def run_lstm_model():
if not is_file_empty("lstm_results.txt"):
with open("lstm_results.txt", "r") as lstm_results:
result_data = lstm_results.readlines()
# result_data_string = '; '.join(result_data)
return result_data
# was return result_data_string
max_sequence_length = 200
min_sequence_length = 20
step_size = 200
random_state = np.random.RandomState(100)
dataset = get_movielens_dataset('1M')
train, rest = user_based_train_test_split(dataset,
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,
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)
# mode = sys.argv[1] # was
mode = "lstm" # is
# TODO: see how to interpret the results --> you can just print out the results and later on see how to interpret them
# results = Results()
# best_results = {"results": results, "best_res_string":'best_results'}
best_results = run(
train, test, validation, random_state,
mode) # it saw the files with the results and prints the best one
# print("Best results from main: {}".format(best_results["best_res_string"]))
print(
best_results) # TODO: now figure out how to pass this to the frontend
# TODO: pass the .txt files with the results as well as the best result
# results.best()
# results.save()
return best_results
def _get_synthetic_data(num_users=100,
num_items=100,
num_interactions=10000,
randomness=0.01,
order=2,
max_sequence_length=10,
random_state=None):
interactions = synthetic.generate_sequential(
num_users=num_users,
num_items=num_items,
num_interactions=num_interactions,
concentration_parameter=randomness,
order=order,
random_state=random_state)
print('Max prob {}'.format(
(np.unique(interactions.item_ids, return_counts=True)[1] /
num_interactions).max()))
train, test = user_based_train_test_split(interactions,
random_state=random_state)
train = train.to_sequence(max_sequence_length=max_sequence_length,
step_size=None)
test = test.to_sequence(max_sequence_length=max_sequence_length,
step_size=None)
return train, test
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 test_user_based_split():
interactions = movielens.get_movielens_dataset('100K')
train, test = (cross_validation.user_based_train_test_split(
interactions, test_percentage=0.2, random_state=RANDOM_STATE))
assert len(train) + len(test) == len(interactions)
users_in_test = len(np.unique(test.user_ids))
assert np.allclose(float(users_in_test) / interactions.num_users,
0.2,
atol=0.001)
results.save(hyperparameters, test_mrr.mean(), val_mrr.mean())
return results
if __name__ == '__main__':
max_sequence_length = 200
min_sequence_length = 20
step_size = 200
random_state = np.random.RandomState(100)
dataset = get_movielens_dataset('1M')
train, rest = user_based_train_test_split(dataset,
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,
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)
# mode = sys.argv[1] # was