| drop dataverse fuzzyjoin if exists; |
| |
| create dataverse fuzzyjoin; |
| |
| use dataverse fuzzyjoin; |
| |
| create type DBLPType as open { |
| id: int32, |
| dblpid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| create type CSXType as open { |
| id: int32, |
| csxid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| create nodegroup group1 if not exists on nc1, nc2; |
| |
| create dataset DBLP(DBLPType) partitioned by key id on group1; |
| create dataset CSX(CSXType) partitioned by key id on group1; |
| |
| load dataset DBLP |
| using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter" |
| (("path"="nc1://data/pub-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":")); |
| |
| load dataset CSX |
| using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter" |
| (("path"="nc1://data/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":")); |
| |
| write output to nc1:'rttest/fuzzyjoin_dblp-csx-3_5.2.adm'; |
| |
| // |
| // -- - Stage 3 - -- |
| // |
| for $ridpair in |
| // |
| // -- - Stage 2 - -- |
| // |
| for $paperDBLP in dataset('DBLP') |
| let $idDBLP := $paperDBLP.id |
| let $tokensUnrankedDBLP := counthashed-word-tokens($paperDBLP.title) |
| let $lenDBLP := len($tokensUnrankedDBLP) |
| let $tokensDBLP := |
| for $tokenUnranked in $tokensUnrankedDBLP |
| for $tokenRanked at $i in |
| // |
| // -- - Stage 1 - -- |
| // |
| for $paper in dataset('DBLP') |
| let $id := $paper.id |
| for $token in counthashed-word-tokens($paper.title) |
| /*+ hash */ |
| group by $tokenGrouped := $token with $id |
| order by count($id), $tokenGrouped |
| return $tokenGrouped |
| where $tokenUnranked = /*+ bcast */ $tokenRanked |
| order by $i |
| return $i |
| for $prefixTokenDBLP in subset-collection( |
| $tokensDBLP, |
| 0, |
| prefix-len-jaccard(len($tokensDBLP), .5f)) |
| |
| for $paperCSX in dataset('CSX') |
| let $idCSX := $paperCSX.id |
| let $tokensUnrankedCSX := counthashed-word-tokens($paperCSX.title) |
| let $lenCSX := len($tokensUnrankedCSX) |
| let $tokensCSX := |
| for $tokenUnranked in $tokensUnrankedCSX |
| for $tokenRanked at $i in |
| // |
| // -- - Stage 1 - -- |
| // |
| for $paper in dataset('DBLP') |
| let $id := $paper.id |
| for $token in counthashed-word-tokens($paper.title) |
| /*+ hash */ |
| group by $tokenGrouped := $token with $id |
| order by count($id), $tokenGrouped |
| return $tokenGrouped |
| where $tokenUnranked = /*+ bcast */ $tokenRanked |
| order by $i |
| return $i |
| for $prefixTokenCSX in subset-collection( |
| $tokensCSX, |
| 0, |
| prefix-len-jaccard(len($tokensCSX), .5f)) |
| |
| where $prefixTokenDBLP = $prefixTokenCSX |
| |
| let $sim := similarity-jaccard-prefix( |
| $lenDBLP, |
| $tokensDBLP, |
| $lenCSX, |
| $tokensCSX, |
| $prefixTokenDBLP, |
| .5f) |
| where $sim >= .5f |
| /*+ hash*/ |
| group by $idDBLP := $idDBLP, $idCSX := $idCSX with $sim |
| return {'idDBLP': $idDBLP, 'idCSX': $idCSX, 'sim': $sim[0]} |
| |
| for $paperDBLP in dataset('DBLP') |
| for $paperCSX in dataset('CSX') |
| where $ridpair.idDBLP = $paperDBLP.id and $ridpair.idCSX = $paperCSX.id |
| order by $paperDBLP.id, $paperCSX.id |
| return {'dblp': $paperDBLP, 'csx': $paperCSX, 'sim': $ridpair.sim} |