# setup from mlwpy import* %matplotlib inline
Regression is the process of predicting a finely graded numerical value from inputs. To illustrate, we need a simple dataset that has numerical results.
sklearn comes with the diabetes dataset that will serve us nicely. The dataset consists of several biometric and demographic measurements. The version included with
sklearn has been modified from raw numerical features by subtracting the mean and dividing by the standard deviation of each column. That process is called standardizing or z-scoring the features. We’ll return to the standard deviation later; briefly, it is a measure of how spread ...