Today I will present a guided tutorial for applying Kemp & Tenembaum's brilliant "form discovery" algorithm to a wine dataset. Ultimately, this provides a data-driven map to choose wines from, based on our tastes. If you are, like me, fond of data science, machine learning, cognition and/or a wine lover, then you might find this post interesting. Actually, if you know of ways it could be improved I'd love to hear them!] First of all, like every recipe, we'll start with a list of things we need: Essentially, in their work Kemp & Tenenbaum created an algorithm which finds the best structural representation for a dataset, without any assumption nor indication about this dimension.