SPARQL object regression examples
Object regression is similar to object classification, except that a numerical
predicate value inferred from the regression model for each node. You can use the
same SPARQL queries for object regression as for object classification with the
exception that the Neptune#ml.limit
and Neptune#ml.threshold
predicates are not applicable.
The following query seeks to predict the <http://www.example.org/accountbalance>
predicate value for all the inputs of type foaf:Person
:
SELECT * WHERE { ?input a foaf:Person . SERVICE neptune-ml:inference { neptune-ml:config neptune-ml:modelType 'OBJECT_REGRESSION' ; neptune-ml:input ?input ; neptune-ml:predicate <http://www.example.org/accountbalance> ; neptune-ml:output ?output . } }
This query can be customized as follows:
SELECT * WHERE { ?input a foaf:Person . SERVICE neptune-ml:inference { neptune-ml:config neptune-ml:endpoint 'node-prediction-account-balance-endpoint' ; neptune-ml:iamRoleArn 'arn:aws:iam::0123456789:role/sagemaker-role' ; neptune-ml:batchSize "40"^^xsd:integer ; neptune-ml:timeout "1000"^^xsd:integer ; neptune-ml:modelType 'OBJECT_REGRESSION' ; neptune-ml:input ?input ; neptune-ml:predicate <http://www.example.org/accountbalance> ; neptune-ml:output ?output . } }