Question

我有以下格式的数据。

match_id   team_id   won_ind
----------------------------
37          Team1    N
67          Team1    Y
98          Team1    N
109         Team1    N
158         Team1    Y
162         Team1    Y
177         Team1    Y
188         Team1    Y
198         Team1    N
207         Team1    Y
217         Team1    Y
10          Team2    N
13          Team2    N
24          Team2    N
39          Team2    Y
40          Team2    Y
51          Team2    Y
64          Team2    N
79          Team2    N
86          Team2    N
91          Team2    Y
101         Team2    N

这里match_id按时间顺序排列，37是第一个，217是team1最后一次比赛。 won_ind表示球队是否赢了比赛。

所以，从上面的数据来看，team1已经失去了第一场比赛，然后赢了一场比赛，然后输了2场比赛，然后赢了4场比赛，依此类推。现在我有兴趣为每支球队找到最长的连胜纪录。

Team_id   longest_streak
------------------------
Team1     4
Team2     3

我知道如何在plsql中找到它，但我想知道这是否可以在纯SQL中计算。我尝试使用LEAD，LAG和其他几个功能，但没有到达任何地方。

我创建了样本小提琴here。

Answer 1

这应该有用，在这里小提琴：http://sqlfiddle.com/#!4/31f95/27

SELECT   team_id, MAX(seq_length) AS longest_sequence
      FROM (SELECT   team_id, COUNT(*) AS seq_length
                 FROM (SELECT team_id, won_ind,match_id, SUM(new_group) OVER(ORDER BY match_id) AS group_no
                         FROM (SELECT   team_id, won_ind, match_id,
                                        DECODE(LAG(won_ind) OVER(ORDER BY match_id), won_ind, 0, 1) AS new_group
                                   FROM matches
                               ORDER BY team_id))
                WHERE won_ind = 'Y'
             GROUP BY team_id, group_no)
   GROUP BY team_id
   ORDER BY 2 DESC, 1;

Answer 2

with original_data as (
  select 37  match_id, 'Team1' team_id, 'N' won_id from dual union all
  select 67  match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 98  match_id, 'Team1' team_id, 'N' won_id from dual union all
  select 109 match_id, 'Team1' team_id, 'N' won_id from dual union all
  select 158 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 162 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 177 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 188 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 198 match_id, 'Team1' team_id, 'N' won_id from dual union all
  select 207 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 217 match_id, 'Team1' team_id, 'Y' won_id from dual union all
  select 10  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 13  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 24  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 39  match_id, 'Team2' team_id, 'Y' won_id from dual union all
  select 40  match_id, 'Team2' team_id, 'Y' won_id from dual union all
  select 51  match_id, 'Team2' team_id, 'Y' won_id from dual union all
  select 64  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 79  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 86  match_id, 'Team2' team_id, 'N' won_id from dual union all
  select 91  match_id, 'Team2' team_id, 'Y' won_id from dual union all
  select 101 match_id, 'Team2' team_id, 'N' won_id from dual 
),
----------------------------------------------------------------------
new_streaks as (
--
--  Identifying new streaks.
--  ------------------------
--
    select
      match_id,
      team_id,
      won_id,
--
--  A new streak is identfied if 
--
    case when
--
--    a) won_id = 'Y' and
--
      won_id = 'Y' and
--
--    b) the previous won_id = 'N':
--    
      lag(won_id) over (partition by team_id order by match_id) = 'N' 
--
--    
      then 1 
--
--    All other cases: no new streak:
      else 0 
-- 
     end new_streak
    from
      original_data
),
-------------------------------
streak_no as (
--
--  Assigning a unique number to each streak.
--  -----------------------------------------
--
select
--
    match_id,
    team_id,
--
--  In order to be able to count the number of records
--  of a streak, we first need to assign a unique number
--  to each streak:
--
    sum(new_streak) over (partition by team_id order by match_id) streak_no
--
from
    new_streaks 
where
--  We're only interested in «winning streaks»:
    won_id = 'Y'
),
-----------------------------------------------
--
--  Counting the elements per streak
--  --------------------------------
--
records_per_streak as (
select 
  count(*) counter,
  team_id,
  streak_no
from
  streak_no
group by
  team_id,
  streak_no
)
------------------------------------------------
--
--   Finally: we can find the «longest streak»
--   per team:
--
select
  max(counter) longest_streak,
  team_id
from
  records_per_streak 
group by team_id
;

Answer 3

使用答案的变体我发布了here

select
    team_id,
    max(wins)
  from
    (
     select
            a.team_id,
            a.match_id amatch,
            b.match_id bmatch,
    (select count(distinct match_id) 
       from matches matches_inner
      where a.team_id = matches_inner.team_id
        and matches_inner.match_id between a.match_id and b.match_id) wins
      from
            matches a
            join matches b on a.team_id = b.team_id 
                      and b.match_id > a.match_id
     where
    not exists 
    (select 'x'
       from matches matches_inner
      where a.team_id = matches_inner.team_id
        and matches_inner.match_id between a.match_id and b.match_id
        and matches_inner.won_ind = 'N')

group by team_id

Answer 4

我在Teradata上有类似的任务，修改它以在Oracle上运行：

SELECT
   team_id,
   MAX(cnt)
FROM
 (
   SELECT
      team_id,
      COUNT(*) AS cnt
   FROM 
    (
      SELECT
        team_id, 
        match_id,
        won_ind,
        SUM(CASE WHEN won_ind <> 'Y' THEN 1 END) 
        OVER (PARTITION BY team_id 
              ORDER BY match_id 
              ROWS UNBOUNDED PRECEDING) AS dummy
      FROM matches
    ) dt
   WHERE won_ind = 'Y'
   GROUP BY team_id, dummy
 ) dt
GROUP BY team_id;

寻找最长的连胜纪录

4 个答案: