Pig读写HBase数据
admin
2023-02-08 04:40:04
0

1、建一个文本

[root@sandbox ~]# vi /customers

4000001,Kristina,Chung,55,Pilot

4000002,Paige,Chen,74,Teacher

4000003,Sherri,Melton,34,Firefighter

4000004,Gretchen,Hill,66,Computerhardware engineer

4000005,Karen,Puckett,74,Lawyer

4000006,Patrick,Song,42,Veterinarian

4000007,Elsie,Hamilton,43,Pilot

4000008,Hazel,Bender,63,Carpenter

4000009,Malcolm,Wagner,39,Artist

4000010,Dolores,McLaughlin,60,Writer

4000011,Francis,McNamara,47,Therapist

4000012,Sandy,Raynor,26,Writer

4000013,Marion,Moon,41,Carpenter

4000014,Beth,Woodard,65,

4000015,Julia,Desai,49,Musician

4000016,Jerome,Wallace,52,Pharmacist

4000017,Neal,Lawrence,72,Computersupport specialist

4000018,Jean,Griffin,45,Childcareworker

4000019,Kristine,Dougherty,63,Financialanalyst

 

2、把数据文件读入pig关系

grunt>copyfromlocal /customers/user/pig/

grunt>raw_data = LOAD'/user/pig/customers' USING PigStorage(',') AS (

>> custno:chararray,

>> firstname:chararray,

>> lastname:chararray,

>> age:int,

>> profession:chararray

>> );

grunt>dump raw_data;

(4000001,Kristina,Chung,55,Pilot)

(4000002,Paige,Chen,74,Teacher)

(4000003,Sherri,Melton,34,Firefighter)

(4000004,Gretchen,Hill,66,Computerhardware engineer)

(4000005,Karen,Puckett,74,Lawyer)

(4000006,Patrick,Song,42,Veterinarian)

(4000007,Elsie,Hamilton,43,Pilot)

(4000008,Hazel,Bender,63,Carpenter)

(4000009,Malcolm,Wagner,39,Artist)

(4000010,Dolores,McLaughlin,60,Writer)

(4000011,Francis,McNamara,47,Therapist)

(4000012,Sandy,Raynor,26,Writer)

(4000013,Marion,Moon,41,Carpenter)

(4000014,Beth,Woodard,65,)

(4000015,Julia,Desai,49,Musician)

(4000016,Jerome,Wallace,52,Pharmacist)

(4000017,Neal,Lawrence,72,Computersupport specialist)

(4000018,Jean,Griffin,45,Childcareworker)

(4000019,Kristine,Dougherty,63,Financialanalyst)

 

3 Pig把关系写到HBase

Hbase建一个表

hbase(main):017:0> create'customers','customer_data'

0row(s) in 1.4870 seconds

=>Hbase::Table - customers

hbase(main):018:0> list

TABLE                                                        

customers                                                                   

iemployee                                                                         

student                                                                          

t1                                                                                 

tc                                                                                  

5row(s) in 0.0390 seconds

hbase(main):019:0>scan 'customers'

ROW                                   COLUMN+CELL                                                                                                    

0row(s) in 0.3840 seconds

grunt> STORE raw_data INTO'hbase://customers' USING org.apache.pig.backend.hadoop.hbase.HBaseStorage(

>> 'customer_data:custno

>> customer_data:firstname

>> customer_data:lastname

>> customer_data:age

>> customer_data:profession'

>> );

hbase(main):023:0>scan 'customers'

ROW                                   COLUMN+CELL                                                                                                    

 4000001                              column=customer_data:age, timestamp=1427249531913, value=Pilot                                                  

 4000001                              column=customer_data:custno, timestamp=1427249531913,value=Kristina                                           

 4000001                              column=customer_data:firstname, timestamp=1427249531913,value=Chung                                           

 4000001                              column=customer_data:lastname, timestamp=1427249531913, value=55                                               

 4000002                              column=customer_data:age, timestamp=1427249531927, value=Teacher                                               

 4000002                              column=customer_data:custno, timestamp=1427249531927, value=Paige                                               

 4000002                              column=customer_data:firstname, timestamp=1427249531927, value=Chen                                            

 4000002                              column=customer_data:lastname,

   

   

                                              

 4000019                              column=customer_data:age, timestamp=1427249531931, value=Financialanalyst                                     

 4000019                              column=customer_data:custno, timestamp=1427249531931,value=Kristine                                           

 4000019                              column=customer_data:firstname, timestamp=1427249531931,value=Dougherty                                       

 4000019                               column=customer_data:lastname,timestamp=1427249531931, value=63                                               

19row(s) in 0.2800 seconds

 

3 PigHBase

grunt>raw = LOAD  'hbase://customers' USINGorg.apache.pig.backend.hadoop.hbase.HBaseStorage(

>> 'customer_data:custno

>> customer_data:firstname

>> customer_data:lastname

>> customer_data:age

>> customer_data:profession'

>> );

 

grunt>dump raw;

(Kristina,Chung,55,Pilot,)

(Paige,Chen,74,Teacher,)

(Sherri,Melton,34,Firefighter,)

(Gretchen,Hill,66,Computerhardware engineer,)

(Karen,Puckett,74,Lawyer,)

(Patrick,Song,42,Veterinarian,)

(Elsie,Hamilton,43,Pilot,)

(Hazel,Bender,63,Carpenter,)

(Malcolm,Wagner,39,Artist,)

(Dolores,McLaughlin,60,Writer,)

(Francis,McNamara,47,Therapist,)

(Sandy,Raynor,26,Writer,)

(Marion,Moon,41,Carpenter,)

(Beth,Woodard,65,,)

(Julia,Desai,49,Musician,)

(Jerome,Wallace,52,Pharmacist,)

(Neal,Lawrence,72,Computersupport specialist,)

(Jean,Griffin,45,Childcareworker,)

(Kristine,Dougherty,63,Financial analyst,)


相关内容

热门资讯

男子在采血站采血后口吐白沫、神... 7月23日,山西广播电视台《慧帮忙》栏目报道“我弟弟在霍州康宝生物科技采血站采血后口吐白沫、神志不清...
“安全先生”,不安全了 当地时间7月17日凌晨,以色列第25届议会以62票赞成、0票反对通过一项有关政党经费法的相关修正案,...
“AI科学家”,实验效率直接“... □ 本报记者 洪叶 徐春晖 窗明几净的空间里没有科研人员,取而代之的是一排充满科技感的自动化岛台,背...
云南一女子电脑屏内现“蚂蚁窝”... 大家平时清洁电脑显示屏吗? 你见过显示屏里进蚂蚁吗? 据媒体报道,云南临沧一名女子近期发现,自己使...
便携脑电采集新品发布,脑电信号... 一根发带将一个比硬币略大的采集设备贴在额头,就能实现脑电信号采集,脑机接口创新企业神舞科技7月22日...
工业和信息化部:依托标准牵引智... 日前,在北京举办的《人工智能 智能体互联》系列标准应用推进专题会上,工业和信息化部科技司副司长甘小斌...
原创 强... 进入下半年,子系品牌新一轮旗舰和中端性能机开始密集预热,近期更是有博主连续放出两条关键信息,分别指向...
“文学超界面”探索数字时代人文... 来源:新华网 当严肃文学的深厚内核遇见人工智能生成内容(AIGC)的影像创造力,会碰撞出怎样的火花...
以防长称已为应对伊朗局势做好“... △以色列国防部长卡茨(资料图)当地时间23日,据以色列方面消息,以色列国防部长卡茨当天表示,鉴于当前...
美参议院否决限制特朗普对伊战争... △美国国会(资料图)当地时间23日,美国参议院以49票对47票的表决结果,否决了旨在限制特朗普对伊朗...