delete from 表 where id not in
(select max(id) from 表 group by mobilePhone,officePhone,email )
or
delete from 表 where id not in
(select min(id) from 表 group by mobilePhone,officePhone,email )
delete from 表 where id not in
(select max(id) from 表 group by mobilePhone,officePhone,email )
or
delete from 表 where id not in
(select min(id) from 表 group by mobilePhone,officePhone,email )
//查询出唯一数据的ID,并把他们导入临时表tmp中
select min(id) as mid into tmp from 表 group by mobilePhone,officePhone,email
//查询出去重后的数据并插入finally表中
insert into finally select (除ID以外的字段) from customers_1 where id in (select mid from tmp)
//查询出唯一数据的ID,并把他们导入临时表tmp中
select min(id) as mid into tmp from 表 group by mobilePhone,officePhone,email
//查询出去重后的数据并插入finally表中
insert into finally select (除ID以外的字段) from customers_1 where id in (select mid from tmp)
效率对比:用delete方法对500万数据去重(1/2重复)约4小时。4小时,很长的时间。
用临时表插入对500万数据去重(1/2重复)不到10分钟。 其实用删除方式是比较慢的,可能是边找边删除的原因吧,而使用临时表,可以将没有重复的数据ID选出来放在临时表里,再将表的信息按临时表的选择出来的ID,将它们找出来插入到新的表,然后将原表删除,这样就可以快速去重啦。 SQL语句去掉重复记录,获取重复记录
按照某几个字段名称查找表中存在这几个字段的重复数据并按照插入的时间先后进行删除,条件取决于order by 和row_num。 方法一按照多条件重复处理:
delete tmp from(
select row_num = row_number() over(partition by 字段,字段 order by 时间 desc)
from 表 where 时间> getdate()-1
) tmp
where row_num > 1
delete tmp from(
select row_num = row_number() over(partition by 字段,字段 order by 时间 desc)
from 表 where 时间> getdate()-1
) tmp
where row_num > 1
方法二按照单一条件进行去重:
delete from 表 where 主键ID not in(
select max(主键ID) from 表 group by 需要去重的字段 having count(需要去重的字段)>=1
)
delete from 表 where 主键ID not in(
select max(主键ID) from 表 group by 需要去重的字段 having count(需要去重的字段)>=1
)
注意:为提高效率如上两个方法都可以使用临时表, not in 中的表可以先提取临时表#tmp,
然后采用not exists来执行,为避免数量过大,可批量用Top控制删除量
delete top(2) from 表
where not exists (select 主键ID
from #tmp where #tmp.主键ID=表.主键ID)