def create_1000_case_test():
li = []
bc = BertClient(ip='222.19.197.230', port=5555, port_out=5556, check_version=False)
test_text = pre_deal.get_test_textVector()
zero_vector = np.zeros((500, 768))
for i in range(0, len(test_text)):
x = tokenize.word_tokenize(test_text[i])
if (len(x) >502):
index = KMP.KMP_algorithm(test_text[i], x[500] + " " + x[501])
if (index != -1):
list = []
sentence_1 = test_text[i][0:index]
sentence_2 = test_text[i][index:]
list.append(sentence_1)
list.append(sentence_2)
vector = bc.encode(list)
ve = np.concatenate((vector[0], vector[1]), axis=0)
li.append(ve.tolist())
else:
list = []
list.append(test_text[i])
vector = bc.encode(list)
ve = np.concatenate((vector[0], zero_vector), axis=0)
li.append(ve.tolist())
else:
list = []
list.append(test_text[i])
vector = bc.encode(list)
ve = np.concatenate((vector[0], zero_vector), axis=0)
li.append(ve.tolist())
li_vector = np.array(li)
np.save("test_case_1000.npy", li_vector)
labels_tag[list_labels[j][7:16]].append(min(l1))
labels_tag[list_labels[j][7:16]].append(max(l1))
print("----------------------")
if (min(l1) == max(l1) and min(l1) > 400):
li = texts_token[j][min(l1):]
print(texts_token[j][min(l1):])
else:
li = texts_token[j][min(l1):max(l1)]
print(texts_token[j][min(l1):max(l1)])
list2 = [str(i) for i in li] # 使用列表推导式把列表中的单个元素全部转化为str类型
list3 = ' '.join(list2) # 把列表中的元素放在空串中，元素间用空格隔开
if (list3 == ''):
pass
else:
a = KMP.KMP_algorithm(test_text[j], list3)
if (a == -1):
list_gai = str(texts_token[j][min(l1)])
a = KMP.KMP_algorithm(test_text[j], list_gai) # 开始位置
print(list_labels[j][7:16])
print("值为：" + str(a))
b = a + len(list3)
print("结束值为：" + str(b))
# str_1 = random.choice(list_tc)
if (a == -1):
if (b > 100):
f.write(list_labels[j][7:16] + '\t' + str(b - 100) +
'\t' + str(b) + '\n')
else:
f.write(list_labels[j][7:16] + '\t' + str(0) + '\t' +
str(b) + '\n')
from nltk import tokenize
import KMP
from bert_serving.client import BertClient
import numpy as np
li = []
bc = BertClient(ip='222.19.197.230',
port=5555,
port_out=5556,
check_version=False)
labels_vector_dict, test_text = pre_deal.get_labels_vector()
zero_vector = np.zeros((500, 768))
for i in range(0, len(test_text)):
x = tokenize.word_tokenize(test_text[i])
if (len(x) > 502):
index = KMP.KMP_algorithm(test_text[i], x[500] + " " + x[501])
if (index != -1):
list = []
sentence_1 = test_text[i][0:index]
sentence_2 = test_text[i][index:]
list.append(sentence_1)
list.append(sentence_2)
vector = bc.encode(list)
ve = np.concatenate((vector[0], vector[1]), axis=0)
li.append(ve.tolist())
else:
list = []
list.append(test_text[i])
vector = bc.encode(list)
ve = np.concatenate((vector[0], zero_vector), axis=0)
li.append(ve.tolist())
