线性回归demo

一个简单的线性回归的例子，可以可视化回归过程

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

N=500
y_point=[]
x_point=[]
a=0.22
b=0.62

for i in range(N):
    x=np.random.normal(0.0,0.5)
    y=a*x+b+np.random.normal(0.0,0.1)
    x_point.append(x)
    y_point.append(y)

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.plot(x_point, y_point,'o')
plt.ion()
plt.legend()
plt.show()

A=tf.Variable(tf.random_uniform([1], -1.0, 1.0, dtype=tf.float32))
B=tf.Variable(tf.zeros([1], dtype=tf.float32))
y_out=A*x_point+B

cost_function=tf.reduce_mean(tf.square(y_out-y_point))

optimizer = tf.train.GradientDescentOptimizer(0.5)

train=optimizer.minimize(cost_function)
model=tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(model)
    for step in range(21):
        sess.run(train)
        if step%5==0:
#             plt.plot(x_point,y_point,'o',label="step={}".format(step))
            try:
                ax.lines.remove(lines[0])
            except Exception:
                pass
            lines=ax.plot(x_point,sess.run(A)*x_point+sess.run(B),'r-', lw=5)
            plt.pause(1)
plt.pause(100)

效果