Use the evaluate() method for evaluation using trained models from Database Engine 20, VAL, and UAF features.
Evaluation are done using the default trained model.
- Evaluation is supported for evaluable model-trainer functions.
- Best model is set as default model by default.
- Default model can be changed using set_model method.
Optional Arguments:
- kwargs: Specifies the keyword arguments. Accepts additional arguments required for the teradataml analytic function evaluations.
If this argument is empty, internal sampled test dataset and arguments are used for evaluation. Otherwise, all arguments required with validation data need to be passed for evaluation.
Output teradataml DataFrames can be accessed using attribute references, such as HPTEvaluateObj.<attribute_name>. Output teradataml DataFrame attribute name is: result.