多元线性回归：波士顿房价预测问题

1.读取数据

从boston.csv中读取所需数据

import numpy as np
import matplotlib.pyplot as plt
import tensorflow.compat.v1 as tf
import pandas as pd
from sklearn.utils import shuffle

df = pd.read_csv("data/boston.csv",header=0)
#打印摘要
print(df.describe())

2.数据预处理

设置数据输入格式，归一化
归一化能提升模型的收敛速度，提升模型的精度

df = df.values
df = np.array(df)
#归一化
for i in range(12):
    df[:,i] = (df[:,i] - df[:,i].min())/(df[:,i].max()-df[:,i].min())
x_data = df[:,:12]
y_data = df[:,12]
#print(x_data,"\n shape = ",x_data.shape)
#print(y_data,"\n shape = ",y_data.shape)

x = tf.placeholder(tf.float32,[None,12],name="X")
y = tf.placeholder(tf.float32,[None,1],name="Y")

3.定义模型

定义多元线性回归模型

with tf.name_scope("Model"):
    w = tf.Variable(tf.random_normal([12,1],stddev=0.01),name="w")
    b = tf.Variable(1.0,name="b")
    
    def model(x,w,b):
        return tf.matmul(x,w)+b
    
    pred = model(x,w,b)

4.训练模型

train_epoch = 50
learn_rate = 0.01

with tf.name_scope("LossFunction"):
    loss_function = tf.reduce_mean(tf.pow(y-pred,2))    
optimizer = tf.train.GradientDescentOptimizer(learn_rate).minimize(loss_function)

sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

loss_list = []

for epoch in range(train_epoch):
    loss_sum = 0.0
    for xs,ys in zip(x_data,y_data):
        xs = xs.reshape(1,12)
        ys = ys.reshape(1,1)
        
        _,loss = sess.run([optimizer,loss_function],feed_dict={x:xs,y:ys})
        loss_sum = loss_sum + loss
        
    xvalues,yvalues = shuffle(x_data,y_data)
    b0temp = b.eval(session=sess)
    w0temp = w.eval(session=sess)
    
    loss_avg = loss_sum/len(y_data)
    loss_list.append(loss_avg)
    
    print("epoch = ",epoch+1,"loss = ",loss_avg,"w = ",w0temp,"b = ",b0temp)

5.测试模型

n = np.random.randint(506)
print(n)
x_test = x_data[n]
x_test = x_test.reshape(1,12)
predict =  sess.run(pred,feed_dict = {x:x_test})
print("预测值：%f" % predict)
print("标签值：%f" % y_data[n] )

6.查看每一epoch平均损失值

plt.plot(loss_list)