#原理https://www.jianshu.com/p/c7e642877b0e
import numpy as np
import sys
# Size of the points dataset.
m = 20
# Points x-coordinate and dummy value (x0, x1).
X0 = np.ones((m, 1))
X1 = np.arange(1, m+1).reshape(m, 1)
X = np.hstack((X0, X1))
# Points y-coordinate
y = np.array([
3, 4, 5, 5, 2, 4, 7, 8, 11, 8, 12,
11, 13, 13, 16, 17, 18, 17, 19, 21
]).reshape(m, 1)
# The Learning Rate alpha.
alpha = 0.01
def error_function(theta, X, y):
'''Error function J definition.'''
diff = np.dot(X, theta) - y
return (1./2*m) * np.dot(np.transpose(diff), diff)
def gradient_function(theta, X, y):
'''Gradient of the function J definition.'''
diff = np.dot(X, theta) - y
return (1./m) * np.dot(np.transpose(X), diff)
def gradient_descent(X, y, alpha):
'''Perform gradient descent.'''
theta = np.array([1, 1]).reshape(2, 1)
gradient = gradient_function(theta, X, y)
while not np.all(np.absolute(gradient) <= 1e-5):
theta = theta - alpha * gradient
#gradient代价函数的梯度
gradient = gradient_function(theta, X, y)
return theta
optimal = gradient_descent(X, y, alpha)
print('optimal:', optimal)
print('error function:', error_function(optimal, X, y)[0,0])
# 作者:六尺帐篷
# 链接:https://www.jianshu.com/p/c7e642877b0e
# 來源:简书
# 简书著作权归作者所有,任何形式的转载都请联系作者获得授权并注明出处。