02使用tensorflow实现线性回归

下面是一个使用完整的tensorflow思路实现的线性回归代码

import tensorflowas tf

import numpy

import matplotlib.pyplotas plt

rng = numpy.random

# 设置训练参数

learning_rate =0.01

training_epochs =10000

display_step =50

# 生成训练数据

train_X = numpy.asarray([3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,

                        7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1])

train_Y = numpy.asarray([1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,

                        2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3])

n_samples = train_X.shape[0]

# 占位节点

X = tf.placeholder(tf.float32)

Y = tf.placeholder(tf.float32)

# 图参数设置。注意要初始化要为浮点数

W = tf.Variable(20.0, name="weight")

b = tf.Variable(20.0, name="bias")

# 只有一个图节点

pred = tf.add(tf.multiply(X, W), b)

# 损失函数

cost = tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * n_samples)

# 优化器

optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# 初始化参数

init = tf.global_variables_initializer()

# 进入图

with tf.Session()as sess:

# 图初始化

    sess.run(init)

# 训练图

    for epochin range(training_epochs):

for (x, y)in zip(train_X, train_Y):

sess.run(optimizer, feed_dict={X: x, Y: y})

# 显示生成过程中的信息

        if (epoch +1) % display_step ==0:

c = sess.run(cost, feed_dict={X: train_X, Y: train_Y})

print("Epoch:", '%04d' % (epoch +1), "cost=", "{:.9f}".format(c), \

"W=", sess.run(W), "b=", sess.run(b))

print("Optimization Finished!")

training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})

print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

# 显示训练结果

    plt.plot(train_X, train_Y, 'ro', label='Original data')

plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')

plt.legend()

plt.show()

# 测试数据集

test_X = numpy.asarray([6.83, 4.668, 8.9, 7.91, 5.7, 8.7, 3.1, 2.1])

test_Y = numpy.asarray([1.84, 2.273, 3.2, 2.831, 2.92, 3.24, 1.35, 1.03])

print("Testing... (Mean square loss Comparison)")

testing_cost = sess.run(

tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * test_X.shape[0]),

        feed_dict={X: test_X, Y: test_Y})# same function as cost above

    print("Testing cost=", testing_cost)

print("Absolute mean square loss difference:", abs(

training_cost - testing_cost))

plt.plot(test_X, test_Y, 'bo', label='Testing data')

plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')

plt.legend()

plt.show()