def interview(self):
model = BLSTMModel.load_model("../健康管理师分字BERT-model")
x_items, train_y = self.read_message('../data/健康管理师分类数据集/test.txt')
model.evaluate(x_items, train_y)
results_string: str = ''
train_string: str = ''
for i in x_items:
results_string += model.predict(i)
for j in train_y:
train_string += j
if len(results_string) == len(train_string):
print('预测结果', results_string, '正确结果', train_string)
print('五个五个去判断 全等就是做对了不全等就是做错了')
a = len(train_string)
b: float = a / 5
right: int = 0
for i in range(int(b)):
var = results_string[5 * i:5 * (i + 1)]
result = train_string[5 * i:5 * (i + 1)]
if var == result:
print('做对了')
right += 1
else:
print('做错了', var, result)
acc = b - right
print('正确答案', right, '错误答案', acc)
print('准确率', right / b)
def interview(self):
model = BLSTMModel.load_model("../西药执业药师-model")
x_items, train_y = self.read_message('../data/西药执业药师/test.txt')
model.evaluate(x_items, train_y)
results_string: str = ''
train_string: str = ''
for i in x_items:
results_string += model.predict(i)
for j in train_y:
train_string += j
if len(results_string) == len(train_string):
print('五个五个去判断 全等就是做对了不全等就是做错了')
a = len(train_string)
b: int = int(a / 5)
print('验证数据集长度', b)
right: int = 0
for i in range(int(b)):
single = x_items[b * 5:b * 5 + 1]
var = results_string[5 * i:5 * (i + 1)]
result = train_string[5 * i:5 * (i + 1)]
if var == result:
print('做对了', single)
right += 1
else:
print('做错了', var, result, single)
acc = b - right
print('正确答案', right, '错误答案', acc)
print('准确率', right / b)
def test_save_and_load(self):
self.test_fit()
model_path = tempfile.gettempdir()
self.model.save(model_path)
new_model = BLSTMModel.load_model(model_path)
self.assertIsNotNone(new_model)
sentence = list('语言学包含了几种分支领域。')
result = new_model.predict(sentence)
self.assertTrue(isinstance(result, str))
def test_save_and_load(self):
self.test_fit()
model_path = os.path.join(tempfile.gettempdir(), 'kashgari_model',
str(time.time()))
self.model.save(model_path)
new_model = BLSTMModel.load_model(model_path)
assert new_model is not None
sentence = list('语言学包含了几种分支领域。')
result = new_model.predict(sentence)
assert isinstance(result, str)
def interview(self):
model = BLSTMModel.load_model("../健康管理师单选分字BERT-model")
x_items, train_y = self.read_message('../data/yingyangshi/test.txt')
x_full = self.full_message('../data/yingyangshi/test.txt')
model.evaluate(x_items, train_y)
results_string: str = ''
train_string: str = ''
right_predict: list = []
wrong_predict: list = []
for i in x_items:
results_string += model.predict(i)
for j in train_y:
train_string += j
if len(results_string) == len(train_string):
print('预测结果', results_string, '正确结果', train_string)
print('五个五个去判断 全等就是做对了不全等就是做错了')
a = len(train_string)
b: int = int(a / 5)
print('验证数据集长度', b)
right: int = 0
for i in range(b):
start_single: int = i * 5
end_single: int = (i + 1) * 5
single = x_full[start_single:end_single]
var = results_string[start_single:end_single]
result = train_string[start_single:end_single]
if var == result:
print('做对了')
right_predict.append(single)
for varey in single:
print(varey)
right += 1
else:
print('做错了', var, result)
wrong_predict.append(single)
for varey in single:
print(varey)
acc = b - right
with open('wrong single.csv', 'w', newline='',
encoding='utf-8') as csv_file:
csv_writer = csv.writer(csv_file)
for wrong_list in wrong_predict:
for message in wrong_list:
wrong_list = message.split('\t')
csv_writer.writerow(wrong_list)
with open('right single.csv', 'w', newline='',
encoding='utf-8') as csv_file:
csv_writer = csv.writer(csv_file)
for right_list in right_predict:
for message in right_list:
message = message.split('\t')
csv_writer.writerow(message)
print('正确答案', right, '错误答案', acc)
print('准确率', right / b)
def test_dataset(model_dir: str) -> list:
# 从数据库中获取正文并使用模型进行预测分类，
# 预测结果写回数据库
conn = pymysql.connect(host=DB_HOST,
port=int(DB_PORT),
user=DB_USER,
password=DB_PASS,
db=DB_NAME,
charset=DB_CHARSET
)
cursor = conn.cursor()
cursor.execute("""
SELECT `page_text`,`page_title`,`category`,`hash` FROM `webpage_text`
WHERE `%s_predict` IS NULL ORDER BY `time` desc
""" % model_dir.split('.model')[0].split('/')[-1]
)
all_text = []
data = cursor.fetchall()
# 判断预测使用的模型
if 'cnn.model' in model_dir:
model = CNNModel.load_model(model_dir)
elif 'cnnlstm.model' in model_dir:
model = CNNLSTMModel.load_model(model_dir)
elif 'blstm.model' in model_dir:
model = BLSTMModel.load_model(model_dir)
for i in tqdm.tqdm(data):
label = i[2]
# 将文章分词，拼接标题与正文
content = strip_stopwords(list(jieba.cut(i[0] + '。' + i[1])))
all_text += content
predict = model.predict(content)
cursor.execute(
'UPDATE `webpage_text` SET {model}_predict="{predict}"'.format(model=model_dir.split('.model')[0].split('/')[-1],predict=predict)+
'WHERE hash="%s"' % i[3]
)
conn.commit()
# print('[+] Predict:'+predict+', Label:'+label+', Title:'+i[1])
# 计算词频并将排行前100的热词写入数据库
c = Counter(all_text)
i = 1
cursor.execute(
'DELETE FROM `hot_key` WHERE 1=1'
)
conn.commit()
for k,v in c.most_common(100):
if len(k) == 1:
continue
cursor.execute(
'INSERT INTO `hot_key` VALUES ({0}, "{1}", {2})'.format(i, k, v)
)
conn.commit()
i += 1
print('[+] Success')
def test_multi_label_model(self):
multi_label_model = self.model_class(multi_label=True)
multi_label_model.fit(train_x,
train_multi_y,
eval_x,
eval_multi_y,
epochs=2)
assert isinstance(multi_label_model.predict(train_x[0]), tuple)
model_path = os.path.join(tempfile.gettempdir(), 'kashgari_model',
str(time.time()))
multi_label_model.save(model_path)
new_model = BLSTMModel.load_model(model_path)
assert new_model is not None
sentence = list('语言学包含了几种分支领域。')
result = new_model.predict(sentence)
assert isinstance(result, tuple)
def interview(self):
model = BLSTMModel.load_model(
"../model/health_manager_multi_bert-model")
x_items, train_y = read_message(
'../data/health_manager_v2/multiple-choice.csv')
model.evaluate(x_items, train_y)
results_string: str = ''
train_string: str = ''
right_predict: list = []
wrong_predict: list = []
for i in x_items:
results_string += model.predict(i)
for j in train_y:
train_string += j
if len(results_string) == len(train_string):
print('预测结果', results_string, '正确结果', train_string)
print('五个五个去判断 全等就是做对了不全等就是做错了')
a = len(train_string)
b: int = int(a / 5)
print('验证数据集长度', b)
right: int = 0
for i in range(b):
start_single: int = i * 5
end_single: int = (i + 1) * 5
var = results_string[start_single:end_single]
result = train_string[start_single:end_single]
if var == result:
print('做对了')
acc = b - right
with open('wrong single.csv', 'w', newline='',
encoding='utf-8') as csv_file:
csv_writer = csv.writer(csv_file)
for wrong_list in wrong_predict:
for message in wrong_list:
wrong_list = message.split('\t')
csv_writer.writerow(wrong_list)
with open('right single.csv', 'w', newline='',
encoding='utf-8') as csv_file:
csv_writer = csv.writer(csv_file)
for right_list in right_predict:
for message in right_list:
message = message.split('\t')
csv_writer.writerow(message)
print('正确答案', right, '错误答案', acc)
print('准确率', right / b)
def predict_each_line(args, model):
import codecs
fout = codecs.open(args.output_file, 'w')
test_x, test_y = fetch_data_set(args.test_set_path)
for line, y in zip(test_x, test_y):
result = model.predict(text_processor(''.join(line)), batch_size=1, debug_info=False)
if result != ''.join(y):
str_message = ''.join(line) + "\t" + ''.join(y) +"\t" + result
print(str_message)
fout.write(str_message+'\n')
fout.close()
if __name__ == '__main__':
# initialize parameter
args = params_setup()
logging.basicConfig(filename=args.log_path, level=logging.DEBUG)
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu_id
bert_embedding = BERTEmbedding('bert-base-chinese', sequence_length=30)
model = BLSTMModel(bert_embedding)
model = model.load_model(args.model_path)
if (args.predict_mode == "from_input"):
predict_from_user_input(model)
else:
predict_from_test_set(args, model)
def pre_train(self):
model = BLSTMModel.load_model("../model/中医执业药师classification-model")
x_items, train_y = self.read_message('../data/Chinese medicine licensed pharmacist/test.txt')
model.evaluate(x_items, train_y)
def pre_evaluate(self):
model = BLSTMModel.load_model("../健康管理师分字-model")
x_items, train_y = self.read_message(
'../data/health_manager_v4/test.txt')
model.evaluate(x_items, train_y)
def pre_evaluate(self):
model = BLSTMModel.load_model(
"../model/health_manager_multi_bert-model")
result = model.predict("")
def pre_train(self):
bilstm_model = BLSTMModel.load_model('../classification-model')
x_items, _ = self.read_message('../data/西药执业药师/dev.txt')
for i in x_items:
result = bilstm_model.predict(i)
print("\n" + result)