利用tensorflow搭建一个简单的线性回归模型，超详细注释版

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

rng = numpy.random

# 这是一个线性回顾的例子，所以就是单纯的线性拟合，不涉及到非线性的问题，就没有激活函数

# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50


# Training Data
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])                         

# 样本数量
n_samples = train_X.shape[0]

# tf Graph input  
# placeholder 一般用来存放模型的样本数据， 不用初始化
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
# Variable 一般用来存放需要训练的数据，值可以从训练的过程中获得，需要初始化
W = tf.Variable(rng.randn(), name = "weight")
b = tf.Variable(rng.randn(), name = "bias")

# Construct a linear model
# 定义模型，即 pred = W * X + b
pred = tf.add(tf.multiply(X, W), b)

# Mean squared error
# reduce_sum 按坐标轴相加，这里有一点，对于二维数组来说，first dimension 就是行维度，second dimension 就是列维度
# 这里的 2 代表的可不是2倍的样本数量，那样理解就偏了。这里是预测值和真值之间的距离，应该理解为二分之一
cost = tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * n_samples)

# Gradient descent
# 所谓的优化器，就是让目标参数达到最优值的方法，这里选用梯度下降法，learning_rate就是梯度下降的步长，要优化的目标是cost
optimizer = tf.train.GradientdescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables (i.e. assign their default value)
# 只有运行了这句之后，才能让之前定义的变量保存需要保存的值，也就是说，只有运行了这句话之后，之前定义的变量才能开始使用。
# 毕竟tf是懒加载的
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:
	sess.run(init)

	# Fit all training data
	for epoch in range(training_epochs):
		for (x, y) in zip(train_X, train_Y):
			# 有了palce_holder，就得配套出现一个feed_dict对其进行初始化
			sess.run(optimizer, feed_dict{X : x, Y : y})

			# Display logs per epoch step，之前定义的，也就是每50步打印一次训练的成果
			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')

	# Graphic display
	plt.plot(train_X, train_Y, 'ro', label = 'Origianl data')
	plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label = 'Fitted line')
	plt.legend()
	plt.show()