def transfer_false_test_MF(self):
# 只需要返回一个train_mashup_api_list
# 把测试集的数据转化为训练集，按照已选服务个数划分
# 分别训练测试，得到1,2,3场景下的指标
# 正例训练集
train_mashup_id_list, train_api_id_list = [], []
Mid_Aid_set = set()
_zip = zip(self.train_data[0], self.train_data[1])
train_labels = self.train_data[-1]
for index, Mid_Aid_pair in enumerate(_zip):
if train_labels[index] and tuple(
Mid_Aid_pair) not in Mid_Aid_set: # 正例且之前未出现过
train_mashup_id_list.append(Mid_Aid_pair[0])
train_api_id_list.append(Mid_Aid_pair[1])
def certain_slt_num_split(train_mashup_id_list, train_api_id_list,
slt_num):
# 测试集
set_ = set() # 存储某个mashup，某个长度已选的数据的集合
test_mashup_id_list, test_api_id_list, grounds = [], [], []
for index, test_mashup_ids in enumerate(self.test_mashup_id_list):
m_id, slt_api_ids = test_mashup_ids[0], self.test_slt_ids[
index]
if len(slt_api_ids) == slt_num and (
m_id, len(slt_api_ids)) not in set_:
train_mashup_id_list.extend([m_id] *
slt_num) # 测试集中已选的服务作为正例,还有负例
train_api_id_list.extend(slt_api_ids)
# 同时也需要测试，跟原来格式相同
test_mashup_id_list.append(test_mashup_ids)
test_api_id_list.append(self.test_api_id_list[index])
grounds.append(self.grounds[index])
self.train_data.append(
list(zip(train_mashup_id_list,
train_api_id_list))) # 供get_U_V使用
self.test_data.append(
(test_mashup_id_list, test_api_id_list, grounds))
self.train_data, self.test_data = [], [
] # 改变格式，按照测试集已选的数目，生成几个不同的训练和测试
for i in range(1, self.args.slt_item_num + 1):
print('slt_num:', i)
print('before, train samples:{}'.format(
len(self.train_mashup_id_list)))
certain_slt_num_split(list(train_mashup_id_list),
list(train_api_id_list), i)
print('after, train samples:{}'.format(len(self.train_data[-1])))
true_train_set_path = os.path.join(
self.data_root, 'train_set_MF_{}.data'.format(i))
save_2D_list(true_train_set_path,
self.train_data[i - 1]) # 把训练集(加上了某个长度的测试集)存起来，java处理
print('transfer for MF,done!')
return self.train_data, self.test_data
def save_true_train_data(self):
# 存储训练集中的正例，供lirbec使用
# 但是选择的服务可能不同，所以同一个m_id,a_id对可能出现多次？？？ 所以新场景下的MF不用这个数据处理方法？
true_train_set_path = os.path.join(self.root_path, 'train_set.data')
if not os.path.exists(true_train_set_path):
true_train_mashup_api_pairs =[]
for index,label in enumerate(self.train_labels):
if label:
true_train_mashup_api_pairs.append(self.train_mashup_api_list[index])
save_2D_list(true_train_set_path,true_train_mashup_api_pairs)
return true_train_mashup_api_pairs
def show_text_tag_features(self, train_data, show_num=10):
"""
检查生成的mashup和api的text和tag的特征是否正常
"""
if self.old_new == 'old':
m_ids, a_ids = train_data[:-1]
instances_tuple = self.get_instances(m_ids[:show_num],
a_ids[:show_num])
elif self.old_new == 'new':
m_ids, a_ids, slt_a_ids = train_data[:-1]
instances_tuple = self.get_instances(m_ids[:show_num],
a_ids[:show_num],
slt_a_ids[:show_num])
text_tag_middle_model = Model(
inputs=[*self.model.inputs],
outputs=[
*self.model.get_layer('all_content_concatenate').input[:4]
])
mashup_text_features, apis_text_features, mashup_tag_features, apis_tag_features = text_tag_middle_model.predict(
[*instances_tuple], verbose=0)
mashup_text_features_path = os.path.join(self.model_dir,
'mashup_text_features.dat')
apis_text_features_path = os.path.join(self.model_dir,
'apis_text_features.dat')
mashup_tag_features_path = os.path.join(self.model_dir,
'mashup_tag_features.dat')
apis_tag_features_path = os.path.join(self.model_dir,
'apis_tag_features.dat')
save_2D_list(mashup_text_features_path, mashup_text_features, 'a+')
save_2D_list(apis_text_features_path, apis_text_features, 'a+')
save_2D_list(mashup_tag_features_path, mashup_tag_features, 'a+')
save_2D_list(apis_tag_features_path, apis_tag_features, 'a+')
def save(self):
# 存储训练测试样本集
save_split_train(self.train_instances_path, self.train_mashup_api_list, self.train_labels)
save_test_instance(self.test_instances_path, self.test_mashup_id_list, self.test_api_id_list)
save_2D_list(self.all_ground_api_ids_path, self.grounds)
# 新场景多存储slt_ids
if new_Para.param.data_mode == 'newScene':
save_2D_list(self.train_slt_ids_path, self.slt_api_ids_instances)
save_2D_list(self.test_slt_ids_path, self.test_slt_ids)