1、視窗函式
視窗範圍限定：
OVER()
CURRENT_ROW 當前行
N PRECEDING 向前N行
N FOLLOWING 向後N行
UNBOUNDED PRECEDING 起點
UNBOUNDED FOLLOWING 終點
order by[asc/desc] 有序
partition by 分組

​ 建表：

​

create table  if not exists  business(
name string,
orderdate string,
cost int
) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
load data local inpath '/home/atbwie/a.txt' overwrite into table business;
 

資料：

資料準備：name，orderdate，cost
jack,2017-01-01,10
tony,2017-01-02,15
jack,2017-02-03,23
tony,2017-01-04,29
jack,2017-01-05,46
jack,2017-04-06,42
tony,2017-01-07,50
jack,2017-01-08,55
mart,2017-04-08,62
mart,2017-04-09,68
neil,2017-05-10,12
mart,2017-04-11,75
neil,2017-06-12,80
mart,2017-04-13,94

​

select * from business;

函式：
LAG(col,n,default_value) 向前第n行，有序視窗

select *,lag(orderdate,1,null) over(partition by name order by orderdate ) as o1  from business

​ LEAD(col,n,default_value) 向後第n行，有序視窗

select *,lag(orderdate,1,null) over(partition by name order by orderdate ) as o1  from business

​

NTILE(n) 將資料分成n組，有序視窗

select *,ntile(6) over(order by orderdate ) as o1  from business;
 

​ percent_rank() 顯示該條記錄佔視窗資料的百分比

select *,percent_rank() over(order by orderdate ) as o1  from business;

建表 載入資料

create table score(
name string,
subject string,
score int)
row format delimited fields terminated by ",";
load data local inpath '/home/atbwie/b.txt' into table score;

資料

孫悟空,數學,95
宋宋,數學,86
婷婷,數學,85
大海,數學,56
宋宋,英語,84
大海,英語,84
婷婷,英語,78
孫悟空,英語,68
大海,語文,94
孫悟空,語文,87
婷婷,語文,65
宋宋,語文,64

select * from score1;

2、排名函式

​ RANK() 排序相同時會重複，總數不會變

select *,rank() over(partition by subject order by score desc) rp
from score1;

​ DENSE_RANK() 排序相同時會重複，總數會減少

select *,dense_rank() over(partition by subject order by score desc) drp
from score1;

​ ROW_NUMBER() 會根據順序計算

select *,row_number() over(partition by subject order by score desc) rmp
from score1;

3、日期函式
CURRENT_DATE() 當前日期

select `current_date`();

​

DATE_ADD(start_date,num_days) 返回開始日期後n天的日期

select date_add(current_date,1);

​ DATE_SUB(start_date,num_days) 返回開始日期前n天的日期

select date_sub(current_date,1);

​ DATE_DIFF(date_1,date_2) 返回兩個日期的差（天數）

select datediff(current_date,“2021-01-01”);

4、其他常用函式
空欄位賦值：
NVL(col,defalut_value) 如果col為空，返回預設值

create table person_info(
name string,
constellation string,
blood_type string)
row format delimited fields terminated by "\t";
load data local inpath "/home/atbwie/b.txt" overwrite into table person_info;
select * from person_info;

資料

孫悟空	白羊座	A
大海	射手座	A
宋宋	白羊座	B
豬八戒	白羊座	A
鳳姐	射手座	A

​ 行轉列：
​ COLLECT_LIST() 可以重複
​ COLLECT_SET() 去重
​ 字串切分：

​ SPLIT(str,regex) 以正則將給定的字串切分為Array

select t1.base,concat_ws('|', collect_set(t1.name)) name
from(select name, concat(constellation, ",", blood_type) base
 from person_info) t1
group by  t1.base;

​ 列轉行：
​ EXPLODE(ARRAY)

create table movie_info(
    movie string, 
    category string) 
row format delimited fields terminated by "\t";
load data local inpath "/opt/module/datas/movie.txt" into table movie_info;

《疑犯追蹤》	懸疑,動作,科幻,劇情
《Lie to me》	懸疑,警匪,動作,心理,劇情
《戰狼2》	戰爭,動作,災難

select m.movie,tbl.cate
from movie_info m
lateral view explode(split(category, ",")) tbl as cate;

UDTF:一進多出函式
UDAF：多進一出函式
UDF：一進一出函式