Mysql 按计数计算的百分位数（不同），其中仅与视图相关（或不具有不同）

我有一个奇怪的问题，我不知道是我的语法看起来很简单，还是一个bug，或者只是不受支持

以下是我的查询，虽然有效，但速度却慢得不必要：

UPDATE table1 
    SET table1column1 = 
        (SELECT COUNT(DISTINCT table2column1) FROM table2view WHERE table2column1 <= (SELECT table2column1 FROM table2 WHERE table2.id = table1.id) )
        / 
        (SELECT COUNT(DISTINCT table2column1) FROM table2) 

       + (SELECT COUNT(DISTINCT table2column2) FROM table2view WHERE table2column2 <= (SELECT table2column2 FROM table2 WHERE table2.id = table1.id) ) 
        / 
        (SELECT COUNT(DISTINCT table2column2) FROM table2) 

       + (SELECT COUNT(DISTINCT table2column3) FROM table2view WHERE table2column3 <= (SELECT table2column3 FROM table2 WHERE table2.id = table1.id) ) 
        / (SELECT COUNT(DISTINCT table2column3) FROM table2);

同样，当我使用table2而不是table2view时，它只会正确更新第一行，并设置所有其他行的table1.table1column1=0

数学

我试图将table1.table1column1=设置为table2column1、table2column2和table2column3的百分位数之和（按id）

---

我通过计算table2columnX的不同值来计算百分位数我可能会说查询速度慢，因为它在触发触发器时重复访问表

我不是SQL专家，但我曾尝试使用临时表组合查询。您可以查看它是否有助于加快查询速度。我在下面的代码示例中使用了不同但听起来相似的列名

编辑：我以前的代码中有一个计算错误。现在更新

SELECT COUNT(id) INTO @no_of_attempts from tb2;

-- DROP TABLE IF EXISTS S1Percentiles;
-- DROP TABLE IF EXISTS S2Percentiles;
-- DROP TABLE IF EXISTS S3Percentiles;

CREATE TEMPORARY TABLE S1Percentiles (
    s1 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);

CREATE TEMPORARY TABLE S2Percentiles (
    s2 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);

CREATE TEMPORARY TABLE S3Percentiles (
    s3 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);



INSERT INTO S1Percentiles (s1, percentile)
    SELECT A.s1, ((COUNT(B.s1)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s1 from tb2) A
    INNER JOIN tb2 B
    ON B.s1 <= A.s1
    GROUP BY A.s1;

INSERT INTO S2Percentiles (s2, percentile)
    SELECT A.s2, ((COUNT(B.s2)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s2 from tb2) A
    INNER JOIN tb2 B
    ON B.s2 <= A.s2
    GROUP BY A.s2;

INSERT INTO S3Percentiles (s3, percentile)
    SELECT A.s3, ((COUNT(B.s3)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s3 from tb2) A
    INNER JOIN tb2 B
    ON B.s3 <= A.s3
    GROUP BY A.s3;

-- select * from S1Percentiles;
-- select * from S2Percentiles;
-- select * from S3Percentiles;

UPDATE tb1 A
    INNER JOIN
    (
    SELECT B.tb1_id AS id, (C.percentile + D.percentile + E.percentile) AS sum FROM tb2 B
        INNER JOIN S1Percentiles C
        ON B.s1 = C.s1
        INNER JOIN S2Percentiles D
        ON B.s2 = D.s2
        INNER JOIN S3Percentiles E
        ON B.s3 = E.s3
    ) F
    ON A.id = F.id

    SET A.sum = F.sum;

-- SELECT * FROM tb1;

DROP TABLE S1Percentiles;
DROP TABLE S2Percentiles;
DROP TABLE S3Percentiles;

这样做的目的是，它记录每个分数组的百分位数，然后用必要的数据更新tb1列，而不是重新计算每个学生行的百分位数

您还应该索引列s1、s2和s3，以优化这些列上的查询

---

注意：请根据您的db架构更新列名。还请注意，每个百分位数的计算都乘以100，因为我认为百分位数通常是这样计算的。

因此，底线是，您建议使用临时表而不是视图？有趣的是，我从未真正使用过临时表。我是否会遇到与视图类似的速度问题？当表2的长度变为1米长时，这行吗？非常感谢您的回答！能否为要更新列的值提供执行计划？如果没有这些，就很难真正弄清楚发生了什么。@Xnoise谢谢您的关注！我一弄清楚那是什么，我就给你回电话。lol现在，我倾向于一个临时表，直到COUNTDISTINCT允许相关子查询，我业余猜测这就是问题所在：

CREATE VIEW myTable.table2view AS SELECT
    table2.table2column1 AS table2column1,
    table2.table2column2 AS table2column2,
    table2.table2column2 AS table2column3,
FROM table2
GROUP BY table2.id;

SELECT COUNT(id) INTO @no_of_attempts from tb2;

-- DROP TABLE IF EXISTS S1Percentiles;
-- DROP TABLE IF EXISTS S2Percentiles;
-- DROP TABLE IF EXISTS S3Percentiles;

CREATE TEMPORARY TABLE S1Percentiles (
    s1 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);

CREATE TEMPORARY TABLE S2Percentiles (
    s2 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);

CREATE TEMPORARY TABLE S3Percentiles (
    s3 FLOAT NOT NULL,
    percentile FLOAT NOT NULL DEFAULT 0.00
);



INSERT INTO S1Percentiles (s1, percentile)
    SELECT A.s1, ((COUNT(B.s1)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s1 from tb2) A
    INNER JOIN tb2 B
    ON B.s1 <= A.s1
    GROUP BY A.s1;

INSERT INTO S2Percentiles (s2, percentile)
    SELECT A.s2, ((COUNT(B.s2)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s2 from tb2) A
    INNER JOIN tb2 B
    ON B.s2 <= A.s2
    GROUP BY A.s2;

INSERT INTO S3Percentiles (s3, percentile)
    SELECT A.s3, ((COUNT(B.s3)/@no_of_attempts)*100)
    FROM (SELECT DISTINCT s3 from tb2) A
    INNER JOIN tb2 B
    ON B.s3 <= A.s3
    GROUP BY A.s3;

-- select * from S1Percentiles;
-- select * from S2Percentiles;
-- select * from S3Percentiles;

UPDATE tb1 A
    INNER JOIN
    (
    SELECT B.tb1_id AS id, (C.percentile + D.percentile + E.percentile) AS sum FROM tb2 B
        INNER JOIN S1Percentiles C
        ON B.s1 = C.s1
        INNER JOIN S2Percentiles D
        ON B.s2 = D.s2
        INNER JOIN S3Percentiles E
        ON B.s3 = E.s3
    ) F
    ON A.id = F.id

    SET A.sum = F.sum;

-- SELECT * FROM tb1;

DROP TABLE S1Percentiles;
DROP TABLE S2Percentiles;
DROP TABLE S3Percentiles;