TEMPORARY FUNCTION my_lower AS 'org.dht.Lower';

hive>select my_upper(name) from tab_ext;

相关推荐
Lx3521 天前
Hadoop数据处理优化:减少Shuffle阶段的性能损耗
大数据·hadoop
Lx3522 天前
Hadoop容错机制深度解析:保障作业稳定运行
大数据·hadoop
IT毕设梦工厂3 天前
大数据毕业设计选题推荐-基于大数据的客户购物订单数据分析与可视化系统-Hadoop-Spark-数据可视化-BigData
大数据·hadoop·数据分析·spark·毕业设计·源码·bigdata
大数据CLUB3 天前
基于spark的澳洲光伏发电站选址预测
大数据·hadoop·分布式·数据分析·spark·数据开发
计算机编程小央姐3 天前
跟上大数据时代步伐:食物营养数据可视化分析系统技术前沿解析
大数据·hadoop·信息可视化·spark·django·课程设计·食物
IT学长编程3 天前
计算机毕业设计 基于Hadoop的健康饮食推荐系统的设计与实现 Java 大数据毕业设计 Hadoop毕业设计选题【附源码+文档报告+安装调试】
java·大数据·hadoop·毕业设计·课程设计·推荐算法·毕业论文
Lx3523 天前
Hadoop数据一致性保障:处理分布式系统常见问题
大数据·hadoop
IT学长编程3 天前
计算机毕业设计 基于Hadoop豆瓣电影数据可视化分析设计与实现 Python 大数据毕业设计 Hadoop毕业设计选题【附源码+文档报告+安装调试
大数据·hadoop·python·django·毕业设计·毕业论文·豆瓣电影数据可视化分析
Dobby_053 天前
【Hadoop】Yarn:Hadoop 生态的资源操作系统
大数据·hadoop·分布式·yarn
笨蛋少年派3 天前
安装Hadoop中遇到的一些问题和解决
大数据·hadoop·分布式