Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Custom modifications to allow better support for Magic: the Gathering card generation.
The most recent release of AllSets.json from MTGJson has some changes that break the script.
Rarities are encoded in lower-case letters only
Mythic Rare is stored as "mythic"
Time Spiral Timeshifted rarity has been moved to rare
Basic Lands are now common.
Other than a couple silver-bordered sets that need excluding to avoid all the unicode characters, it seems to work when the lower-case rarities are implemented for common through mythic. The last two merely affect how the net will associate rarities, and are less important.
I'm guessing somewhere along the way that the order that fields are fed to the neural network changed, and the script was never updated. Priming with the rarity parameter (I think) actually primes the name, and so on.
A sound plan would probably be to use the numbers that follow the fields as an identifier layer (those are less likely to change than the field order) and have the script use those as a mapping to the correct fields. This should reduce the amount of maintenance that would need to be done when column orders are changed in the future.