1 #! /usr/bin/python
 2 # -*- coding: utf-8 -*-
 3
 4 import tensorflow as tf
 5 import numpy
 6 import matplotlib.pyplot as plt
 7 rng = numpy.random
 8
 9 learning_rate = 0.01
10 training_epochs = 1000
11 display_step = 50
12 #数据集x
13 train_X = numpy.asarray([3.3,4.4,5.5,7.997,5.654,.71,6.93,4.168,9.779,6.182,7.59,2.167,
14                          7.042,10.791,5.313,9.27,3.1])
15 #数据集y
16 train_Y = numpy.asarray([1.7,2.76,3.366,2.596,2.53,1.221,1.694,1.573,3.465,1.65,2.09,
17                          2.827,3.19,2.904,2.42,2.94,1.3])
18 n_samples = train_X.shape[0]
19 X = tf.placeholder("float")
20 Y = tf.placeholder("float")
21
22 W = tf.Variable(rng.randn(), name="weight")
23 b = tf.Variable(rng.randn(), name="bias")
24
25 pred = tf.add(tf.multiply(X, W), b)
26
27 cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
28
29 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
30
31 init = tf.initialize_all_variables()
32 with tf.Session() as sess:
33     sess.run(init)
34
35     # 训练数据
36     for epoch in range(training_epochs):
37         for (x, y) in zip(train_X, train_Y):
38             sess.run(optimizer, feed_dict={X: x, Y: y})
39
40     print "优化完成!"
41     training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
42     print "Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n'
43
44     #可视化显示
45     plt.plot(train_X, train_Y, 'ro', label='Original data')
46     plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
47     plt.legend()
48     plt.show()