Portable Game Notation

The project started in the simplest possible way.

A friend of mine, around two thousand Elo, exported his chess.com games and sent me the PGN file.

Unfortunately, the site's export limits meant I only had about one thousand four hundred games.

That was enough to prototype the pipeline, but nowhere near enough to train our reliable model.

Interestingly, Ding Liren only had four available games through the endpoint I used.

The sample was tiny, but I decided to keep it anyway.

Building the extraction pipeline using Python Chess, I built a parser capable of reading PGN files and stopping every game at exactly move ten, which is the position later used by the models.

The core of the extraction pipeline simply iterates through each PGN game until the desired snapshot is reached.