evaluation(on:)
Evaluates the classifier on the provided labeled data.
Declaration
func evaluation(on labeledData: DataFrame) -> MLRegressorMetricsParameters
- labeledData:
A
DataFrameto evaluate the trained model on.
Return Value
Metrics that describe the maximum error (maximumError) or the average error (rootMeanSquaredError).
Discussion
Evaluation should be done on a testing data set that the model has not seen as part of the training or validation data sets. The data should have feature columns with identical name and type to the training data, as well as a labels column with the same name.