"Food Style Finder" is a Map of Food to show which country an ingredient belongs to (best viewed on desktop).
This is created through vectorizing the variety of recipes around the world, and our model achieved a classification accuracy of 79% on the test data. Common ingredients, onions for example, that appear in many regional recipes are assigned to all countries with low probability. On the other hands some ingredients that appear only in specific country are assigned to the country with high probability.
This is a barycentric Newton diagram, which is inspired by Isaac Newton's visualization of the color spectrum, is to express a mixture in terms of its constituents as represented in barycentric coordinates. Similar style countries are placed nearby on the circle, and an ingredient is mapped near the country belongs to.
Node : represents ingredient
Link : is connected to the country belongs to
Data Visualization: Sho Izumo
Data Science : Masahiro Kazama