发布于 2015-01-16 12:23:19 | 163 次阅读 | 评论: 0 | 来源: PHPERZ
Apache Pig
Apache Pig 是一个高级过程语言，是基于hadoop的处理框，适合于使用 Hadoop 和 MapReduce 平台来查询大型半结构化数据集。通过允许对分布式数据集进行类似 SQL 的查询，Pig 可以简化 Hadoop 的使用。
本文为大家整理总结了一些常用的 pig示例，感兴趣的同学参考下
在pig中， dump和store会分别完成两个MR，不会一起进行
LOAD'/user/wizad/data/wizad/raw/2014-0{6,7-0,7-1,7-2,7-3,8}*/3_1/adwords*'
或者定义引用：%default cleanedLog/user/wizad/data/wizad/cleaned/2014-11-{0[3-9],1[0-8]}/*/part*正确，
而%default cleanedLog/user/wizad/data/wizad/cleaned/2014-11-{0[3-9],[10-18]}/* /part*（这语法居然错了， 用hadoop fs -ls/user/wizad/data/wizad/cleaned/2014-11-{0[3-9],[10-18]}/ 发现[10-18]不能使用，是错误的，所以只能用1[0-8]。原因是[]只能在10之内。我试了一年0[10-18]查的是01和08两个文件。而 0[100-108] 查的10,11,18三个文件。所以只能在10之内使用。使用时格式为{[10-18]}也是一样的！）
注意：文件名读入不支持所有的正则表达式，是hadoop支持什么云可是用什么。hadoop2.0支持，
?
*
[abc]或者[^abc]
[a-z]或者[^a-z]
\c:转移字符表达，\d标示0到9的数字
{ab,cd}
按值过滤
FILTERclickDate_all BY log_type=='2';
FILTERmapping_table BY mapping_ad_network_id=='3' AND mapping_type=='5';
test=FILTER allRow BY (ad_id=='14997' OR ad_id=='14998' OR ad_id=='14999') ANDlog_type==2;
test=FILTERallRow BY (INDEXOF(ad_id,'14997')==0 OR INDEXOF(ad_id,'14998')==0 OR INDEXOF(ad_id,'14999')==0)AND log_type==2;
配合size函数
FILTERcount_imei BY (SIZE(cimei)>14 AND SIZE(cimei)<17);
FILTERcimei2 BY NOT cimei MATCHES '^[0-9]*$';
FILTERcmac2 BY cmac MATCHES'/[A-F\d]{2}:[A-F\d]{2}:[A-F\d]{2}:[A-F\d]{2}:[A-F\d]{2}:[A-F\d]{2}/';
ORDER province_count BY $2 DESC;
注意order多个文件，比如hdfs上part00000和part00001，order后只生成一个文件，因为合并成一个文件的操作只能用一个reduce完成，所以结果可能生成很大的文件
可用于生成独立的一列，如count了的一个数，前面加一列名称
FOREACHorigin_cleaned_data GENERATE CONCAT('<-_','->') AS cou,guid,log_type;
read_social_14=FOREACH metadata_social_14 GENERATE CONCAT('14','=='),guid_social;
all_id=FOREACH allRow GENERATE id,CONCAT('_','-') as cc;
条件表达式“（判断式）？a：b”的应用：直接对列操作
origin_historical= FOREACH origin_cleaned_data GENERATE wizad_ad_id,guid,log_type,
((province_region_id== '') ? 'unknown' : province_region_id)
另外注意：pig判断取值为null，是用is null（is not null）或者== null(!= null)
SPLIT geelyTuiGuang INTO android IFos_id==1,ios IF os_id==2;
SPLIT ios INTO ios6 IF(INDEXOF(os_version,'7')!=0),ios7 IF INDEXOF(os_version,'7')==0;
SPLITallCleaned INTO log_42 IF (
((chararray)$34=='1'OR (chararray)$34=='2' OR (chararray)$34=='3' OR (chararray)$34=='1' OR(chararray)$34=='4')
AND
(INDEXOF((chararray)$35,'.')>0)
AND
((chararray)$36=='1'OR (chararray)$36=='')
),
log_43IF (
((chararray)$34=='1'OR (chararray)$34=='2')
AND
((chararray)$35=='1'OR (chararray)$35=='2' OR (chararray)$35=='3' OR (chararray)$35=='1' OR(chararray)$35=='4')
AND
(INDEXOF((chararray)$36,'.')>0)
);
FOREACH ios6 GENERATE imei,mac_address ascmac,REPLACE(idfa,'null','');
en_guid =STREAM duimei THROUGH `awk-F"," '{if($3 == "null") print$1","$2","; else print $0}'`;
cleaned_data_42=FOREACH log_42 GENERATE
(chararray)$1 AS wizad_ad_id:chararray,
(chararray)$2 AS guid:chararray,
(chararray)$6 AS log_type:chararray,
(chararray)$18AS imei:chararray,
(chararray)$22AS idfa:chararray,
(chararray)$23AS mac_address:chararray
allAdId=FOREACH allRow GENERATE REGEX_EXTRACT((chararray)$3,'(.*) (.*)',1) AStime,REGEX_EXTRACT((chararray)$0,'(.*)_(.*)',1) AS adn,$6 AS ad_id;
allAdId=FOREACH allRow GENERATE REGEX_EXTRACT(create_time,'(.*) (.*)',1) AStime,ad_id;
split jn_data into same_prov if(SUBSTRING(province,0,2) == SUBSTRING(province_ad,0,2)), diff_prov if(SUBSTRING(province,0,2)
!= SUBSTRING(province_ad,0,2));
时间类型提取分钟，做计算
log_data= foreach click_log generate log_type,guid,ip,SUBSTRING(create_time,0,13) astime,SUBSTRING(create_time,14,16) as minute2,os_id,os_version,device_type;
minute_compare= foreach join_data generatelog_type,cookie_id,guid,(int)minute1,(int)minute2,time_extract::os_version,log_data::os_version;
same_users= filter minute_compare by (ABS(minute1-minute2) <= 5);
grp_diff_city= group diff_city all;
count_diff_city= foreach grp_diff_city generate COUNT_STAR($1);
dump count_same_city;
join_data= join time_extract by (ip,time,os_id), log_data by (ip,time,os_id);
从左向右依次比较