梯度下降法算法实现

from numpy import *

# 数据集大小 即20个数据点
m = 20
# x的坐标以及对应的矩阵
X0 = ones((m, 1))  # 生成一个m行1列的向量，也就是x0，全是1
X1 = arange(1, m+1).reshape(m, 1)  # 生成一个m行1列的向量，也就是x1，从1到m
X = hstack((X0, X1))  # 按照列堆叠形成数组，其实就是样本数据
# 对应的y坐标
Y = array([
    3, 4, 5, 5, 2, 4, 7, 8, 11, 8, 12,
    11, 13, 13, 16, 17, 18, 17, 19, 21
]).reshape(m, 1)
# 学习率
alpha = 0.01


# 定义代价函数
def cost_function(theta, X, Y):
    diff = dot(X, theta) - Y  # dot() 数组需要像矩阵那样相乘，就需要用到dot()
    return (1/(2*m)) * dot(diff.transpose(), diff)


# 定义代价函数对应的梯度函数
def gradient_function(theta, X, Y):
    diff = dot(X, theta) - Y
    return (1/m) * dot(X.transpose(), diff)


# 梯度下降迭代
def gradient_descent(X, Y, alpha):
    theta = array([1, 1]).reshape(2, 1)
    gradient = gradient_function(theta, X, Y)
    while not all(abs(gradient) <= 1e-5):
        theta = theta - alpha * gradient
        gradient = gradient_function(theta, X, Y)