numpy含nan值进行归一化操做

1. 方法一

import numpy as np

A = np.array([[  7,     4,   5,  7000],
              [  1,   900,   9,   nan],
              [  5, -1000, nan,   100],
              [nan,   nan,   3,  1000]])

#Compute NaN-norms
L1_norm = np.nansum(np.abs(A), axis=1)
L2_norm = np.sqrt(np.nansum(A**2, axis=1))
max_norm = np.nanmax(np.abs(A), axis=1)

#Normalize rows
A_L1 =  A / L1_norm[:,np.newaxis] # A.values if Dataframe
A_L2 =  A / L2_norm[:,np.newaxis]
A_max = A / max_norm[:,np.newaxis]

#Check that it worked
L1_norm_after = np.nansum(np.abs(A_L1), axis=1)
L2_norm_after = np.sqrt(np.nansum(A_L2**2, axis=1))
max_norm_after = np.nanmax(np.abs(A_max), axis=1)

 In[182]: L1_norm_after
Out[182]: array([1., 1., 1., 1.])

 In[183]: L2_norm_after
Out[183]: array([1., 1., 1., 1.])

 In[184]: max_norm_after
Out[184]: array([1., 1., 1., 1.])

方法二

rom numpy import nan, nanmean
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

A = [[  7,     4,   5,  7000],
     [  1,   900,   9,   nan],
     [  5, -1000, nan,   100],
     [nan,   nan,   3,  1000]]

scaler.fit(A)

In [45]: scaler.mean_
Out[45]: array([4.33333333,  -32.,    5.66666667, 2700.])

In [46]: scaler.transform(A)
Out[46]: array([[ 1.06904497,  0.04638641, -0.26726124,  1.40399977],
                [-1.33630621,  1.20089267,  1.33630621,         nan],
                [ 0.26726124, -1.24727908,         nan, -0.84893009],
                [        nan,         nan, -1.06904497, -0.55506968]])

In [54]: nanmean(scaler.transform(A), axis=0)
Out[54]: array([ 1.48029737e-16,  0.00000000e+00, -1.48029737e-16,0.00000000e+00])

参考:python

1. stackoverflow