Normalizing labels

I was trying to understand why did you normalize labels as follows:
`y = 1.0*y
tmp_no = numpy.sum(y)
pno = (data_no + tmp_no) / 2
nno = (data_no - tmp_no) / 2
y[y>0] = y[y>0]/pno
y[y<0] = y[y<0]/nno`
Why did you chose (160+sum_of_labels)/2?`