根据虚拟列和顺序日期查找 Min/Max 日期范围
Find Min/Max Date Range based on Dummy Columns and sequential dates
我有以下table。我需要找到每个 "Seq" 列的 min/max 日期，其中有一个 1 或连续的 1。每行只能有一个“1”
Animal Calendar_Date SeqA SeqB SeqC SeqD SeqE
Cat 2/5/2017 0 0 0 1 0
Cat 2/6/2017 1 0 0 0 0
Cat 2/7/2017 1 0 0 0 0
Cat 2/8/2017 1 0 0 0 0
Cat 2/9/2017 1 0 0 0 0
Cat 2/10/2017 0 0 0 0 1
Cat 2/11/2017 0 0 0 0 1
Cat 2/12/2017 0 0 0 0 1
Cat 2/13/2017 0 0 0 0 1
Dog 2/5/2017 1 0 0 0 0
Dog 2/6/2017 1 0 0 0 0
Dog 2/7/2017 0 1 0 0 0
Dog 2/8/2017 0 1 0 0 0
Dog 2/9/2017 1 0 0 0 0
Dog 2/10/2017 1 0 0 0 0
Dog 2/11/2017 0 0 0 1 0
Dog 2/12/2017 0 0 0 1 0
Dog 2/13/2017 0 0 0 1 0
想要的结果是这样的。我已经尝试使用 row_number、rank 和 dense_rank 但未能破解此问题。
Animal Sequence min Max
Cat D 2/5/2017 2/5/2017
Cat A 2/6/2017 2/9/2017
Cat E 2/10/2017 2/13/2017
Dog A 2/5/2017 2/6/2017
Dog B 2/7/2017 2/8/2017
Dog A 2/9/2017 2/10/2017
Dog D 2/11/2017 2/13/2017
dnoeth 的以下答案有效。但是，在我的数据集中有一些实例 Animal 和 Calendar_Date 有多个 Seq 填充了 1。这意味着它不是每个 Animal 每个 Calendar_Date 的唯一 Seq。我不得不修改代码，运行 修改了五次（每个 Seq 一次），然后 union 它们一起修改，如下所示。
SELECT Animal,
cast(Min(Trim(Both ',' FROM Seq)) as varchar(8)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END ||
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END ||
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END ||
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END ||
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END ||
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
由于您只有五列，一种方法是手动旋转它们，然后执行简单的 GROUP BY 以获得结果：
SELECT Animal, Sequence, MIN(Calendar_Date), MAX(Calendar_Date)
FROM (
SELECT Animal, 'A' AS Sequence, Calendar_Date FROM MyTable WHERE SeqA=1
UNION ALL
SELECT Animal, 'B' AS Sequence, Calendar_Date FROM MyTable WHERE SeqB=1
UNION ALL
SELECT Animal, 'C' AS Sequence, Calendar_Date FROM MyTable WHERE SeqC=1
UNION ALL
SELECT Animal, 'D' AS Sequence, Calendar_Date FROM MyTable WHERE SeqD=1
UNION ALL
SELECT Animal, 'E' AS Sequence, Calendar_Date FROM MyTable WHERE SeqE=1
) dt
GROUP BY Animal, Sequence
根据您的数据，这可能是最有效的：
select animal,
(case when seqA = 1 then 'A'
when seqB = 1 then 'B'
when seqC = 1 then 'C'
when seqD = 1 then 'D'
when seqE = 1 then 'E'
end) as sequence,
min(calendar_date), max(calendar_date)
from t
group by seqA, seqB, seqC, seqD, seqE;
之所以有效，是因为 "seq" 列中只有一列在每一行中都有一个值。
老实说，我建议向 table 添加一个计算列并使用它：
alter table animal
add sequence as (case when seqA = 1 then 'A'
when seqB = 1 then 'B'
when seqC = 1 then 'C'
when seqD = 1 then 'D'
when seqE = 1 then 'E'
end);
那么你可以这样做：
select animal, sequence, min(calendar_date), max(calendar_date)
from t
group by animal, sequence;
遗憾的是，Teradata 不支持计算列。 Teradata 标签是在我最初回答后添加的。但是，您可以使用视图来获得大致相同的效果。
您需要嵌套的 OLAP 函数：
SELECT Animal,
Min(Trim(Both ',' FROM Seq)),
Min(Calendar_Date),
Max(Calendar_Date)
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
CASE WHEN SeqA = 1 THEN 'A' ELSE ',' END ||
CASE WHEN SeqB = 1 THEN 'B' ELSE ',' END ||
CASE WHEN SeqC = 1 THEN 'C' ELSE ',' END ||
CASE WHEN SeqD = 1 THEN 'D' ELSE ',' END ||
CASE WHEN SeqE = 1 THEN 'E' ELSE ',' END AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM tab
) AS dt
) AS dt
GROUP BY Animal, grp
我有以下table。我需要找到每个 "Seq" 列的 min/max 日期，其中有一个 1 或连续的 1。每行只能有一个“1”
Animal Calendar_Date SeqA SeqB SeqC SeqD SeqE
Cat 2/5/2017 0 0 0 1 0
Cat 2/6/2017 1 0 0 0 0
Cat 2/7/2017 1 0 0 0 0
Cat 2/8/2017 1 0 0 0 0
Cat 2/9/2017 1 0 0 0 0
Cat 2/10/2017 0 0 0 0 1
Cat 2/11/2017 0 0 0 0 1
Cat 2/12/2017 0 0 0 0 1
Cat 2/13/2017 0 0 0 0 1
Dog 2/5/2017 1 0 0 0 0
Dog 2/6/2017 1 0 0 0 0
Dog 2/7/2017 0 1 0 0 0
Dog 2/8/2017 0 1 0 0 0
Dog 2/9/2017 1 0 0 0 0
Dog 2/10/2017 1 0 0 0 0
Dog 2/11/2017 0 0 0 1 0
Dog 2/12/2017 0 0 0 1 0
Dog 2/13/2017 0 0 0 1 0
想要的结果是这样的。我已经尝试使用 row_number、rank 和 dense_rank 但未能破解此问题。
Animal Sequence min Max
Cat D 2/5/2017 2/5/2017
Cat A 2/6/2017 2/9/2017
Cat E 2/10/2017 2/13/2017
Dog A 2/5/2017 2/6/2017
Dog B 2/7/2017 2/8/2017
Dog A 2/9/2017 2/10/2017
Dog D 2/11/2017 2/13/2017
dnoeth 的以下答案有效。但是，在我的数据集中有一些实例 Animal 和 Calendar_Date 有多个 Seq 填充了 1。这意味着它不是每个 Animal 每个 Calendar_Date 的唯一 Seq。我不得不修改代码，运行 修改了五次（每个 Seq 一次），然后 union 它们一起修改，如下所示。
SELECT Animal,
cast(Min(Trim(Both ',' FROM Seq)) as varchar(8)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END ||
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END ||
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END ||
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END ||
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END ||
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
-- CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
Union
SELECT Animal,
Min(Trim(Both ',' FROM Seq)) as POS_Type,
Min(Calendar_Date) as Min_Date,
Max(Calendar_Date) as Max_Date
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
-- CASE WHEN SeqA = 1 THEN 'SeqA' ELSE null END
-- CASE WHEN SeqB = 1 THEN 'SeqB' ELSE null END
-- CASE WHEN SeqC = 1 THEN 'SeqC' ELSE null END
-- CASE WHEN SeqD = 1 THEN 'SeqD' ELSE null END
CASE WHEN SeqE = 1 THEN 'SeqE' ELSE null END
AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM Table_A
--and SeqA = 1
) AS dt
where seq is not null
) AS dt
GROUP BY Animal, grp
由于您只有五列，一种方法是手动旋转它们，然后执行简单的 GROUP BY 以获得结果：
SELECT Animal, Sequence, MIN(Calendar_Date), MAX(Calendar_Date)
FROM (
SELECT Animal, 'A' AS Sequence, Calendar_Date FROM MyTable WHERE SeqA=1
UNION ALL
SELECT Animal, 'B' AS Sequence, Calendar_Date FROM MyTable WHERE SeqB=1
UNION ALL
SELECT Animal, 'C' AS Sequence, Calendar_Date FROM MyTable WHERE SeqC=1
UNION ALL
SELECT Animal, 'D' AS Sequence, Calendar_Date FROM MyTable WHERE SeqD=1
UNION ALL
SELECT Animal, 'E' AS Sequence, Calendar_Date FROM MyTable WHERE SeqE=1
) dt
GROUP BY Animal, Sequence
根据您的数据，这可能是最有效的：
select animal,
(case when seqA = 1 then 'A'
when seqB = 1 then 'B'
when seqC = 1 then 'C'
when seqD = 1 then 'D'
when seqE = 1 then 'E'
end) as sequence,
min(calendar_date), max(calendar_date)
from t
group by seqA, seqB, seqC, seqD, seqE;
之所以有效，是因为 "seq" 列中只有一列在每一行中都有一个值。
老实说，我建议向 table 添加一个计算列并使用它：
alter table animal
add sequence as (case when seqA = 1 then 'A'
when seqB = 1 then 'B'
when seqC = 1 then 'C'
when seqD = 1 then 'D'
when seqE = 1 then 'E'
end);
那么你可以这样做：
select animal, sequence, min(calendar_date), max(calendar_date)
from t
group by animal, sequence;
遗憾的是，Teradata 不支持计算列。 Teradata 标签是在我最初回答后添加的。但是，您可以使用视图来获得大致相同的效果。
您需要嵌套的 OLAP 函数：
SELECT Animal,
Min(Trim(Both ',' FROM Seq)),
Min(Calendar_Date),
Max(Calendar_Date)
FROM
(
SELECT Animal, Calendar_Date, Seq,
-- calculate groups of consecutive values
Sum(flag)
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS Unbounded Preceding) AS grp
FROM
(
SELECT Animal, Calendar_Date,
-- combine all columns into one
CASE WHEN SeqA = 1 THEN 'A' ELSE ',' END ||
CASE WHEN SeqB = 1 THEN 'B' ELSE ',' END ||
CASE WHEN SeqC = 1 THEN 'C' ELSE ',' END ||
CASE WHEN SeqD = 1 THEN 'D' ELSE ',' END ||
CASE WHEN SeqE = 1 THEN 'E' ELSE ',' END AS Seq,
-- check if current and previous row are different
CASE WHEN Min(Seq) -- or LAG in TD16.10
Over (PARTITION BY Animal
ORDER BY Calendar_Date
ROWS BETWEEN 1 Preceding AND 1 Preceding) = Seq
THEN 0
ELSE 1
END AS flag
FROM tab
) AS dt
) AS dt
GROUP BY Animal, grp