python - 线性回归-意外结果(Python)

对于我编写的线性回归，我得到了意外的结果。
有时我会出现内存不足错误，平方错误，乘法错误，基本上是我用完了。

该代码对我来说似乎还不错，而且我无法确定为什么它无法正常工作。

X = np.array([ 6.1101,  5.5277,  8.5186,  7.0032,  5.8598,  8.3829, 7.4764,
        8.5781,  6.4862,  5.0546,  5.7107, 14.164 ,  5.734 ,  8.4084,
        5.6407,  5.3794,  6.3654,  5.1301,  6.4296,  7.0708,  6.1891,
       20.27  ,  5.4901,  6.3261,  5.5649, 18.945 , 12.828 , 10.957 ,
       13.176 , 22.203 ,  5.2524,  6.5894,  9.2482,  5.8918,  8.2111,
        7.9334,  8.0959,  5.6063, 12.836 ,  6.3534,  5.4069,  6.8825,
       11.708 ,  5.7737,  7.8247,  7.0931,  5.0702,  5.8014, 11.7   ,
        5.5416,  7.5402,  5.3077,  7.4239,  7.6031,  6.3328,  6.3589,
        6.2742,  5.6397,  9.3102,  9.4536,  8.8254,  5.1793, 21.279 ,
       14.908 , 18.959 ,  7.2182,  8.2951, 10.236 ,  5.4994, 20.341 ,
       10.136 ,  7.3345,  6.0062,  7.2259,  5.0269,  6.5479,  7.5386,
        5.0365, 10.274 ,  5.1077,  5.7292,  5.1884,  6.3557,  9.7687,
        6.5159,  8.5172,  9.1802,  6.002 ,  5.5204,  5.0594,  5.7077,
        7.6366,  5.8707,  5.3054,  8.2934, 13.394 ,  5.4369])
y = np.array([17.592  ,  9.1302 , 13.662  , 11.854  ,  6.8233 , 11.886  ,
        4.3483 , 12.     ,  6.5987 ,  3.8166 ,  3.2522 , 15.505  ,
        3.1551 ,  7.2258 ,  0.71618,  3.5129 ,  5.3048 ,  0.56077,
        3.6518 ,  5.3893 ,  3.1386 , 21.767  ,  4.263  ,  5.1875 ,
        3.0825 , 22.638  , 13.501  ,  7.0467 , 14.692  , 24.147  ,
       -1.22   ,  5.9966 , 12.134  ,  1.8495 ,  6.5426 ,  4.5623 ,
        4.1164 ,  3.3928 , 10.117  ,  5.4974 ,  0.55657,  3.9115 ,
        5.3854 ,  2.4406 ,  6.7318 ,  1.0463 ,  5.1337 ,  1.844  ,
        8.0043 ,  1.0179 ,  6.7504 ,  1.8396 ,  4.2885 ,  4.9981 ,
        1.4233 , -1.4211 ,  2.4756 ,  4.6042 ,  3.9624 ,  5.4141 ,
        5.1694 , -0.74279, 17.929  , 12.054  , 17.054  ,  4.8852 ,
        5.7442 ,  7.7754 ,  1.0173 , 20.992  ,  6.6799 ,  4.0259 ,
        1.2784 ,  3.3411 , -2.6807 ,  0.29678,  3.8845 ,  5.7014 ,
        6.7526 ,  2.0576 ,  0.47953,  0.20421,  0.67861,  7.5435 ,
        5.3436 ,  4.2415 ,  6.7981 ,  0.92695,  0.152  ,  2.8214 ,
        1.8451 ,  4.2959 ,  7.2029 ,  1.9869 ,  0.14454,  9.0551 ,
        0.61705])
theta = np.array([0,0]) #Initial values of theta_0 and theta_1

#Calculates cost function for given theta
def costFunction(X,y,theta):
    m = y.size
    hypothesis = (X * theta[1]) + theta[0]
    return (1/m) * sum((hypothesis - y) ** 2)

#Calculates the partial derivatives of theta_0 and theta_1
def slope(X,y,theta):
    m=y.size
    hypothesis = (X * theta[1]) + theta[0]
    theta_0 = 2/(m) * sum(hypothesis - y)
    theta_1 = 2/(m) * sum((hypothesis - y) * X)
    return np.array([theta_0,theta_1])

#running the gradient descent with 200 iters with learning rate 0.1
for i in range(200):
    theta = theta - 0.1*slope(X,y,theta)

costFunction(X,y,theta) # Prints inf

最佳答案

您的学习率太大，GD无法收敛。尝试将其更改为0.01并运行更多的时间，它对我有用。

关于python - 线性回归-意外结果(Python)，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/57085013/