First of all, we need to know which data we have as input. Here, we have two CSV files. One of them is named Products.csv, while the second is named Categories.csv. The Products.csv file contains a list of products with their names, list prices, and a CategoryID column, which is a reference to a certain category placed in the Categories.csv file. From the previous section, we know that machine learning models tend to recognize numerical values as features, but we also know that the CategoryID column is just a reference and it makes no sense for this to be a feature. This is why we need to join data from both files to create a dataset with records containing the name of the category.
Let's start to create a new project ...
