我希望你写一个基于MINIST数据集的神经网络，使用Pycharm，实现手写数字分类，不要解释，给出代码

import tensorflow as tf
from tensorflow import keras

# 导入MINIST数据集
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

# 数据预处理
x_train = x_train / 255.0
x_test = x_test / 255.0

# 构建模型
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

# 编译模型
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# 训练模型
model.fit(x_train, y_train, epochs=5)

# 测试模型
test_loss, test_acc = model.evaluate(x_test,  y_test, verbose=2)
print('\nTest accuracy:', test_acc)