Error Analysis
In the previous chapter, we explained the importance of error analysis. In this section, the different evaluation metrics will be calculated for all three models that were created in the previous activities, so that we can compare them.
Keep in mind that the selection of an evaluation metric is done according to the purpose of the case study. Nonetheless, next, we will compare the models using the accuracy, precision, and recall metrics, for learning purposes. This way, it will be possible to see that even though a model may be better in terms of one metric, it can be worse when measuring a different metric, which helps to emphasize the importance of choosing the right metric.
Accuracy, Precision, and Recall
As a quick reminder, in order to measure performance and perform error analysis, it is required that you use the predict method on the different sets of data (training, validation, and testing). The following code snippets present a clean way of measuring...
