def test_dimension_methods():
movieLensDataHandler = AEDataHandler('MovieLensSmall', train_data_path,
validation_input_data_path,
validation_output_data_path,
test_input_data_path,
test_output_data_path)
assert 8936 == movieLensDataHandler.get_input_dim()
assert 8936 == movieLensDataHandler.get_output_dim()
train_data_path = os.path.join(dir_path, 'movielens_small_training.npy')
validation_input_data_path = os.path.join(
dir_path, 'movielens_small_validation_input.npy')
validation_output_data_path = os.path.join(
dir_path, 'movielens_small_validation_test.npy')
test_input_data_path = os.path.join(dir_path, 'movielens_small_test_input.npy')
test_output_data_path = os.path.join(dir_path, 'movielens_small_test_test.npy')
products_data_path = os.path.join(dir_path, 'movielens_products_data.npy')
data_handler = AEDataHandler('MovieLensSmall', train_data_path,
validation_input_data_path,
validation_output_data_path, test_input_data_path,
test_output_data_path)
input_dim = data_handler.get_input_dim()
output_dim = data_handler.get_output_dim()
products_data_np = np.load(products_data_path)
products_data_torch = torch.tensor(products_data_np,
dtype=torch.float32).to(device)
# create model
model = MultiVAE(params='yaml_files/params_multi_VAE_training.yaml')
correctness_loss = VAELoss()
revenue_loss = VAELoss(weighted_vector=products_data_torch)
losses = [correctness_loss, revenue_loss]
recallAtK = RecallAtK(k=10)
revenueAtK = RevenueAtK(k=10, revenue=products_data_np)
np.save(train_data_path, np.random.rand(10000, 8936).astype('float32'))
np.save(validation_input_data_path,
np.random.rand(2000, 8936).astype('float32'))
np.save(validation_output_data_path,
np.random.rand(2000, 8936).astype('float32'))
np.save(test_input_data_path, np.random.rand(2000, 8936).astype('float32'))
np.save(test_output_data_path, np.random.rand(2000, 8936).astype('float32'))
np.save(products_data_path, np.random.rand(8936))
dataHandler = AEDataHandler('Testing trainer random dataset', train_data_path,
validation_input_data_path,
validation_output_data_path, test_input_data_path,
test_output_data_path)
input_dim = dataHandler.get_input_dim()
output_dim = dataHandler.get_output_dim()
products_data_np = np.load(products_data_path)
products_data_torch = torch.tensor(products_data_np,
dtype=torch.float32).to(device)
# create model
model = MultiVAE(params='yaml_files/params_multi_VAE.yaml')
correctness_loss = VAELoss()
revenue_loss = VAELoss(weighted_vector=products_data_torch)
losses = [correctness_loss, revenue_loss]
recallAtK = RecallAtK(k=10)
revenueAtK = RevenueAtK(k=10, revenue=products_data_np)