blob: 3b4a6fe78f38b67bebd0930f6169008bde4603f9 [file] [log] [blame]
drop dataverse fuzzyjoin if exists;
create dataverse fuzzyjoin;
use dataverse fuzzyjoin;
create type UserType as open {
uid: int32,
name: string,
lottery_numbers: [int32],
interests: <string>
}
create nodegroup group1 if not exists on nc1, nc2;
create dataset Users(UserType) partitioned by key uid on group1;
load dataset Users from nc1:'data/users-visitors-small/users.json';
write output to nc1:'rttest/fuzzyjoin_user-lot-aqlplus_1.adm';
set simthreshold '.5f';
for $user in dataset('Users')
for $user2 in dataset('Users')
where $user.lottery_numbers ~= $user2.lottery_numbers and $user.uid < $user2.uid
order by $user.uid, $user2.uid
return { 'user': $user, 'user2': $user2 }