Processing ordinal data
Ordinal data (for instance, rankings or star values in a review) is certainly more similar to numerical data than it is to categorical data, yet we have to first consider certain differences before dealing with it plainly as a number. The problem with categorical data is that you can process it as numerical data, but probably the distance between one point and the following one in the scale is different than the distance between the following one and the next (technically the steps could be different). This is because ordinal data doesn't represent quantities, but just ordering. On the other hand, we also treat it as categorical data, because categories are independent and we will lose the information implied in the ordering. The solution for ordinal data is simply to treat it as both a numerical and a categorical variable.
Getting ready
First, we need to import the OrdinalEncoder function from scikit-learn, which will help us in numerically recoding...
