从数据集SQL创建趋势线

时间：2012-04-06 17:23:18

标签： sql visual-studio math linear-regression

以下代码返回已解决的故障单数量以及一段时间（期间为YYYY，WW）的特定天数的已打开故障单数量。例如，如果@NoOfDays是7：

  

已解决|打开|一周|一年|期

     

56 | 30 | 13 | 2012 | 2012,13

     

237 | 222 | 14 | 2012 | 2012,14

'已解决'和'已打开'在时间段（x）上的行（y）上绘制。我想添加另一个列'趋势'，它将返回一个数字，当绘制一段时间时，将成为趋势线（简单线性回归）。 我做想要将这两组值用作趋势的一个数据源。

这是我的代码：

SELECT a.resolved, b.opened, a.weekClosed AS week, a.yearClosed AS year,
    CAST(a.yearClosed as varchar(5)) + ', ' + CAST(a.weekClosed as varchar(5)) AS period
FROM 
    (SELECT TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS resolved, { fn WEEK(date_closed) } AS weekClosed, { fn YEAR(date_closed) } AS yearClosed
    FROM v_rpt_Service
    WHERE (date_closed >= DateAdd(Day, DateDiff(Day, 0, GetDate()) - @NoOfDays, 0))
    GROUP BY { fn WEEK(date_closed) }, { fn YEAR(date_closed) }) AS a 
LEFT OUTER JOIN
    (SELECT TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS opened, { fn WEEK(date_entered) } AS weekEntered, { fn YEAR(date_entered) 
    } AS yearEntered
    FROM v_rpt_Service AS v_rpt_Service_1
    WHERE        (date_entered > = DateAdd(Day, DateDiff(Day, 0, GetDate()) - @NoOfDays, 0))
    GROUP BY { fn WEEK(date_entered) }, { fn YEAR(date_entered) }) AS b ON a.weekClosed = b.weekEntered AND a.yearClosed = b.yearEntered
ORDER BY year, week

修改

根据serc.carleton.edu/files/mathyouneed/best_fit_line_dividing.pdf，似乎我想将数据分成两半，然后计算平均值。然后我需要找到最佳拟合线，并使用斜率和y轴截距来计算使用y = mx + b在'趋势'中返回所需的值？

我知道这在SQL中很有可能，但是，我插入SQL的程序对我能做的事情有限制。

红色和蓝色点是我现在返回的数字（已打开并已解决）。我需要为'趋势'中的每个句点返回一个值，以便创建紫色线。 （此图片是假设的）

Hypothetical Chart

3 个答案:

答案 0 :(得分：4)

我对这个问题感兴趣，并且我发现了解决复杂查询的最佳方法是使用我自己的样式和约定重新格式化它。我将它们应用到您的解决方案中，结果如下。我不知道这对你有什么价值......

  • 我不相信有一些代码是MS T-SQL语法的一部分，例如({fn xxx }和WEEK(xxx)函数。
  • 此代码编译，但我无法运行它，因为我没有正确配置数据表。
  • 我做了大量的编码更改，需要进行大量的解释，而且我将跳过其中的大部分内容。如果您想要任何明确的内容，请添加评论。
  • 我扔了很多空白。易读和难以理解的代码之间的区别往往只是旁观者的感知和敏感，你可能会讨厌我的约定。
  • 不确定最终结果集应该是什么（即返回哪些列）

进一步说明：

  • 如果在该周内没有关闭任何项目，则此查询将不会获得一周内输入的项目
  • 周可能是部分的，例如并非所有七天都存在（将@Interval调整为总是包括整周 - 但奇数编号的间隔呢？）
  • 将count（*）值乘以1.0，将它们提前转换为浮点数（避免强制转换和整数数学截断）
  • 使它成为一个cte，允许先前的公式被后面的公式中的符号替换（此时事情变得更加清晰）

所以这就是我提出的：

;WITH cte as (
select
   c.period
  ,resolved_half1
  ,resolved_half2
  ,opened_half1
  ,opened_half2
  ,row = row_number() over(order by c.yearClosed, c.weekClosed)
  ,y1 = ((SUM(resolved_half1) + SUM(opened_half1)) - (SUM(resolved_half2) + SUM(opened_half2))) / ((count(resolved_half1) + count(opened_half1)) / 2)
  ,y2 = ((SUM(resolved_half2) + SUM(opened_half2)) / (count(resolved_half2) + COUNT (opened_half2)))
  ,x1 = ((count(c.period)) / 4)
  ,x2 = (((count(c.period)) / 4) * 3)
 from (select
          a.yearclosed
         ,a.weekClosed
         ,a.resolved_half1
         ,b.yearEntered
         ,b.weekEntered
         ,b.opened_half1
         ,cast(a.yearClosed as varchar(5)) + ', ' + cast(a.weekClosed as varchar(5))  period 
        from (--  Number of items per week that closed within @Interval
              select
                 count(distinct TicketNbr) * 1.0  resolved_half1
                ,datepart(wk, date_closed)        weekClosed
                ,year(date_closed)                yearClosed
               from v_rpt_Service 
               where date_closed >= @FullInterval
               group by
                 datepart(wk, date_closed)
                ,year(date_closed) )  a
         left outer join (--  Number of items per week that were entered within @Interval
                          select 
                             count(distinct TicketNbr) * 1.0  opened_half1
                            ,datepart(wk, date_entered)       weekEntered
                            ,year(date_entered)               yearEntered
                           from v_rpt_Service
                           where date_entered >= @FullInterval
                           group by
                             datepart(wk, date_entered)
                            ,year(date_entered) )  b
          on a.weekClosed = b.weekEntered 
           and a.yearClosed = b.yearEntered)  c
  left outer join (select
                       d.yearclosed
                      ,d.weekClosed
                      ,d.resolved_half2
                      ,e.yearEntered
                      ,e.weekEntered
                      ,e.opened_half2
                      ,cast(yearClosed as varchar(5)) + ', ' + cast(weekClosed as varchar(5))  period 
                    from (select
                             count(distinct TicketNbr) * 1.0  resolved_half2
                            ,datepart(wk, date_closed)        weekClosed
                            ,year(date_closed)                yearClosed
                           from v_rpt_Service
                           where date_closed >= @HalfInterval
                           group by
                             datepart(wk, date_closed) 
                            ,year(date_closed) )  d 
                     left outer join (select
                                         count(distinct TicketNbr) * 1.0  opened_half2
                                        ,datepart(wk, date_entered)       weekEntered
                                        ,year(date_entered)               yearEntered
                                       from v_rpt_Service
                                       where date_entered >= @HalfInterval
                                       group by
                                           datepart(wk, date_entered) 
                                          ,year(date_entered) )  e
                      on d.weekClosed = e.weekEntered
                       and d.yearClosed = e.yearEntered )  f
   on c.period = f.period 
 group by
   c.period
  ,resolved_half1
  ,resolved_half2
  ,opened_half1
  ,opened_half2
  ,c.yearClosed
  ,c.weekClosed
)
SELECT
   row
  ,Period
  ,x1
  ,y1
  ,x2
  ,y2
  ,m = ((y1 - y2) / (x1 - x2))
  ,b = (y2 - (((y1 - y2) / (x1 - x2)) * x2))
  ,trend = ((((y1 - y2) / (x1 - x2)) * (row)) + (y2 - (((y1 - y2) / (x1 - x2)) * x2)))
 from cte
 order by row

作为附录，所有子查询“c”都可以替换为以下内容，而“f”则稍加修改。性能好坏取决于表格大小，索引和其他不可估量性。

select
   datepart(wk, date_closed)  weekClosed
  ,year(date_closed)          yearClosed
  ,count (distinct case
                  when date_closed >= @FullInterval then TicketNbr
                  else null
                end)          resolved_half1
  ,count (distinct case
                  when date_entered >= @FullInterval then TicketNbr
                  else null
                end)          opened_half1
 from v_rpt_Service 
 where date_closed >= @FullInterval
  or date_entered >= @FullInterval
 group by
   datepart(wk, date_closed)
  ,year(date_closed)

答案 1 :(得分：1)

我明白了。我将数据分成多个派生表和子查询，基本上将数据分成两半。这些是获取每个值的公式：

*(each row is a week)*
y1 = average of data first half
y2 = average of data second half
x1 = 1/4 of number of weeks
x2 = 3/4 of number of weeks
m = (y1-y2)/(x1-x2)
b = y2 - (m * x2)
trend = (m * row_number) + b

这是我的（非常脏的）SQL代码：

SELECT  resolved_half1,resolved_half2,opened_half1,opened_half2, c.period,
((SUM (resolved_half1) OVER () + SUM(opened_half1) OVER ()) - (SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ())) / ((COUNT(resolved_half1) OVER () + COUNT(opened_half1) OVER ()) / 2) as y1, 
((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as y2,
((COUNT(c.period) OVER ()) / 4) as x1,
(((COUNT(c.period) OVER ()) / 4) * 3) as x2,
((CAST(((SUM (resolved_half1) OVER () + SUM(opened_half1) OVER ()) - (SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ())) / ((COUNT(resolved_half1) OVER () + COUNT(opened_half1) OVER ()) / 2) as float) - CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float)) / (CAST(((COUNT(c.period) OVER ()) / 4) as float) - CAST( (((COUNT(c.period) OVER ()) / 4) * 3) as float))) as m,
(CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float) - (((CAST(((SUM (resolved_half1) OVER () + SUM(opened_half1) OVER ()) - (SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ())) / ((COUNT(resolved_half1) OVER () + COUNT(opened_half1) OVER ()) / 2) as float) - CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float)) / (CAST(((COUNT(c.period) OVER ()) / 4) as float) - CAST( (((COUNT(c.period) OVER ()) / 4) * 3) as float))) * (((COUNT(c.period) OVER ()) / 4) * 3))) as b,
((((CAST(((SUM (resolved_half1) OVER () + SUM(opened_half1) OVER ()) - (SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ())) / ((COUNT(resolved_half1) OVER () + COUNT(opened_half1) OVER ()) / 2) as float) - CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float)) / (CAST(((COUNT(c.period) OVER ()) / 4) as float) - CAST( (((COUNT(c.period) OVER ()) / 4) * 3) as float))) * (ROW_NUMBER() OVER(ORDER BY c.yearClosed,c.weekClosed))) + (CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float) - (((CAST(((SUM (resolved_half1) OVER () + SUM(opened_half1) OVER ()) - (SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ())) / ((COUNT(resolved_half1) OVER () + COUNT(opened_half1) OVER ()) / 2) as float) - CAST(((SUM(resolved_half2) OVER () + SUM(opened_half2) OVER ()) / (COUNT(resolved_half2) OVER () + COUNT (opened_half2) OVER ())) as float)) / (CAST(((COUNT(c.period) OVER ()) / 4) as float) - CAST( (((COUNT(c.period) OVER ()) / 4) * 3) as float))) * (((COUNT(c.period) OVER ()) / 4) * 3)))) as trend,
ROW_NUMBER() OVER(ORDER BY c.yearClosed,c.weekClosed) as row

FROM
    (SELECT *, CAST(yearClosed as varchar(5)) + ', ' + CAST(weekClosed as varchar(5)) AS period
     FROM  (SELECT        TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS resolved_half1, { fn WEEK(date_closed) } AS weekClosed, { fn YEAR(date_closed) } AS yearClosed
                          FROM            v_rpt_Service
      WHERE (date_closed >= DateAdd(Day, DateDiff(Day, 0, GetDate()) - (180), 0))

      GROUP BY { fn WEEK(date_closed) }, { fn YEAR(date_closed) }) AS a 
      LEFT OUTER JOIN
      (SELECT TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS opened_half1, { fn WEEK(date_entered) } AS weekEntered, { fn YEAR(date_entered) 
       FROM v_rpt_Service AS v_rpt_Service_1
       WHERE (date_entered > = DateAdd(Day, DateDiff(Day, 0, GetDate()) - (180), 0))
       GROUP BY { fn WEEK(date_entered) }, { fn YEAR(date_entered) }) AS b ON a.weekClosed = b.weekEntered AND a.yearClosed = b.yearEntered) as c 
       LEFT OUTER JOIN
       (SELECT *, CAST(yearClosed as varchar(5)) + ', ' + CAST(weekClosed as varchar(5)) AS period 
       FROM  (SELECT TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS resolved_half2, { fn WEEK(date_closed) } AS weekClosed, { fn YEAR(date_closed) } AS yearClosed
       FROM v_rpt_Service
       WHERE (date_closed >= DateAdd(Day, DateDiff(Day, 0, GetDate()) - (180 / 2), 0))
       GROUP BY { fn WEEK(date_closed) }, { fn YEAR(date_closed) }) AS d 
       LEFT OUTER JOIN
       (SELECT TOP (100) PERCENT COUNT(DISTINCT TicketNbr) AS opened_half2, { fn WEEK(date_entered) } AS weekEntered, { fn YEAR(date_entered)} AS yearEntered
       FROM v_rpt_Service AS v_rpt_Service_1
       WHERE (date_entered > = DateAdd(Day, DateDiff(Day, 0, GetDate()) - (180 / 2), 0))
       GROUP BY { fn WEEK(date_entered) }, { fn YEAR(date_entered) }) AS e ON d.weekClosed = e.weekEntered AND d.yearClosed = e.yearEntered
) as f ON c.yearClosed = f.yearClosed AND c.weekClosed = f.weekClosed AND c.weekEntered = f.weekEntered AND c.yearEntered = f.yearEntered AND c.period = f.period
GROUP BY c.period, resolved_half1,resolved_half2,opened_half1,opened_half2,c.yearClosed,c.weekClosed
ORDER BY row

此代码使用180天的硬编码值。我仍然需要能够使用varibale来选择天数（没有得到除以0的错误），并且代码确实需要清理。 如果有人可以为我做这两件事（我不是最好的SQL），那么赏金就是他们的。

图像：

Chart

答案 2 :(得分：0)

我相信这会解决问题 - 如果不发布一些实际的样本数据，我会看看是否可以调整它来修复它：

DECLARE @noOfDays INT
SET @noofdays = 180

;WITH tickets AS
(
SELECT DISTINCT
DATENAME(YEAR,date_closed) + RIGHT('000' + CAST(DATEPART(WEEK,date_closed) AS VARCHAR(5)),3) as Period
,ticket_nbr
,1 as ticket_type --resolved
FROM v_rpt_Service
WHERE (date_closed >= DateAdd(Day, DateDiff(Day, 0, GetDate()) - @NoOfDays, 0)) 
UNION ALL
SELECT DISTINCT
DATENAME(YEAR,date_closed) + RIGHT('000' + CAST(DATEPART(WEEK,date_closed) AS VARCHAR(5)),3) as Period
,ticket_nbr
,0 as ticket_type --opened
FROM v_rpt_Service
WHERE  (date_entered > = DateAdd(Day, DateDiff(Day, 0, GetDate()) - @NoOfDays, 0)) 
)
,tickets2 AS
(
SELECT
Period
,SUM(CASE WHEN ticket_type = 0 THEN 1 ELSE 0 END) as opened
,SUM(CASE WHEN ticket_type = 1 THEN 1 ELSE 0 END) as closed
FROM tickets
GROUP BY
Period
)
,tickets3 AS
(
SELECT
Period
,row_number() OVER (ORDER BY period ASC) as row
,opened
,closed
,COUNT(period) OVER() as base
,SUM(opened) OVER () as [Sumopened]
,SUM(opened * opened) OVER () as [Sumopened^2]
,SUM(opened * closed) OVER () as [Sumopenedclosed]
,SUM(closed) OVER () as [Sumclosed]
,SUM(closed * closed) OVER () as [Sumclosed^2]
,SUM(opened * closed) OVER () * COUNT(period) OVER () AS [nSumopenedclosed]
,SUM(opened) OVER () * SUM(closed) OVER () AS [Sumopened*Sumclosed]
,SUM(opened * opened) OVER () * COUNT(period) OVER () AS [nSumopened^2]
,SUM(opened) OVER () * SUM(opened) OVER () as [Sumopened*Sumopened]
FROM tickets2
)
--Formula for linear regression is Y = A + BX
SELECT
period
,opened
,closed
,((1.0 / base) * [Sumclosed]) - 
([Sumopenedclosed] - ([Sumopened*Sumclosed] / base)) / ([Sumopened^2] - ([Sumopened*Sumopened] / base)) *((1.0 / base) * [Sumopened]) 
+ row * ([Sumopenedclosed] - ([Sumopened*Sumclosed] / base)) / ([Sumopened^2] - ([Sumopened*Sumopened] / base))  
AS trend_point
,((1.0 / base) * [Sumclosed]) - 
([Sumopenedclosed] - ([Sumopened*Sumclosed] / base)) / ([Sumopened^2] - ([Sumopened*Sumopened] / base)) *((1.0 / base) * [Sumopened]) AS A
,([Sumopenedclosed] - ([Sumopened*Sumclosed] / base)) / ([Sumopened^2] - ([Sumopened*Sumopened] / base)) as B
from tickets3
相关问题
最新问题