我有一个包含大约10亿行的数据库，我们需要它来确定集合中的年龄中位数。对十亿行进行排序是困难的，但如果你将可以找到的不同值(年龄范围从0到100)聚合在一起，你可以对这个列表进行排序，并使用一些算术魔术来找到你想要的任何百分位数，如下所示:

with rawData(count_value) as
(
    select p.YEAR_OF_BIRTH
        from dbo.PERSON p
),
overallStats (avg_value, stdev_value, min_value, max_value, total) as
(
  select avg(1.0 * count_value) as avg_value,
    stdev(count_value) as stdev_value,
    min(count_value) as min_value,
    max(count_value) as max_value,
    count(*) as total
  from rawData
),
aggData (count_value, total, accumulated) as
(
  select count_value, 
    count(*) as total, 
        SUM(count(*)) OVER (ORDER BY count_value ROWS UNBOUNDED PRECEDING) as accumulated
  FROM rawData
  group by count_value
)
select o.total as count_value,
  o.min_value,
    o.max_value,
    o.avg_value,
    o.stdev_value,
    MIN(case when d.accumulated >= .50 * o.total then count_value else o.max_value end) as median_value,
    MIN(case when d.accumulated >= .10 * o.total then count_value else o.max_value end) as p10_value,
    MIN(case when d.accumulated >= .25 * o.total then count_value else o.max_value end) as p25_value,
    MIN(case when d.accumulated >= .75 * o.total then count_value else o.max_value end) as p75_value,
    MIN(case when d.accumulated >= .90 * o.total then count_value else o.max_value end) as p90_value
from aggData d
cross apply overallStats o
GROUP BY o.total, o.min_value, o.max_value, o.avg_value, o.stdev_value
;

这个查询取决于你的db支持窗口函数(包括ROWS UNBOUNDED precede)，但如果你没有，这是一个简单的事情，将aggData CTE与自身连接，并将所有先前的总数聚合到' cumulative '列，用于确定哪个值包含指定的预分词。上面的示例计算p10、p25、p50(中位数)、p75和p90。

屁股的

你也可以选择在存储过程中这样做:

DROP PROCEDURE IF EXISTS median;
DELIMITER //
CREATE PROCEDURE median (table_name VARCHAR(255), column_name VARCHAR(255), where_clause VARCHAR(255))
BEGIN
  -- Set default parameters
  IF where_clause IS NULL OR where_clause = '' THEN
    SET where_clause = 1;
  END IF;

  -- Prepare statement
  SET @sql = CONCAT(
    "SELECT AVG(middle_values) AS 'median' FROM (
      SELECT t1.", column_name, " AS 'middle_values' FROM
        (
          SELECT @row:=@row+1 as `row`, x.", column_name, "
          FROM ", table_name," AS x, (SELECT @row:=0) AS r
          WHERE ", where_clause, " ORDER BY x.", column_name, "
        ) AS t1,
        (
          SELECT COUNT(*) as 'count'
          FROM ", table_name, " x
          WHERE ", where_clause, "
        ) AS t2
        -- the following condition will return 1 record for odd number sets, or 2 records for even number sets.
        WHERE t1.row >= t2.count/2
          AND t1.row <= ((t2.count/2)+1)) AS t3
    ");

  -- Execute statement
  PREPARE stmt FROM @sql;
  EXECUTE stmt;
END//
DELIMITER ;


-- Sample usage:
-- median(table_name, column_name, where_condition);
CALL median('products', 'price', NULL);

在某些情况下，中位数的计算如下:

“中位数”是数字列表中按值排序时的“中间”值。对于偶数集，中位数是两个中间值的平均值。 我为此创建了一个简单的代码:

$midValue = 0;
$rowCount = "SELECT count(*) as count {$from} {$where}";

$even = FALSE;
$offset = 1;
$medianRow = floor($rowCount / 2);
if ($rowCount % 2 == 0 && !empty($medianRow)) {
  $even = TRUE;
  $offset++;
  $medianRow--;
}

$medianValue = "SELECT column as median 
               {$fromClause} {$whereClause} 
               ORDER BY median 
               LIMIT {$medianRow},{$offset}";

$medianValDAO = db_query($medianValue);
while ($medianValDAO->fetch()) {
  if ($even) {
    $midValue = $midValue + $medianValDAO->median;
  }
  else {
    $median = $medianValDAO->median;
  }
}
if ($even) {
  $median = $midValue / 2;
}
return $median;

返回的$中位数将是所需的结果:-)

你可以使用这里的用户定义函数。

这是我的办法。当然，你可以把它放到一个过程中:-)

SET @median_counter = (SELECT FLOOR(COUNT(*)/2) - 1 AS `median_counter` FROM `data`);

SET @median = CONCAT('SELECT `val` FROM `data` ORDER BY `val` LIMIT ', @median_counter, ', 1');

PREPARE median FROM @median;

EXECUTE median;

你可以避免变量@median_counter，如果你替换它:

SET @median = CONCAT( 'SELECT `val` FROM `data` ORDER BY `val` LIMIT ',
                      (SELECT FLOOR(COUNT(*)/2) - 1 AS `median_counter` FROM `data`),
                      ', 1'
                    );

PREPARE median FROM @median;

EXECUTE median;

create table med(id integer);
insert into med(id) values(1);
insert into med(id) values(2);
insert into med(id) values(3);
insert into med(id) values(4);
insert into med(id) values(5);
insert into med(id) values(6);

select (MIN(count)+MAX(count))/2 from 
(select case when (select count(*) from 
med A where A.id<B.id)=(select count(*)/2 from med) OR 
(select count(*) from med A where A.id>B.id)=(select count(*)/2 
from med) then cast(B.id as float)end as count from med B) C;

 ?column? 
----------
  3.5
(1 row)

OR

select cast(avg(id) as float) from 
(select t1.id from med t1 JOIN med t2 on t1.id!= t2.id 
group by t1.id having ABS(SUM(SIGN(t1.id-t2.id)))=1) A;