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
#nn settings
epochs = 300
back_propagation_batch_size = 64
training_batch_size = 6000
min_skill_size = 0
min_member_size = 0
encoding_dim = 1000
print(K.tensorflow_backend._get_available_gpus())
t2v_model = Team2Vec()
t2v_model = load_T2V_model(t2v_model)
embedding_dim = t2v_model.model.vector_size
if dblp.ae_data_exist(file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.format(embedding_dim)):
dataset = dblp.load_ae_dataset(file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.format(embedding_dim))
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)
preprocessed_dataset = dblp.load_preprocessed_dataset()
dblp.nn_t2v_dataset_generator(t2v_model, preprocessed_dataset, output_file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.format(embedding_dim), mode='skill')
del preprocessed_dataset
dataset = dblp.load_ae_dataset(file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.format(embedding_dim))
# reparameterization trick
# instead of sampling from Q(z|X), sample epsilon = N(0,I)
print('Skill embedding options')
t2v_model_skill = Team2Vec()
t2v_model_skill = load_T2V_model(t2v_model_skill)
embedding_dim_skill = t2v_model_skill.model.vector_size
print('User embedding options')
t2v_model_user = Team2Vec()
t2v_model_user = load_T2V_model(t2v_model_user)
embedding_dim_user = t2v_model_user.model.vector_size
if dblp.ae_data_exist(
file_path='../dataset/ae_t2v_dimSkill{}_dimUser{}_tFull_dataset.pkl'.
format(embedding_dim_skill, embedding_dim_user)):
dataset = dblp.load_ae_dataset(
file_path='../dataset/ae_t2v_dimSkill{}_dimUser{}_tFull_dataset.pkl'.
format(embedding_dim_skill, embedding_dim_user))
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)
preprocessed_dataset = dblp.load_preprocessed_dataset()
dblp.nn_t2v_dataset_generator(
back_propagation_batch_size = 64
training_batch_size = 6000
min_skill_size = 0
min_member_size = 0
latent_dim = 2
print(tf.test.is_gpu_available())
t2v_model = Team2Vec()
t2v_model = load_T2V_model(t2v_model)
embedding_dim = t2v_model.model.vector_size
if dblp.ae_data_exist(file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.
format(embedding_dim)):
dataset = dblp.load_ae_dataset(
file_path='../dataset/ae_t2v_dim{}_tSkill_dataset.pkl'.format(
embedding_dim))
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)
preprocessed_dataset = dblp.load_preprocessed_dataset()
dblp.nn_t2v_dataset_generator(
#nn settings
epochs = 2000
back_propagation_batch_size = 32
training_batch_size = 6000
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)