arr0 = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24]) arr1 = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24]) arr2 = np.array(input("请输入连续24个月的车辆销售数据，元素之间用空格隔开：").split(), dtype=float) arr3 = np.array(input("请输入连续24个月的配件销售数据，元素之间用空格隔开：").split(), dtype=float) data_array = np.vstack((arr0, arr1, arr2, arr3)) data_matrix = data_array.T data = pd.DataFrame(data_matrix, columns=['num', 'month', 'car sales', 'sales']) data = data[['month', 'car sales', 'sales']] train_data, test_data = train_test_split(data, test_size=0.3) scaler = MinMaxScaler(feature_range=(0, 1)) data_scaled = scaler.fit_transform(data) train_size = int(len(data_scaled) * 0.7) test_size = len(data_scaled) - train_size train, test = data_scaled[0:train_size,:], data_scaled[train_size:len(data_scaled),:] def create_dataset(dataset, look_back=1): X, Y = [], [] for i in range(len(dataset)-look_back): X.append(dataset[i:(i+look_back), :]) Y.append(dataset[i+look_back, :]) return np.array(X), np.array(Y) look_back = 3 X_train, Y_train = create_dataset(train, look_back) X_test, Y_test = create_dataset(test, look_back) model = Sequential() model.add(LSTM(4, input_shape=(look_back, 3))) model.add(Dense(3)) model.compile(loss='mean_squared_error', optimizer='adam') model.fit(X_train, Y_train, epochs=100, batch_size=1, verbose=0) train_predict = model.predict(X_train) test_predict = model.predict(X_test) train_predict = scaler.inverse_transform(train_predict) Y_train = scaler.inverse_transform(Y_train) test_predict = scaler.inverse_transform(test_predict) Y_test = scaler.inverse_transform(Y_test) last_month = data_scaled[-look_back:] last_month = last_month.reshape((1, look_back, 3))#1，12，3 next_month = model.predict(last_month) next_month = scaler.inverse_transform(next_month) print('下个月的预测结果是:', round(next_month[0][2])),如何将以下代码稍作修改插入到上面的最后，def comput_acc(real,predict,level): num_error=0 for i in range(len(real)): if abs(real[i]-predict[i])/real[i]>level: num_error+=1 return 1-num_error/len(real) a=np.array(test_data[label]) real_y=a real_predict=test_predict print("置信水平：{},预测准确率：{}".format(0.2,round(comput_acc(real_y,real_predict,0.2)* 100,2)),"%")

你可以在代码的末尾添加以下内容：

label = 'sales'
a = np.array(test_data[label])
real_y = a
real_predict = test_predict[:, 2]
print("置信水平：{},预测准确率：{}".format(0.2, round(comput_acc(real_y, real_predict, 0.2) * 100, 2)), "%")

这段代码是在计算预测的准确率，其中`label`是指测试数据中需要预测的列的名称，这里默认为`'sales'`。`real_y`和`real_predict`分别是真实值和预测值，通过调用`comput_acc`函数计算预测的准确率。如果需要计算其他置信水平的预测准确率，只需要修改0.2即可。