MySql分组后随机获取每组一条数据的操作

思路：先随机排序然后再分组就好了。

1、创建表：

CREATE TABLE `xdx_test` (
 `id` int(11) NOT NULL,
 `name` varchar(255) DEFAULT NULL,
 `class` varchar(255) DEFAULT NULL,
 PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;

2、插入数据

INSERT INTO xdx_test VALUES (1, '张三-1','1');
INSERT INTO xdx_test VALUES (2, '李四-1','1');
INSERT INTO xdx_test VALUES (3, '王五-1','1');
INSERT INTO xdx_test VALUES (4, '张三-2','2');
INSERT INTO xdx_test VALUES (5, '李四-2','2');
INSERT INTO xdx_test VALUES (6, '王五-2','2');
INSERT INTO xdx_test VALUES (7, '张三-3','3');
INSERT INTO xdx_test VALUES (8, '李四-3','3');
INSERT INTO xdx_test VALUES (9, '王五-3','3');

3、查询语句

SELECT * FROM 
 (SELECT * FROM xdx_test ORDER BY RAND()) a
GROUP BY a.class

4、查询结果

3 王五-1 1

5 李四-2 2

9 王五-3 3

3 王五-1 1

4 张三-2 2

7 张三-3 3

2 李四-1 1

5 李四-2 2

8 李四-3 3

补充知识：mysql实现随机获取几条数据的方法（效率和离散型比较）

sql语句有几种写法、效率、以及离散型比较

1：SELECT * FROM tablename ORDER BY RAND() LIMIT 想要获取的数据条数；

2：SELECT *FROM `table` WHERE id >= (SELECT FLOOR( MAX(id) * RAND()) FROM `table` ) ORDER BY id LIMIT 想要获取的数据条数;

3：SELECT * FROM `table` AS t1 JOIN (SELECT ROUND(RAND() * (SELECT MAX(id) FROM `table`)) AS id) AS t2 WHERE t1.id >= t2.id

ORDER BY t1.id ASC LIMIT 想要获取的数据条数;

4：SELECT * FROM `table`WHERE id >= (SELECT floor(RAND() * (SELECT MAX(id) FROM `table`))) ORDER BY id LIMIT 想要获取的数据条数;

5：SELECT * FROM `table` WHERE id >= (SELECT floor( RAND() * ((SELECT MAX(id) FROM `table`)-(SELECT MIN(id) FROM `table`)) + (SELECT MIN(id) FROM `table`))) ORDER BY id LIMIT 想要获取的数据条数;

6：SELECT * FROM `table` AS t1 JOIN (SELECT ROUND(RAND() * ((SELECT MAX(id) FROM `table`)-(SELECT MIN(id) FROM `table`))+(SELECT MIN(id) FROM `table`)) AS id) AS t2 WHERE t1.id >= t2.id ORDER BY t1.id LIMIT 想要获取的数据条数;

1的查询时间>>2的查询时间>>5的查询时间>6的查询时间>4的查询时间>3的查询时间，也就是3的效率最高。

以上6种只是单纯的从效率上做了比较；

上面的6种随机数抽取可分为2类：

第一个的离散型比较高，但是效率低；其他5个都效率比较高，但是存在离散性不高的问题；

怎么解决效率和离散型都满足条件啦？

我们有一个思路就是：写一个存储过程；

select * FROM test t1 JOIN (SELECT ROUND(RAND() * ((SELECT MAX(id) FROM test)-(SELECT MIN(id) FROM test)) + (SELECT MIN(id) FROM test)) AS id) t2 where t1.id >= t2.id limit 1

每次取出一条，然后循环写入一张临时表中；最后返回 select 临时表就OK；

这样既满足了效率又解决了离散型的问题；可以兼并二者的优点；

下面是具体存储过程的伪代码

DROP PROCEDURE IF EXISTS `evaluate_Check_procedure`;
DELIMITER ;;
CREATE DEFINER=`root`@`%` PROCEDURE `evaluate_Check_procedure`(IN startTime datetime, IN endTime datetime,IN checkNum INT,IN evaInterface VARCHAR(36))
BEGIN

-- 新建一张临时表 ,存放随机取出的数据

create temporary table if not exists xdr_authen_tmp ( 
 `ID` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '序号',
 `LENGTH` int(5) DEFAULT NULL COMMENT '字节数',
 `INTERFACE` int(3) NOT NULL COMMENT '接口',
 `XDR_ID` varchar(32) NOT NULL COMMENT 'XDR ID',
 `MSISDN` varchar(32) DEFAULT NULL COMMENT '用户号码',
 `PROCEDURE_START_TIME` datetime NOT NULL DEFAULT '0000-00-00 00:00:00' COMMENT '开始时间',
 `PROCEDURE_END_TIME` datetime DEFAULT NULL COMMENT '结束时间',
 `SOURCE_NE_IP` varchar(39) DEFAULT NULL COMMENT '源网元IP',
 `SOURCE_NE_PORT` int(5) DEFAULT NULL COMMENT '源网元端口',
 `DESTINATION_NE_IP` varchar(39) DEFAULT NULL COMMENT '目的网元IP',
 `DESTINATION_NE_PORT` int(5) DEFAULT NULL COMMENT '目的网元端口',
 `INSERT_DATE` datetime DEFAULT NULL COMMENT '插入时间',
 `EXTEND1` varchar(50) DEFAULT NULL COMMENT '扩展1',
 `EXTEND2` varchar(50) DEFAULT NULL COMMENT '扩展2',
 `EXTEND3` varchar(50) DEFAULT NULL COMMENT '扩展3',
 `EXTEND4` varchar(50) DEFAULT NULL COMMENT '扩展4',
 `EXTEND5` varchar(50) DEFAULT NULL COMMENT '扩展5',
 PRIMARY KEY (`ID`,`PROCEDURE_START_TIME`),
 KEY `index_procedure_start_time` (`PROCEDURE_START_TIME`),
 KEY `index_source_dest_ip` (`SOURCE_NE_IP`,`DESTINATION_NE_IP`),
 KEY `index_xdr_id` (`XDR_ID`) 
) ENGINE = InnoDB DEFAULT CHARSET=utf8;

BEGIN
DECLARE j INT;
DECLARE i INT;

DECLARE CONTINUE HANDLER FOR NOT FOUND SET i = 1;

-- 这里的checkNum是需要随机获取的数据数，比如随机获取10条，那这里就是10，通过while循环来逐个获取单个随机记录；

SET j = 0;
WHILE j < checkNum DO 
 set @sqlexi = concat( ' SELECT t1.ID,t1.LENGTH,t1.LOCAL_PROVINCE,t1.LOCAL_CITY,t1.OWNER_PROVINCE,t1.OWNER_CITY,t1.ROAMING_TYPE,t1.INTERFACE,t1.XDR_ID,t1.RAT,t1.IMSI,t1.IMEI,t1.MSISDN,t1.PROCEDURE_START_TIME,t1.PROCEDURE_END_TIME,t1.TRANSACTION_TYPE,t1.TRANSACTION_STATUS,t1.SOURCE_NE_IP,t1.SOURCE_NE_PORT,t1.DESTINATION_NE_IP,t1.DESTINATION_NE_PORT,t1.RESULT_CODE,t1.EXPERIMENTAL_RESULT_CODE,t1.ORIGIN_REALM,t1.DESTINATION_REALM,t1.ORIGIN_HOST,t1.DESTINATION_HOST,t1.INSERT_DATE',
    ' into @ID,@LENGTH,@LOCAL_PROVINCE,@LOCAL_CITY,@OWNER_PROVINCE,@OWNER_CITY,@ROAMING_TYPE,@INTERFACE,@XDR_ID,@RAT,@IMSI,@IMEI,@MSISDN,@PROCEDURE_START_TIME,@PROCEDURE_END_TIME,@TRANSACTION_TYPE,@TRANSACTION_STATUS,@SOURCE_NE_IP,@SOURCE_NE_PORT,@DESTINATION_NE_IP,@DESTINATION_NE_PORT,@RESULT_CODE,@EXPERIMENTAL_RESULT_CODE,@ORIGIN_REALM,@DESTINATION_REALM,@ORIGIN_HOST,@DESTINATION_HOST,@INSERT_DATE ',
    ' FROM xdr_authen t1 JOIN (SELECT ROUND(RAND() * ((SELECT MAX(id) FROM xdr_authen)-(SELECT MIN(id) FROM xdr_authen)) + (SELECT MIN(id) FROM xdr_authen)) AS id) t2',
    ' WHERE t1.PROCEDURE_START_TIME >= "',startTime,'"',
       ' AND t1.PROCEDURE_START_TIME < "',endTime,'"',' AND t1.INTERFACE IN (',evaInterface,')',
       ' and t1.id >= t2.id limit 1');
 PREPARE sqlexi FROM @sqlexi;
 EXECUTE sqlexi;
 DEALLOCATE PREPARE sqlexi;

-- 这里获取的记录有可能会重复，如果是重复数据，我们则不往临时表中插入此条数据，再进行下一次随机数据的获取。依次类推，直到随机数据取够为止；

 select count(1) into @num from xdr_authen_tmp where id = @ID;
 
 if @num > 0 or i=1 then 
  SET j = j;
 ELSE
  insert into xdr_authen_tmp(ID,LENGTH,LOCAL_PROVINCE,LOCAL_CITY,OWNER_PROVINCE,OWNER_CITY,ROAMING_TYPE,INTERFACE,XDR_ID,RAT,IMSI,IMEI,MSISDN,PROCEDURE_START_TIME,PROCEDURE_END_TIME,TRANSACTION_TYPE,TRANSACTION_STATUS,SOURCE_NE_IP,SOURCE_NE_PORT,DESTINATION_NE_IP,DESTINATION_NE_PORT,RESULT_CODE,EXPERIMENTAL_RESULT_CODE,ORIGIN_REALM,DESTINATION_REALM,ORIGIN_HOST,DESTINATION_HOST,INSERT_DATE)
  VALUES(@ID,@LENGTH,@LOCAL_PROVINCE,@LOCAL_CITY,@OWNER_PROVINCE,@OWNER_CITY,@ROAMING_TYPE,@INTERFACE,@XDR_ID,@RAT,@IMSI,@IMEI,@MSISDN,@PROCEDURE_START_TIME,@PROCEDURE_END_TIME,@TRANSACTION_TYPE,@TRANSACTION_STATUS,@SOURCE_NE_IP,@SOURCE_NE_PORT,@DESTINATION_NE_IP,@DESTINATION_NE_PORT,@RESULT_CODE,@EXPERIMENTAL_RESULT_CODE,@ORIGIN_REALM,@DESTINATION_REALM,@ORIGIN_HOST,@DESTINATION_HOST,@INSERT_DATE);
 
  SET j = j + 1;
 end if; 
 SET i=0;

END WHILE;

-- 最后我们将所有的随机数查询出来，以结果集的形式返回给后台

select ID,LENGTH,LOCAL_PROVINCE,LOCAL_CITY,OWNER_PROVINCE,OWNER_CITY,ROAMING_TYPE,INTERFACE,XDR_ID,RAT,IMSI,IMEI,MSISDN,PROCEDURE_START_TIME,PROCEDURE_END_TIME,TRANSACTION_TYPE,TRANSACTION_STATUS,SOURCE_NE_IP,SOURCE_NE_PORT,DESTINATION_NE_IP,DESTINATION_NE_PORT,RESULT_CODE,EXPERIMENTAL_RESULT_CODE,ORIGIN_REALM,DESTINATION_REALM,ORIGIN_HOST,DESTINATION_HOST,INSERT_DATE from xdr_authen_tmp;

END;
truncate TABLE xdr_authen_tmp;

END
;;
DELIMITER ;

频道导航

MySql分组后随机获取每组一条数据的操作

您可能感兴趣的文章: