SQL 按 Top 3 和其他对行进行分组。 （按州和其他排名前 3 名的城市的收入）
Posted
技术标签:
【中文标题】SQL 按 Top 3 和其他对行进行分组。 （按州和其他排名前 3 名的城市的收入）【英文标题】：SQL group rows by Top 3 and other. (Revenue by Top 3 cities by state and then other) 【发布时间】：2019-07-01 17:17:26 【问题描述】：所以我有一个查询，它提供了我的每个城市、对应的州以及我的客户在该城市花费的价值。
我想按每个城市的 TotalCustomerValue 来定义前 3 名。
查询比这复杂一点，但这是它的核心：
SELECT DISTINCT
--*
LTRIM(RTRIM(cs.City)) City
,LTRIM(RTRIM(cs.State)) State
,SUM(cs.TotalCustomerValueOverBase) over (partition by cs.City, cs.State) TotalCustomerValue
,SUM(cs.TotalOrdersBase) over (partition by cs.City, cs.State) TotalOrders
FROM ( -- This table gives full customer information per customer.
)CSS
我想要做的是创建一个表格，其中包含每个州的前 3 个城市，然后是另一行（将被视为每隔一行），它将是所有其他城市的总和。所以总表将有 200 行，(50*4)。
我正在尝试用行号做一些事情，但我似乎无法工作
,ROW_NUMBER() over (partition by cs.City, cs.State Order by sum(CS.TotalCustomerValueOverBase)) rowNr
然后我可以尝试将所有大于 3 的行号相加。
有人有什么想法吗？
然后我假设 s-s-rS 当我想用这些数据创建视觉效果时，我可以使用关键字“其他”在所有行上创建一个过滤器，对吧？
这是我的完整查询（尝试实施 Gordon 的解决方案）
SELECT
(case when CSS.seqnum <= 3 then city else 'Others' end) as city,
(case when seqnum <= 3 then state end) as state
sum(TotalCustomerValue) as TotalCustomerValue,
sum(TotalOrders) as TotalOrders
FROM
(
SELECT DISTINCT
--*
LTRIM(RTRIM(cs.City)) City
,LTRIM(RTRIM(cs.State)) State
,right(left(lat, len(lat) -1),len(lat) -2) lat -- the lat and long are wrapped in quotes
,right(left(lng, len(lng) -1),len(lng) -2) lng -- so i have to do the left right to get rid of them.
,SUM(cs.TotalCustomerValueOverBase) over (partition by cs.City, cs.State) TotalCustomerValue
,SUM(cs.TotalOrdersBase) over (partition by cs.City, cs.State) TotalOrders
--,SUM(cs.TotalQuantityOverBase) over (partition by cs.City, cs.State) TotalQuantity
,CONVERT(float, right(left(population_proper, len(population_proper) -1),len(population_proper) -2)) population_proper
,CAST(
SUM(cs.TotalOrdersBase) over (partition by cs.City, cs.State)
/
NULLIF(convert(float, right(left(population_proper, len(population_proper) -1),len(population_proper) -2)),0)--*100
as decimal(10,4)) AS OrderDensityPercent
,SUM(cs.BrandNewCustomer) over (partition by cs.City, cs.State) BrandNewCustomers
,SUM(cs.RecurringCustomer) over (partition by cs.City, cs.State) RecurringCustomers
,SUM(cs.ReactivatedCustomer) over (partition by cs.City, cs.State) ReactivatedCustomers
,row_number() over (partition by ltrim(rtrim(cs.State)) order by sum(cs.TotalCustomerValueOverBase) desc) as seqnum
FROM ( -- This table gives full customer information per customer.
SELECT
CC.CustomerEmail
,CC.Month Month
,CONCAT(CC.Year, '-', CASE WHEN CC.Month < 10 then '0' else '' end, CC.Month) Date
,CASE WHEN
( ISNULL(CC.TotalOrdersCustomerBase,0) >= 1
AND ISNULL(RC.TotalOrdersRecurringBase,0) = 0
AND ISNULL(LC.TotalOrdersLifetimeBase,0) = 0)
THEN 1 ELSE 0 END BrandNewCustomer
,CASE WHEN
( ISNULL(CC.TotalOrdersCustomerBase,0) >= 1
AND ISNULL(RC.TotalOrdersRecurringBase,0) >= 1)
THEN 1 ELSE 0 END RecurringCustomer
,CASE WHEN
( ISNULL(CC.TotalOrdersCustomerBase,0) >= 1
AND ISNULL(RC.TotalOrdersRecurringBase,0) = 0
AND ISNULL(LC.TotalOrdersLifetimeBase,0) >= 1)
THEN 1 ELSE 0 END ReactivatedCustomer
,ISNULL(CC.TotalCustomerValueOverCustomerBase,0) TotalCustomerValueOverCustomerBase
,ISNULL(CC.TotalOrdersCustomerBase,0) TotalOrdersCustomerBase
,ISNULL(CC.TotalQuantityOverCustomerBase,0) TotalQuantityOverCustomerBase
,ISNULL(RC.TotalCustomerValueOverRecurringBase,0) TotalCustomerValueOverRecurringBase
,ISNULL(RC.TotalOrdersRecurringBase,0) TotalOrdersRecurringBase
,ISNULL(RC.TotalQuantityOverRecurringBase,0) TotalQuantityOverRecurringBase
,ISNULL(LC.TotalCustomerValueOverLifetimeBase,0) TotalCustomerValueOverLifetimeBase
,ISNULL(LC.TotalOrdersLifetimeBase,0) TotalOrdersLifetimeBase
,ISNULL(LC.TotalQuantityOverLifetimeBase,0) TotalQuantityOverLifetimeBase
,ISNULL(FC.TotalCustomerValueOverBase,0) TotalCustomerValueOverBase
,ISNULL(FC.TotalOrdersBase,0) TotalOrdersBase
,ISNULL(FC.TotalQuantityOverBase,0) TotalQuantityOverBase
,ISNULL(CC.TotalCustomersOverCustomerBase,0) TotalCustomersOverCustomerBase
,ISNULL(RC.TotalCustomersOverRecurringBase,0) TotalCustomersOverRecurringBase
,ISNULL(LC.TotalCustomersOverLifetimeBase,0) TotalCustomersOverLifetimeBase
,ISNULL(FC.TotalCustomersOverBase,0) TotalCustomersOverBase
,CC.City
,CC.State
,CC.CountryCode
From
(
SELECT
C.CustomerEmail
,C.Month
,C.Year
,C.TotalCustomersOverCustomerBase
,C.TotalCustomerValueOverCustomerBase
,C.TotalOrdersCustomerBase
,C.TotalQuantityOverCustomerBase
,C.City
,C.State
,C.CountryCode
FROM
#CustomerBase C
WHERE C.OrderCountCustomerBase = 1 -- This makes it return only the first row of a customer with multiple purchases.
--and TotalOrdersCustomerBase = TotalQuantityOverCustomerBase
) CC
LEFT JOIN
(
SELECT
R.CustomerEmail
,R.TotalCustomersOverRecurringBase
,R.TotalCustomerValueOverRecurringBase
,R.TotalOrdersRecurringBase
,R.TotalQuantityOverRecurringBase
FROM
#RecurringBase R
WHERE R.OrderCountRecurringBase = 1
) RC ON CC.CustomerEmail = RC.CustomerEmail
LEFT JOIN
(
SELECT
L.CustomerEmail
,L.TotalCustomersOverLifetimeBase
,L.TotalCustomerValueOverLifetimeBase
,L.TotalOrdersLifetimeBase
,L.TotalQuantityOverLifetimeBase
FROM
#LifetimeBase L
WHERE L.OrderCountLifetimeBase = 1
) LC ON CC.CustomerEmail = LC.CustomerEmail
LEFT JOIN
(
SELECT
F.CustomerEmail
,F.TotalCustomersOverBase
,F.TotalCustomerValueOverBase
,F.TotalOrdersBase
,F.TotalQuantityOverBase
FROM
#FullBase F
WHERE F.OrderCountBase = 1
) FC ON CC.CustomerEmail = FC.CustomerEmail
) Cs --Customers
LEFT JOIN [A1Warehouse].[dbo].[uscities] Ci ON cs.City = right(left(ci.city_ascii, len(ci.city_ascii) -1),len(ci.city_ascii) -2) and cs.State = right(left(ci.state_id, len(ci.state_id) -1),len(ci.state_id) -2)
WHERE
LAT IS NOT NULL
AND LNG IS NOT NULL
group by ltrim(rtrim(cs.City)), ltrim(rtrim(cs.State))
)CSS
Where CAST(CSS.LAT AS FLOAT) > 20 AND CAST(CSS.LNG AS FLOAT) > -120
group by (case when seqnum <= 3 then city else 'Others' end),
(case when seqnum <= 3 then state end)
ORDER BY TotalCustomerValue DESC
【问题讨论】：
如何定义“前三名”？ 我已经通过 TotalCustomerValue 添加了该信息 【参考方案1】：您可以使用两个级别的聚合和一些条件逻辑：
select (case when seqnum <= 3 then city else 'Others' end) as city,
state,
sum(TotalCustomerValue) as TotalCustomerValue,
sum(TotalOrders) as TotalOrders
from (select ltrim(rtrim(cs.City)) as City, ltrim(rtrim(cs.State)) as State,
sum(cs.TotalCustomerValueOverBase) as TotalCustomerValue,
sum(cs.TotalOrdersBase) as TotalOrders,
row_number() over (partition by ltrim(rtrim(cs.State)) order by sum(cs.TotalCustomerValueOverBase) desc) as seqnum
from . . . cs
group by ltrim(rtrim(cs.City)), ltrim(rtrim(cs.State))
) cs
group by (case when seqnum <= 3 then city else 'Others' end),
(case when seqnum <= 3 then state end)
编辑：
根据评论，您可以：
select (case when seqnum <= 3 then city else 'Others' end) as city,
(case when seqnum <= 3 then state end) as state,
sum(TotalCustomerValue) as TotalCustomerValue,
sum(TotalOrders) as TotalOrders
from (select ltrim(rtrim(cs.City)) as City, ltrim(rtrim(cs.State)) as State,
sum(cs.TotalCustomerValueOverBase) as TotalCustomerValue,
sum(cs.TotalOrdersBase) as TotalOrders,
row_number() over (partition by ltrim(rtrim(cs.State)) order by sum(cs.TotalCustomerValueOverBase) desc) as seqnum
from . . . cs
group by ltrim(rtrim(cs.City)), ltrim(rtrim(cs.State))
) cs
group by (case when seqnum <= 3 then city else 'Others' end),
state
【讨论】：
戈登，我已经尝试实施您的解决方案，但我似乎无法让它发挥作用。我已经编辑了我的原始问题以包含完整的查询和我尝试集成您的代码。我做错了吗？ 问题似乎出在group by上，我想不通。 我得到了查询，但它把所有其他的都当作一个大桶，我试图每个州做一个其他桶。那可能吗？ i.imgur.com/95OYAn7.png @Natan 。 . .你只需要调整GROUP BY。以上是关于SQL 按 Top 3 和其他对行进行分组。 （按州和其他排名前 3 名的城市的收入）的主要内容，如果未能解决你的问题，请参考以下文章
Django：将价格注释到行，然后按字段对行进行分组，并将价格总和注释到组