B. Regression Models (20 points) B.1. Data preparation (5 points) List the relevant features which you will use for regression and explain your answer (a relevant feature is a feature that can have an impact on the glucose measures of the patients). Divide your data into a training set (70%) and a testing set (30%). All models will be trained and tested on the same splits. B.2. Regression models (10 points) Train two different regression models of your choice using the training set. Explain the rationale behind selecting each of these two algorithms. B.3. Evaluation of regression models (5 points) Evaluate the performance of your two regression models on the testing set using the following metrics: mean absolute error,mean squared error, and R-square. Based on the models evaluation results, what is the best model and why? How can you improve the performance of the models?