def evaluate_cnn_model(hyperparameters, train, test, validation, random_state):
h = hyperparameters
net = CNNNet(train.num_items,
embedding_dim=h['embedding_dim'],
kernel_width=h['kernel_width'],
dilation=h['dilation'],
num_layers=h['num_layers'],
nonlinearity=h['nonlinearity'],
residual_connections=h['residual'])
model = ImplicitSequenceModel(loss=h['loss'],
representation=net,
batch_size=h['batch_size'],
learning_rate=h['learning_rate'],
l2=h['l2'],
n_iter=h['n_iter'],
use_cuda=CUDA,
random_state=random_state)
model.fit(train, verbose=True)
test_mrr = sequence_mrr_score(model, test)
val_mrr = sequence_mrr_score(model, validation)
return test_mrr, val_mrr
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 test_implicit_cnn_dilation_synthetic(num_layers, dilation, expected_mrr):
random_state = np.random.RandomState(RANDOM_SEED)
train, test = _get_synthetic_data(randomness=1e-03,
num_interactions=20000,
random_state=random_state)
model = ImplicitSequenceModel(loss=LOSS,
representation=CNNNet(
train.num_items,
embedding_dim=EMBEDDING_DIM,
kernel_width=3,
dilation=dilation,
num_layers=num_layers),
batch_size=BATCH_SIZE,
learning_rate=1e-2,
l2=0.0,
n_iter=NUM_EPOCHS * 5 * num_layers,
random_state=random_state,
use_cuda=CUDA)
model.fit(train, verbose=VERBOSE)
mrr = _evaluate(model, test)
assert mrr.mean() > expected_mrr
def data_implicit_sequence():
max_sequence_length = 200
min_sequence_length = 20
step_size = 200
interactions = movielens.get_movielens_dataset('100K')
train, test = user_based_train_test_split(interactions,
random_state=RANDOM_STATE)
train = train.to_sequence(max_sequence_length=max_sequence_length,
min_sequence_length=min_sequence_length,
step_size=step_size)
test = test.to_sequence(max_sequence_length=max_sequence_length,
min_sequence_length=min_sequence_length,
step_size=step_size)
model = ImplicitSequenceModel(loss='adaptive_hinge',
representation='lstm',
batch_size=8,
learning_rate=1e-2,
l2=1e-3,
n_iter=2,
use_cuda=CUDA,
random_state=RANDOM_STATE)
model.fit(train, verbose=True)
return train, test, 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_implicit_pooling_synthetic(randomness, expected_mrr):
random_state = np.random.RandomState(RANDOM_SEED)
train, test = _get_synthetic_data(randomness=randomness,
random_state=random_state)
model = ImplicitSequenceModel(loss=LOSS,
batch_size=BATCH_SIZE,
embedding_dim=EMBEDDING_DIM,
learning_rate=1e-1,
l2=1e-9,
n_iter=NUM_EPOCHS,
random_state=random_state,
use_cuda=CUDA)
model.fit(train, verbose=VERBOSE)
mrr = _evaluate(model, test)
assert mrr.mean() > expected_mrr
def evaluate_pooling_model(hyperparameters, train, test, validation,
random_state):
h = hyperparameters
model = ImplicitSequenceModel(loss=h['loss'],
representation='pooling',
batch_size=h['batch_size'],
learning_rate=h['learning_rate'],
l2=h['l2'],
n_iter=h['n_iter'],
use_cuda=CUDA,
random_state=random_state)
model.fit(train, verbose=True)
test_mrr = sequence_mrr_score(model, test)
val_mrr = sequence_mrr_score(model, validation)
return test_mrr, val_mrr
def test_implicit_sequence_serialization(data):
train, test = data
train = train.to_sequence(max_sequence_length=128)
test = test.to_sequence(max_sequence_length=128)
model = ImplicitSequenceModel(loss='bpr',
representation=CNNNet(train.num_items,
embedding_dim=32,
kernel_width=3,
dilation=(1, ),
num_layers=1),
batch_size=128,
learning_rate=1e-1,
l2=0.0,
n_iter=5,
random_state=RANDOM_STATE,
use_cuda=CUDA)
model.fit(train)
mrr_original = sequence_mrr_score(model, test).mean()
mrr_recovered = sequence_mrr_score(_reload(model), test).mean()
assert mrr_original == mrr_recovered
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
