min_skill_size = 0
min_member_size = 0
latent_dim = 100
if dblp.preprocessed_dataset_exist() and dblp.train_test_indices_exist():
train_test_indices = dblp.load_train_test_indices()
else:
if not dblp.ae_data_exist(file_path='../dataset/ae_dataset.pkl'):
dblp.extract_data(filter_journals=True,
skill_size_filter=min_skill_size,
member_size_filter=min_member_size)
if not dblp.preprocessed_dataset_exist(
) or not dblp.train_test_indices_exist():
dblp.dataset_preprocessing(
dblp.load_ae_dataset(file_path='../dataset/ae_dataset.pkl'),
seed=seed,
kfolds=k_fold,
shuffle_at_the_end=True)
dblp.load_preprocessed_dataset()
train_test_indices = dblp.load_train_test_indices()
fold_counter = 1
preprocessed_dataset = dblp.load_preprocessed_dataset()
x_train, y_train, x_test, y_test = dblp.get_fold_data(fold_counter,
preprocessed_dataset,
train_test_indices)
df_train = dblp.create_user_item(x_train, y_train)
reader = sr.Reader(rating_scale=(1, 1))
data_train = sr.Dataset.load_from_df(df_train[['userID', 'itemID', 'rating']],
reader)
df_test = dblp.create_user_item(x_test, y_test)
latent_dim = 50
print(K.tensorflow_backend._get_available_gpus())
if dblp.preprocessed_dataset_exist() and dblp.train_test_indices_exist():
dataset = dblp.load_preprocessed_dataset()
train_test_indices = dblp.load_train_test_indices()
else:
if not dblp.ae_data_exist(file_path='../dataset/ae_dataset.pkl'):
dblp.extract_data(filter_journals=True,
skill_size_filter=min_skill_size,
member_size_filter=min_member_size)
if not dblp.preprocessed_dataset_exist(
) or not dblp.train_test_indices_exist():
dblp.dataset_preprocessing(
dblp.load_ae_dataset(file_path='../dataset/ae_dataset.pkl'),
seed=seed,
kfolds=k_fold)
dataset = dblp.load_preprocessed_dataset()
train_test_indices = dblp.load_train_test_indices()
# k_fold Cross Validation
cvscores = []
# Defining evaluation scores holders for train data
r_at_k_all_train = dblp_eval.init_eval_holder(
evaluation_k_set
) # all r@k of instances in one fold and one k_evaluation_set
r_at_k_overall_train = dblp_eval.init_eval_holder(
evaluation_k_set
) # overall r@k of instances in one fold and one k_evaluation_set
min_skill_size = 0
min_member_size = 0
latent_dim = 2
beta = 30
print(tf.test.is_gpu_available())
m2v_path = '../dataset/embedding_dict.pkl'
if dblp.ae_data_exist(file_path='../dataset/ae_e_m2v_tSkill_dataset.pkl'):
dataset = dblp.load_ae_dataset(file_path='../dataset/ae_e_m2v_tSkill_dataset.pkl')
else:
if not dblp.ae_data_exist(file_path='../dataset/ae_dataset.pkl'):
dblp.extract_data(filter_journals=True, skill_size_filter=min_skill_size, member_size_filter=min_member_size, output_dir='../dataset/ae_dataset.pkl')
if not dblp.preprocessed_dataset_exist(file_path='../dataset/dblp_preprocessed_dataset.pkl') or not dblp.train_test_indices_exist(file_path='../dataset/Train_Test_indices.pkl'):
dblp.dataset_preprocessing(dblp.load_ae_dataset(file_path='../dataset/ae_dataset.pkl'), indices_dict_file_path='../dataset/Train_Test_indices.pkl', preprocessed_dataset_file_path='../dataset/dblp_preprocessed_dataset.pkl', seed=seed, kfolds=k_fold)
preprocessed_dataset = dblp.load_preprocessed_dataset(file_path='../dataset/dblp_preprocessed_dataset.pkl')
dblp.nn_m2v_embedding_dataset_generator(model_path=m2v_path, dataset=preprocessed_dataset, output_file_path='../dataset/ae_e_m2v_tSkill_dataset.pkl', mode='skill', max_length=22)
del preprocessed_dataset
dataset = dblp.load_ae_dataset(file_path='../dataset/ae_e_m2v_tSkill_dataset.pkl')
# reparameterization trick
# instead of sampling from Q(z|X), sample epsilon = N(0,I)
# z = z_mean + sqrt(var) * epsilon
def sampling(args):
"""Reparameterization trick by sampling from an isotropic unit Gaussian.
# Arguments