初学者在这里。我一直在尝试使用遗传编程技术来为数据创建最佳的多元回归模型。 This是整个代码的链接。我不明白为什么我的协方差值这么低。当前基于的模型方程为：
c1*x + c2*y + c3*z
运行代码后收到的错误消息如下：
`F:\Documents>python gp_three.py
C:\Users\Dr.Siva Sridhar\AppData\Local\Programs\Python\Python36\lib\site-packages\deap\tools\_hypervolume\pyhv.py:33: ImportWarning: Falling back to the python version of hypervolume module. Expect this to be very slow.
"module. Expect this to be very slow.", ImportWarning)
C:\Users\Dr.Siva Sridhar\AppData\Local\Programs\Python\Python36\lib\importlib\_bootstrap.py:219: ImportWarning: can't resolve package from __spec__ or __package__, falling back on __name__ and __path__ return f(*args, **kwds)
(3, 500)
[[ 90. 90.08016032 90.16032064 ... 129.83967936 129.91983968 130. ] [ 20. 20.04008016 20.08016032 ... 39.91983968 39.95991984 40. ]
[ 2. 2.00400802 2.00801603 ... 3.99198397 3.99599198
4. ]]
(500,)
Optimal parameters for regression model:
[-0.08671535 -0.07615775 0.96088428]
Covariance:
[[ 2.61480617e-35 -4.80978998e-29 4.80978054e-28]
[-4.80979373e-29 6.35250888e-21 -6.35250869e-20]
[ 4.80978426e-28 -6.35250869e-20 6.35250850e-19]]
[5.11351754e-18 7.97026278e-11 7.97026254e-10]Traceback (most recent call last): File "gp_three.py", line 105, in <module>
main()
File "gp_three.py", line 98, in main algorithms.eaSimple(pop, toolbox, 0.5, 0.1, 50, stats,hof) File "C:\Users\Dr.Siva Sridhar\AppData\Local\Programs\Python\Python36\lib\site-packages\deap\algorithms.py", line 151, in eaSimple
for ind, fit in zip(invalid_ind, fitnesses):
File "gp_three.py", line 75, in evalSymReg
fitness = math.sqrt( sum( map (diff_func, values_one, values_two, values_three) ) )
File "gp_three.py", line 74, in <lambda> diff_func = lambda x,y,z: ( func (x,y,z) - reg_model ( [x,y,z], coeffs ) ) ** 2
File "<string>", line 1, in <lambda>
OverflowError: math range error
`
我该如何解决？