def generate_dataset_table():
headers = ['Dataset', 'Users', 'Items', 'Density', '95th/50th']
rows = []
for name, dataset in (('Movielens 10M', get_movielens_dataset('10M')),
('Amazon', get_amazon_dataset()),
('Goodbooks', get_goodbooks_dataset())):
item_counts = dataset.tocoo().getnnz(axis=0)
print('Dataset {}, ratio: {:0,}'
.format(name, np.percentile(item_counts, 95) / np.percentile(item_counts, 50)))
row = [
name,
'{:0,}'.format(dataset.num_users),
'{:0,}'.format(dataset.num_items),
len(dataset) / dataset.num_users / dataset.num_items,
'{0:.2f}'.format(np.percentile(item_counts, 95) / np.percentile(item_counts, 50))
]
rows.append(row)
return _full_width_table(
tabulate(rows,
headers=headers,
floatfmt='.4f',
tablefmt='latex_booktabs'))
def main(args):
status = 'available' if CUDA else 'not available'
print("CUDA is {}!".format(status))
args = parse_args(args)
# Fix random_state
seed = 72
set_seed(seed)
random_state = np.random.RandomState(seed)
max_sequence_length = 100
min_sequence_length = 20
step_size = max_sequence_length
if args.dataset == 'amazon':
max_sequence_length = 50
min_sequence_length = 5
step_size = max_sequence_length
dataset = get_amazon_dataset()
elif args.dataset == 'goodbooks':
dataset = get_goodbooks_dataset()
else:
dataset = get_movielens_dataset(args.dataset.upper())
args.variant = args.dataset
train, rest = user_based_train_test_split(
dataset,
test_percentage=0.2,
random_state=random_state)
test, valid = user_based_train_test_split(
rest,
test_percentage=0.5,
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)
valid = valid.to_sequence(
max_sequence_length=max_sequence_length,
min_sequence_length=min_sequence_length,
step_size=step_size)
print('model: {}, data: {}'.format(args.model, train))
fname = 'experiment_{}_{}.pickle'.format(args.model, args.dataset)
objective = get_objective(train, valid, test, random_state)
space = hyperparameter_space(args.model)
for iteration in range(args.num_trials):
print('Iteration {}'.format(iteration))
trials = optimize(objective,
space,
trials_fname=fname,
max_evals=iteration + 1)
summarize_trials(trials)
def load_data(dataset, random_state):
if 'goodbooks' in dataset:
dataset = get_goodbooks_dataset()
elif 'amazon' in dataset:
dataset = get_amazon_dataset()
else:
dataset = get_movielens_dataset(dataset)
train, rest = random_train_test_split(dataset,
test_percentage=0.05,
random_state=random_state)
test, validation = random_train_test_split(rest,
test_percentage=0.5,
random_state=random_state)
return train, validation, test
def load_data(dataset, random_state):
max_sequence_length = 100
min_sequence_length = 20
step_size = max_sequence_length
if 'goodbooks' in dataset:
dataset = get_goodbooks_dataset()
elif 'amazon' in dataset:
dataset = get_amazon_dataset()
# This is a dataset with shorter sequences
max_sequence_length = 50
min_sequence_length = 5
step_size = max_sequence_length
else:
dataset = get_movielens_dataset(dataset)
train_nonsequence, rest = user_based_train_test_split(
dataset, test_percentage=0.2, random_state=random_state)
test, validation = user_based_train_test_split(rest,
test_percentage=0.5,
random_state=random_state)
train = train_nonsequence.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)
validation = validation.to_sequence(
max_sequence_length=max_sequence_length,
min_sequence_length=min_sequence_length,
step_size=step_size)
return train_nonsequence, train, validation, test
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('dataset', type=str)
parser.add_argument('model', type=str)
args = parser.parse_args()
random_state = np.random.RandomState(100)
if args.dataset == 'movielens':
dataset = get_movielens_dataset('1M')
test_percentage = 0.2
else:
test_percentage = 0.01
dataset = get_amazon_dataset(min_user_interactions=20,
min_item_interactions=5)
print(dataset)
if args.model == 'sequence':
max_sequence_length = int(
np.percentile(dataset.tocsr().getnnz(axis=1), 95))
min_sequence_length = 20
step_size = max_sequence_length
train, rest = user_based_train_test_split(dataset,
test_percentage=0.05,
random_state=random_state)
test, validation = user_based_train_test_split(
rest, test_percentage=0.5, random_state=random_state)
train = train.to_sequence(max_sequence_length=max_sequence_length,
parser.add_argument('--variant', type=str, default='100K')
parser.add_argument('--n_epoch', type=int, default='20')
parser.add_argument('--loss', type=str, default='bpr')
parser.add_argument('--lr', type=float, default=1e-4)
parser.add_argument('--sparsity', type=float, default=0.05)
parser.add_argument('--data', type=str, default='synthetic')
args = parser.parse_args()
if str(args.data) == 'synthetic':
split, dataset = make_synthetic(args.sparsity)
elif str(args.data).lower() == 'movielens':
print('MovieLens')
dataset = get_movielens_dataset(variant=args.variant)
split = 0.2
elif str(args.data).lower() == 'amazon':
print('Amazon')
dataset = get_amazon_dataset()
split = 0.2
else:
print('GoodBook')
dataset = get_goodbooks_dataset()
split = 0.2
rmses = []
mrrs = []
rs = np.random.RandomState(100)
pdb.set_trace()
for i in range(5):
print('Split - {} , Run {}'.format(split, i))
train, test = random_train_test_split(dataset,
random_state=rs,
test_percentage=split)
if args.model == 'implicit':