Evaluating Feature Scores Using a Learn Model (lkt_rleval)

The following command is used to evaluate a feature vector on a TIBCO Patterns Learn Model.

dvkerr_t lkt_rleval(lpar_t host, lpar_t modelname, lpar_t indata, 
                     lpar_t *outdata );

Input

host (optional)

This is used to identify the server. For more information, see Communicating with TIBCO Patterns Servers

This is used to identify the server. For more information, see Communicating with TIBCO Patterns Servers

This is used to identify the server. For more information, see Communicating with Servers.

modelname (required)

is the name of the model (LPAR_STR_RLMODELNAME) to be used.

indata (required)

must be a generic list containing an lpar of type LPAR_DBLARR_RLFEATUREVEC, which is an array of double feature values (from 0.0 to 1.0, or -1.0 for a missing feature value) which are evaluated by the model. The number and meaning of features in this array must be identical to the features used when training the model.

Output

outdata (required)

is a generic list (LPAR_LST_GENERIC) containing one value of type LPAR_DBL_RLRLINKSCORE in the range of 0.0 to 1.0. This value is the evaluation result produced by the model for the given feature vector.

 

Error codes and items returned by lkt_rleval

NORLINKMODEL
PARAMVAL
PARAMMISSING
RLINKMODELNOTFOUND
NOFEATUREVEC
NUMFEATURESMISMATCH