1.窗口函数
2015年4月份购买过的顾客及总人数
select distinct name,count(1) over() as cnt from test_window_yf
where substr(orderdate,1,7)='2015-04';
select name,count(1) over() as cnt from test_window_yf
where substr(orderdate,1,7)='2015-04' group by name;
顾客的购买明细及月购买总额
将cost按照月进行累加
//默认从起始行到当前行
select name,orderdate,cost,sum(cost) over(partition by month(orderdate) order by orderdate) from test_window_yf;
sum(cost) over() as sample1,--所有行相加
sum(cost) over(partition by name) as sample2,--按name分组，组内数据相加
sum(cost) over(partition by name order by orderdate) as sample3,--按name分组，组内数据累加
sum(cost) over(partition by name order by orderdate rows between UNBOUNDED PRECEDING and current row ) as sample4 ,--和sample3一样,由起点到当前行的聚合
sum(cost) over(partition by name order by orderdate rows between 1 PRECEDING and current row) as sample5, --当前行和前面一行做聚合
sum(cost) over(partition by name order by orderdate rows between 1 PRECEDING AND 1 FOLLOWING ) as sample6,--当前行和前边一行及后面一行
sum(cost) over(partition by name order by orderdate rows between current row and UNBOUNDED FOLLOWING ) as sample7 --当前行及后面所有行
select name,orderdate,cost,
from test_window_yf;
name orderdate cost sample1 sample2 sample3 sample4 sample5 sample6 sample7
jack 2015-01-01 10 661 176 10 10 10 56 176
jack 2015-01-05 46 661 176 56 56 56 111 166
jack 2015-01-08 55 661 176 111 111 101 124 120
jack 2015-02-03 23 661 176 134 134 78 120 65
jack 2015-04-06 42 661 176 176 176 65 65 42
mart 2015-04-08 62 661 299 62 62 62 130 299
mart 2015-04-09 68 661 299 130 130 130 205 237
mart 2015-04-11 75 661 299 205 205 143 237 169
mart 2015-04-13 94 661 299 299 299 169 169 94
neil 2015-05-10 12 661 92 12 12 12 92 92
neil 2015-06-12 80 661 92 92 92 92 92 80
tony 2015-01-02 15 661 94 15 15 15 44 94
tony 2015-01-04 29 661 94 44 44 44 94 79
tony 2015-01-07 50 661 94 94 94 79 79 50
select name,orderdate,cost,
ntile(4) over() as sample1 , --全局数据切片
ntile(4) over(partition by name), -- 按照name进行分组,在分组内将数据切成3份
ntile(4) over(order by cost),--全局按照cost升序排列,数据切成3份
ntile(4) over(partition by name order by cost ) --按照name分组，在分组内按照cost升序排列,数据切成3份
from test_window_yf;
2.高级聚合函数
grouping sets / cube / rollup
grouping__id
2015-03,2015-03-10,cookie1
2015-03,2015-03-10,cookie5
2015-03,2015-03-12,cookie7
2015-04,2015-04-12,cookie3
2015-04,2015-04-13,cookie2
2015-04,2015-04-13,cookie4
2015-04,2015-04-16,cookie4
2015-03,2015-03-10,cookie2
2015-03,2015-03-10,cookie3
2015-04,2015-04-12,cookie5
2015-04,2015-04-13,cookie6
2015-04,2015-04-15,cookie3
2015-04,2015-04-15,cookie2
2015-04,2015-04-16,cookie1
CREATE TABLE sospdm.test_function_yf (
month STRING,
day STRING,
cookieid STRING
) ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
stored as textfile;
GROUPING SETS
在一个GROUP BY查询中，根据不同的维度组合进行聚合，等价于将不同维度的GROUP BY结果集进行 UNION ALL
SELECT
month,
day,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM sospdm.test_function_yf
GROUP BY month,day
GROUPING SETS ((month,day),day);
--
ORDER BY GROUPING__ID;
--GROUPING__ID，表示结果属于哪一个分组集合。
month day uv GROUPING__ID
2015-03 NULL 5 1
2015-04 NULL 6 1
NULL 2015-03-10 4 2
NULL 2015-03-12 1 2
NULL 2015-04-12 2 2
NULL 2015-04-13 3 2
NULL 2015-04-15 2 2
NULL 2015-04-16 2 2
<=>
SELECT month,NULL,COUNT(DISTINCT cookieid) AS uv,1 AS GROUPING__ID FROM lxw1234 GROUP BY month
UNION ALL
SELECT NULL,day,COUNT(DISTINCT cookieid) AS uv,2 AS GROUPING__ID FROM lxw1234 GROUP BY day
SELECT
month,
day,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM sospdm.test_function_yf
GROUP BY month,day
GROUPING SETS ((month,day),(day))
ORDER BY GROUPING__ID;
2015-04 NULL 6 1
2015-03 NULL 5 1
NULL 2015-03-10 4 2
NULL 2015-04-16 2 2
NULL 2015-04-15 2 2
NULL 2015-04-13 3 2
NULL 2015-04-12 2 2
NULL 2015-03-12 1 2
2015-04 2015-04-16 2 3
2015-04 2015-04-12 2 3
2015-04 2015-04-13 3 3
2015-03 2015-03-12 1 3
2015-03 2015-03-10 4 3
2015-04 2015-04-15 2 3
cube:
根据GROUP BY的维度的所有组合进行聚合。
SELECT
month,
day,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM sospdm.test_function_yf
GROUP BY month,day
WITH CUBE
ORDER BY GROUPING__ID;
<=>
SELECT
month,
day,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM sospdm.test_function_yf
GROUP BY month,day
grouping sets((month,day),month,day,())
ORDER BY GROUPING__ID;
NULL NULL 7 0 --区别
2015-03 NULL 5 1
2015-04 NULL 6 1
NULL 2015-04-16 2 2
NULL 2015-04-15 2 2
NULL 2015-04-13 3 2
NULL 2015-04-12 2 2
NULL 2015-03-12 1 2
NULL 2015-03-10 4 2
2015-04 2015-04-12 2 3
2015-04 2015-04-16 2 3
2015-03 2015-03-12 1 3
2015-03 2015-03-10 4 3
2015-04 2015-04-15 2 3
2015-04 2015-04-13 3 3
ROLLUP
是CUBE的子集，以最左侧的维度为主，从该维度进行层级聚合。
比如，以month维度进行层级聚合：
SELECT
month,
day,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM lxw1234
GROUP BY month,day
WITH ROLLUP
ORDER BY GROUPING__ID;
month day uv GROUPING__ID
---------------------------------------------------
NULL NULL 7 0
2015-03 NULL 5 1
2015-04 NULL 6 1
2015-03 2015-03-10 4 3
2015-03 2015-03-12 1 3
2015-04 2015-04-12 2 3
2015-04 2015-04-13 3 3
2015-04 2015-04-15 2 3
2015-04 2015-04-16 2 3
--把month和day调换顺序，则以day维度进行层级聚合：
SELECT
day,
month,
COUNT(DISTINCT cookieid) AS uv,
GROUPING__ID
FROM lxw1234
GROUP BY day,month
WITH ROLLUP
ORDER BY GROUPING__ID;
day month uv GROUPING__ID
------------------------------------
NULL NULL 7 0
2015-04-13 NULL 3 1
2015-03-12 NULL 1 1
2015-04-15 NULL 2 1
2015-03-10 NULL 4 1
2015-04-16 NULL 2 1
2015-04-12 NULL 2 1
2015-04-12 2015-04 2 3
2015-03-10 2015-03 4 3
2015-03-12 2015-03 1 3
2015-04-13 2015-04 3 3
2015-04-15 2015-04 2 3
2015-04-16 2015-04 2 3
------
二、日期函数
1.日期函数 to_date(string expr)
返回类型：string
描述：返回时间字符串日期部分
to_date(expr) - Extracts the date part of the date or datetime expression expr
实例：
hive> select to_date('2014-09-16 15:50:08.119') from default.dual;
2014-09-16
2.年份函数 year(string expr)
返回类型：int
描述：返回时间字符串年份数字
year(date) - Returns the year of date
实例：
hive> select year('2014-09-16 15:50:08.119') from default.dual;
2014
3.月份函数 month(string expr)
返回类型：int
描述：返回时间字符串月份数字
month(date) - Returns the month of date
实例：
hive> select month('2014-09-16 15:50:08.119') from default.dual;
09
4.天函数 day(string expr)
返回类型：int
描述：返回时间字符串的天
day(date) - Returns the date of the month of date
实例：
hive> select day('2014-09-16 15:50:08.119') from default.dual;
16
5.小时函数 hour(string expr)
返回类型：int
描述：返回时间字符串小时数字
hour(date) - Returns the hour of date
实例：
hive> select hour('2014-09-16 15:50:08.119') from default.dual;
15
6.分钟函数 hour(string expr)
返回类型：int
描述：返回时间字符串分钟数字
minute(date) - Returns the minute of date
实例：
hive> select minute('2014-09-16 15:50:08.119') from default.dual;
50
7.秒函数 second(string expr)
返回类型：int
描述：返回时间字符串分钟数字
second(date) - Returns the second of date
实例：
hive> select second('2014-09-16 15:50:08.119') from default.dual;
08
8.日期增加函数 date_add(start_date, num_days)
返回类型：string
描述：返回增加num_days 天数的日期（负数则为减少）
date_add(start_date, num_days) - Returns the date that is num_days after start_date.
实例：
hive>select date_add('2014-09-16 15:50:08.119',10) from default.dual;
2014-09-26
hive>select date_add('2014-09-16 15:50:08.119',-10) from default.dual;
2014-09-06
9.日期减少函数 date_sub(start_date, num_days)
返回类型：string
描述：返回num_days 天数之前的日期（负数则为增加）
date_sub(start_date, num_days) - Returns the date that is num_days before start_date.
实例：
hive>select date_sub('2014-09-16 15:50:08.119',10) from default.dual;
2014-09-06
hive>select date_sub('2014-09-16 15:50:08.119',-10) from default.dual;
2014-09-26
10.周期函数 weekofyear(start_date, num_days)
返回类型：int
描述：返回当前日期位于本年的周期 一周一个周期
weekofyear(date) - Returns the week of the year of the given date. A week is considered to start on a Monday and week 1 is the first week with >3 days.
实例：
hive>select weekofyear('2014-09-16 15:50:08.119') from default.dual;
38
11.日期比较函数 weekofyear(start_date, num_days)
返回类型：string
描述：返回2个时间的日期差
datediff(date1, date2) - Returns the number of days between date1 and date2
date1-date2
实例：
hive>select datediff('2014-09-16 15:50:08.119','2014-09-15') from default.dual;
1