Oracle110個常用函式

梓沐發表於2016-02-15
```
1.ASCII
返回與指定的字元對應的十進位制數;
SQL> select ascii('A') A,ascii('a') a,ascii('0') zero,ascii(' ') space from dual;
A  A ZERO SPACE
---------------
65 97 48   32

2.CHR
給出整數,返回對應的字元;
SQL> select chr(54740) zhao,chr(65) chr65 from dual;
ZHAO CHAR65
-----------
趙    A

3.CONCAT
連線兩個字串;
SQL> select concat('010-','88888888')||'轉23' XX電話 from dual;
XX電話
----------------
010-88888888轉23

4. INITCAP
返回字串並將字串的第一個字母變為大寫;
SQL> select initcap('smith') upp from dual;
UPP
------
Smith

5.INSTR(C1,C2,I,J)
在一個字串中搜尋指定的字元,返回發現指定的字元的位置;
C1 被搜尋的字串
C2 希望搜尋的字串
I 搜尋的開始位置,預設為1
J 出現的位置,預設為1
SQL> select instr('oracle traning','ra',1,2) instring from dual;
INSTRING
-----------
9

6.LENGTH
返回字串的長度;
SQL> select length('cancer') len from dual;
len
------------
6

7.LOWER
返回字串,並將所有的字元小寫
SQL> select lower('AaBbCcDd')AaBbCcDd from dual;
AABBCCDD
-----------
aabbccdd

8.UPPER
返回字串,並將所有的字元大寫
SQL> select upper('AaBbCcDd') upper from dual;
UPPER
---------
AABBCCDD

9.RPAD和LPAD(貼上字元)
RPAD 在列的右邊貼上字元
LPAD 在列的左邊貼上字元
SQL> select lpad(rpad('gao',10,'*'),17,'*') lpad from dual;

LPAD
--------
*******gao*******
不夠字元則用*來填滿

10.LTRIM和RTRIM
LTRIM 刪除左邊出現的字串
RTRIM 刪除右邊出現的字串
SQL> select ltrim(rtrim(' gao qian jing ')) from dual;

LTRIM(RTRIM(

gao qian jing

11.SUBSTR(string,start,count)
取子字串,從start開始,取count個
SQL> select substr(13088888888,3,8) substr from dual;
SUBSTR
---------
08888888

12.REPLACE(string,s1,s2)
string 希望被替換的字元或變數
s1 被替換的字串
s2 要替換的字串
SQL> select replace('he love you','he','i') replace from dual;
REPLACE
------------
i love you

13.SOUNDEX
返回一個與給定的字串讀音相同的字串
SQL> create table table1(xm varchar(8));
SQL> insert into table1 values(weather);
SQL> insert into table1 values(wether);
SQL> insert into table1 values(gao);
SQL> select xm from table1 where soundex(xm)=soundex(weather);
XM
---------
weather
wether

? 14.TRIM(s from string)
LEADING 剪掉前面的字元
TRAILING 剪掉後面的字元
如果不指定,預設為空格符

15.ABS
返回指定值的絕對值
SQL> select abs(100),abs(-100) from dual;
ABS(100) ABS(-100)
---------------------------
100      100

16.ACOS
給出反餘弦的值
SQL> select acos(-1) from dual;
ACOS(-1)
----------------------
3.1415927

17.ASIN
給出反正弦的值
SQL> select asin(0.5) from dual;
ASIN(0.5)
-------------
.52359878

18.ATAN
返回一個數字的反正切值
SQL> select atan(1) from dual;
ATAN(1)
----------------------------
.78539816

19.CEIL
返回大於或等於給出數字的最小整數
SQL> select ceil(3.1415927) from dual;
CEIL(3.1415927)
-----------------------------------
4

20.COS
返回一個給定數字的餘弦
SQL> select cos(-3.1415927) from dual;
COS(-3.1415927)
--------------------------------
-1

21.COSH
返回一個數字反餘弦值
SQL> select cosh(20) from dual;
COSH(20)
----------------------------------
242582598

22.EXP
返回一個數字e的n次方根
SQL> select exp(2),exp(1) from dual;
EXP(2)     EXP(1)
----------------------------------
7.3890561 2.7182818

23.FLOOR
對給定的數字取整數
SQL> select floor(2345.67) from dual;
FLOOR(2345.67)
--------------------------------
2345

24.LN
返回一個數字的對數值
SQL> select ln(1),ln(2),ln(2.7182818) from dual;
LN(1)    LN(2)        LN(2.7182818)
------------------------------------------------
0       .69314718     .99999999

25.LOG(n1,n2)
返回一個以n1為底n2的對數
SQL> select log(2,1),log(2,4) from dual;
LOG(2,1) LOG(2,4)
----------------------------------
0        2

26.MOD(n1,n2)
返回一個n1除以n2的餘數
SQL> select mod(10,3),mod(3,3),mod(2,3) from dual;
MOD(10,3) MOD(3,3) MOD(2,3)
-----------------------------
1         0        2

27.POWER
返回n1的n2次方根
SQL> select power(2,10),power(3,3) from dual;
POWER(2,10) POWER(3,3)
----------------------------
1024        27

28.ROUND和TRUNC
按照指定的精度進行舍入
SQL> select round(55.5),round(-55.4),trunc(55.5),trunc(-55.5) from dual;
ROUND(55.5) ROUND(-55.4) TRUNC(55.5) TRUNC(-55.5)
-------------------------------------------------
56          -55          55          -55

29.SIGN
取數字n的符號,大於0返回1,小於0返回-1,等於0返回0
SQL> select sign(123),sign(-100),sign(0) from dual;
SIGN(123) SIGN(-100) SIGN(0)
---------------------------------
1         -1         0

30.SIN
返回一個數字的正弦值
SQL> select sin(1.57079) from dual;
SIN(1.57079)
------------
1

?31.SIGH
返回雙曲正弦的值
SQL> select sin(20),sinh(20) from dual;
SIN(20)              SINH(20)
---------------------------------
.91294525            242582598

32.SQRT
返回數字n的根
SQL> select sqrt(64),sqrt(10) from dual;
SQRT(64) SQRT(10)
-----------------
8        3.1622777

33.TAN
返回數字的正切值
SQL> select tan(20),tan(10) from dual;
TAN(20)     TAN(10)
--------------------
2.2371609  .64836083

34.TANH
返回數字n的雙曲正切值
SQL> select tanh(20),tan(20) from dual;
TANH(20)  TAN(20)
--------------------
1         2.2371609

35.TRUNC
按照指定的精度擷取一個數
SQL> select trunc(124.1666,-2) trunc1,trunc(124.16666,2) from dual;
TRUNC1 TRUNC(124.16666,2)

100 124.16

36.ADD_MONTHS
增加或減去月份
SQL> select to_char(add_months(to_date(199912,yyyymm),2),yyyymm) from dual;

TO_CHA

200002
SQL> select to_char(add_months(to_date(199912,yyyymm),-2),yyyymm) from dual;

TO_CHA

199910

37.LAST_DAY
返回日期的最後一天
SQL> select to_char(sysdate,yyyy.mm.dd),to_char((sysdate)+1,yyyy.mm.dd) from dual;
TO_CHAR(SY TO_CHAR((S

2004.05.09 2004.05.10
SQL> select last_day(sysdate) from dual;

LAST_DAY(S

31-5月 -04

38.MONTHS_BETWEEN(date2,date1)
給出date2-date1的月份
SQL> select months_between(19-12月-1999,19-3月-1999) mon_between from dual;

MON_BETWEEN

9
SQL>selectmonths_between(to_date(2000.05.20,yyyy.mm.dd),to_date(2005.05.20,yyyy.mm.dd)) mon_betw from dual;

MON_BETW

-60

39.NEW_TIME(date,this,that)
給出在this時區=other時區的日期和時間
SQL> select to_char(sysdate,yyyy.mm.dd hh24:mi:ss) bj_time,to_char(new_time
2 (sysdate,PDT,GMT),yyyy.mm.dd hh24:mi:ss) los_angles from dual;
BJ_TIME LOS_ANGLES

2004.05.09 11:05:32 2004.05.09 18:05:32

40.NEXT_DAY(date,day)
給出日期date和星期x之後計算下一個星期的日期
SQL> select next_day(‘18-5月-2001’,’星期五’) next_day from dual;

NEXT_DAY

25-5月 -01

41.SYSDATE
用來得到系統的當前日期
SQL> select to_char(sysdate,dd-mm-yyyy day) from dual;

TO_CHAR(SYSDATE,

09-05-2004 星期日
trunc(date,fmt)按照給出的要求將日期截斷,如果fmt=mi表示保留分,截斷秒
SQL> select to_char(trunc(sysdate,hh),yyyy.mm.dd hh24:mi:ss) hh,
2 to_char(trunc(sysdate,mi),yyyy.mm.dd hh24:mi:ss) hhmm from dual;
HH HHMM

2004.05.09 11:00:00 2004.05.09 11:17:00

42.CHARTOROWID
將字元資料型別轉換為ROWID型別
SQL> select rowid,rowidtochar(rowid),ename from scott.emp;
ROWID ROWIDTOCHAR(ROWID) ENAME

AAAAfKAACAAAAEqAAA AAAAfKAACAAAAEqAAA SMITH
AAAAfKAACAAAAEqAAB AAAAfKAACAAAAEqAAB ALLEN
AAAAfKAACAAAAEqAAC AAAAfKAACAAAAEqAAC WARD
AAAAfKAACAAAAEqAAD AAAAfKAACAAAAEqAAD JONES

43.CONVERT(c,dset,sset)
將源字串 sset從一個語言字符集轉換到另一個目的dset字符集
SQL> select convert(strutz,we8hp,f7dec) “conversion” from dual;

conver

strutz

44.HEXTORAW
將一個十六進位制構成的字串轉換為二進位制

45.RAWTOHEXT
將一個二進位制構成的字串轉換為十六進位制

46.ROWIDTOCHAR
將ROWID資料型別轉換為字元型別

47.TO_CHAR(date,format)
SQL> select to_char(sysdate,yyyy/mm/dd hh24:mi:ss) from dual;

TO_CHAR(SYSDATE,YY

2004/05/09 21:14:41
? 48.TO_DATE(string,format)
將字串轉化為ORACLE中的一個日期

49.TO_MULTI_BYTE
將字串中的單位元組字元轉化為多位元組字元
SQL> select to_multi_byte(高) from dual;

TO



50.TO_NUMBER
將給出的字元轉換為數字
SQL> select to_number(1999) year from dual;

YEAR

1999
51.BFILENAME(dir,file)
指定一個外部二進位制檔案
SQL>insert into file_tb1 values(bfilename(lob_dir1,image1.gif));

52.CONVERT(x,desc,source)
將x欄位或變數的源source轉換為desc
SQL> select sid,serial#,username,decode(command,
2 0,none,
3 2,insert,
4 3,
5 select,
6 6,update,
7 7,delete,
8 8,drop,
9 other) cmd from v$session where type!=background;
SID SERIAL# USERNAME CMD

1 1 none
2 1 none
3 1 none
4 1 none
5 1 none
6 1 none
7 1275 none
8 1275 none
9 20 GAO select
10 40 GAO none

53.DUMP(s,fmt,start,length)
DUMP函式以fmt指定的內部數字格式返回一個VARCHAR2型別的值
SQL> col global_name for a30
SQL> col dump_string for a50
SQL> set lin 200
SQL> select global_name,dump(global_name,1017,8,5) dump_string from global_name;
GLOBAL_NAME DUMP_STRING

ORACLE.WORLD Typ=1 Len=12 CharacterSet=ZHS16GBK: W,O,R,L,D

54.EMPTY_BLOB()和EMPTY_CLOB()
這兩個函式都是用來對大資料型別欄位進行初始化操作的函式

55.GREATEST
返回一組表示式中的最大值,即比較字元的編碼大小.
SQL> select greatest(AA,AB,AC) from dual;

GR

AC
SQL> select greatest(啊,安,天) from dual;

GR



56.LEAST
返回一組表示式中的最小值
SQL> select least(啊,安,天) from dual;

LE



57.UID
返回標識當前使用者的唯一整數
SQL> show user
USER 為”GAO”
SQL> select username,user_id from dba_users where user_id=uid;
USERNAME USER_ID

GAO 25

58.USER
返回當前使用者的名字
SQL> select user from dual;

USER

GAO

59.USEREVN
返回當前使用者環境的資訊,opt可以是:
ENTRYID,SESSIONID,TERMINAL,ISDBA,LABLE,LANGUAGE,CLIENT_INFO,LANG,VSIZE
ISDBA 檢視當前使用者是否是DBA如果是則返回true
SQL> select userenv(isdba) from dual;

USEREN

FALSE
SQL> select userenv(isdba) from dual;

USEREN

TRUE
SESSION
返回會話標誌
SQL> select userenv(sessionid) from dual;

USERENV(SESSIONID)

152
ENTRYID
返回會話人口標誌
SQL> select userenv(entryid) from dual;

USERENV(ENTRYID)

0
INSTANCE
返回當前INSTANCE的標誌
SQL> select userenv(instance) from dual;

USERENV(INSTANCE)

1
LANGUAGE
返回當前環境變數
SQL> select userenv(language) from dual;

USERENV(LANGUAGE)

SIMPLIFIED CHINESE_CHINA.ZHS16GBK
LANG
返回當前環境的語言的縮寫
SQL> select userenv(lang) from dual;

USERENV(LANG)

ZHS
TERMINAL
返回使用者的終端或機器的標誌
SQL> select userenv(terminal) from dual;

USERENV(TERMINA

GAO
VSIZE(X)
返回X的大小(位元組)數
SQL> select vsize(user),user from dual;
VSIZE(USER) USER

6 SYSTEM
? 60.AVG(DISTINCT|ALL)
all表示對所有的值求平均值,distinct只對不同的值求平均值
SQLWKS> create table table3(xm varchar(8),sal number(7,2));
語句已處理。
SQLWKS> insert into table3 values(gao,1111.11);
SQLWKS> insert into table3 values(gao,1111.11);
SQLWKS> insert into table3 values(zhu,5555.55);
SQLWKS> commit;
SQL> select avg(distinct sal) from gao.table3;

AVG(DISTINCTSAL)

3333.33
SQL> select avg(all sal) from gao.table3;

AVG(ALLSAL)

2592.59

61.MAX(DISTINCT|ALL)
求最大值,ALL表示對所有的值求最大值,DISTINCT表示對不同的值求最大值,相同的只取一次
SQL> select max(distinct sal) from scott.emp;

MAX(DISTINCTSAL)

5000

62.MIN(DISTINCT|ALL)
求最小值,ALL表示對所有的值求最小值,DISTINCT表示對不同的值求最小值,相同的只取一次
SQL> select min(all sal) from gao.table3;

MIN(ALLSAL)

1111.11

63.STDDEV(distinct|all)
求標準差,ALL表示對所有的值求標準差,DISTINCT表示只對不同的值求標準差
SQL> select stddev(sal) from scott.emp;

STDDEV(SAL)

1182.5032
SQL> select stddev(distinct sal) from scott.emp;

STDDEV(DISTINCTSAL)

1229.951

64.VARIANCE(DISTINCT|ALL)
求協方差
SQL> select variance(sal) from scott.emp;

VARIANCE(SAL)

1398313.9

65.GROUP BY
主要用來對一組數進行統計
SQL> select deptno,count(*),sum(sal) from scott.emp group by deptno;
DEPTNO COUNT(*) SUM(SAL)

10 3 8750
20 5 10875
30 6 9400

66.HAVING
對分組統計再加限制條件
SQL> select deptno,count(),sum(sal) from scott.emp group by deptno having count()>=5;
DEPTNO COUNT(*) SUM(SAL)

20 5 10875
30 6 9400
SQL> select deptno,count(),sum(sal) from scott.emp having count()>=5 group by deptno ;
DEPTNO COUNT(*) SUM(SAL)

20 5 10875
30 6 9400

67.ORDER BY
用於對查詢到的結果進行排序輸出
SQL> select deptno,ename,sal from scott.emp order by deptno,sal desc;
DEPTNO ENAME SAL

10 KING 5000
10 CLARK 2450
10 MILLER 1300
20 SCOTT 3000
20 FORD 3000
20 JONES 2975
20 ADAMS 1100
20 SMITH 800
30 BLAKE 2850
30 ALLEN 1600
30 TURNER 1500
30 WARD 1250
30 MARTIN 1250
30 JAMES 950
68. pl/sql中的case語句
select (case when DUMMY=’X’ then 0 else 1 end) as flag from dual;
case的第1種用法:
case col when ‘a’ then 1
when ‘b’ then 2
else 0 end
這種用法跟decode一樣沒什麼區別
case的第2種用法:
case when score <60 then ‘d’
when score >=60 and score <70 then ‘c’
when score >=70 and score <80 then ‘b’
else ‘a’ end
69.NVL(expr1, expr2)
NVL(expr1, expr2)->expr1為NULL,返回expr2;不為NULL,返回expr1。注意兩者的型別要一致
NVL2 (expr1, expr2, expr3) ->expr1不為NULL,返回expr2;為NULL,返回expr3。expr2和expr3型別不同的話,expr3會轉換為expr2的型別
NULLIF (expr1, expr2) ->相等返回NULL,不等返回expr1

? Oracle分析函式參考手冊

作者: xsb([url]http://xsb.itpub.net)[/url]
發表於:2006.03.01 12:22
分類: DW&BI

出處:http://xsb.itpub.net/post/419/33028

Oracle從8.1.6開始提供分析函式,分析函式用於計算基於組的某種聚合值,它和聚合函式的不同之處是對於每個組返回多行,
而聚合函式對於每個組只返回一行。
常用的分析函式如下所列:
row_number() over(partition by … order by …)
rank() over(partition by … order by …)
dense_rank() over(partition by … order by …)
count() over(partition by … order by …)
max() over(partition by … order by …)
min() over(partition by … order by …)
sum() over(partition by … order by …)
avg() over(partition by … order by …)
first_value() over(partition by … order by …)
last_value() over(partition by … order by …)
lag() over(partition by … order by …)
lead() over(partition by … order by …)

下面例子中使用的表來自Oracle自帶的HR使用者下的表,如果沒有安裝該使用者,可以在SYS使用者下執行
$ORACLE_HOME/demo/schema/human_resources/hr_main.sql來建立。
除本文內容外,你還可參考:
ROLLUP與CUBE [url]http://xsb.itpub.net/post/419/29159[/url]
分析函式使用例子介紹:[url]http://xsb.itpub.net/post/419/44634[/url]
本文如果未指明,預設是在HR使用者下執行例子。
開窗函式的的理解:
開窗函式指定了分析函式工作的資料視窗大小,這個資料視窗大小可能會隨著行的變化而變化,舉例如下:
over(order by salary) 按照salary排序進行累計,order by是個預設的開窗函式
over(partition by deptno)按照部門分割槽
over(order by salary range between 50 preceding and 150 following)
每行對應的資料視窗是之前行幅度值不超過50,之後行幅度值不超過150
over(order by salary rows between 50 preceding and 150 following)
每行對應的資料視窗是之前50行,之後150行
over(order by salary rows between unbounded preceding and unbounded following)
每行對應的資料視窗是從第一行到最後一行,等效:
over(order by salary range between unbounded preceding and unbounded following)
主要參考資料:《expert one-on-one》 Tom Kyte 《Oracle9i SQL Reference》第6章
ohwww 2007-3-12 09:19
70。AVG
功能描述:用於計算一個組和資料視窗內表示式的平均值。
SAMPLE:下面的例子中列c_mavg計算員工表中每個員工的平均薪水報告,該平均值由當前員工和與之具有相同經理的前一個和後一個三者的平均數得來;
SELECT manager_id, last_name, hire_date, salary,
AVG(salary) OVER (PARTITION BY manager_id ORDER BY hire_date
ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING) AS c_mavg
FROM employees;
MANAGER_ID LAST_NAME HIRE_DATE SALARY C_MAVG

100 Kochhar 21-SEP-89 17000 17000
100 De Haan 13-JAN-93 17000 15000
100 Raphaely 07-DEC-94 11000 11966.6667
100 Kaufling 01-MAY-95 7900 10633.3333
100 Hartstein 17-FEB-96 13000 9633.33333
100 Weiss 18-JUL-96 8000 11666.6667
100 Russell 01-OCT-96 14000 11833.3333
71。CORR
功能描述:返回一對錶達式的相關係數,它是如下的縮寫:
COVAR_POP(expr1,expr2)/STDDEV_POP(expr1)*STDDEV_POP(expr2))
從統計上講,相關性是變數之間關聯的強度,變數之間的關聯意味著在某種程度
上一個變數的值可由其它的值進行預測。透過返回一個-1~1之間的一個數, 相關
係數給出了關聯的強度,0表示不相關。
SAMPLE:下例返回1998年月銷售收入和月單位銷售的關係的累積係數(本例在SH使用者下執行)
SELECT t.calendar_month_number,
CORR (SUM(s.amount_sold), SUM(s.quantity_sold))
OVER (ORDER BY t.calendar_month_number) as CUM_CORR
FROM sales s, times t
WHERE s.time_id = t.time_id AND calendar_year = 1998
GROUP BY t.calendar_month_number
ORDER BY t.calendar_month_number;
CALENDAR_MONTH_NUMBER CUM_CORR

1
2 1
3 .994309382
4 .852040875
5 .846652204
6 .871250628
7 .910029803
8 .917556399
9 .920154356
10 .86720251
11 .844864765
12 .903542662

72。COVAR_POP
功能描述:返回一對錶達式的總體協方差。
SAMPLE:下例CUM_COVP返回定價和最小產品價格的累積總體協方差
SELECT product_id, supplier_id,
COVAR_POP(list_price, min_price)
OVER (ORDER BY product_id, supplier_id) AS CUM_COVP,
COVAR_SAMP(list_price, min_price)
OVER (ORDER BY product_id, supplier_id) AS CUM_COVS
FROM product_information p
WHERE category_id = 29
ORDER BY product_id, supplier_id;
PRODUCT_ID SUPPLIER_ID CUM_COVP CUM_COVS

1774 103088 0
1775 103087 1473.25 2946.5
1794 103096 1702.77778 2554.16667
1825 103093 1926.25 2568.33333
2004 103086 1591.4 1989.25
2005 103086 1512.5 1815
2416 103088 1475.97959 1721.97619
.
.

73。COVAR_SAMP
功能描述:返回一對錶達式的樣本協方差
SAMPLE:下例CUM_COVS返回定價和最小產品價格的累積樣本協方差
SELECT product_id, supplier_id,
COVAR_POP(list_price, min_price)
OVER (ORDER BY product_id, supplier_id) AS CUM_COVP,
COVAR_SAMP(list_price, min_price)
OVER (ORDER BY product_id, supplier_id) AS CUM_COVS
FROM product_information p
WHERE category_id = 29
ORDER BY product_id, supplier_id;
PRODUCT_ID SUPPLIER_ID CUM_COVP CUM_COVS

1774 103088 0
1775 103087 1473.25 2946.5
1794 103096 1702.77778 2554.16667
1825 103093 1926.25 2568.33333
2004 103086 1591.4 1989.25
2005 103086 1512.5 1815
2416 103088 1475.97959 1721.97619
? 74。COUNT
功能描述:對一組內發生的事情進行累積計數,如果指定*或一些非空常數,count將對所有行計數,如果指定一個表示式,count
返回表示式非空賦值的計數,當有相同值出現時,這些相等的值都會被納入被計算的值;可以使用DISTINCT來記錄去掉一組中完全
相同的資料後出現的行數。
SAMPLE:下面例子中計算每個員工在按薪水排序中當前行附近薪水在[n-50,n+150]之間的行數,n表示當前行的薪水
例如,Philtanker的薪水2200,排在他之前的行中薪水大於等於2200-50的有1行,排在他之後的行中薪水小於等於2200+150的行
沒有,所以count計數值cnt3為2(包括自己當前行);cnt2值相當於小於等於當前行的SALARY值的所有行數
SELECT last_name, salary, COUNT(*) OVER () AS cnt1,
COUNT(*) OVER (ORDER BY salary) AS cnt2,
COUNT(*) OVER (ORDER BY salary RANGE BETWEEN 50 PRECEDING
AND 150 FOLLOWING) AS cnt3 FROM employees;
LAST_NAME SALARY CNT1 CNT2 CNT3

Olson 2100 107 1 3
Markle 2200 107 3 2
Philtanker 2200 107 3 2
Landry 2400 107 5 8
Gee 2400 107 5 8
Colmenares 2500 107 11 10
Patel 2500 107 11 10
.
.
75。CUME_DIST
功能描述:計算一行在組中的相對位置,CUME_DIST總是返回大於0、小於或等於1的數,該數表示該行在N行中的位置。例如,
在一個3行的組中,返回的累計分佈值為1/3、2/3、3/3
SAMPLE:下例中計算每個工種的員工按薪水排序依次累積出現的分佈百分比
SELECT job_id, last_name, salary, CUME_DIST()
OVER (PARTITION BY job_id ORDER BY salary) AS cume_dist
FROM employees WHERE job_id LIKE ‘PU%’;
JOB_ID LAST_NAME SALARY CUME_DIST

PU_CLERK Colmenares 2500 .2
PU_CLERK Himuro 2600 .4
PU_CLERK Tobias 2800 .6
PU_CLERK Baida 2900 .8
PU_CLERK Khoo 3100 1
PU_MAN Raphaely 11000 1
76。DENSE_RANK
功能描述:根據ORDER BY子句中表示式的值,從查詢返回的每一行,計算它們與其它行的相對位置。組內的資料按ORDER BY子句排序,然後給每一行賦一個號,從而形成一個序列,該序列從1開始,往後累加。每次ORDER BY表示式的值發生變化時,該序列也隨之增加。有同樣值的行得到同樣的數字序號(認為null時相等的)。密集的序列返回的時沒有間隔的數
SAMPLE:下例中計算每個員工按部門分割槽再按薪水排序,依次出現的序列號(注意與RANK函式的區別)
SELECT d.department_id , e.last_name, e.salary, DENSE_RANK()
OVER (PARTITION BY e.department_id ORDER BY e.salary) as drank
FROM employees e, departments d
WHERE e.department_id = d.department_id
AND d.department_id IN (‘60’, ‘90’);
DEPARTMENT_ID LAST_NAME SALARY DRANK

60 Lorentz 4200 1
60 Austin 4800 2
60 Pataballa 4800 2
60 Ernst 6000 3
60 Hunold 9000 4
90 Kochhar 17000 1
90 De Haan 17000 1
90 King 24000 2

77。FIRST
功能描述:從DENSE_RANK返回的集合中取出排在最前面的一個值的行(可能多行,因為值可能相等),因此完整的語法需要在開始處加上一個集合函式以從中取出記錄
SAMPLE:下面例子中DENSE_RANK按部門分割槽,再按佣金commission_pct排序,FIRST取出佣金最低的對應的所有行,然後前面的MAX函式從這個集合中取出薪水最低的值;LAST取出佣金最高的對應的所有行,然後前面的MIN函式從這個集合中取出薪水最高的值
SELECT last_name, department_id, salary,
MIN(salary) KEEP (DENSE_RANK FIRST ORDER BY commission_pct)
OVER (PARTITION BY department_id) “Worst”,
MAX(salary) KEEP (DENSE_RANK LAST ORDER BY commission_pct)
OVER (PARTITION BY department_id) “Best”
FROM employees
WHERE department_id in (20,80)
ORDER BY department_id, salary;
LAST_NAME DEPARTMENT_ID SALARY Worst Best

Fay 20 6000 6000 13000
Hartstein 20 13000 6000 13000
Kumar 80 6100 6100 14000
Banda 80 6200 6100 14000
Johnson 80 6200 6100 14000
Ande 80 6400 6100 14000
Lee 80 6800 6100 14000
Tuvault 80 7000 6100 14000
Sewall 80 7000 6100 14000
Marvins 80 7200 6100 14000
Bates 80 7300 6100 14000
.
.
.
78。FIRST_VALUE
功能描述:返回組中資料視窗的第一個值。
SAMPLE:下面例子計算按部門分割槽按薪水排序的資料視窗的第一個值對應的名字,如果薪水的第一個值有多個,則從多個對應的名字中取預設排序的第一個名字
SELECT department_id, last_name, salary, FIRST_VALUE(last_name)
OVER (PARTITION BY department_id ORDER BY salary ASC ) AS lowest_sal
FROM employees
WHERE department_id in(20,30);
DEPARTMENT_ID LAST_NAME SALARY LOWEST_SAL

20 Fay 6000 Fay
20 Hartstein 13000 Fay
30 Colmenares 2500 Colmenares
30 Himuro 2600 Colmenares
30 Tobias 2800 Colmenares
30 Baida 2900 Colmenares
30 Khoo 3100 Colmenares
30 Raphaely 11000 Colmenares

79。LAG
功能描述:可以訪問結果集中的其它行而不用進行自連線。它允許去處理遊標,就好像遊標是一個陣列一樣。在給定組中可參考當前行之前的行,這樣就可以從組中與當前行一起選擇以前的行。Offset是一個正整數,其預設值為1,若索引超出視窗的範圍,就返回預設值(預設返回的是組中第一行),其相反的函式是LEAD
SAMPLE:下面的例子中列prev_sal返回按hire_date排序的前1行的salary值
SELECT last_name, hire_date, salary,
LAG(salary, 1, 0) OVER (ORDER BY hire_date) AS prev_sal
FROM employees
WHERE job_id = ‘PU_CLERK’;
LAST_NAME HIRE_DATE SALARY PREV_SAL

Khoo 18-5月 -95 3100 0
Tobias 24-7月 -97 2800 3100
Baida 24-12月-97 2900 2800
Himuro 15-11月-98 2600 2900
Colmenares 10-8月 -99 2500 2600

80。LAST
功能描述:從DENSE_RANK返回的集合中取出排在最後面的一個值的行(可能多行,因為值可能相等),因此完整的語法需要在開始處加上一個集合函式以從中取出記錄
SAMPLE:下面例子中DENSE_RANK按部門分割槽,再按佣金commission_pct排序,FIRST取出佣金最低的對應的所有行,然後前面的MAX函式從這個集合中取出薪水最低的值;LAST取出佣金最高的對應的所有行,然後前面的MIN函式從這個集合中取出薪水最高的值
SELECT last_name, department_id, salary,
MIN(salary) KEEP (DENSE_RANK FIRST ORDER BY commission_pct)
OVER (PARTITION BY department_id) “Worst”,
MAX(salary) KEEP (DENSE_RANK LAST ORDER BY commission_pct)
OVER (PARTITION BY department_id) “Best”
FROM employees
WHERE department_id in (20,80)
ORDER BY department_id, salary;
LAST_NAME DEPARTMENT_ID SALARY Worst Best

Fay 20 6000 6000 13000
Hartstein 20 13000 6000 13000
Kumar 80 6100 6100 14000
Banda 80 6200 6100 14000
Johnson 80 6200 6100 14000
Ande 80 6400 6100 14000
Lee 80 6800 6100 14000
Tuvault 80 7000 6100 14000
Sewall 80 7000 6100 14000
Marvins 80 7200 6100 14000
Bates 80 7300 6100 14000
.
81。LAST_VALUE
功能描述:返回組中資料視窗的最後一個值。
SAMPLE:下面例子計算按部門分割槽按薪水排序的資料視窗的最後一個值對應的名字,如果薪水的最後一個值有多個,則從多個對應的名字中取預設排序的最後一個名字
SELECT department_id, last_name, salary, LAST_VALUE(last_name)
OVER(PARTITION BY department_id ORDER BY salary) AS highest_sal
FROM employees
WHERE department_id in(20,30);
DEPARTMENT_ID LAST_NAME SALARY HIGHEST_SAL

20 Fay 6000 Fay
20 Hartstein 13000 Hartstein
30 Colmenares 2500 Colmenares
30 Himuro 2600 Himuro
30 Tobias 2800 Tobias
30 Baida 2900 Baida
30 Khoo 3100 Khoo
30 Raphaely 11000 Raphaely
82。LEAD
功能描述:LEAD與LAG相反,LEAD可以訪問組中當前行之後的行。Offset是一個正整數,其預設值為1,若索引超出視窗的範圍,就返回預設值(預設返回的是組中第一行)
SAMPLE:下面的例子中每行的”NextHired”返回按hire_date排序的下一行的hire_date值
SELECT last_name, hire_date,
LEAD(hire_date, 1) OVER (ORDER BY hire_date) AS “NextHired”
FROM employees WHERE department_id = 30;
LAST_NAME HIRE_DATE NextHired

Raphaely 07-DEC-94 18-MAY-95
Khoo 18-MAY-95 24-JUL-97
Tobias 24-JUL-97 24-DEC-97
Baida 24-DEC-97 15-NOV-98
Himuro 15-NOV-98 10-AUG-99
Colmenares 10-AUG-99

83。MAX
功能描述:在一個組中的資料視窗中查詢表示式的最大值。
SAMPLE:下面例子中dept_max返回當前行所在部門的最大薪水值
SELECT department_id, last_name, salary,
MAX(salary) OVER (PARTITION BY department_id) AS dept_max
FROM employees WHERE department_id in (10,20,30);
DEPARTMENT_ID LAST_NAME SALARY DEPT_MAX

10 Whalen 4400 4400
20 Hartstein 13000 13000
20 Fay 6000 13000
30 Raphaely 11000 11000
30 Khoo 3100 11000
30 Baida 2900 11000
30 Tobias 2800 11000
30 Himuro 2600 11000
30 Colmenares 2500 11000

84。MIN
功能描述:在一個組中的資料視窗中查詢表示式的最小值。
SAMPLE:下面例子中dept_min返回當前行所在部門的最小薪水值
SELECT department_id, last_name, salary,
MIN(salary) OVER (PARTITION BY department_id) AS dept_min
FROM employees WHERE department_id in (10,20,30);
DEPARTMENT_ID LAST_NAME SALARY DEPT_MIN

10 Whalen 4400 4400
20 Hartstein 13000 6000
20 Fay 6000 6000
30 Raphaely 11000 2500
30 Khoo 3100 2500
30 Baida 2900 2500
30 Tobias 2800 2500
30 Himuro 2600 2500
30 Colmenares 2500 2500

85。NTILE
功能描述:將一個組分為”表示式”的雜湊表示,例如,如果表示式=4,則給組中的每一行分配一個數(從1到4),如果組中有20行,則給前5行分配1,給下5行分配2等等。如果組的基數不能由表示式值平均分開,則對這些行進行分配時,組中就沒有任何percentile的行數比其它percentile的行數超過一行,最低的percentile是那些擁有額外行的percentile。例如,若表示式=4,行數=21,則percentile=1的有5行,percentile=2的有5行等等。
SAMPLE:下例中把6行資料分為4份
SELECT last_name, salary,
NTILE(4) OVER (ORDER BY salary DESC) AS quartile FROM employees
WHERE department_id = 100;
LAST_NAME SALARY QUARTILE

Greenberg 12000 1
Faviet 9000 1
Chen 8200 2
Urman 7800 2
Sciarra 7700 3
Popp 6900 4

86。PERCENT_RANK
功能描述:和CUME_DIST(累積分配)函式類似,對於一個組中給定的行來說,在計算那行的序號時,先減1,然後除以n-1(n為組中所有的行數)。該函式總是返回0~1(包括1)之間的數。
SAMPLE:下例中如果Khoo的salary為2900,則pr值為0.6,因為RANK函式對於等值的返回序列值是一樣的
SELECT department_id, last_name, salary,
PERCENT_RANK()
OVER (PARTITION BY department_id ORDER BY salary) AS pr
FROM employees
WHERE department_id < 50
ORDER BY department_id,salary;
DEPARTMENT_ID LAST_NAME SALARY PR

10 Whalen 4400 0
20 Fay 6000 0
20 Hartstein 13000 1
30 Colmenares 2500 0
30 Himuro 2600 0.2
30 Tobias 2800 0.4
30 Baida 2900 0.6
30 Khoo 3100 0.8
30 Raphaely 11000 1
40 Mavris 6500 0
? 87。PERCENTILE_CONT
功能描述:返回一個與輸入的分佈百分比值相對應的資料值,分佈百分比的計算方法見函式PERCENT_RANK,如果沒有正好對應的資料值,就透過下面演算法來得到值:
RN = 1+ (P*(N-1)) 其中P是輸入的分佈百分比值,N是組內的行數
CRN = CEIL(RN) FRN = FLOOR(RN)
if (CRN = FRN = RN) then
(value of expression from row at RN)
else
(CRN - RN) * (value of expression for row at FRN) +
(RN - FRN) * (value of expression for row at CRN)
注意:本函式與PERCENTILE_DISC的區別在找不到對應的分佈值時返回的替代值的計算方法不同
SAMPLE:在下例中,對於部門60的Percentile_Cont值計算如下:
P=0.7 N=5 RN =1+ (P*(N-1)=1+(0.7*(5-1))=3.8 CRN = CEIL(3.8)=4
FRN = FLOOR(3.8)=3
(4 - 3.8)* 4800 + (3.8 - 3) * 6000 = 5760
SELECT last_name, salary, department_id,
PERCENTILE_CONT(0.7) WITHIN GROUP (ORDER BY salary)
OVER (PARTITION BY department_id) “Percentile_Cont”,
PERCENT_RANK()
OVER (PARTITION BY department_id ORDER BY salary) “Percent_Rank”
FROM employees WHERE department_id IN (30, 60);
LAST_NAME SALARY DEPARTMENT_ID Percentile_Cont Percent_Rank

Colmenares 2500 30 3000 0
Himuro 2600 30 3000 0.2
Tobias 2800 30 3000 0.4
Baida 2900 30 3000 0.6
Khoo 3100 30 3000 0.8
Raphaely 11000 30 3000 1
Lorentz 4200 60 5760 0
Austin 4800 60 5760 0.25
Pataballa 4800 60 5760 0.25
Ernst 6000 60 5760 0.75
Hunold 9000 60 5760 1

88。PERCENTILE_DISC
功能描述:返回一個與輸入的分佈百分比值相對應的資料值,分佈百分比的計算方法見函式CUME_DIST,如果沒有正好對應的資料值,就取大於該分佈值的下一個值。
注意:本函式與PERCENTILE_CONT的區別在找不到對應的分佈值時返回的替代值的計算方法不同
SAMPLE:下例中0.7的分佈值在部門30中沒有對應的Cume_Dist值,所以就取下一個分佈值0.83333333所對應的SALARY來替代
SELECT last_name, salary, department_id,
PERCENTILE_DISC(0.7) WITHIN GROUP (ORDER BY salary )
OVER (PARTITION BY department_id) “Percentile_Disc”,
CUME_DIST() OVER (PARTITION BY department_id ORDER BY salary) “Cume_Dist”
FROM employees
WHERE department_id in (30, 60);
LAST_NAME SALARY DEPARTMENT_ID Percentile_Disc Cume_Dist

Colmenares 2500 30 3100 .166666667
Himuro 2600 30 3100 .333333333
Tobias 2800 30 3100 .5
Baida 2900 30 3100 .666666667
Khoo 3100 30 3100 .833333333
Raphaely 11000 30 3100 1
Lorentz 4200 60 6000 .2
Austin 4800 60 6000 .6
Pataballa 4800 60 6000 .6
Ernst 6000 60 6000 .8
Hunold 9000 60 6000 1
89。RANK
功能描述:根據ORDER BY子句中表示式的值,從查詢返回的每一行,計算它們與其它行的相對位置。組內的資料按ORDER BY子句排序,
然後給每一行賦一個號,從而形成一個序列,該序列從1開始,往後累加。每次ORDER BY表示式的值發生變化時,該序列也隨之增加。
有同樣值的行得到同樣的數字序號(認為null時相等的)。然而,如果兩行的確得到同樣的排序,則序數將隨後跳躍。若兩行序數為1,
則沒有序數2,序列將給組中的下一行分配值3,DENSE_RANK則沒有任何跳躍。
SAMPLE:下例中計算每個員工按部門分割槽再按薪水排序,依次出現的序列號(注意與DENSE_RANK函式的區別)
SELECT d.department_id , e.last_name, e.salary, RANK()
OVER (PARTITION BY e.department_id ORDER BY e.salary) as drank
FROM employees e, departments d
WHERE e.department_id = d.department_id
AND d.department_id IN (‘60’, ‘90’);
DEPARTMENT_ID LAST_NAME SALARY DRANK

60 Lorentz 4200 1
60 Austin 4800 2
60 Pataballa 4800 2
60 Ernst 6000 4
60 Hunold 9000 5
90 Kochhar 17000 1
90 De Haan 17000 1
90 King 24000 3

90。RATIO_TO_REPORT
功能描述:該函式計算expression/(sum(expression))的值,它給出相對於總數的百分比,即當前行對sum(expression)的貢獻。
SAMPLE:下例計算每個員工的工資佔該類員工總工資的百分比
SELECT last_name, salary, RATIO_TO_REPORT(salary) OVER () AS rr
FROM employees
WHERE job_id = ‘PU_CLERK’;
LAST_NAME SALARY RR

Khoo 3100 .223021583
Baida 2900 .208633094
Tobias 2800 .201438849
Himuro 2600 .18705036
Colmenares 2500 .179856115
? 91。REGR_ (Linear Regression) Functions
功能描述:這些線性迴歸函式適合最小二乘法迴歸線,有9個不同的迴歸函式可使用。
REGR_SLOPE:返回斜率,等於COVAR_POP(expr1, expr2) / VAR_POP(expr2)
REGR_INTERCEPT:返回迴歸線的y截距,等於
AVG(expr1) - REGR_SLOPE(expr1, expr2) * AVG(expr2)
REGR_COUNT:返回用於填充迴歸線的非空數字對的數目
REGR_R2:返回迴歸線的決定係數,計算式為:
If VAR_POP(expr2) = 0 then return NULL
If VAR_POP(expr1) = 0 and VAR_POP(expr2) != 0 then return 1
If VAR_POP(expr1) > 0 and VAR_POP(expr2 != 0 then
return POWER(CORR(expr1,expr),2)
REGR_AVGX:計算迴歸線的自變數(expr2)的平均值,去掉了空對(expr1, expr2)後,等於AVG(expr2)
REGR_AVGY:計算迴歸線的應變數(expr1)的平均值,去掉了空對(expr1, expr2)後,等於AVG(expr1)
REGR_SXX: 返回值等於REGR_COUNT(expr1, expr2) * VAR_POP(expr2)
REGR_SYY: 返回值等於REGR_COUNT(expr1, expr2) * VAR_POP(expr1)
REGR_SXY: 返回值等於REGR_COUNT(expr1, expr2) * COVAR_POP(expr1, expr2)
(下面的例子都是在SH使用者下完成的)
SAMPLE 1:下例計算1998年最後三個星期中兩種產品(260和270)在週末的銷售量中已開發票數量和總數量的累積斜率和迴歸線的截距
SELECT t.fiscal_month_number “Month”, t.day_number_in_month “Day”,
REGR_SLOPE(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month) AS CUM_SLOPE,
REGR_INTERCEPT(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month) AS CUM_ICPT
FROM sales s, times t
WHERE s.time_id = t.time_id
AND s.prod_id IN (270, 260)
AND t.fiscal_year=1998
AND t.fiscal_week_number IN (50, 51, 52)
AND t.day_number_in_week IN (6,7)
ORDER BY t.fiscal_month_desc, t.day_number_in_month;
Month Day CUM_SLOPE CUM_ICPT

12 12 -68 1872
12 12 -68 1872
12 13 -20.244898 1254.36735
12 13 -20.244898 1254.36735
12 19 -18.826087 1287
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 26 67.2658228 58.9712313
12 26 67.2658228 58.9712313
12 27 37.5245541 284.958221
12 27 37.5245541 284.958221
12 27 37.5245541 284.958221
SAMPLE 2:下例計算1998年4月每天的累積交易數量
SELECT UNIQUE t.day_number_in_month,
REGR_COUNT(s.amount_sold, s.quantity_sold)
OVER (PARTITION BY t.fiscal_month_number ORDER BY t.day_number_in_month)
“Regr_Count”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND t.fiscal_year = 1998 AND t.fiscal_month_number = 4;
DAY_NUMBER_IN_MONTH Regr_Count

1 825
2 1650
3 2475
4 3300
26 21450
30 22200
SAMPLE 3:下例計算1998年每月銷售量中已開發票數量和總數量的累積迴歸線決定係數
SELECT t.fiscal_month_number,
REGR_R2(SUM(s.amount_sold), SUM(s.quantity_sold))
OVER (ORDER BY t.fiscal_month_number) “Regr_R2”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND t.fiscal_year = 1998
GROUP BY t.fiscal_month_number
ORDER BY t.fiscal_month_number;
FISCAL_MONTH_NUMBER Regr_R2

1
2 1
3 .927372984
4 .807019972
5 .932745567
6 .94682861
7 .965342011
8 .955768075
9 .959542618
10 .938618575
11 .880931415
12 .882769189
SAMPLE 4:下例計算1998年12月最後兩週產品260的銷售量中已開發票數量和總數量的累積平均值
SELECT t.day_number_in_month,
REGR_AVGY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month)
“Regr_AvgY”,
REGR_AVGX(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month)
“Regr_AvgX”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND s.prod_id = 260
AND t.fiscal_month_desc = ‘1998-12’
AND t.fiscal_week_number IN (51, 52)
ORDER BY t.day_number_in_month;
DAY_NUMBER_IN_MONTH Regr_AvgY Regr_AvgX

14 882 24.5
14 882 24.5
15 801 22.25
15 801 22.25
16 777.6 21.6
18 642.857143 17.8571429
18 642.857143 17.8571429
20 589.5 16.375
21 544 15.1111111
22 592.363636 16.4545455
22 592.363636 16.4545455
24 553.846154 15.3846154
24 553.846154 15.3846154
26 522 14.5
27 578.4 16.0666667
SAMPLE 5:下例計算產品260和270在1998年2月週末銷售量中已開發票數量和總數量的累積REGR_SXY, REGR_SXX, and REGR_SYY統計值
SELECT t.day_number_in_month,
REGR_SXY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_sxy”,
REGR_SYY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_syy”,
REGR_SXX(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_sxx”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND prod_id IN (270, 260)
AND t.fiscal_month_desc = ‘1998-02’
AND t.day_number_in_week IN (6,7)
ORDER BY t.day_number_in_month;
DAY_NUMBER_IN_MONTH Regr_sxy Regr_syy Regr_sxx

1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
7 18870.4 2116198.4 258.4
8 18870.4 2116198.4 258.4
14 18870.4 2116198.4 258.4
15 18870.4 2116198.4 258.4
21 18870.4 2116198.4 258.4
22 18870.4 2116198.4 258.4
92。ROW_NUMBER
功能描述:返回有序組中一行的偏移量,從而可用於按特定標準排序的行號。
SAMPLE:下例返回每個員工再在每個部門中按員工號排序後的順序號
SELECT department_id, last_name, employee_id, ROW_NUMBER()
OVER (PARTITION BY department_id ORDER BY employee_id) AS emp_id
FROM employees
WHERE department_id < 50;
DEPARTMENT_ID LAST_NAME EMPLOYEE_ID EMP_ID

10 Whalen 200 1
20 Hartstein 201 1
20 Fay 202 2
30 Raphaely 114 1
30 Khoo 115 2
30 Baida 116 3
30 Tobias 117 4
30 Himuro 118 5
30 Colmenares 119 6
40 Mavris 203 1
93。STDDEV
功能描述:計算當前行關於組的標準偏離。(Standard Deviation)
SAMPLE:下例返回部門30按僱傭日期排序的薪水值的累積標準偏離
SELECT last_name, hire_date,salary,
STDDEV(salary) OVER (ORDER BY hire_date) “StdDev”
FROM employees
WHERE department_id = 30;
LAST_NAME HIRE_DATE SALARY StdDev

Raphaely 07-12月-94 11000 0
Khoo 18-5月 -95 3100 5586.14357
Tobias 24-7月 -97 2800 4650.0896
Baida 24-12月-97 2900 4035.26125
Himuro 15-11月-98 2600 3649.2465
Colmenares 10-8月 -99 2500 3362.58829
94。STDDEV_POP
功能描述:該函式計算總體標準偏離,並返回總體變數的平方根,其返回值與VAR_POP函式的平方根相同。(Standard Deviation-Population)
SAMPLE:下例返回部門20、30、60的薪水值的總體標準偏差
SELECT department_id, last_name, salary,
STDDEV_POP(salary) OVER (PARTITION BY department_id) AS pop_std
FROM employees
WHERE department_id in (20,30,60);
DEPARTMENT_ID LAST_NAME SALARY POP_STD

20 Hartstein 13000 3500
20 Fay 6000 3500
30 Raphaely 11000 3069.6091
30 Khoo 3100 3069.6091
30 Baida 2900 3069.6091
30 Colmenares 2500 3069.6091
30 Himuro 2600 3069.6091
30 Tobias 2800 3069.6091
60 Hunold 9000 1722.32401
60 Ernst 6000 1722.32401
60 Austin 4800 1722.32401
60 Pataballa 4800 1722.32401
60 Lorentz 4200 1722.32401
95。STDDEV_SAMP
功能描述: 該函式計算累積樣本標準偏離,並返回總體變數的平方根,其返回值與VAR_POP函式的平方根相同。(Standard Deviation-Sample)
SAMPLE:下例返回部門20、30、60的薪水值的樣本標準偏差
SELECT department_id, last_name, hire_date, salary,
STDDEV_SAMP(salary) OVER
(PARTITION BY department_id ORDER BY hire_date
ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS cum_sdev
FROM employees
WHERE department_id in (20,30,60);
DEPARTMENT_ID LAST_NAME HIRE_DATE SALARY CUM_SDEV

20 Hartstein 17-2月 -96 13000
20 Fay 17-8月 -97 6000 4949.74747
30 Raphaely 07-12月-94 11000
30 Khoo 18-5月 -95 3100 5586.14357
30 Tobias 24-7月 -97 2800 4650.0896
30 Baida 24-12月-97 2900 4035.26125
30 Himuro 15-11月-98 2600 3649.2465
30 Colmenares 10-8月 -99 2500 3362.58829
60 Hunold 03-1月 -90 9000
60 Ernst 21-5月 -91 6000 2121.32034
60 Austin 25-6月 -97 4800 2163.33077
60 Pataballa 05-2月 -98 4800 1982.42276
60 Lorentz 07-2月 -99 4200 1925.61678

96。SUM
功能描述:該函式計算組中表示式的累積和。
SAMPLE:下例計算同一經理下員工的薪水累積值
SELECT manager_id, last_name, salary,
SUM (salary) OVER (PARTITION BY manager_id ORDER BY salary
RANGE UNBOUNDED PRECEDING) l_csum
FROM employees
WHERE manager_id in (101,103,108);
MANAGER_ID LAST_NAME SALARY L_CSUM

101 Whalen 4400 4400
101 Mavris 6500 10900
101 Baer 10000 20900
101 Greenberg 12000 44900
101 Higgins 12000 44900
103 Lorentz 4200 4200
103 Austin 4800 13800
103 Pataballa 4800 13800
103 Ernst 6000 19800
108 Popp 6900 6900
108 Sciarra 7700 14600
108 Urman 7800 22400
108 Chen 8200 30600
108 Faviet 9000 39600
97。VAR_POP
功能描述:(Variance Population)該函式返回非空集合的總體變數(忽略null),VAR_POP進行如下計算:
(SUM(expr2) - SUM(expr)2 / COUNT(expr)) / COUNT(expr)
SAMPLE:下例計算1998年每月銷售的累積總體和樣本變數(本例在SH使用者下執行)
SELECT t.calendar_month_desc,
VAR_POP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Pop”,
VAR_SAMP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Samp”
FROM sales s, times t
WHERE s.time_id = t.time_id AND t.calendar_year = 1998
GROUP BY t.calendar_month_desc;
CALENDAR Var_Pop Var_Samp

1998-01 0
1998-02 6.1321E+11 1.2264E+12
1998-03 4.7058E+11 7.0587E+11
1998-04 4.6929E+11 6.2572E+11
1998-05 1.5524E+12 1.9405E+12
1998-06 2.3711E+12 2.8453E+12
1998-07 3.7464E+12 4.3708E+12
1998-08 3.7852E+12 4.3260E+12
1998-09 3.5753E+12 4.0222E+12
1998-10 3.4343E+12 3.8159E+12
1998-11 3.4245E+12 3.7669E+12
1998-12 4.8937E+12 5.3386E+12
? 98。VAR_SAMP
功能描述:(Variance Sample)該函式返回非空集合的樣本變數(忽略null),VAR_POP進行如下計算:
(SUM(expr*expr)-SUM(expr)*SUM(expr)/COUNT(expr))/(COUNT(expr)-1)
SAMPLE:下例計算1998年每月銷售的累積總體和樣本變數
SELECT t.calendar_month_desc,
VAR_POP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Pop”,
VAR_SAMP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Samp”
FROM sales s, times t
WHERE s.time_id = t.time_id AND t.calendar_year = 1998
GROUP BY t.calendar_month_desc;
CALENDAR Var_Pop Var_Samp

1998-01 0
1998-02 6.1321E+11 1.2264E+12
1998-03 4.7058E+11 7.0587E+11
1998-04 4.6929E+11 6.2572E+11
1998-05 1.5524E+12 1.9405E+12
1998-06 2.3711E+12 2.8453E+12
1998-07 3.7464E+12 4.3708E+12
1998-08 3.7852E+12 4.3260E+12
1998-09 3.5753E+12 4.0222E+12
1998-10 3.4343E+12 3.8159E+12
1998-11 3.4245E+12 3.7669E+12
1998-12 4.8937E+12 5.3386E+12
99。VARIANCE
功能描述:該函式返回表示式的變數,Oracle計算該變數如下:
如果表示式中行數為1,則返回0
如果表示式中行數大於1,則返回VAR_SAMP
SAMPLE:下例返回部門30按僱傭日期排序的薪水值的累積變化
SELECT last_name, salary, VARIANCE(salary)
OVER (ORDER BY hire_date) “Variance”
FROM employees
WHERE department_id = 30;
LAST_NAME SALARY Variance

Raphaely 11000 0
Khoo 3100 31205000
Tobias 2800 21623333.3
Baida 2900 16283333.3
Himuro 2600 13317000
Colmenares 2500 11307000
100。RANK
功能描述:根據ORDER BY子句中表示式的值,從查詢返回的每一行,計算它們與其它行的相對位置。組內的資料按ORDER BY子句排序,
然後給每一行賦一個號,從而形成一個序列,該序列從1開始,往後累加。每次ORDER BY表示式的值發生變化時,該序列也隨之增加。
有同樣值的行得到同樣的數字序號(認為null時相等的)。然而,如果兩行的確得到同樣的排序,則序數將隨後跳躍。若兩行序數為1,
則沒有序數2,序列將給組中的下一行分配值3,DENSE_RANK則沒有任何跳躍。
SAMPLE:下例中計算每個員工按部門分割槽再按薪水排序,依次出現的序列號(注意與DENSE_RANK函式的區別)
SELECT d.department_id , e.last_name, e.salary, RANK()
OVER (PARTITION BY e.department_id ORDER BY e.salary) as drank
FROM employees e, departments d
WHERE e.department_id = d.department_id
AND d.department_id IN (‘60’, ‘90’);
DEPARTMENT_ID LAST_NAME SALARY DRANK

60 Lorentz 4200 1
60 Austin 4800 2
60 Pataballa 4800 2
60 Ernst 6000 4
60 Hunold 9000 5
90 Kochhar 17000 1
90 De Haan 17000 1
90 King 24000 3

101。RATIO_TO_REPORT
功能描述:該函式計算expression/(sum(expression))的值,它給出相對於總數的百分比,即當前行對sum(expression)的貢獻。
SAMPLE:下例計算每個員工的工資佔該類員工總工資的百分比
SELECT last_name, salary, RATIO_TO_REPORT(salary) OVER () AS rr
FROM employees
WHERE job_id = ‘PU_CLERK’;
LAST_NAME SALARY RR

Khoo 3100 .223021583
Baida 2900 .208633094
Tobias 2800 .201438849
Himuro 2600 .18705036
Colmenares 2500 .179856115
? 102。REGR_ (Linear Regression) Functions
功能描述:這些線性迴歸函式適合最小二乘法迴歸線,有9個不同的迴歸函式可使用。
REGR_SLOPE:返回斜率,等於COVAR_POP(expr1, expr2) / VAR_POP(expr2)
REGR_INTERCEPT:返回迴歸線的y截距,等於
AVG(expr1) - REGR_SLOPE(expr1, expr2) * AVG(expr2)
REGR_COUNT:返回用於填充迴歸線的非空數字對的數目
REGR_R2:返回迴歸線的決定係數,計算式為:
If VAR_POP(expr2) = 0 then return NULL
If VAR_POP(expr1) = 0 and VAR_POP(expr2) != 0 then return 1
If VAR_POP(expr1) > 0 and VAR_POP(expr2 != 0 then
return POWER(CORR(expr1,expr),2)
REGR_AVGX:計算迴歸線的自變數(expr2)的平均值,去掉了空對(expr1, expr2)後,等於AVG(expr2)
REGR_AVGY:計算迴歸線的應變數(expr1)的平均值,去掉了空對(expr1, expr2)後,等於AVG(expr1)
REGR_SXX: 返回值等於REGR_COUNT(expr1, expr2) * VAR_POP(expr2)
REGR_SYY: 返回值等於REGR_COUNT(expr1, expr2) * VAR_POP(expr1)
REGR_SXY: 返回值等於REGR_COUNT(expr1, expr2) * COVAR_POP(expr1, expr2)
(下面的例子都是在SH使用者下完成的)
SAMPLE 1:下例計算1998年最後三個星期中兩種產品(260和270)在週末的銷售量中已開發票數量和總數量的累積斜率和迴歸線的截距
SELECT t.fiscal_month_number “Month”, t.day_number_in_month “Day”,
REGR_SLOPE(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month) AS CUM_SLOPE,
REGR_INTERCEPT(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month) AS CUM_ICPT
FROM sales s, times t
WHERE s.time_id = t.time_id
AND s.prod_id IN (270, 260)
AND t.fiscal_year=1998
AND t.fiscal_week_number IN (50, 51, 52)
AND t.day_number_in_week IN (6,7)
ORDER BY t.fiscal_month_desc, t.day_number_in_month;
Month Day CUM_SLOPE CUM_ICPT

12 12 -68 1872
12 12 -68 1872
12 13 -20.244898 1254.36735
12 13 -20.244898 1254.36735
12 19 -18.826087 1287
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 20 62.4561404 125.28655
12 26 67.2658228 58.9712313
12 26 67.2658228 58.9712313
12 27 37.5245541 284.958221
12 27 37.5245541 284.958221
12 27 37.5245541 284.958221
SAMPLE 2:下例計算1998年4月每天的累積交易數量
SELECT UNIQUE t.day_number_in_month,
REGR_COUNT(s.amount_sold, s.quantity_sold)
OVER (PARTITION BY t.fiscal_month_number ORDER BY t.day_number_in_month)
“Regr_Count”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND t.fiscal_year = 1998 AND t.fiscal_month_number = 4;
DAY_NUMBER_IN_MONTH Regr_Count

1 825
2 1650
3 2475
4 3300
.
26 21450
30 22200
SAMPLE 3:下例計算1998年每月銷售量中已開發票數量和總數量的累積迴歸線決定係數
SELECT t.fiscal_month_number,
REGR_R2(SUM(s.amount_sold), SUM(s.quantity_sold))
OVER (ORDER BY t.fiscal_month_number) “Regr_R2”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND t.fiscal_year = 1998
GROUP BY t.fiscal_month_number
ORDER BY t.fiscal_month_number;
FISCAL_MONTH_NUMBER Regr_R2

1
2 1
3 .927372984
4 .807019972
5 .932745567
6 .94682861
7 .965342011
8 .955768075
9 .959542618
10 .938618575
11 .880931415
12 .882769189
SAMPLE 4:下例計算1998年12月最後兩週產品260的銷售量中已開發票數量和總數量的累積平均值
SELECT t.day_number_in_month,
REGR_AVGY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month)
“Regr_AvgY”,
REGR_AVGX(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_month_desc, t.day_number_in_month)
“Regr_AvgX”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND s.prod_id = 260
AND t.fiscal_month_desc = ‘1998-12’
AND t.fiscal_week_number IN (51, 52)
ORDER BY t.day_number_in_month;
DAY_NUMBER_IN_MONTH Regr_AvgY Regr_AvgX

14 882 24.5
14 882 24.5
15 801 22.25
15 801 22.25
16 777.6 21.6
18 642.857143 17.8571429
18 642.857143 17.8571429
20 589.5 16.375
21 544 15.1111111
22 592.363636 16.4545455
22 592.363636 16.4545455
24 553.846154 15.3846154
24 553.846154 15.3846154
26 522 14.5
27 578.4 16.0666667
SAMPLE 5:下例計算產品260和270在1998年2月週末銷售量中已開發票數量和總數量的累積REGR_SXY, REGR_SXX, and REGR_SYY統計值
SELECT t.day_number_in_month,
REGR_SXY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_sxy”,
REGR_SYY(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_syy”,
REGR_SXX(s.amount_sold, s.quantity_sold)
OVER (ORDER BY t.fiscal_year, t.fiscal_month_desc) “Regr_sxx”
FROM sales s, times t
WHERE s.time_id = t.time_id
AND prod_id IN (270, 260)
AND t.fiscal_month_desc = ‘1998-02’
AND t.day_number_in_week IN (6,7)
ORDER BY t.day_number_in_month;
DAY_NUMBER_IN_MONTH Regr_sxy Regr_syy Regr_sxx

1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
1 18870.4 2116198.4 258.4
7 18870.4 2116198.4 258.4
8 18870.4 2116198.4 258.4
14 18870.4 2116198.4 258.4
15 18870.4 2116198.4 258.4
21 18870.4 2116198.4 258.4
22 18870.4 2116198.4 258.4
? 103。ROW_NUMBER
功能描述:返回有序組中一行的偏移量,從而可用於按特定標準排序的行號。
SAMPLE:下例返回每個員工再在每個部門中按員工號排序後的順序號
SELECT department_id, last_name, employee_id, ROW_NUMBER()
OVER (PARTITION BY department_id ORDER BY employee_id) AS emp_id
FROM employees
WHERE department_id < 50;
DEPARTMENT_ID LAST_NAME EMPLOYEE_ID EMP_ID

10 Whalen 200 1
20 Hartstein 201 1
20 Fay 202 2
30 Raphaely 114 1
30 Khoo 115 2
30 Baida 116 3
30 Tobias 117 4
30 Himuro 118 5
30 Colmenares 119 6
40 Mavris 203 1
104。STDDEV
功能描述:計算當前行關於組的標準偏離。(Standard Deviation)
SAMPLE:下例返回部門30按僱傭日期排序的薪水值的累積標準偏離
SELECT last_name, hire_date,salary,
STDDEV(salary) OVER (ORDER BY hire_date) “StdDev”
FROM employees
WHERE department_id = 30;
LAST_NAME HIRE_DATE SALARY StdDev

Raphaely 07-12月-94 11000 0
Khoo 18-5月 -95 3100 5586.14357
Tobias 24-7月 -97 2800 4650.0896
Baida 24-12月-97 2900 4035.26125
Himuro 15-11月-98 2600 3649.2465
Colmenares 10-8月 -99 2500 3362.58829

105。STDDEV_POP
功能描述:該函式計算總體標準偏離,並返回總體變數的平方根,其返回值與VAR_POP函式的平方根相同。(Standard Deviation-Population)
SAMPLE:下例返回部門20、30、60的薪水值的總體標準偏差
SELECT department_id, last_name, salary,
STDDEV_POP(salary) OVER (PARTITION BY department_id) AS pop_std
FROM employees
WHERE department_id in (20,30,60);
DEPARTMENT_ID LAST_NAME SALARY POP_STD

20 Hartstein 13000 3500
20 Fay 6000 3500
30 Raphaely 11000 3069.6091
30 Khoo 3100 3069.6091
30 Baida 2900 3069.6091
30 Colmenares 2500 3069.6091
30 Himuro 2600 3069.6091
30 Tobias 2800 3069.6091
60 Hunold 9000 1722.32401
60 Ernst 6000 1722.32401
60 Austin 4800 1722.32401
60 Pataballa 4800 1722.32401
60 Lorentz 4200 1722.32401
106。STDDEV_SAMP
功能描述: 該函式計算累積樣本標準偏離,並返回總體變數的平方根,其返回值與VAR_POP函式的平方根相同。(Standard Deviation-Sample)
SAMPLE:下例返回部門20、30、60的薪水值的樣本標準偏差
SELECT department_id, last_name, hire_date, salary,
STDDEV_SAMP(salary) OVER
(PARTITION BY department_id ORDER BY hire_date
ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS cum_sdev
FROM employees
WHERE department_id in (20,30,60);
DEPARTMENT_ID LAST_NAME HIRE_DATE SALARY CUM_SDEV

20 Hartstein 17-2月 -96 13000
20 Fay 17-8月 -97 6000 4949.74747
30 Raphaely 07-12月-94 11000
30 Khoo 18-5月 -95 3100 5586.14357
30 Tobias 24-7月 -97 2800 4650.0896
30 Baida 24-12月-97 2900 4035.26125
30 Himuro 15-11月-98 2600 3649.2465
30 Colmenares 10-8月 -99 2500 3362.58829
60 Hunold 03-1月 -90 9000
60 Ernst 21-5月 -91 6000 2121.32034
60 Austin 25-6月 -97 4800 2163.33077
60 Pataballa 05-2月 -98 4800 1982.42276
60 Lorentz 07-2月 -99 4200 1925.61678

107。SUM
功能描述:該函式計算組中表示式的累積和。
SAMPLE:下例計算同一經理下員工的薪水累積值
SELECT manager_id, last_name, salary,
SUM (salary) OVER (PARTITION BY manager_id ORDER BY salary
RANGE UNBOUNDED PRECEDING) l_csum
FROM employees
WHERE manager_id in (101,103,108);
MANAGER_ID LAST_NAME SALARY L_CSUM

101 Whalen 4400 4400
101 Mavris 6500 10900
101 Baer 10000 20900
101 Greenberg 12000 44900
101 Higgins 12000 44900
103 Lorentz 4200 4200
103 Austin 4800 13800
103 Pataballa 4800 13800
103 Ernst 6000 19800
108 Popp 6900 6900
108 Sciarra 7700 14600
108 Urman 7800 22400
108 Chen 8200 30600
108 Faviet 9000 39600
108。VAR_POP
功能描述:(Variance Population)該函式返回非空集合的總體變數(忽略null),VAR_POP進行如下計算:
(SUM(expr2) - SUM(expr)2 / COUNT(expr)) / COUNT(expr)
SAMPLE:下例計算1998年每月銷售的累積總體和樣本變數(本例在SH使用者下執行)
SELECT t.calendar_month_desc,
VAR_POP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Pop”,
VAR_SAMP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Samp”
FROM sales s, times t
WHERE s.time_id = t.time_id AND t.calendar_year = 1998
GROUP BY t.calendar_month_desc;
CALENDAR Var_Pop Var_Samp

1998-01 0
1998-02 6.1321E+11 1.2264E+12
1998-03 4.7058E+11 7.0587E+11
1998-04 4.6929E+11 6.2572E+11
1998-05 1.5524E+12 1.9405E+12
1998-06 2.3711E+12 2.8453E+12
1998-07 3.7464E+12 4.3708E+12
1998-08 3.7852E+12 4.3260E+12
1998-09 3.5753E+12 4.0222E+12
1998-10 3.4343E+12 3.8159E+12
1998-11 3.4245E+12 3.7669E+12
1998-12 4.8937E+12 5.3386E+12
109。VAR_SAMP
功能描述:(Variance Sample)該函式返回非空集合的樣本變數(忽略null),VAR_POP進行如下計算:
(SUM(expr*expr)-SUM(expr)*SUM(expr)/COUNT(expr))/(COUNT(expr)-1)
SAMPLE:下例計算1998年每月銷售的累積總體和樣本變數
SELECT t.calendar_month_desc,
VAR_POP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Pop”,
VAR_SAMP(SUM(s.amount_sold))
OVER (ORDER BY t.calendar_month_desc) “Var_Samp”
FROM sales s, times t
WHERE s.time_id = t.time_id AND t.calendar_year = 1998
GROUP BY t.calendar_month_desc;
CALENDAR Var_Pop Var_Samp

1998-01 0
1998-02 6.1321E+11 1.2264E+12
1998-03 4.7058E+11 7.0587E+11
1998-04 4.6929E+11 6.2572E+11
1998-05 1.5524E+12 1.9405E+12
1998-06 2.3711E+12 2.8453E+12
1998-07 3.7464E+12 4.3708E+12
1998-08 3.7852E+12 4.3260E+12
1998-09 3.5753E+12 4.0222E+12
1998-10 3.4343E+12 3.8159E+12
1998-11 3.4245E+12 3.7669E+12
1998-12 4.8937E+12 5.3386E+12
110。VARIANCE
功能描述:該函式返回表示式的變數,Oracle計算該變數如下:
如果表示式中行數為1,則返回0
如果表示式中行數大於1,則返回VAR_SAMP
SAMPLE:下例返回部門30按僱傭日期排序的薪水值的累積變化
SELECT last_name, salary, VARIANCE(salary)
OVER (ORDER BY hire_date) “Variance”
FROM employees
WHERE department_id = 30;
LAST_NAME SALARY Variance

Raphaely 11000 0
Khoo 3100 31205000
Tobias 2800 21623333.3
Baida 2900 16283333.3
Himuro 2600 13317000
Colmenares 2500 11307000
```

來自 “ ITPUB部落格 ” ,連結:http://blog.itpub.net/29812844/viewspace-1988745/,如需轉載,請註明出處,否則將追究法律責任。

相關文章