On Canvas, you will find a data set on the quality of red wines (different than the other wine data set we have previously considered in lectures). Provide a thorough analysis attempting to predict the quality of wine according to the several predictors included in the data set. At minimum, trees, boosting, linear models, random forests, and lasso should be used…with appropriate diagnostics, cross-validation, etc. Which model is most likely to provide the lowest MSE in the long-run? Which model would you choose if you were consulting a company on this data set? If they don’t match, explain why

data link: https://drive.google.com/open?id=1l1WUrJZG8uVdPYC9kjel2meKzFwuUED0