梯度下降算法的python实现

import sys
 
#Training data set
#each element in x represents (x0,x1,x2)
x = [(1,0.,3) , (1,1.,3) ,(1,2.,3), (1,3.,2) , (1,4.,4)]
#y[i] is the output of y = theta0 * x[0] + theta1 * x[1] +theta2 * x[2]
y = [95.364,97.217205,75.195834,60.105519,49.342380]
 
 
epsilon = 0.0001
#learning rate
alpha = 0.01
diff = [0,0]
max_itor = 1000
error1 = 0
error0 =0
cnt = 0
m = len(x)
 
 
#init the parameters to zero
theta0 = 0
theta1 = 0
theta2 = 0
 
while True:
     
    cnt = cnt + 1
 
    #calculate the parameters
    for i in range(m):
 
        diff[0] = y[i]-( theta0 + theta1 * x[i][1] + theta2 * x[i][2] )
         
        theta0 = theta0 + alpha * diff[0] * x[i][0]
        theta1 = theta1 + alpha * diff[0]* x[i][1]
        theta2 = theta2 + alpha * diff[0]* x[i][2]
 
    #calculate the cost function
    error1 = 0
    for lp in range(len(x)):
        error1 += ( y[i]-( theta0 + theta1 * x[i][1] + theta2 * x[i][2] ) )**2/2
     
    if abs(error1-error0) < epsilon:
        break
    else:
        error0 = error1
 
    print ' theta0 : %f, theta1 : %f, theta2 : %f, error1 : %f'%(theta0,theta1,theta2,error1)
 
print 'Done: theta0 : %f, theta1 : %f, theta2 : %f'%(theta0,theta1,theta2)

上面这段用的是随机梯度下降算法，原来无法收敛是因为1）1楼提到的error1没有复位置零和下标问题；2)步长alpha和误差epsilon的取值不合适。aplha和epsilon的取值感觉比较关键，我用原先的输入数据，怎么调整这两个参数也没法收敛，换了一组数（也就是上面这段代码里的训练数据）很快就得到结果了。

下面这段基本借鉴的是一个国外网友blog上贴出来的代码段，地址忘了，在此致谢！这段代码里用的是批量梯度下降算法，而且判断收敛的准则也不同：

import sys
 
#Training data set
data1 = [(0.000000,95.364693) ,
        (1.000000,97.217205) ,
        (2.000000,75.195834),
        (3.000000,60.105519) ,
        (4.000000,49.342380),
        (5.000000,37.400286),
        (6.000000,51.057128),
        (7.000000,25.500619),
        (8.000000,5.259608),
        (9.000000,0.639151),
        (10.000000,-9.409936),
        (11.000000, -4.383926),
        (12.000000,-22.858197),
        (13.000000,-37.758333),
        (14.000000,-45.606221)]
 
data2 = [(2104.,400.),
         (1600.,330.),
         (2400.,369.),
         (1416.,232.),
         (3000.,540.)]
 
def create_hypothesis(theta1, theta0):
    return lambda x: theta1*x + theta0
 
def linear_regression(data, learning_rate=0.001, variance=0.00001):
    """ Takes a set of data points in the form: [(1,1), (2,2), ...] and outputs (slope, y0). """
 
    
    #init the parameters to zero
    theta0_guess = 1.
    theta1_guess = 1.
 
 
    theta0_last = 100.
    theta1_last = 100.
     
    m = len(data)
 
    while (abs(theta1_guess-theta1_last) > variance or abs(theta0_guess - theta0_last) > variance):
 
        theta1_last = theta1_guess
        theta0_last = theta0_guess
 
        hypothesis = create_hypothesis(theta1_guess, theta0_guess)
 
        theta0_guess = theta0_guess - learning_rate * (1./m) * sum([hypothesis(point[0]) - point[1] for point in data])
        theta1_guess = theta1_guess - learning_rate * (1./m) * sum([ (hypothesis(point[0]) - point[1]) * point[0] for point in data])   
 
    return ( theta0_guess,theta1_guess )
 
 
 
points = [(float(x),float(y)) for (x,y) in data1]
 
res = linear_regression(points)
print res