Hive报错"Expression not in GROUP BY key"

select user_id,
       distance
  from table a
 group by user_id

这是由于根据user_id做group by时，每个user_id存在多个distance，考虑只保留一个distance或使用collect_set函数。

select user_id,
       min(distance)
  from table a
 group by user_id

select user_id,
       collect_set(distance) as distances
  from table a
 group by user_id