一、代码中的数据集下载地址如下：

百度网盘提取码：lala

二、代码运行环境：

Tensorflow-gpu==2.4.0

Python==3.7

三、训练代码如下所示：

import tensorflow as tf
import os
import pandas as pd
import matplotlib.pyplot as plt

# 环境变量配置
os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices'
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'

# 数据的读取
data = pd.read_csv(r'dataset/getter.csv')

# 数据的展示
plt.scatter(data.Education, data.Income)
plt.show()

# 模型的构建
x = data.Education
y = data.Income
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(1, input_shape=(1,)))

# 模型的相关配置
model.compile(
    optimizer='adam',
    loss='mse'
)

# 模型的训练
history = model.fit(x, y, epochs=60000, batch_size=20)

# 模型的预测
pre_y = model.predict(x)
pre_y = pre_y.flatten()

# 预测结果的展示
plt.scatter(x, y)
plt.plot(x, pre_y, 'red')
plt.show()

# 模型的保存
model.save(r'model_data/model.h5')

四、预测代码如下所示：

import tensorflow as tf
import os
import pandas as pd
import matplotlib.pyplot as plt

# 环境变量配置
os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices'
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'

# 数据的读取
data = pd.read_csv(r'dataset/getter.csv')
x = data.Education
y = data.Income

# 模型的加载
pre_model = tf.keras.models.load_model(r'model_data/model.h5')

# 结果的预测
pre_y = pre_model.predict(x)

# 预测结果的展示
plt.scatter(x, y)
plt.plot(x, pre_y, 'red')
plt.show()

五、预测结果展示