def post_process(predict_file):
test_entity = load_pkl('test_doc_entity_list')
true_y=load_pkl('tests_y')
file = open('../result/' + predict_file, 'rb')
predict = pickle.load(file)
file.close()
test = load_pkl('test_doc_entity')
y,y_dict=ansisy_predict(predict,test_entity)
doc_dict=ansis_doc(test)
new_y = match(y,y_dict,test_entity,doc_dict)
# p, r, f = f1(true_y, (predict > 0.5).astype(int))
p1, r1, f_1 = f1(true_y, new_y)
# print(f)
print(f_1)
print("///////")
return new_y,true_y
def delete_dev_neg_ins(self, dev_x, dev_y):
deletelist = load_pkl('dev_delete_list')
positive = 0
negetive = 0
nopair = 0
# 倒序进行删除
redelete = list(reversed(deletelist))
for p in redelete:
print('del')
del dev_x[p]
del dev_y[p]
print("finish")
print("pos" + str(positive))
print("neg" + str(negetive))
print("nopair" + str(nopair))
return dev_x, dev_y
out = Dense(1, activation='sigmoid', name='output')(res)
model = Model([inputs_indices, inputs_segment, entity1_mask, entity2_mask],
out)
model.summary()
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
return model
if __name__ == "__main__":
train_entity1_pos = load_pkl("train_pos1")
dev_entity1_pos = load_pkl("dev_pos1")
test_entity1_pos = load_pkl("test_pos1")
train_entity2_pos = load_pkl("train_pos2")
dev_entity2_pos = load_pkl("dev_pos2")
test_entity2_pos = load_pkl("test_pos2")
train_x_indices = load_pkl('train_indices')
train_x_segments = load_pkl('train_segments')
train_y = load_pkl('train_y')
dev_x_indices = load_pkl('dev_indices')
dev_x_segments = load_pkl('dev_segments')
dev_y = load_pkl('dev_y')
test_x_indices = load_pkl('test_indices')
test_x_segments = load_pkl('test_segments')
test_y = load_pkl('tests_y')
loss='binary_crossentropy',
metrics=['accuracy'])
return model
if __name__ == "__main__":
# train_entity1_pos = load_pkl("train_pos1")
# dev_entity1_pos = load_pkl("dev_pos1")
# test_entity1_pos = load_pkl("test_pos1")
# train_entity2_pos = load_pkl("train_pos2")
# dev_entity2_pos = load_pkl("dev_pos2")
# test_entity2_pos = load_pkl("test_pos2")
train_x_indices = load_pkl('train_indices')
train_x_segments = load_pkl('train_segments')
train_y = load_pkl('train_y')
dev_x_indices = load_pkl('dev_indices')
dev_x_segments = load_pkl('dev_segments')
dev_y = load_pkl('dev_y')
test_x_indices = load_pkl('test_indices')
test_x_segments = load_pkl('test_segments')
test_y = load_pkl('tests_y')
train = []
for i in range(len(train_x_indices)):
temp = []
temp.append(train_x_indices[i])
temp.append(train_x_segments[i])
# temp.append(train_entity1_pos[i])
for sen in doc:
se += 1
leng = sen.split(" ")
max_len = max(len(leng), max_len)
if len(leng) < l:
ll += 1
print("max_sen", max_sen)
print("max_len", max_len)
print("ss", ss)
print("ll", ll)
print("sen", se)
if __name__ == "__main__":
train_text = load_pkl("train_sentence")
train_pos1 = load_pkl("entity1_pos")
train_pos2 = load_pkl("entity2_pos")
train_indices = load_pkl("position1")
train_segments = load_pkl("position2")
print()
# myreader = Reader()
# train_instances, train_y, train_entity ,train_doc= myreader.read_file(name='train')
# dev_instances, dev_y, dev_entity, dev_doc = myreader.read_file(name='dev')
# test_instances, tests_y, test_entity,test_doc = myreader.read_file(name='test')
#
# train_instances,train_y, dev_instances, dev_y,train_entity,dev_entity = myreader.resign_dev(train_instances, dev_instances, train_y, dev_y, train_entity,dev_entity) # 20%
#
# train_all_doc, train_max_sentence = myreader.divide_sentence(train_instances)
# dev_all_doc, dev_max_sentence = myreader.divide_sentence(dev_instances)
def topk():
x = [100, 200, 300, 400, 500, 600]
y = [57.55, 59.01, 56.46, 60.09, 58.38, 56.92]
plt.figure(figsize=(8, 4)) # 创建绘图对象
plt.plot(x, y, "b--", linewidth=1) # 在当前绘图对象绘图（X轴，Y轴，蓝色虚线，线宽度）
plt.xlabel("K") # X轴标签
plt.ylabel("F(%)") # Y轴标签
plt.title("the performance comparison") # 图标题
plt.show() # 显示图
plt.savefig("topk_k.jpg") # 保存图
if __name__ == "__main__":
attention = load_pkl('entity_align')
# temp=[2.702659,3.7815566,3.170545 ]
# a.append(temp)
# temp = [1.0777982,1.203137,1.1610005]
# a.append(temp)
# temp = [1.0904192,0.62009156,1.1182997]
# a.append(temp)
# temp = [3.3131166,4.273107,3.8353167]
# a.append(temp)
# temp = [2.820662,2.4218264,3.0692577]
# a.append(temp)
# temp = [1.5665073,1.5812267,1.740691]
a = []
temp = [3.170545, 1.1610005, 1.1182997, 3.8353167, 3.0692577, 1.740691]
a.append(temp)
temp = [3.7815566, 1.203137, 0.62009156, 4.273107, 2.4218264, 1.5812267]
new_pre=[]
new_y=[]
index=0
for i in range(len(predict)):
if i not in delete_list:
new_pre.append(predict[i])
new_y.append(true_y[i])
new_pre=np.array(new_pre)
new_y = np.array(new_y)
# p, r, f = f1(true_y, (predict > 0.5).astype(int))
p1, r1, f_1 = f1(new_y, (new_pre > 0.5).astype(int))
# print(f)
print(f_1)
if __name__ == "__main__":
predict='0.6009433962264151_predict'
new_y,predict_y=post_process(predict)
test_entity = load_pkl('test_doc_entity_list')
train_entity = load_pkl('train_doc_entity_list')
dev_entity = load_pkl('dev_doc_entity_list')
mesh_dict = mesh_id_dict()
instance_entity_mesh = get_entity_mesh(mesh_dict,test_entity)
delete_list = delete_special_instance(instance_entity_mesh)
train_entity_mesh = get_entity_mesh(mesh_dict, train_entity)
train_delete_list = delete_special_instance(train_entity_mesh)
dev_entity_mesh = get_entity_mesh(mesh_dict, dev_entity)
dev_delete_list = delete_special_instance(dev_entity_mesh)
#
post2(predict,delete_list,new_y,predict_y)
if (predict[i] > 0.5):
intre_predict.append(1)
else:
intre_predict.append(0)
true_y = true_y.tolist()
for i in range(len(true_y)):
if i in list:
temp = true_y[i][0]
intre_true_y.append(true_y[i][0])
return intre_predict, intre_true_y
if __name__ == "__main__":
test_inter_sen_list = load_pkl('test_delete_list')
list = test_inter_sen_list[0]
file = open('../result/' + '0.5632286995515694_predict', 'rb')
predict = pickle.load(file)
file.close()
true_y = load_pkl('tests_y')
intra_predict, intra_true_y = intra_sen_classify(list, predict, true_y)
intre_predict, intre_true_y = inter_sen_classify(list, predict, true_y)
p1, r1, f_1 = f1(intra_true_y, intra_predict)
print(f_1)
p2, r2, f_2 = f1(intre_true_y, intre_predict)
print(f_2)
