def train(self):
x_items, train_y, valid_x, valid_y = self.read_message('car/train.csv')
# 获取bert字向量
model = CNNModel()
# 输入模型训练数据 标签 步数
model.fit(x_items,
train_y,
valid_x,
valid_y,
batch_size=64,
epochs=12,
callbacks=[tf_board_callback])
# 保存模型
file = pd.read_csv("car/test.csv", encoding='utf-8').values.tolist()
test_data = []
id_list = []
for i in file:
test_data.append(jieba.lcut(str(i[1]) + str(i[2])))
id_list.append(i[0])
predict_answers = model.predict(x_data=test_data)
file = open("data/test_predict_bert_car.csv", 'w', encoding='utf-8')
for i, j in zip(id_list, predict_answers):
i = i.strip()
file.write(str(i) + "," + str(j) + "\n")
model.save("../model/news-classification-bert-model")
def train():
x_items, train_y = read_message()
# 获取bert字向量
model = CNNModel(bert)
# 输入模型训练数据 标签 步数
model.fit(x_items,
train_y,
epochs=20,
class_weight=True,
fit_kwargs={'callbacks': [tf_board_callback]})
# 保存模型
model.save("../classification-model")
for i in x_items:
result = model.predict(i)
print("\n" + result)
