Evaluation metrics

In this section, we will take a look at a few metrics that will allow us to mathematically quantify the performance of our classifiers, regressors, and filters. 

Accuracy

Accuracy is the most widely used metric to gauge the performance of a classification model. It is the ratio of the number of correct predictions to the total number of predictions made by the model:

                                                                 

Root mean square error

The Root Mean Square Error (or RMSE) is a metric widely used to gauge the performance of regressors. Mathematically, it is represented as follows:

                                                                 

Here, 

 is the i^th real target value and 

 is the i^th predicted target value.

Binary classification metrics

Sometimes, accuracy does not give us a good estimate of the performance of a model.

For instance, consider a binary class dataset where 99% of the data belongs to one class and only 1% of the data belongs to the other...