hive日志分析实战（二）

?需求

统计某游戏平台新用户渠道来源

日志格式如下：

?

Jul 23 0:00:47  [info] {SPR}gjzq{SPR}20130723000047{SPR}85493108{SPR}S1{SPR}{SPR}360wan-2j-reg{SPR}58.240.209.78{SPR}

?

?分析

依据map/reduce思想，可以按照如下方式找出新用户：

假如某用户在某月份出现过，则（qid，year，month）=1按qid汇总该用户出现过的月数，即构建(qid,count(year,month))对新用户的count（year，month）=1，且(year,month)=(2013,07).

找出新用户的来源渠道

来源渠道：新用户在201307可能多次登录平台，需要找出最早登陆平台所属渠道

分两步来做：

找出新用户所有登陆记录（qid,logintime,src）针对同一qid找出logintime最小时的src实现

数据准备

??? 1）建表

??

create table if not exists glogin_daily (year int,month int,day int,hour int,logintime string,qid int,gkey string,skey string,loginip string,registsrc string,loginfrom string) partitioned by (dt string);

???? 依据日志内容及所关心的信息创建表格，按天组织分区

?? 2 ) 数据导入

??? 因日志文件存在于多处，我们先将日志汇总到一临时目录，创建临时外部表将数据加载进hive，然后通过正则匹配的方式分隔出各字段。（内部表只能load单文件，通过这种方式可以load文件夹）

???

echo "==== load data into tmp table $TMP_TABLE ==="    ${SOFTWARE_BASE}/hive/bin/hive -e "create external table $TMP_TABLE (info string) location '${TMP_DIR}';"    echo "==== M/R ==="    CURR_YEAR=`echo $CURR_DOING|cut -b 1-4`    CURR_MONTH=`echo $CURR_DOING|cut -b 5-6`    CURR_DAY=`echo $CURR_DOING|cut -b 7-8`    dt="${CURR_YEAR}-${CURR_MONTH}-${CURR_DAY}"    ${SOFTWARE_BASE}/hive/bin/hive -e "add file ${SCRIPT_PATH}/${MAP_SCRIPT_FILE};set hive.exec.dynamic.partition=true;insert overwrite table glogin_daily partition (dt='${dt}') select transform (t.i) using '$MAP_SCRIPT_PARSER ./${MAP_SCRIPT_FILE}' as (y,m,d,h,t,q,g,s,ip,src,f) from (select info as i from ${TMP_TABLE}) t;"

??

其中filter_login.php:

$fr=fopen("php://stdin","r");$month_dict = array(    'Jan' => 1,    'Feb' => 2,    'Mar' => 3,    'Apr' => 4,    'May' => 5,    'Jun' => 6,    'Jul' => 7,    'Aug' => 8,    'Sep' => 9,    'Oct' => 10,    'Nov' => 11,    'Dec' => 12,);while(!feof($fr)){    $input = fgets($fr,256);    $input = rtrim($input);    //Jul 23 0:00:00  [info] {SPR}xxj{SPR}20130723000000{SPR}245396389{SPR}S9{SPR}iwan-ng-mnsg{SPR}cl-reg-xxj0if{SPR}221.5.67.136{SPR}    if(preg_match("/([^ ]+) +(\d+) (\d+):.*\{SPR\}([^\{]*)\{SPR\}(\d+)\{SPR\}(\d+)\{SPR\}([^\{]*)\{SPR\}([^\{]*)\{SPR\}(([^\{]*)\{SPR\}([^\{]*)\{SPR\})?/",$input,$matches))    {       $year = substr($matches[5],0,4);       echo $year."\t".$month_dict[$matches[1]]."\t".$matches[2]."\t".$matches[3]."\t".$matches[5]."\t".$matches[6]."\t".$matches[4]."\t".$matches[7]."\t".$matches[11]."\t".$matches[8]."\t".$matches[10]."\n";    }}fclose ($fr);

?

2.找出新用户

?

1)用户登陆平台记录按月消重汇总

?

create table distinct_login_monthly_tmp_07 as select qid,year,month from glogin_daily group by qid,year,month;

?
2)用户登陆平台月数

?

create table login_stat_monthly_tmp_07 as select qid,count(1) as c from distinct_login_monthly_tmp_07 where year<2013 or (year=2013 and month<=7) group by qid; 

?
平台级新用户：
1)找出登陆月数为1的用户;

2.判断这些用户是否在7月份出现，如果有出现，找出登陆所有src

?

create table new_player_monthly_07 as select distinct a.qid,b.src,b.logintime from (select qid from login_stat_monthly_tmp_07 where c=1) a join (select qid,loginfrom as src,logintime from glogin_daily where month=7 and year=2013) b on a.qid=b.qid;

?
找出最早登陆的src:

?

add file /home/game/lvbenwei/load_login/get_player_src.php;create table new_player_src_07 as select transform (t.qid,t.src,t.logintime) using 'php ./get_player_src.php' as (qid,src,logintime) from (select * from new_player_monthly_07 order by qid,logintime) t;

?

其中get_player_src.php:

$fr=fopen("php://stdin","r");$curr_qid = null;$curr_src = null;$curr_logintime=null;while(!feof($fr)){$input = fgets($fr,1024);$input = rtrim($input);$arr   = explode("\t", $input);$qid   = trim($arr[0]);        if(empty($curr_qid)||$curr_qid != $qid)        {                $curr_qid = $qid;                echo $input."\n";        }}fclose ($fr);

?
平台级新用户数：

select count(*) from new_player_src_07;

?
平台级各渠道新用户汇总：

create table new_player_src_stat_07 as select src,count(*) from new_player_monthly_07 group by src;

?