三、常见分析函数详解
为了方便进行实践，特将演示表和数据罗列如下：
一、创建表
create table t(
bill_month varchar2(12) ,
area_code number,
net_type varchar(2),
local_fare number
);
二、插入数据
insert into t values('200405',5761,'G', 7393344.04);
insert into t values('200405',5761,'J', 5667089.85);
insert into t values('200405',5762,'G', 6315075.96);
insert into t values('200405',5762,'J', 6328716.15);
insert into t values('200405',5763,'G', 8861742.59);
insert into t values('200405',5763,'J', 7788036.32);
insert into t values('200405',5764,'G', 6028670.45);
insert into t values('200405',5764,'J', 6459121.49);
insert into t values('200405',5765,'G', 13156065.77);
insert into t values('200405',5765,'J', 11901671.70);
insert into t values('200406',5761,'G', 7614587.96);
insert into t values('200406',5761,'J', 5704343.05);
insert into t values('200406',5762,'G', 6556992.60);
insert into t values('200406',5762,'J', 6238068.05);
insert into t values('200406',5763,'G', 9130055.46);
insert into t values('200406',5763,'J', 7990460.25);
insert into t values('200406',5764,'G', 6387706.01);
insert into t values('200406',5764,'J', 6907481.66);
insert into t values('200406',5765,'G', 13562968.81);
insert into t values('200406',5765,'J', 12495492.50);
insert into t values('200407',5761,'G', 7987050.65);
insert into t values('200407',5761,'J', 5723215.28);
insert into t values('200407',5762,'G', 6833096.68);
insert into t values('200407',5762,'J', 6391201.44);
insert into t values('200407',5763,'G', 9410815.91);
insert into t values('200407',5763,'J', 8076677.41);
insert into t values('200407',5764,'G', 6456433.23);
insert into t values('200407',5764,'J', 6987660.53);
insert into t values('200407',5765,'G', 14000101.20);
insert into t values('200407',5765,'J', 12301780.20);
insert into t values('200408',5761,'G', 8085170.84);
insert into t values('200408',5761,'J', 6050611.37);
insert into t values('200408',5762,'G', 6854584.22);
insert into t values('200408',5762,'J', 6521884.50);
insert into t values('200408',5763,'G', 9468707.65);
insert into t values('200408',5763,'J', 8460049.43);
insert into t values('200408',5764,'G', 6587559.23);
insert into t values('200408',5764,'J', 7342135.86);
insert into t values('200408',5765,'G', 14450586.63);
insert into t values('200408',5765,'J', 12680052.38);
commit;
三、first_value()与last_value()：求最值对应的其他属性
问题、取出每月通话费最高和最低的两个地区。
SELECT BILL_MONTH,
AREA_CODE,
SUM(LOCAL_FARE) LOCAL_FARE,
FIRST_VALUE(AREA_CODE)
OVER(PARTITION BY BILL_MONTH
ORDER BY SUM(LOCAL_FARE) DESC
ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) FIRSTVAL,
LAST_VALUE(AREA_CODE)
OVER(PARTITION BY BILL_MONTH
ORDER BY SUM(LOCAL_FARE) DESC
ROWS BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING) LASTVAL
FROM T
GROUP BY BILL_MONTH, AREA_CODE
ORDER BY BILL_MONTH
运行结果：
四、rank(),dense_rank()与row_number()：求排序
rank，dense_rank，row_number函数为每条记录产生一个从1开始至n的自然数，n的值可能小于等于记录的总数。这3个函数的唯一区别在于当碰到相同数据时的排名策略。
①row_number：
row_number函数返回一个唯一的值，当碰到相同数据时，排名按照记录集中记录的顺序依次递增。
②dense_rank：
dense_rank函数返回一个唯一的值，当碰到相同数据时，此时所有相同数据的排名都是一样的。
③rank：
rank函数返回一个唯一的值，当碰到相同的数据时，此时所有相同数据的排名是一样的，同时会在最后一条相同记录和下一条不同记录的排名之间空出排名。
演示数据在Oracle自带的scott用户下：
1、rank()值相同时排名相同，其后排名跳跃不连续
SELECT *
FROM (SELECT DEPTNO,
RANK() OVER(PARTITION BY DEPTNO ORDER BY SAL DESC) RW,
ENAME,
SAL
FROM SCOTT.EMP)
WHERE RW <= 4;
运行结果：
2、dense_rank()值相同时排名相同，其后排名连续不跳跃
SELECT *
FROM (SELECT DEPTNO,
DENSE_RANK() OVER(PARTITION BY DEPTNO ORDER BY SAL DESC) RW,
ENAME,
SAL
FROM SCOTT.EMP)
WHERE RW <= 4;
运行结果：
3、row_number()值相同时排名不相等，其后排名连续不跳跃
SELECT *
FROM (SELECT DEPTNO,
ROW_NUMBER() OVER(PARTITION BY DEPTNO ORDER BY SAL DESC) RW,
ENAME,
SAL
FROM SCOTT.EMP)
WHERE RW <= 4;
运行结果：
五、lag()与lead()：求之前或之后的第N行
lag和lead函数可以在一次查询中取出同一字段的前n行的数据和后n行的值。这种操作可以使用对相同表的表连接来实现，不过使用lag和lead有更高的效率。
lag(arg1,arg2,arg3)
第一个参数是列名，
第二个参数是偏移的offset，
第三个参数是超出记录窗口时的默认值。
举例如下：
SQL> select * from kkk;
ID NAME
---------- --------------------
1 1name
2 2name
3 3name
4 4name
5 5name
SQL> select id,name,lag(name,1,0) over(order by id) from kkk;
ID NAME LAG(NAME,1,0)OVER(ORDERBYID)
---------- -------------------- ----------------------------
1 1name 0
2 2name 1name
3 3name 2name
4 4name 3name
5 5name 4name
SQL> select id,name,lead(name,1,0) over(order by id) from kkk;
ID NAME LEAD(NAME,1,0)OVER(ORDERBYID)
---------- -------------------- -----------------------------
1 1name 2name
2 2name 3name
3 3name 4name
4 4name 5name
5 5name 0
SQL> select id,name,lead(name,2,0) over(order by id) from kkk;
ID NAME LEAD(NAME,2,0)OVER(ORDERBYID)
---------- -------------------- -----------------------------
1 1name 3name
2 2name 4name
3 3name 5name
4 4name 0
5 5name 0
SQL> select id,name,lead(name,1,'linjiqin') over(order by id) from kkk;
ID NAME LEAD(NAME,1,'ALSDFJLASDJFSAF')
---------- -------------------- ------------------------------
1 1name 2name
2 2name 3name
3 3name 4name
4 4name 5name
5 5name linjiqin
---------------------------------------------------------------------------------------
六、rollup()与cube()：排列组合分组
1)、group by rollup(a, b, c)：
首先会对(a、b、c)进行group by，
然后再对(a、b)进行group by，
其后再对(a)进行group by，
最后对全表进行汇总操作。
2)、group by cube(a, b, c)：
则首先会对(a、b、c)进行group by，
然后依次是(a、b)，(a、c)，(a)，(b、c)，(b)，(c)，
最后对全表进行汇总操作。
1、生成演示数据：
Connected to Oracle Database 10g Enterprise Edition Release 10.2.0.1.0
Connected as ds_trade
SQL> conn system/oracle as sysdba
Connected to Oracle Database 10g Enterprise Edition Release 10.2.0.3.0
Connected as SYS
SQL> create table scott.t as select * from dba_indexes;
Table created
SQL> connect scott/oracle
Connected to Oracle Database 10g Enterprise Edition Release 10.2.0.3.0
Connected as scott
SQL>
2、普通group by体验
sql> select owner, index_type, status, count(*) from t where owner like 'SY%' group by owner, index_type, status;
3、group by rollup(A,B,C)
GROUP BY ROLLUP(A, B, C)：
首先会对(A、B、C)进行GROUP BY，
然后再对(A、B)进行GROUP BY，
其后再对(A)进行GROUP BY，
最后对全表进行汇总操作。
sql> select owner, index_type, status, count(*) from t where owner like 'SY%' group by ROLLUP(owner, index_type, status);
4、group by cube(A,B,C)
GROUP BY CUBE(A, B, C)：
则首先会对(A、B、C)进行GROUP BY，
然后依次是(A、B)，(A、C)，(A)，(B、C)，(B)，(C)，
最后对全表进行汇总操作。
sql> select owner, index_type, status, count(*) from t where owner like 'SY%' group by cube(owner, index_type, status);
七、max(),min(),sun()与avg()：求移动的最值总和与平均值
问题：计算出各个地区连续3个月的通话费用的平均数(移动平均值)
SELECT AREA_CODE,
BILL_MONTH,
LOCAL_FARE,
SUM(LOCAL_FARE) OVER(PARTITION BY AREA_CODE
ORDER BY TO_NUMBER(BILL_MONTH)
RANGE BETWEEN 1 PRECEDING AND 1 FOLLOWING) "3month_sum",
AVG(LOCAL_FARE) OVER(PARTITION BY AREA_CODE
ORDER BY TO_NUMBER(BILL_MONTH)
RANGE BETWEEN 1 PRECEDING AND 1 FOLLOWING) "3month_avg",
MAX(LOCAL_FARE) OVER(PARTITION BY AREA_CODE
ORDER BY TO_NUMBER(BILL_MONTH)
RANGE BETWEEN 1 PRECEDING AND 1 FOLLOWING) "3month_max",
MIN(LOCAL_FARE) OVER(PARTITION BY AREA_CODE
ORDER BY TO_NUMBER(BILL_MONTH)
RANGE BETWEEN 1 PRECEDING AND 1 FOLLOWING) "3month_min"
FROM (SELECT T.AREA_CODE, T.BILL_MONTH, SUM(T.LOCAL_FARE) LOCAL_FARE
FROM T
GROUP BY T.AREA_CODE, T.BILL_MONTH)
运行结果：
问题：求各地区按月份累加的通话费
SELECT AREA_CODE,
BILL_MONTH,
LOCAL_FARE,
SUM(LOCAL_FARE) OVER(PARTITION BY AREA_CODE
ORDER BY BILL_MONTH ASC) "last_sum_value"
FROM (SELECT T.AREA_CODE, T.BILL_MONTH, SUM(T.LOCAL_FARE) LOCAL_FARE
FROM T
GROUP BY T.AREA_CODE, T.BILL_MONTH)
ORDER BY AREA_CODE, BILL_MONTH
运行结果：
--------------------------------------------------------------------------
Blog：http://www.cnblogs.com/linjiqin/
J2EE、Android、Linux、Oracle QQ交流群：142463980、158560018(满)
题外话：
本人来自铁观音的发源地——泉州安溪，正宗安溪铁观音，有需要的友友欢迎加我Q:416501600。
茶叶淘宝店：http://shop61968332.taobao.com/
