[英]SQL count consecutive rows
我在表中有以下數據:
|event_id |starttime |person_id|attended|
|------------|-----------------|---------|--------|
| 11512997-1 | 01-SEP-16 08:00 | 10001 | N |
| 11512997-2 | 01-SEP-16 10:00 | 10001 | N |
| 11512997-3 | 01-SEP-16 12:00 | 10001 | N |
| 11512997-4 | 01-SEP-16 14:00 | 10001 | N |
| 11512997-5 | 01-SEP-16 16:00 | 10001 | N |
| 11512997-6 | 01-SEP-16 18:00 | 10001 | Y |
| 11512997-7 | 02-SEP-16 08:00 | 10001 | N |
| 11512997-1 | 01-SEP-16 08:00 | 10002 | N |
| 11512997-2 | 01-SEP-16 10:00 | 10002 | N |
| 11512997-3 | 01-SEP-16 12:00 | 10002 | N |
| 11512997-4 | 01-SEP-16 14:00 | 10002 | Y |
| 11512997-5 | 01-SEP-16 16:00 | 10002 | N |
| 11512997-6 | 01-SEP-16 18:00 | 10002 | Y |
| 11512997-7 | 02-SEP-16 08:00 | 10002 | Y |
我想生成以下結果,其中返回atended ='N'的最大連續出現次數:
|person_id|consec_missed_max|
| 1001 | 5 |
| 1002 | 3 |
如何在Oracle(或ANSI)SQL中完成此操作? 謝謝!
編輯:
到目前為止,我嘗試過:
WITH t1 AS
(SELECT t.person_id,
row_number() over(PARTITION BY t.person_id ORDER BY t.starttime) AS idx
FROM the_table t
WHERE t.attended = 'N'),
t2 AS
(SELECT person_id, MAX(idx) max_idx FROM t1 GROUP BY person_id)
SELECT t1.person_id, COUNT(1) ct
FROM t1
JOIN t2
ON t1.person_id = t2.person_id
GROUP BY t1.person_id;
主要工作在因子子查詢“准備”中。 您似乎對分析功能有點熟悉,但這還不夠。 該解決方案使用所謂的“tabibitosan”方法在一個或多個維度中創建具有相同特征的連續行組; 在這種情況下,您希望將每個序列的連續N行分組為不同的組。 這是通過兩個ROW_NUMBER()調用的差異來完成的 - 一個是按人員划分的,另一個是按人划分並參加。 谷歌“tabibitosan”如果需要,可以閱讀更多關於這個想法的內容。
with
inputs ( event_id, starttime, person_id, attended ) as (
select '11512997-1', to_date('01-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-2', to_date('01-SEP-16 10:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-3', to_date('01-SEP-16 12:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-4', to_date('01-SEP-16 14:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-5', to_date('01-SEP-16 16:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-6', to_date('01-SEP-16 18:00', 'dd-MON-yy hh24:mi'), 10001, 'Y' from dual union all
select '11512997-7', to_date('02-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-1', to_date('01-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-2', to_date('01-SEP-16 10:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-3', to_date('01-SEP-16 12:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-4', to_date('01-SEP-16 14:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual union all
select '11512997-5', to_date('01-SEP-16 16:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-6', to_date('01-SEP-16 18:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual union all
select '11512997-7', to_date('02-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual
),
prep ( starttime, person_id, attended, gp ) as (
select starttime, person_id, attended,
row_number() over (partition by person_id order by starttime) -
row_number() over (partition by person_id, attended
order by starttime)
from inputs
),
counts ( person_id, consecutive_absences ) as (
select person_id, count(*)
from prep
where attended = 'N'
group by person_id, gp
)
select person_id, max(consecutive_absences) as max_consecutive_absences
from counts
group by person_id
order by person_id;
OUTPUT:
PERSON_ID MAX_CONSECUTIVE_ABSENCES
---------- ---------------------------------------
10001 5
10002 3
如果您使用的是Oracle 12c
,則可以使用MATCH_RECOGNIZE
:
數據:
CREATE TABLE data AS
SELECT *
FROM (
with inputs ( event_id, starttime, person_id, attended ) as (
select '11512997-1', to_date('01-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-2', to_date('01-SEP-16 10:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-3', to_date('01-SEP-16 12:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-4', to_date('01-SEP-16 14:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-5', to_date('01-SEP-16 16:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-6', to_date('01-SEP-16 18:00', 'dd-MON-yy hh24:mi'), 10001, 'Y' from dual union all
select '11512997-7', to_date('02-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10001, 'N' from dual union all
select '11512997-1', to_date('01-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-2', to_date('01-SEP-16 10:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-3', to_date('01-SEP-16 12:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-4', to_date('01-SEP-16 14:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual union all
select '11512997-5', to_date('01-SEP-16 16:00', 'dd-MON-yy hh24:mi'), 10002, 'N' from dual union all
select '11512997-6', to_date('01-SEP-16 18:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual union all
select '11512997-7', to_date('02-SEP-16 08:00', 'dd-MON-yy hh24:mi'), 10002, 'Y' from dual
)
SELECT * FROM inputs
);
並查詢:
SELECT PERSON_ID, MAX(LEN) AS MAX_ABSENCES_IN_ROW
FROM data
MATCH_RECOGNIZE (
PARTITION BY PERSON_ID
ORDER BY STARTTIME
MEASURES FINAL COUNT(*) AS len
ALL ROWS PER MATCH
PATTERN(a b*)
DEFINE b AS attended = a.attended
)
WHERE attended = 'N'
GROUP BY PERSON_ID;
輸出:
"PERSON_ID","MAX_ABSENCES_IN_ROW"
10001,5
10002,3
編輯:
正如@mathguy指出的那樣,它可以改寫為:
SELECT PERSON_ID, MAX(LEN) AS MAX_ABSENCES_IN_ROW
FROM data
MATCH_RECOGNIZE (
PARTITION BY PERSON_ID
ORDER BY STARTTIME
MEASURES COUNT(*) AS len
PATTERN(a+)
DEFINE a AS attended = 'N'
)
GROUP BY PERSON_ID;
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.