scikit-learn的t-SNE中的熵计算

Question

在t-SNE的scikit-learn实现中 https://github.com/scikit-learn/scikit-learn/blob/f0ab589f1541b1ca4570177d93fd7979613497e3/sklearn/manifold/_utils.pyx

有人可以解释为什么在第98行中按如下方式计算熵吗？

Date1, Student1, Student2, Student3, Student4, School1, School2, School3, School4, Time1, Time2, Time3, Time4   
Date2, Student1, Student2, Student3, Student4, School1, School2, School3, School4, Time1, Time2, Time3, Time4    
Date3, Student1, Student2, Student3, Student4, School1, School2, School3, School4, Time1, Time2, Time3, Time4    
Date4, Student1, Student2, Student3, Student4, School1, School2, School3, School4, Time1, Time2, Time3, Time4