T-SQL:更好的滑动分布函数/查询

Question

我需要一种类似于NTILE()提供的T-SQL排名方法,除了每个图块的成员都在滑动分布上,以便更高排名的图块具有更少的成员.

例如

CREATE TABLE #Rank_Table(
id int identity(1,1) not null,
hits bigint not null default 0,
PERCENTILE smallint null
)
--Slant the distribution of the data
INSERT INTO #Rank_Table (hits)
select CASE 
  when DATA > 9500 THEN DATA*30
  WHEN data > 8000  THEN DATA*5 
  WHEN data < 7000  THEN DATA/3 +1
  ELSE DATA
 END
FROM
 (select top 10000 (ABS(CHECKSUM(NewId())) % 99 +1) * (ABS(CHECKSUM(NewId())) % 99 +1 ) DATA
 from master..spt_values t1
  cross JOIN master..spt_values t2) exponential

Declare @hitsPerGroup as bigint
Declare @numGroups as smallint
set @numGroups=100

select @hitsPerGroup=SUM(hits)/(@numGroups -1) FROM #Rank_Table 

select @hitsPerGroup HITS_PER_GROUP

--This is an even distribution
SELECT  id,HITS, NTILE(@numGroups) Over (Order By HITS DESC) PERCENTILE 
FROM #Rank_Table 
GROUP by id, HITS

--This is my best attempt, but it skips groups because of the erratic distribution
select 
    T1.ID, 
    T1.hits, 
    T.RunningTotal/@hitsPerGroup + 1 TILE,
    T.RunningTotal
FROM    #Rank_Table T1
        CROSS APPLY ( Select SUM(hits) RunningTotal FROM #Rank_Table where hits <= T1.hits) T
order by T1.hits 

DROP TABLE #Rank_Table

在#Rank_table中,NTILE(@numGroups)创建@numGroups组的均匀分布.我需要的是@numGroups组,其中tile 1具有最少的成员,tile 2将具有一个或多个tile 1,tile 3将具有1或多于tile 2 ... tile 100将具有最多.

我正在使用SQL Server 2008.实际上,这将针对可能有数百万行的永久表运行,以便定期更新PERCENTILE列,其百分位数为1-100.

我上面的最佳尝试将跳过百分位并且表现不佳.肯定有更好的办法.

Answer 1

为了创建更线性的分布，我向数据表 HITS_SQRT 添加了一个计算列HITS_SQRT AS (CONVERT([int],sqrt(HITS*4),(0))) PERSISTED。

使用此列，您可以计算“每百分位点击数”的目标数量。

select @hitsPerGroup=SUM(HITS_SQRT)/(@numGroups -1)-@numGroups, @dataPoints=COUNT(*) FROM #Rank_Table 

然后，该脚本创建一个临时表，其中包含按命中数排序的 ROW_NUMBER() 并按降序迭代行，将其百分位数从 100 更新为 1。 保留命中数的运行总计，并且当传递时@hitsPerGroup，百分位数从 100 降低到 99、99 降低到 98，等等。

然后使用其百分位数更新源数据表。临时工作表有一个索引以加快更新速度。

#Rank_Table用作源数据表的完整脚本。

--Create Test Data
CREATE TABLE #Rank_Table(
id int identity(1,1) not null,
hits bigint not null default 0,
PERCENTILE smallint NULL,
HITS_SQRT  AS (CONVERT([int],sqrt(HITS*4),(0))) PERSISTED
)
--Slant the distribution of the data
INSERT INTO #Rank_Table (hits)
select CASE 
  when DATA > 9500 THEN DATA*30
  WHEN data > 8000  THEN DATA*5 
  WHEN data < 7000  THEN DATA/3 +1
  ELSE DATA
 END
FROM
 (select top 10000 (ABS(CHECKSUM(NewId())) % 99 +1) * (ABS(CHECKSUM(NewId())) % 99 +1 ) DATA
 from master..spt_values t1
  cross JOIN master..spt_values t2) exponential

--Create temp work table and variables to calculate percentiles
    Declare @hitsPerGroup as int
    Declare @numGroups as int
    Declare @dataPoints as int
    set @numGroups=100

    select @hitsPerGroup=SUM(HITS_SQRT)/(@numGroups -1)-@numGroups, @dataPoints=COUNT(*) FROM #Rank_Table 

    --show the number of hits that each group should have
    select @hitsPerGroup HITS_PER_GROUP

    --Use temp table for the calculation
    CREATE TABLE #tbl (
        row int,
        hits int,
        ID bigint,
        PERCENTILE smallint null
    )
    --add index to row
    CREATE CLUSTERED INDEX idxRow ON #tbl(row) 

    insert INTO #tbl
    select ROW_NUMBER() over (ORDER BY HITS), hits_SQRT, ID, null from #Rank_Table

    --Update each row with a running total.
    --lower the percentile by one when we cross a threshold for the maximum number of hits per group (@hitsPerGroup)
    DECLARE @row as int
    DEClare @runningTotal as int
    declare @percentile int
    set @row = 0
    set @runningTotal = 0
    set @percentile = @numGroups

    while @row <= @dataPoints
    BEGIN
        select @runningTotal=@runningTotal + hits from #tbl where row=@row

        if @runningTotal >= @hitsPerGroup
        BEGIN

            update #tbl
            set PERCENTILE=@percentile
            WHERE PERCENTILE is null and row <@row

            set @percentile = @percentile - 1

            set @runningTotal = 0
        END

        --change rows
        set @row = @row + 1
    END

    --get remaining
    update #tbl
    set PERCENTILE=@percentile
    WHERE PERCENTILE is null

    --update source data
    UPDATE m SET PERCENTILE = t.PERCENTILE
    FROM #tbl t
    inner join #Rank_Table m on t.ID=m.ID


--Show the results
    SELECT PERCENTILE, COUNT(id) NUMBER_RECORDS, SUM(HITS) HITS_IN_PERCENTILE 
    FROM #Rank_Table 
    GROUP BY PERCENTILE
    ORDER BY PERCENTILE 

--cleanup
    DROP TABLE #Rank_Table
    DROP TABLE #tbl

性能不是很出色，但它实现了平滑滑动分布的目标。