def test_bloom(compression_ratio, expected_rmse):
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 = ExplicitFactorizationModel(loss='regression',
n_iter=10,
batch_size=1024,
learning_rate=1e-2,
l2=1e-5,
representation=network,
use_cuda=CUDA)
model.fit(train)
print(model)
rmse = rmse_score(model, test)
print(rmse)
assert rmse - EPSILON < expected_rmse
def factorization_model(num_embeddings, bloom):
if bloom:
user_embeddings = BloomEmbedding(num_embeddings, EMBEDDING_DIM,
num_hash_functions=NUM_HASH_FUNCTIONS)
item_embeddings = BloomEmbedding(num_embeddings, EMBEDDING_DIM,
num_hash_functions=NUM_HASH_FUNCTIONS)
else:
user_embeddings = ScaledEmbedding(num_embeddings, EMBEDDING_DIM)
item_embeddings = ScaledEmbedding(num_embeddings, EMBEDDING_DIM)
network = BilinearNet(num_embeddings,
num_embeddings,
user_embedding_layer=user_embeddings,
item_embedding_layer=item_embeddings)
model = ImplicitFactorizationModel(loss='adaptive_hinge',
n_iter=N_ITER,
embedding_dim=EMBEDDING_DIM,
batch_size=2048,
learning_rate=1e-2,
l2=1e-6,
representation=network,
use_cuda=CUDA)
return model
def build_sequence_model(hyperparameters, train, random_state):
h = hyperparameters
set_seed(42, CUDA)
if h['compression_ratio'] < 1.0:
item_embeddings = BloomEmbedding(
train.num_items,
h['embedding_dim'],
compression_ratio=h['compression_ratio'],
num_hash_functions=4,
padding_idx=0)
else:
item_embeddings = ScaledEmbedding(train.num_items,
h['embedding_dim'],
padding_idx=0)
network = LSTMNet(train.num_items,
h['embedding_dim'],
item_embedding_layer=item_embeddings)
model = ImplicitSequenceModel(loss=h['loss'],
n_iter=h['n_iter'],
batch_size=h['batch_size'],
learning_rate=h['learning_rate'],
embedding_dim=h['embedding_dim'],
l2=h['l2'],
representation=network,
use_cuda=CUDA,
random_state=np.random.RandomState(42))
return model
def test_bloom_pooling(compression_ratio, expected_mrr):
random_state = np.random.RandomState(RANDOM_SEED)
train, test = _get_synthetic_data(randomness=1e-03,
num_interactions=20000,
random_state=random_state)
embedding = BloomEmbedding(train.num_items,
32,
compression_ratio=compression_ratio,
num_hash_functions=2)
representation = PoolNet(train.num_items,
embedding_dim=EMBEDDING_DIM,
item_embedding_layer=embedding)
model = ImplicitSequenceModel(loss=LOSS,
representation=representation,
batch_size=BATCH_SIZE,
learning_rate=1e-2,
l2=1e-7,
n_iter=NUM_EPOCHS * 5,
random_state=random_state,
use_cuda=CUDA)
model.fit(train, verbose=VERBOSE)
mrr = _evaluate(model, test)
assert mrr.mean() > expected_mrr
def sequence_model(num_embeddings, bloom):
if bloom:
item_embeddings = BloomEmbedding(num_embeddings, EMBEDDING_DIM,
num_hash_functions=NUM_HASH_FUNCTIONS)
else:
item_embeddings = ScaledEmbedding(num_embeddings, EMBEDDING_DIM)
network = LSTMNet(num_embeddings, EMBEDDING_DIM,
item_embedding_layer=item_embeddings)
model = ImplicitSequenceModel(loss='adaptive_hinge',
n_iter=N_ITER,
batch_size=512,
learning_rate=1e-3,
l2=1e-2,
representation=network,
use_cuda=CUDA)
return model