It looks like you need a Cartesian product between the bag and yourself. To do this, you need to use FLATTEN (bag) twice.
The code:
inpt = load '.../group.txt' using PigStorage(',') as (id, val);
grp = group inpt by (id);
id_grp = foreach grp generate group as id, inpt.val as value_bag;
result = foreach id_grp generate id, FLATTEN(value_bag) as v1, FLATTEN(value_bag) as v2;
dump result;
, . , TOP (...) FLATTEN:
inpt = load '....group.txt' using PigStorage(',') as (id, val);
grp = group inpt by (id);
id_grp = foreach grp generate group as id, inpt.val as values;
result = foreach id_grp {
limited_bag = TOP(50, 0, values); -- all sorts of filtering could be done here
generate id, FLATTEN(limited_bag) as v1, FLATTEN(limited_bag) as v2;
};
dump result;
FLATTEN:
inpt = load '..../group.txt' as (id, val);
grp = group inpt by (id);
id_grp = foreach grp generate group as id, inpt.val as values;
result = foreach id_grp {
l = filter values by val == 'b1' or val == 'b2';
generate id, FLATTEN(l) as v1, FLATTEN(values) as v2;
};
result = filter result by v1 != v2;
, .