hive tips

cumsum

select 
    a.id,
    a.sum_all,
    sum(a.sum_all) over (order by a.sum_all, a.id
                         rows between unbounded preceding
                                  and current row)
        as csum
from
        ( select col1 as id,
                 sum(col2) as sum_all
          from t
          group by col1
        )  a
order by 
    sum_all, id ;

select 
    col1 as id,
    sum(col2) as sum_all,
    sum(sum(col2)) over (order by sum(col2), col1
                         rows between unbounded preceding
                                  and current row)
        as csum
from
    t
group by 
    col1
order by 
    sum_all, id ;