hive的 LAG,LEAD,FIRST_VALUE,LAST_VALUE函数

1、数据准备

CREATE EXTERNAL TABLE lxw1234 (
cookieid string,
createtime string,  --页面访问时间
url STRING       --被访问页面
) ;
 
 
hive> select * from lxw1234;
OK
cookie1 2015-04-10 10:00:02     url2
cookie1 2015-04-10 10:00:00     url1
cookie1 2015-04-10 10:03:04     1url3
cookie1 2015-04-10 10:50:05     url6
cookie1 2015-04-10 11:00:00     url7
cookie1 2015-04-10 10:10:00     url4
cookie1 2015-04-10 10:50:01     url5
cookie2 2015-04-10 10:00:02     url22
cookie2 2015-04-10 10:00:00     url11
cookie2 2015-04-10 10:03:04     1url33
cookie2 2015-04-10 10:50:05     url66
cookie2 2015-04-10 11:00:00     url77
cookie2 2015-04-10 10:10:00     url44
cookie2 2015-04-10 10:50:01     url55

2、LAG

LAG(col,n,DEFAULT) 用于统计窗口内往上第n行值
第一个参数为列名，第二个参数为往上第n行（可选，默认为1），第三个参数为默认值（当往上第n行为NULL时候，取默认值，如不指定，则为NULL）

SELECT cookieid,
createtime,
url,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
LAG(createtime,1,'1970-01-01 00:00:00') OVER(PARTITION BY cookieid ORDER BY createtime) AS last_1_time,
LAG(createtime,2) OVER(PARTITION BY cookieid ORDER BY createtime) AS last_2_time 
FROM lxw1234;
 
 
cookieid createtime             url    rn       last_1_time             last_2_time
-------------------------------------------------------------------------------------------
cookie1 2015-04-10 10:00:00     url1    1       1970-01-01 00:00:00     NULL
cookie1 2015-04-10 10:00:02     url2    2       2015-04-10 10:00:00     NULL
cookie1 2015-04-10 10:03:04     1url3   3       2015-04-10 10:00:02     2015-04-10 10:00:00
cookie1 2015-04-10 10:10:00     url4    4       2015-04-10 10:03:04     2015-04-10 10:00:02
cookie1 2015-04-10 10:50:01     url5    5       2015-04-10 10:10:00     2015-04-10 10:03:04
cookie1 2015-04-10 10:50:05     url6    6       2015-04-10 10:50:01     2015-04-10 10:10:00
cookie1 2015-04-10 11:00:00     url7    7       2015-04-10 10:50:05     2015-04-10 10:50:01
cookie2 2015-04-10 10:00:00     url11   1       1970-01-01 00:00:00     NULL
cookie2 2015-04-10 10:00:02     url22   2       2015-04-10 10:00:00     NULL
cookie2 2015-04-10 10:03:04     1url33  3       2015-04-10 10:00:02     2015-04-10 10:00:00
cookie2 2015-04-10 10:10:00     url44   4       2015-04-10 10:03:04     2015-04-10 10:00:02
cookie2 2015-04-10 10:50:01     url55   5       2015-04-10 10:10:00     2015-04-10 10:03:04
cookie2 2015-04-10 10:50:05     url66   6       2015-04-10 10:50:01     2015-04-10 10:10:00
cookie2 2015-04-10 11:00:00     url77   7       2015-04-10 10:50:05     2015-04-10 10:50:01

3、LEAD

与LAG相反
LEAD(col,n,DEFAULT) 用于统计窗口内往下第n行值
第一个参数为列名，第二个参数为往下第n行（可选，默认为1），第三个参数为默认值（当往下第n行为NULL时候，取默认值，如不指定，则为NULL）

SELECT cookieid,
createtime,
url,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
LEAD(createtime,1,'1970-01-01 00:00:00') OVER(PARTITION BY cookieid ORDER BY createtime) AS next_1_time,
LEAD(createtime,2) OVER(PARTITION BY cookieid ORDER BY createtime) AS next_2_time 
FROM lxw1234;
 
 
cookieid createtime             url    rn       next_1_time             next_2_time 
-------------------------------------------------------------------------------------------
cookie1 2015-04-10 10:00:00     url1    1       2015-04-10 10:00:02     2015-04-10 10:03:04
cookie1 2015-04-10 10:00:02     url2    2       2015-04-10 10:03:04     2015-04-10 10:10:00
cookie1 2015-04-10 10:03:04     1url3   3       2015-04-10 10:10:00     2015-04-10 10:50:01
cookie1 2015-04-10 10:10:00     url4    4       2015-04-10 10:50:01     2015-04-10 10:50:05
cookie1 2015-04-10 10:50:01     url5    5       2015-04-10 10:50:05     2015-04-10 11:00:00
cookie1 2015-04-10 10:50:05     url6    6       2015-04-10 11:00:00     NULL
cookie1 2015-04-10 11:00:00     url7    7       1970-01-01 00:00:00     NULL
cookie2 2015-04-10 10:00:00     url11   1       2015-04-10 10:00:02     2015-04-10 10:03:04
cookie2 2015-04-10 10:00:02     url22   2       2015-04-10 10:03:04     2015-04-10 10:10:00
cookie2 2015-04-10 10:03:04     1url33  3       2015-04-10 10:10:00     2015-04-10 10:50:01
cookie2 2015-04-10 10:10:00     url44   4       2015-04-10 10:50:01     2015-04-10 10:50:05
cookie2 2015-04-10 10:50:01     url55   5       2015-04-10 10:50:05     2015-04-10 11:00:00
cookie2 2015-04-10 10:50:05     url66   6       2015-04-10 11:00:00     NULL
cookie2 2015-04-10 11:00:00     url77   7       1970-01-01 00:00:00     NULL
 
--逻辑与LAG一样，只不过LAG是往上，LEAD是往下。

4、FIRST_VALUE

取分组内排序后，截止到当前行，第一个值

SELECT cookieid,
createtime,
url,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
FIRST_VALUE(url) OVER(PARTITION BY cookieid ORDER BY createtime) AS first1 
FROM lxw1234;
 
cookieid  createtime            url     rn      first1
---------------------------------------------------------
cookie1 2015-04-10 10:00:00     url1    1       url1
cookie1 2015-04-10 10:00:02     url2    2       url1
cookie1 2015-04-10 10:03:04     1url3   3       url1
cookie1 2015-04-10 10:10:00     url4    4       url1
cookie1 2015-04-10 10:50:01     url5    5       url1
cookie1 2015-04-10 10:50:05     url6    6       url1
cookie1 2015-04-10 11:00:00     url7    7       url1
cookie2 2015-04-10 10:00:00     url11   1       url11
cookie2 2015-04-10 10:00:02     url22   2       url11
cookie2 2015-04-10 10:03:04     1url33  3       url11
cookie2 2015-04-10 10:10:00     url44   4       url11
cookie2 2015-04-10 10:50:01     url55   5       url11
cookie2 2015-04-10 10:50:05     url66   6       url11
cookie2 2015-04-10 11:00:00     url77   7       url11

5、LAST_VALUE

取分组内排序后，截止到当前行，最后一个值

SELECT cookieid,
createtime,
url,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
LAST_VALUE(url) OVER(PARTITION BY cookieid ORDER BY createtime) AS last1 
FROM lxw1234;
 
 
cookieid  createtime            url    rn       last1  
-----------------------------------------------------------------
cookie1 2015-04-10 10:00:00     url1    1       url1
cookie1 2015-04-10 10:00:02     url2    2       url2
cookie1 2015-04-10 10:03:04     1url3   3       1url3
cookie1 2015-04-10 10:10:00     url4    4       url4
cookie1 2015-04-10 10:50:01     url5    5       url5
cookie1 2015-04-10 10:50:05     url6    6       url6
cookie1 2015-04-10 11:00:00     url7    7       url7
cookie2 2015-04-10 10:00:00     url11   1       url11
cookie2 2015-04-10 10:00:02     url22   2       url22
cookie2 2015-04-10 10:03:04     1url33  3       1url33
cookie2 2015-04-10 10:10:00     url44   4       url44
cookie2 2015-04-10 10:50:01     url55   5       url55
cookie2 2015-04-10 10:50:05     url66   6       url66
cookie2 2015-04-10 11:00:00     url77   7       url77