天池task06

-- 请使用A股上市公司季度营收预测数据集《Income Statement.xls》和《Company Operating.xlsx》和《Market Data.xlsx》，以Market Data为主表，将三张表中的TICKER_SYMBOL为600383和600048的信息合并在一起
SELECT ist.TICKER_SYMBOL,ist.END_DATE,ist.T_REVENUE,ist.T_COGS,ist.N_INCOME,
                md.TICKER_SYMBOL,md.END_DATE,md.CLOSE_PRICE,
                co.TICKER_SYMBOL,co.INDIC_NAME_EN,co.END_DATE,co.`VALUE`
FROM `income statement` ist
JOIN `company operating` co ON ist.TICKER_SYMBOL = co.TICKER_SYMBOL
JOIN `market data` md ON md.TICKER_SYMBOL = co.TICKER_SYMBOL
WHERE ist.TICKER_SYMBOL in(600383,600048)
;

-- 请使用 Wine Quality Data 数据集《winequality-red.csv》，找出 pH=3.03的所有红葡萄酒，然后，对其 citric acid 进行中式排名（相同排名的下一个名次应该是下一个连续的整数值。换句话说，名次之间不应该有“间隔”）

SELECT *, DENSE_RANK() OVER (ORDER bY `winequality-red`.`citric acid` desc) as rank_num
FROM `winequality-red`
WHERE `winequality-red`.pH=3.03;

-- 使用Coupon Usage Data for O2O中的数据集《ccf_offline_stage1_test_revised.csv》，试分别找出在2016年7月期间，发放优惠券总金额最多和发放优惠券张数最多的商家。

-- 发放优惠券总金额最多的
-- 按照优惠比率中最后数字作为优惠金额

SELECT Merchant_id,    SUM(SUBSTRING_INDEX(Discount_rate,':',-1)) as discount_amount
FROM ccf_offline_stage1_test_revised
WHERE Date_received BETWEEN '2016-07-01' AND '2016-07-31'
GROUP BY Merchant_id
ORDER bY discount_amount desc 
LIMIT 1;

-- 发放优惠券最多的
SELECT Merchant_id, count(Merchant_id) FROM ccf_offline_stage1_test_revised
GROUP By Merchant_id
ORDER BY count(Merchant_id) desc 
LIMIT 1;

-- 请使用A股上市公司季度营收预测中的数据集《Macro&Industry.xlsx》中的sheet-INDIC_DATA，请计算全社会用电量:第一产业:当月值在2015年用电最高峰是发生在哪月？并且相比去年同期增长/减少了多少个百分比？

SELECT PERIOD_DATE,MAX(DATA_VALUE) as finalvalue FROM `macro industry` 
WHERE indic_id = '2020101522' AND year(PERIOD_DATE) = 2015
GROUP BY PERIOD_DATE
ORDER BY finalvalue DESC
LIMIT 1;

SELECT concat(ROUND((fb.finalvalue - fc.finalvalue)/fc.finalvalue *100,3),'%')
FROM (SELECT PERIOD_DATE,MAX(DATA_VALUE) as finalvalue FROM `macro industry` 
WHERE indic_id = '2020101522' AND year(PERIOD_DATE) = 2015
GROUP BY PERIOD_DATE
ORDER BY finalvalue DESC
LIMIT 1) fb -- 2015年的表
LEFT JOIN (SELECT PERIOD_DATE,MAX(DATA_VALUE) as finalvalue FROM `macro industry` 
WHERE indic_id = '2020101522' AND year(PERIOD_DATE) = 2014
GROUP BY PERIOD_DATE
)  fc -- 2014年的表
ON 
YEAR(fb.PERIOD_DATE) = YEAR(fc.PERIOD_DATE) + 1
AND MONTH(fb.PERIOD_DATE) = MONTH(fc.PERIOD_DATE)

-- 使用Coupon Usage Data for O2O中的数据集《ccf_online_stage1_train.csv》，试统计在2016年6月期间，线上总体优惠券弃用率为多少？并找出优惠券弃用率最高的商家。

-- 弃用率 = 被领券但未使用的优惠券张数 / 总的被领取优惠券张数
-- 总优惠券数
SELECT sum(case WHEN date is null AND Coupon_id is not null
THEN 1 ELSE 0 end 
)/sum(CASE  WHEN
Coupon_id is not null
THEN 1 ELSE 0 end 
)  as discard_rate
FROM ccf_online_stage1_train
WHERE year(Date_received) = 2016 

SELECT Merchant_id ,sum(case WHEN date is null AND Coupon_id is not null
THEN 1 ELSE 0 end 
)/sum(CASE  WHEN
Coupon_id is not null
THEN 1 ELSE 0 end 
)  as discard_rate
FROM ccf_online_stage1_train
WHERE year(Date_received) = 2016 
GROUP BY Merchant_id
ORDER BY Merchant_id desc
LIMIT 1;

--  Wine Quality Data 数据集《winequality-white.csv》，找出 pH=3.63的所有白葡萄酒，然后，对其 residual sugar 量进行英式排名（非连续的排名）

SELECT pH,`residual sugar`, rank()OVER(order by `residual sugar`desc) as t_rank FROM 
`winequality-white`

-- 请使用A股上市公司季度营收预测中的数据集《Market Data.xlsx》中的sheet-DATA，
-- 
-- 计算截止到2018年底，市值最大的三个行业是哪些？以及这三个行业里市值最大的三个公司是哪些？（每个行业找出前三大的公司，即一共要找出9个）

SELECT TYPE_NAME_CN,sum(MARKET_VALUE) as value_m FROM `market data`
WHERE END_DATE = '2018-05-31'
GROUP BY TYPE_NAME_CN
ORDER BY value_m desc
LIMIt 3

-- 要求出每个行业前三名，可分区进行排名
 SELECT TYPE_NAME_CN,TICKER_SYMBOL,
DENSE_RANK()OVER (partition by TYPE_NAME_CN order by MARKET_VALUE  desc ) as t_rank
FROM `market data`
WHERE END_DATE = '2018-05-31' 

SELECT a.TYPE_NAME_CN,a.TICKER_SYMBOL   FROM ( SELECT TYPE_NAME_CN,TICKER_SYMBOL,
DENSE_RANK()OVER (partition by TYPE_NAME_CN order by MARKET_VALUE  desc ) as t_rank
FROM `market data`
WHERE END_DATE = '2018-05-31' 
) as a
JOIN (SELECT TYPE_NAME_CN,sum(MARKET_VALUE) as value_m FROM `market data`
WHERE END_DATE = '2018-05-31'
GROUP BY TYPE_NAME_CN
ORDER BY value_m desc
LIMIt 3) as b
ON a.TYPE_NAME_CN = b.TYPE_NAME_CN
WHERE t_rank <=3
LIMIT 9

-- 使用Coupon Usage Data for O2O中的数据集《ccf_online_stage1_train.csv》和《ccf_offline_stage1_train.csv》，试找出在2016年6月期间，线上线下累计优惠券使用次数最多的顾客。
SELECT user_id ,sum(c) as custom_u FROM (
SELECT user_id,count(*) as c FROM ccf_online_stage1_train
WHERE Date_received BETWEEN '2016-06-01' AND '2016-06-30'
AND Date_received is not null 
AND Date is NOT NULL 
GROUP bY user_id
union all 
SELECT user_id,count(*)  as c FROM ccf_offline_stage1_train
WHERE Date_received BETWEEN '2016-06-01' AND '2016-06-30'
AND Date_received is not null 
AND Date is NOT NULL 
GROUP bY user_id) as data_base 
GROUP BY user_id 
ORDER BY custom_u DESC
LIMIT 1

-- 请使用A股上市公司季度营收预测数据集《Income Statement.xls》中的sheet-General Business和《Company Operating.xlsx》中的sheet-EN。
-- 
-- 找出在数据集所有年份中，按季度统计，白云机场旅客吞吐量最高的那一季度对应的净利润是多少？（注意，是单季度对应的净利润，非累计净利润。）

SELECT TICKER_SYMBOL,year(END_DATE) as y,QUARTER(END_DATE) as q,
sum(`VALUE`) OVER (partition BY year(END_DATE),QUARTER(END_DATE) ) amount FROM `company operating`
WHERE INDIC_NAME_EN = 'Baiyun Airport:Passenger throughput'
GROUP BY TICKER_SYMBOL,year(END_DATE) ,QUARTER(END_DATE)
ORDER BY sum(`VALUE`)  DESC

SELECT TICKER_SYMBOL,y , q,MAX(amount)  FROM (SELECT TICKER_SYMBOL,year(END_DATE) as y,QUARTER(END_DATE) as q,
sum(`VALUE`) OVER (partition BY year(END_DATE),QUARTER(END_DATE) ) amount FROM `company operating`
WHERE INDIC_NAME_EN = 'Baiyun Airport:Passenger throughput'
GROUP BY TICKER_SYMBOL,year(END_DATE) ,QUARTER(END_DATE)
ORDER BY sum(`VALUE`)  DESC)as data_amount
GROUP BY y

-- 使用Coupon Usage Data for O2O中的数据集《ccf_online_stage1_train.csv》和《ccf_offline_stage1_train.csv》，试找出在2016年6月期间，线上线下累计被使用优惠券满减最多的前3名商家。
-- 
-- 比如商家A，消费者A在其中使用了一张200减50的，消费者B使用了一张30减1的，那么商家A累计被使用优惠券满减51元。

SELECT Merchant_id,user_id,    SUM(SUBSTRING_INDEX(Discount_rate,':',-1)) as discount_amount
FROM ccf_offline_stage1_test_revised
WHERE Date_received BETWEEN '2016-07-01' AND '2016-07-31'
GROUP BY user_id
ORDER bY discount_amount desc 

SELECT Merchant_id,    SUM(SUBSTRING_INDEX(Discount_rate,':',-1)) as discount_amount
FROM ccf_online_stage1_train
WHERE Date != NULL AND Coupon_id != NULL
AND Date BETWEEN '2016-06-01' AND '2016-06-30'
GROUP BY Merchant_id

SELECT Merchant_id,    SUM(SUBSTRING_INDEX(Discount_rate,':',-1)) as discount_amount
FROM ccf_offline_stage1_train
WHERE Date != NULL AND Coupon_id != NULL
AND Date BETWEEN '2016-06-01' AND '2016-06-30'
GROUP BY Merchant_id

-- 提供的答案

select Merchant_id,sum(discount_amount) discount_amount FROM
(SELECT Merchant_id,sum(SUBSTRING_INDEX(Discount_rate,':',-1)) as discount_amount
FROM ccf_online_stage1_train
WHERE (Date != null AND Coupon_id != null)
AND LEFT (DATE,4)=2016
AND MONTH(date) = 6
GROUP BY Merchant_id
UNION aLL
SELECT Merchant_id,sum(SUBSTRING_INDEX(Discount_rate,':',-1))as discount_amount
FROM ccf_offline_stage1_train
WHERE (Date != null AND Coupon_id != null)
AND LEFT (DATE,4)=2016
AND MONTH(date)=6
GROUP BY Merchant_id

) basedata
GROUP BY Merchant_id
ORDER BY sum(discount_amount) desc
LIMIT 1;