def read_node2vec_result(path):
print('读入，node2vec的结果')
node_list, edge_list = return_node_list_and_edge_list()
serialNumber_listIndex_dict = nodeSerialNumber_listIndex_dict_generation(
node_list)
node2vec_result_file = open(path, mode='r')
lines = node2vec_result_file.readlines()
lines.pop(0) # 第一行包含：节点个数 节点嵌入后的维度
for line in lines:
arr = line.strip().split(' ')
serial_number = int(arr[0])
arr.pop(0)
node_list[
serialNumber_listIndex_dict[serial_number]].embedded_vector = arr
for node in node_list:
if len(node.embedded_vector) != 64:
print('node2vec读入有问题')
node2vec_result_file.close()
def read_node2vec_result(path):
print('read node2vec result')
node_list, edge_list = return_node_list_and_edge_list()
serialNumber_listIndex_dict = nodeSerialNumber_listIndex_dict_generation(node_list)
node2vec_result_file = open(path, mode='r')
lines = node2vec_result_file.readlines()
lines.pop(0) # 第一行包含：节点个数 节点嵌入后的维度
for line in lines:
arr = line.strip().split(' ')
serial_number = int(arr[0])
arr.pop(0)
node_list[serialNumber_listIndex_dict[serial_number]].embedded_vector = arr
count_node_without_node2vecResult = 0
for node in node_list:
if len(node.embedded_vector) != 64:
count_node_without_node2vecResult += 1
node.embedded_vector = [0] * 64
print(f'没有node2vec结果的节点数：{count_node_without_node2vecResult}')
node2vec_result_file.close()
def reduce_dataset_mentainConnected(G, ratio, list_interaction,
list_negativeInteraction, list_lncRNA,
list_protein):
print(f'reduce the dataset to its {ratio}')
# 确定要删减的数据的数量
len_list_interaction = len(list_interaction)
len_list_negativeInteraction = len(list_negativeInteraction)
num_delete_interaction = int(
len(list_interaction) - (len(list_interaction) * ratio))
num_delete_negativeInteraction = int(
len(list_negativeInteraction) -
(len(list_negativeInteraction) * ratio))
# 创建从serial_number到索引的字典，方便找到lncRNA, protein
dict_serialNumber_listIndex_lncRNA = nodeSerialNumber_listIndex_dict_generation(
list_lncRNA)
dict_serialNumber_listIndex_protein = nodeSerialNumber_listIndex_dict_generation(
list_protein)
# 打乱
random.shuffle(list_interaction)
random.shuffle(list_negativeInteraction)
# 从list_interaction中删除
num_deleted_positive = 0
num_deleted_negative = 0
delete_positive = True
count = 0
while num_deleted_positive + num_deleted_negative < num_delete_interaction + num_delete_negativeInteraction:
# 挑选正例来删除
delete_positive = not delete_positive
if delete_positive == True and num_deleted_positive < num_delete_interaction:
index_interaction = random.sample(
range(0, len_list_interaction - num_deleted_positive), 1)[0]
interaction = list_interaction[index_interaction]
# 定位到interaction对应的lncRNA和protein
index_lncRNA = dict_serialNumber_listIndex_lncRNA[
interaction.lncRNA.serial_number]
index_protein = dict_serialNumber_listIndex_protein[
interaction.protein.serial_number]
lncRNA = list_lncRNA[index_lncRNA]
protein = list_protein[index_protein]
# 判断删除这个相互作用，会不会使数据集的二部图成为非连通图
G_temp = G.copy()
e = (lncRNA.serial_number, protein.serial_number)
G_temp.remove_edge(*e)
num_connectedComponent_G_temp = len(
list(nx.connected_components(G_temp)))
if num_connectedComponent_G_temp == 1:
# 删除这个条边，二部图还是一个连通分量
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G = G_temp
del list_interaction[index_interaction]
num_deleted_positive += 1
elif num_connectedComponent_G_temp == 2 and len(
lncRNA.interaction_list) == 1:
# 删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的lncRNA
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G_temp.remove_node(lncRNA.serial_number)
G = G_temp
del list_interaction[index_interaction]
num_deleted_positive += 1
elif num_connectedComponent_G_temp == 2 and len(
protein.interaction_list) == 1:
# 删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的protein
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G_temp.remove_node(protein.serial_number)
G = G_temp
del list_interaction[index_interaction]
num_deleted_positive += 1
# 回收垃圾
gc.collect()
elif delete_positive == False and num_deleted_negative < num_delete_negativeInteraction:
# 挑选负例来删除
index_interaction = random.sample(
range(0, len_list_negativeInteraction - num_deleted_negative),
1)[0]
interaction = list_negativeInteraction[index_interaction]
# 定位到interaction对应的lncRNA和protein
index_lncRNA = dict_serialNumber_listIndex_lncRNA[
interaction.lncRNA.serial_number]
index_protein = dict_serialNumber_listIndex_protein[
interaction.protein.serial_number]
lncRNA = list_lncRNA[index_lncRNA]
protein = list_protein[index_protein]
# 判断删除这个相互作用，会不会使数据集的二部图成为非连通图
G_temp = G.copy()
e = (lncRNA.serial_number, protein.serial_number)
G_temp.remove_edge(*e)
num_connectedComponent_G_temp = len(
list(nx.connected_components(G_temp)))
if num_connectedComponent_G_temp == 1:
# 删除这个条边，二部图还是一个连通分量
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G = G_temp
del list_negativeInteraction[index_interaction]
num_deleted_negative += 1
elif num_connectedComponent_G_temp == 2 and len(
lncRNA.interaction_list) == 1:
# 删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的lncRNA
# print('删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的lncRNA')
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G_temp.remove_node(lncRNA.serial_number)
G = G_temp
del list_negativeInteraction[index_interaction]
num_deleted_negative += 1
elif num_connectedComponent_G_temp == 2 and len(
protein.interaction_list) == 1:
# 删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的protein
# print('删除这条边，二部图变成两个连通分量，其中小的那个只包含一个孤立的protein')
delete_interaction_from_lncRNA_protein(lncRNA, protein)
G_temp.remove_node(protein.serial_number)
G = G_temp
del list_negativeInteraction[index_interaction]
num_deleted_negative += 1
# 回收垃圾
gc.collect()
if count % 100 == 0:
print(
f'number of positive samples need to be deleted: {num_delete_interaction-num_deleted_positive}，number of negative samples need to be deleted: {num_delete_negativeInteraction-num_deleted_negative}'
)
count += 1
print('reduce process done')