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，不同之处在于每个图块的成员将采用滑动分布，以便排名较高的图块具有较少的成员。

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) 创建均匀分布的@numGroups 组。我需要的是 @numGroups 组，其中图块 1 的成员最少，图块 2 的成员数量比图块 1 多一个或多个，图块 3 的成员数量比图块 2 多一个或多个...图块 100 的成员最多。

我正在使用 SQL Server 2008。实际上，这将针对可能包含数百万行的永久表运行，以便定期更新 PERCENTILE 列及其从 1 到 100 的百分位。

我上面的最佳尝试将跳过百分位数并且表现不佳。一定有更好的方法。

Answer 1

更好的 NTILE 实现？青年MMV

Answer 2

为了创建更线性的分布，我向数据表添加了一个计算列 HITS_SQRT 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，该脚本使用按命中数排序的 ROW_NUMBER() 创建一个临时表，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@hitsPerGroup，百分位数从 100 降低到 99、99 到 98 等。

然后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。

使用#Rank_Table 作为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。