统计从2013七月份开始每周2013-07-01~2013-07-07,2013-07-08~2013-07-14，。。。2013-12-16~2013-12-22,2013-12-23~2013-12-29的wau，
以及相对于第一周7.1-7.7的保留率，累积25周

#第一周wau
hive -e "use acorn_3g;select count(distinct uid) from tmp_user_info where log_date>='2013-07-01' and log_date<='2013-07-07' and uid>0 and type='client';"
#第二周wau
hive -e "use acorn_3g;select count(distinct uid) from tmp_user_info where log_date>='2013-07-08' and log_date<='2013-07-14' and uid>0 and type='client';" 190s
#第二周保留
hive -e "use acorn_3g;select count(distinct t.uid) from (select distinct uid from tmp_user_info where log_date='2013-12-01' and uid>0 and type='client') t join (select distinct uid from tmp_user_info where log_date='2013-12-02' and uid>0 and type='client') m on t.uid=m.uid;" 510s

#第一周登陆用户id
select distinct uid from  tmp_user_info where log_date>='2013-07-01' and log_date<='2013-07-07' and uid>0 and type='client'>  0701-0707.txt 180s#第二周登陆用户id
select distinct uid from  tmp_user_info where log_date>='2013-07-08' and log_date<='2013-07-14' and uid>0 and type='client'>  0708-0714.txt#周wau
wc -l 0701-07-07.txt#周保留率，通过comm命令，拿到交集
comm 0701-0707.txt 0708-0714.txt -12| wc -l

#临时表
hive -hiveconf hive.exec.compress.output=true -hiveconf io.seqfile.compression.type=BLOCK -e "use acorn_3g;
create table tmp_xinyan_client_wau as
select cast ((datediff(log_date,'2013-07-01')/7) as int) as week,uid as user_id from tmp_user_info where log_date>='2013-07-01' and log_date<='2013-12-29' and uid>0 and type='client' group by cast ((datediff(log_date,'2013-07-01')/7) as int),uid;"  420s#一次性统计25周wau
hive -e "use acorn_3g;select week,count(1) from  tmp_xinyan_client_wau group by week" > wau.txt  48s#一次性统计25周保留率
hive -e "set hive.mapjoin.smalltable.filesize=250000000;use acorn_3g;select  /* + MAPJOIN(t7)*/ tu.week,count(1) from (select user_id from tmp_xinyan_client_wau where week=0)  t7  join tmp_xinyan_client_wau tu on t7.user_id = tu.user_id group by tu.week;"  360s