import numpy as np
udacity_set = np.array(
[[1,1,1,0],
[1,0,1,0],
[0,1,0,1],
[1,0,0,1]])
label = udacity_set[:,udacity_set.shape[1]-1]
fx = label.size
positive = label[label == 1].shape[0]
positive_probability = positive/fx
negative = label[label == 0].shape[0]
negative_probability = negative/fx
entropy = -negative_probability*np.log2(negative_probability) - positive_probability*np.log2(positive_probability)
atribute = 0
V = 1
attribute_set = udacity_set[np.where(udacity_set[:,atribute] == 1)] #selecting positive instance of occurance in attribute 14
instances = attribute_set.shape[0]
negative_labels = attribute_set[np.where(attribute_set[:,attribute_set.shape[1]-1]== 0)].shape[0]
positive_labels = attribute_set[np.where(attribute_set[:,attribute_set.shape[1]-1]== 1)].shape[0]
p0 = negative_labels/instances
p1 = positive_labels/instances
entropy2 = - p0*np.log2(p0) - p1*np.log2(p1)
attribute_set2 = udacity_set[np.where(udacity_set[:,atribute] == 0)] #selecting positive instance of occurance in attribute 14
instances2 = attribute_set2.shape[0]
negative_labels2 = attribute_set[np.where(attribute_set2[:,attribute_set2.shape[1]-1]== 0)].shape[0]
positive_labels2 = attribute_set[np.where(attribute_set2[:,attribute_set2.shape[1]-1]== 1)].shape[0]
p02 = negative_labels2/instances2
p12 = positive_labels2/instances2
entropy22 = - p02*np.log2(p02) - p12*np.log2(p12)
问题是当属性是纯粹的并且熵意味着为0.但是当我把它放入公式时我得到NaN。我知道如何编写变通方法，但为什么这个公式被操纵了？