Applying linear regression

We have worked through a toy problem to learn how linear regression models relationships between explanatory and response variables. Now we'll use a real dataset and apply linear regression to an important task. Assume that you are at a party, and that you wish to drink the best wine that is available. You could ask your friends for recommendations, but you suspect that they will drink anything, regardless of its provenance. Fortunately, you have brought pH test strips and other tools for measuring various physicochemical properties—it is, after all, a party. We will use machine learning to predict the quality of wine based on its physicochemical attributes.

The UCI Machine Learning Repository's Wine dataset measures eleven physicochemical attributes, including pH and alcohol content, of 1,599 different red wines. Each wine's quality has been scored by human judges. The scores range from zero to ten; zero is the worst quality, and ten is the best quality. The dataset...