In [8]:

    

import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error, mean_absolute_error


    

In [24]:

    

N=100000000
sigma=3.14159
xg=np.arange(N)
xp=xg+np.random.randn(N)*sigma

rmse=np.sqrt(mean_squared_error(xg,xp))
mae=mean_absolute_error(xg,xp)
print "rmse: %f mae:%f"%(sigma2,u)


    

    




rmse: 3.141098 mae:2.506248

In [13]:

    




    

    
Out[13]:





3.4109970538590497

In [15]:

    




    

    
Out[15]:





2.7401192759342798

In [ ]: