About when using DatasetPure.build_trainset

[kyorisann]

HI! I am trying to use the data from movie rens. The algorithm is NFC_neural_collaborative_filtering. When "DatasetPure.build_trainset" is used to split the data during training, Is the data of user and item encoded? If so, when looking at the original data of user and item after the prediction, is it correct to map the original ID from "data_info.user2id"? Is this correct?

[massquantity]

Yes, DatasetPure.build_trainset will encode the data. The predict function will convert the original user and item internally, so you do not need to map it by yourself.