`

pig过滤A表中有B表中无的数据实例

 
阅读更多
--加载数据文件
events_raw_short = load '$EVT_RECENT_FILES' using PigStorage('\u0001') as (
 id:chararray,
 event_id:int,
 valid_flag:int
);
--时间过滤

events_raw_short = filter events_raw_short by e_date >= '$EVTLKBK' ;

--events_raw_short与converted_events做聚合运算

events_cgrpd = cogroup events_raw_short by id, converted_events by eventdata_id;

--过滤出A表中有B表中无的数据

events_ajnd = filter events_cgrpd by IsEmpty(converted_events);

--加载过滤数据

events_fltnd = foreach events_ajnd generate FLATTEN(events_raw_short);

--遍历实例化

events = foreach events_fltnd generate
 id as  id,
 event_id as  event_id,
 valid_flag as  valid_flag

0
0
分享到:
评论

相关推荐

Global site tag (gtag.js) - Google Analytics