sbr
An implementation of sequence recommenders based on the wyrm autdifferentiaton library.
sbr-rs
sbr
implements efficient recommender algorithms which operate on
sequences of items: given previous items a user has interacted with,
the model will recommend the items the user is likely to interact with
in the future.
Example
You can fit a model on the Movielens 100K dataset in about 10 seconds:
let mut data = download_movielens_100k.unwrap;
let mut rng = from_seed;
let = user_based_split;
let train_mat = train.to_compressed;
let test_mat = test.to_compressed;
println!;
let mut model = new
.embedding_dim
.learning_rate
.l2_penalty
.lstm_variant
.loss
.optimizer
.num_epochs
.rng
.build;
let start = now;
let loss = model.fit.unwrap;
let elapsed = start.elapsed;
let train_mrr = mrr_score.unwrap;
let test_mrr = mrr_score.unwrap;
println!;
License: MIT