def test_implicit_serialization(data):
train, test = data
model = ImplicitFactorizationModel(loss='bpr',
n_iter=3,
batch_size=1024,
learning_rate=1e-2,
l2=1e-6,
use_cuda=CUDA)
model.fit(train)
mrr_original = mrr_score(model, test, train=train).mean()
mrr_recovered = mrr_score(_reload(model), test, train=train).mean()
assert mrr_original == mrr_recovered
def test_bpr_bloom(compression_ratio, expected_mrr):
interactions = movielens.get_movielens_dataset('100K')
train, test = random_train_test_split(interactions,
random_state=RANDOM_STATE)
user_embeddings = BloomEmbedding(interactions.num_users,
32,
compression_ratio=compression_ratio,
num_hash_functions=2)
item_embeddings = BloomEmbedding(interactions.num_items,
32,
compression_ratio=compression_ratio,
num_hash_functions=2)
network = BilinearNet(interactions.num_users,
interactions.num_items,
user_embedding_layer=user_embeddings,
item_embedding_layer=item_embeddings)
model = ImplicitFactorizationModel(loss='bpr',
n_iter=10,
batch_size=1024,
learning_rate=1e-2,
l2=1e-6,
representation=network,
use_cuda=CUDA)
model.fit(train)
print(model)
mrr = mrr_score(model, test, train=train).mean()
assert mrr + EPSILON > expected_mrr
def evaluate_model(model, train, test, validation):
start_time = time.time()
model.fit(train, verbose=True)
elapsed = time.time() - start_time
print('Elapsed {}'.format(elapsed))
print(model)
if hasattr(test, 'sequences'):
test_mrr = sequence_mrr_score(model, test)
val_mrr = sequence_mrr_score(model, validation)
else:
test_mrr = mrr_score(model, test)
val_mrr = mrr_score(model, test.tocsr() + validation.tocsr())
return test_mrr, val_mrr, elapsed
def test_hinge():
interactions = movielens.get_movielens_dataset('100K')
train, test = random_train_test_split(interactions,
random_state=RANDOM_STATE)
model = ImplicitFactorizationModel(loss='hinge',
n_iter=10,
batch_size=1024,
learning_rate=1e-2,
l2=1e-6,
use_cuda=CUDA)
model.fit(train)
mrr = mrr_score(model, test, train=train).mean()
assert mrr + EPSILON > 0.07
def test_bpr_custom_optimizer():
interactions = movielens.get_movielens_dataset('100K')
train, test = random_train_test_split(interactions,
random_state=RANDOM_STATE)
def adagrad_optimizer(model_params, lr=1e-2, weight_decay=1e-6):
return torch.optim.Adagrad(model_params,
lr=lr,
weight_decay=weight_decay)
model = ImplicitFactorizationModel(loss='bpr',
n_iter=10,
batch_size=1024,
optimizer_func=adagrad_optimizer,
use_cuda=CUDA)
model.fit(train)
mrr = mrr_score(model, test, train=train).mean()
assert mrr + EPSILON > 0.05