最近终于有点时间了,不容易啊, 下次给大家分享点Azkaban怎么调度,脚本里面定制化参数,整个数据的流入,流出,到数据的展示一整套架构, hive的维度建模,设计原理, 包括flink,kylin等, Mllib!!
//将数据按data_date分区动态插入到kpi_company_perform_rate_day表中
set hive.exec.dynamic.partition.mode=nonstrict;
set hive.exec.dynamic.partition=true;
SET hive.exec.max.dynamic.partitions=100000;
SET hive.exec.max.dynamic.partitions.pernode=100000;
insert overwrite table dm.kpi_company_perform_rate_day partition(etl_tx_dt)
SELECT
data_date
,kpi_name
,goal_value
,reach_value
,reach_rate
,from_unixtime(unix_timestamp(), 'yyyy-MM-dd HH:mm:ss')
,cast(regexp_replace(data_date,'-','') as int ) etl_tx_dt
FROM test.test_kpi_company_perform_rate_day
//查询数据库中所有为null的表
USE information_schema;
SELECT table_schema,table_name,table_rows FROM TABLES WHERE table_rows = 0 ORDER BY table_name ;
;
