20210329wt,简单线性函数利用sgd求解w和b

线性回归+梯度下降

import numpy
#2021/3/29/wt， 简单的线性函数利用梯度下降来求解w和b


# y = wx + b, 计算当前的权重时的误差
def compute_error_for_line_given_points(b, w, points):
    totalError = 0
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        totalError += (y - (w*x + b))**2
    return totalError / float(len(points))


# 迭代计算每经过一个点的w和b的更新
def step_gradient(b_current, w_current, points, learningRate):
    b_gradient = 0
    w_gradient = 0
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        b_gradient += -(2/N)*(y - ((w_current*x)+b_current))
        w_gradient += -(2/N)*x*(y - ((w_current*x)+b_current))
    new_b = b_current - (learningRate*b_gradient)
    new_w = w_current - (learningRate*w_gradient)
    return [new_b, new_w]


# 多个epoch的迭代计算最终的w和b
def gradient_descent_runner(points, starting_b, starting_w, learningRate, num_iter):
    b = starting_b
    w = starting_w
    for i in range(num_iter):
        b, w = step_gradient(b, w, np.array(points), learningRate)
    return [b, w]


def run():
    points = np.genformtxt('data.csv', delimiter=',')
    learningRate = 0.0001
    initial_b = 0
    initial_w = 0
    num_iter = 100
    [b, w] = gradient_descent_runner(points, initial_b, initial_w, learningRate, num_iter)
    print('After {0} iteration b = {1}, m = {2}, error={3}'.format(num_iter, b, w,
                                                                   compute_error_for_line_given_points(b, w, points)))


if __name__ == '__main__':
    run()