NanoSocrates/Scripts/DataBaseQueries/dataset.sql

-- To pass to Pandas
SELECT *
FROM RDFs
INNER JOIN Subjects USING (SubjectID)
INNER JOIN Relationships USING (RelationshipID)
INNER JOIN Objects USING (ObjectID);

-- To pass to Pandas for abstracts
SELECT *
FROM RDFs
INNER JOIN WikipediaAbstracts USING (MovieID);

-- To pass to Pandas for abbreviations
SELECT *
FROM Abbreviations;

-- More complex to have clean dataset
-- More complex to have clean dataset
SELECT MovieID, GROUP_CONCAT('<SOT>' || '<SUB>' || SubjectURI || '<REL>' || RelationshipURI || '<OBJ>' || ObjectURI || '<EOT>', '') as RDF_String, Abstract
FROM RDFs
INNER JOIN SubjectsCountInRDFs USING (SubjectID)
INNER JOIN RelationshipsCountInRDFs USING(RelationshipID)
INNER JOIN ObjectsCountInRDFs USING (ObjectID)
INNER JOIN ParsedSubjects USING (SubjectID)
INNER JOIN ParsedRelationships USING (RelationshipID)
INNER JOIN ParsedObjects USING (ObjectID)
INNER JOIN WikipediaAbstracts USING (MovieID)
    -- insert WHERE here
-- WHERE SubjectID = 134626
GROUP BY MovieID;