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

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

在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、 Pig读HBase表

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

空调连续工作多久需要停机休息 空调连续工作的时间取决于多个因素,包括空调的型号、功率、使用环境和维护情况等。一般来说,空调可以连续...
空调哪个符号是除湿的 空调除湿功能通常用一个水滴形状的符号表示。不同品牌和型号的空调遥控器可能会有所差异,但一般来说,除湿...
格力空调多长时间加一次氟利昂 1、一般情况下,空调对氟利昂的使用量是非常小的,所以在空调使用了四年左右的时候再考虑加也没问题。2、...
空调用多长时间需要加氟一次 一般情况下是五年。当出现以下这几种情况时,空调才需要加氟。1、空调的室内机和室外机各有两个接口,当接...
格调生活·C标思享荟:卡萨帝在... 9月12日的郑州龙湖金融岛,夜风轻拂,灯光璀璨。“C标时刻共传奇——卡萨帝思享荟暨20周年品牌盛典郑...
品牌价值破千亿、高端份额持续领... 9月12日,“C标时刻共传奇——卡萨帝思享荟暨20周年品牌盛典郑州站”在郑州龙湖金融岛举办。2026...
空调主板坏了修800还是换新的 空调主板坏了是修还是换新,需要考虑多个因素,以下是一些建议:1. 维修成本:如果维修费用较低,比如 ...
空调开多久需要休息多长时间 问题:空调开多久需要休息多长时间回答:1、在使用空调的过程中,一般空调开7~8个小时左右需要休息2~...
中央空调多长时间清洗一次 1、一般空调开机前清洗一次即可,空调开机中间时段再清洗一次,空调关机时清洗一次,这样比较合理。2、空...
中央空调氟利昂多久加一次 看空调制热和制冷程度,很多人的观点认为氟利昂必须一年放一次,其实这个观点是错误的,理解上面有点偏差,...