TensorFlow2 study notes: 8. tf.keras implements linear regression, Income dataset: years of education and income dataset

1、Income数据集

IncomeThe dataset is machine learning、Typical learning data for linear regression in a deep learning experiment：下载Income数据集

It mainly has two types of data,受教育年限和对应的收入情况

It can be observed by the scatter plot,apparently linear relationship

数据预览：

散点图：

2、创建模型

2.1导入数据、定义特征和标签

import tensorflow as tf
import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_csv("./Income.csv")
 
# Define input featuresx 和对应标签y
x=data.Education
y=data.Income

2.2创建模型

#顺序模型：只有一个输入和一个输出.tf.keras.Sequential()is a sequential model
model=tf.keras.Sequential()   #初始化模型
model.add(tf.keras.layers.Dense(1,input_shape=(1,)))  #添加层
model.compile(optimizer='adam',loss='mse') # Configure training items mse均方差 梯度优化Adam

通过：model.summary()function to look at the model

3、训练模型

model.fit(x,y,epochs=500)
#x y Feed the data features and labels defined above epochsis the number of training iterations

训练结果：

4、完整代码

import tensorflow as tf
import pandas as pd
import matplotlib.pyplot as plt
data=pd.read_csv("./Income.csv")
x=data.Education
y=data.Income
model=tf.keras.Sequential()
model.add(tf.keras.layers.Dense(1,input_shape=(1,)))
model.summary()
model.compile(optimizer='adam',loss='mse')
h=model.fit(x,y,epochs=500)