Evaluator for ML models

This module belongs to the ""Evaluation and fine-tuning" category of modules.

The Evaluator Module serves to evaluate the trained model , making uses of different metrics such as accuracy, F1 Score etc.

The input ports

Trained model, features and labels: every set goes into its own input port.

The output port

Parameters

As evaluation metrics, we have the option between:

• Accuracy

• Adjusted mutual info

• Adjusted Random

• Average precision

• Balanced accuracy

• Brier score loss

• Completeness

• Explained variance

• F1score

• Fowlkes Mallows

• Homogeneity

• Cross entropy loss

• Mean absolute error

• Mean squared error

• Median absolute error

• Mean squared error

• Mean squared log error

• Median absolute error

• Mutual info

• Precision

• ROC AUC

• Recall

• V-Measure