def objective(trial):
start = time.time()
# ハイパラ読み込み
# gamma = trial.suggest_loguniform('gamma', 1e-6, 1e-3)
# lin_model = trial.suggest_categorical('lin_model', ['lasso', 'elastic'])
alpha = trial.suggest_uniform('alpha', 0, 1)
beta = trial.suggest_uniform('beta', 0, 0.5)
data_dirs = [
'../' + data_path + '/valid1/', '../' + data_path + '/valid2/'
]
score_sum = 0
for data_dir in data_dirs:
# dataload
dataset = AmazonDataset(data_dir)
# laod model
#slim = train_SLIM(data_dir, load=True)
sim_mat = load_sim_mat('sim_mat' + data_dir[-2] + '.csr',
len(dataset.user_list), len(dataset.item_list))
edges = [[r[0], r[1]] for r in dataset.triplet_df.values]
# user-itemとitem-userどちらの辺も追加
for r in dataset.triplet_df.values:
if r[2] == 0:
edges.append([r[1], r[0]])
# load network
G = nx.DiGraph()
G.add_nodes_from([i for i in range(len(dataset.entity_list))])
G.add_edges_from(edges)
evaluater = Evaluater(data_dir)
#ranking_mat = get_ranking_mat(G, slim, alpha, beta, dataset)
ranking_mat = get_ranking_mat(G, sim_mat, alpha, beta, dataset)
#score = evaluater.topn_map(ranking_mat)
score = evaluater.topn_precision(ranking_mat)
score_sum += score
mi, sec = time_since(time.time() - start)
print('{}m{}s'.format(mi, sec))
return -1 * score_sum / 2
def objective(trial):
start = time.time()
# hyper parameter
alpha = trial.suggest_uniform('alpha', 0, 0.5)
beta = trial.suggest_uniform('beta', 0, 0.5)
gamma1 = trial.suggest_uniform('gamma1', 0, 1)
gamma2 = trial.suggest_uniform('gamma2', 0, 1)
gamma3 = trial.suggest_uniform('gamma3', 0, 1)
gamma = [gamma1, gamma2, gamma3]
data_dir = ['../' + data_path + '/valid1', '../' + data_path + '/valid2']
score_sum = 0
for i in range(len(data_dir)):
# dataload
dataset = AmazonDataset(data_dir[i], model_name='TransE')
# load network
edges = [[r[0], r[1]] for r in dataset.triplet_df.values]
# user-itemとitem-userどちらの辺も追加
for r in dataset.triplet_df.values:
if r[2] == 0:
edges.append([r[1], r[0]])
G = nx.DiGraph()
G.add_nodes_from([i for i in range(len(dataset.entity_list))])
G.add_edges_from(edges)
ranking_mat = get_ranking_mat(G, dataset, model[i], gamma, alpha, beta)
evaluater = Evaluater(data_dir[i])
score = evaluater.topn_precision(ranking_mat)
score_sum += score
mi, sec = time_since(time.time() - start)
print('{}m{}sec'.format(mi, sec))
return -1 * score_sum / 2
# dataload
data_dir = '../data_luxury_5core/test/'
dataset = AmazonDataset(data_dir)
# laod model
slim_param = pickle.load(open('best_param_slim.pickle', 'rb'))
slim = train_SLIM2(data_dir, slim_param)
# load network
edges = [[r[0], r[1]] for r in dataset.triplet_df.values]
## user-itemとitem-userどちらの辺も追加
for r in dataset.triplet_df.values:
if r[2] == 0:
edges.append([r[1], r[0]])
G = nx.DiGraph()
G.add_nodes_from([i for i in range(len(dataset.entity_list))])
G.add_edges_from(edges)
evaluater = Evaluater(data_dir)
model_mat = load_sim_mat('sim_mat_test.csr', len(dataset.user_list),
len(dataset.item_list))
ranking_mat = get_ranking_mat(G, model_mat, alpha, beta, dataset)
#score = evaluater.topn_map(ranking_mat)
score = evaluater.topn_precision(ranking_mat)
mi, sec = time_since(time.time() - start)
print('{}m{}s'.format(mi, sec))
np.savetxt('score.txt', np.array([score]))
