The scoring APIs are documented in the javadoc. After installation, you can invoke Scorer in the following ways (the code blocks show high-level method calls to invoke scorer).
Scoring Requests from File System
This usage provides a simple interface to test scorer functionality.
// initialize Scorer scorer = new Scorer (); // configure // make sure that AML file modelFile is available on file system scorer.configure (modelFile); // run scorer (multiple calls) // make sure that CSV file requestFile is available on file system scorer.score (requestFile);
Scoring Requests Using API
Teradata recommends this usage in a production environment. By preventing the I/O overheads from populating and reading request files from the file system, it improves performance.
// initialize Scorer scorer = new Scorer (); // configure // make sure that AML file modelFile is available on file system Request request = scorer.configure (modelFile); // populate data structure request // run scorer (multiple calls) scorer.score (request);