基于Numpy+Python2.7的线性回归

  
#The optimal values of m and b can be actually calculated with way less effort than doing a linear regression. #this is just to demonstrate gradient descentfrom numpy import *# y = mx + b# m is slope, b is y-interceptdef compute_error_for_line_given_points(b, m, points):    totalError = 0    for i in range(0, len(points)):        x = points[i, 0]        y = points[i, 1]        totalError += (y - (m * x + b)) ** 2    return totalError / float(len(points))def step_gradient(b_current, m_current, points, learningRate):    b_gradient = 0    m_gradient = 0    N = float(len(points))    for i in range(0, len(points)):        x = points[i, 0]        y = points[i, 1]        b_gradient += -(2/N) * (y - ((m_current * x) + b_current))        m_gradient += -(2/N) * x * (y - ((m_current * x) + b_current))    new_b = b_current - (learningRate * b_gradient)    new_m = m_current - (learningRate * m_gradient)    return [new_b, new_m]def gradient_descent_runner(points, starting_b, starting_m, learning_rate, num_iterations):    b = starting_b    m = starting_m    for i in range(num_iterations):        b, m = step_gradient(b, m, array(points), learning_rate)    return [b, m]def run():    points = genfromtxt("G:\\Workspaces\\py\\linear_regression_live-master\\data.csv", delimiter=",")    learning_rate = 0.0001    initial_b = 0 # initial y-intercept guess    initial_m = 0 # initial slope guess    num_iterations = 1000    print "Starting gradient descent at b = {0}, m = {1}, error = {2}".format(initial_b, initial_m, compute_error_for_line_given_points(initial_b, initial_m, points))    print "Running..."    [b, m] = gradient_descent_runner(points, initial_b, initial_m, learning_rate, num_iterations)    print "After {0} iterations b = {1}, m = {2}, error = {3}".format(num_iterations, b, m, compute_error_for_line_given_points(b, m, points))if __name__ == '__main__':    run()
    此代码来自Udacity Siraj的直播课程，代码与数据集下载地址：https://github.com/llSourcell/linear_regression_live

查看原文：http://data.1kapp.com/?p=331