Optimizing a Pokémon team with simulation

Emily Robinson recently took up Pokémon on Nintendo Switch:

I recently started playing Pokémon again – “Pokémon Let’s Go Eevee” on the Nintendo Switch to be specific. In the classic Pokémon games, you have a team of 6 Pokémon that you use to battle against other trainers. In battles, type match-ups are very important, as some types of moves are “super effective” against other types. For example, fire moves are super effective against grass Pokémon, which means they do double the damage they normally would. If you can set your team up so that you’re always optimally matched, you’re going to have a much easier time.

So, she took the natural next step for a data scientist: assemble an optimized team in R.

Tags: ,

Posted by in Pokemon, R, statistics

Tags: ,

Permalink

Charting all the Pokemon

Pokemon space

Pokemon is everywhere these days. I think it’s just something the world really needs right now. I know very little about the universe, but I do like it when people analyze fictional worlds and characters. Joshua Kunst grabbed a data dump about all the Pokemon (seriously, I don’t even know if I’m referring to them/it/thing correctly) and clustered them algorithmically. The t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm to be specific.

Tags: ,