hive分析窗口函数
基础函数
SUM、AVG、MIN、MAX
SELECT cookieid,
createtime,
pv,
SUM(pv) OVER(PARTITION BY cookieid ORDER BY createtime) AS pv1, -- 默认为从起点到当前行
SUM(pv) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS pv2, --从起点到当前行，结果同pv1
SUM(pv) OVER(PARTITION BY cookieid) AS pv3, --分组内所有行
SUM(pv) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN 3 PRECEDING AND CURRENT ROW) AS pv4, --当前行+往前3行
SUM(pv) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN 3 PRECEDING AND 1 FOLLOWING) AS pv5, --当前行+往前3行+往后1行
SUM(pv) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING) AS pv6 ---当前行+往后所有行
FROM lxw1234;
cookieid createtime pv pv1 pv2 pv3 pv4 pv5 pv6
-----------------------------------------------------------------------------
cookie1 2015-04-10 1 1 1 26 1 6 26
cookie1 2015-04-11 5 6 6 26 6 13 25
cookie1 2015-04-12 7 13 13 26 13 16 20
cookie1 2015-04-13 3 16 16 26 16 18 13
cookie1 2015-04-14 2 18 18 26 17 21 10
cookie1 2015-04-15 4 22 22 26 16 20 8
cookie1 2015-04-16 4 26 26 26 13 13 4
序列函数
序列函数，NTILE,ROW_NUMBER,RANK,DENSE_RANK
NTILE
NTILE(n)，用于将分组数据按照顺序切分成n片，返回当前切片值
NTILE不支持ROWS BETWEEN，比如 NTILE(2) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN 3 PRECEDING AND CURRENT ROW)
如果切片不均匀，默认增加第一个切片的分布
SELECT
cookieid,
createtime,
pv,
NTILE(2) OVER(PARTITION BY cookieid ORDER BY createtime) AS rn1, --分组内将数据分成2片
NTILE(3) OVER(PARTITION BY cookieid ORDER BY createtime) AS rn2, --分组内将数据分成3片
NTILE(4) OVER(ORDER BY createtime) AS rn3 --将所有数据分成4片
FROM lxw1234
ORDER BY cookieid,createtime;
cookieid day pv rn1 rn2 rn3
-------------------------------------------------
cookie1 2015-04-10 1 1 1 1
cookie1 2015-04-11 5 1 1 1
cookie1 2015-04-12 7 1 1 2
cookie1 2015-04-13 3 1 2 2
cookie1 2015-04-14 2 2 2 3
cookie1 2015-04-15 4 2 3 3
cookie1 2015-04-16 4 2 3 4
cookie2 2015-04-10 2 1 1 1
cookie2 2015-04-11 3 1 1 1
cookie2 2015-04-12 5 1 1 2
cookie2 2015-04-13 6 1 2 2
cookie2 2015-04-14 3 2 2 3
cookie2 2015-04-15 9 2 3 4
cookie2 2015-04-16 7 2 3 4
ROW_NUMBER
ROW_NUMBER() –从1开始，按照顺序，生成分组内记录的序列
–比如，按照pv降序排列，生成分组内每天的pv名次
ROW_NUMBER() 的应用场景非常多，再比如，获取分组内排序第一的记录;获取一个session中的第一条refer等。
SELECT
cookieid,
createtime,
pv,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY pv desc) AS rn
FROM lxw1234;
cookieid day pv rn
-------------------------------------------
cookie1 2015-04-12 7 1
cookie1 2015-04-11 5 2
cookie1 2015-04-15 4 3
cookie1 2015-04-16 4 4
cookie1 2015-04-13 3 5
cookie1 2015-04-14 2 6
cookie1 2015-04-10 1 7
cookie2 2015-04-15 9 1
cookie2 2015-04-16 7 2
cookie2 2015-04-13 6 3
cookie2 2015-04-12 5 4
cookie2 2015-04-14 3 5
cookie2 2015-04-11 3 6
cookie2 2015-04-10 2 7
RANK 和 DENSE_RANK
—RANK() 生成数据项在分组中的排名，排名相等会在名次中留下空位
—DENSE_RANK() 生成数据项在分组中的排名，排名相等会在名次中不会留下空位
SELECT
cookieid,
createtime,
pv,
RANK() OVER(PARTITION BY cookieid ORDER BY pv desc) AS rn1,
DENSE_RANK() OVER(PARTITION BY cookieid ORDER BY pv desc) AS rn2,
ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY pv DESC) AS rn3
FROM lxw1234
WHERE cookieid = 'cookie1';
cookieid day pv rn1 rn2 rn3
--------------------------------------------------
cookie1 2015-04-12 7 1 1 1
cookie1 2015-04-11 5 2 2 2
cookie1 2015-04-15 4 3 3 3
cookie1 2015-04-16 4 3 3 4
cookie1 2015-04-13 3 5 4 5
cookie1 2015-04-14 2 6 5 6
cookie1 2015-04-10 1 7 6 7
rn1: 15号和16号并列第3, 13号排第5
rn2: 15号和16号并列第3, 13号排第4
rn3: 如果相等，则按记录值排序，生成唯一的次序，如果所有记录值都相等，或许会随机排吧。
CUME_DIST
–CUME_DIST 小于等于当前值的行数/分组内总行数
–比如，统计小于等于当前薪水的人数，所占总人数的比例
–CUME_DIST 小于等于当前值的行数/分组内总行数
–比如，统计小于等于当前薪水的人数，所占总人数的比例
SELECT
dept,
userid,
sal,
CUME_DIST() OVER(ORDER BY sal) AS rn1,
CUME_DIST() OVER(PARTITION BY dept ORDER BY sal) AS rn2
FROM lxw1234;
dept userid sal rn1 rn2
-------------------------------------------
d1 user1 1000 0.2 0.3333333333333333
d1 user2 2000 0.4 0.6666666666666666
d1 user3 3000 0.6 1.0
d2 user4 4000 0.8 0.5
d2 user5 5000 1.0 1.0
rn1: 没有partition,所有数据均为1组，总行数为5，
第一行：小于等于1000的行数为1，因此，1/5=0.2
第三行：小于等于3000的行数为3，因此，3/5=0.6
rn2: 按照部门分组，dpet=d1的行数为3,
第二行：小于等于2000的行数为2，因此，2/3=0.6666666666666666
PERCENT_RANK
–PERCENT_RANK 分组内当前行的RANK值-1/分组内总行数-1
SELECT
dept,
userid,
sal,
PERCENT_RANK() OVER(ORDER BY sal) AS rn1, --分组内
RANK() OVER(ORDER BY sal) AS rn11, --分组内RANK值
SUM(1) OVER(PARTITION BY NULL) AS rn12, --分组内总行数
PERCENT_RANK() OVER(PARTITION BY dept ORDER BY sal) AS rn2
FROM lxw1234;
dept userid sal rn1 rn11 rn12 rn2
---------------------------------------------------
d1 user1 1000 0.0 1 5 0.0
d1 user2 2000 0.25 2 5 0.5
d1 user3 3000 0.5 3 5 1.0
d2 user4 4000 0.75 4 5 0.0
d2 user5 5000 1.0 5 5 1.0
rn1: rn1 = (rn11-1) / (rn12-1)
第一行,(1-1)/(5-1)=0/4=0
第二行,(2-1)/(5-1)=1/4=0.25
第四行,(4-1)/(5-1)=3/4=0.75
rn2: 按照dept分组，
dept=d1的总行数为3
第一行，(1-1)/(3-1)=0
第三行，(3-1)/(3-1)=1
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
last_1_time: 指定了往上第1行的值，default为'1970-01-01 00:00:00'
cookie1第一行，往上1行为NULL,因此取默认值 1970-01-01 00:00:00
cookie1第三行，往上1行值为第二行值，2015-04-10 10:00:02
cookie1第六行，往上1行值为第五行值，2015-04-10 10:50:01
last_2_time: 指定了往上第2行的值，为指定默认值
cookie1第一行，往上2行为NULL
cookie1第二行，往上2行为NULL
cookie1第四行，往上2行为第二行值，2015-04-10 10:00:02
cookie1第七行，往上2行为第五行值，2015-04-10 10:50:01
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。
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
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