import statsmodels.api as sm
from scipy.io import loadmat
from pandas import Series
from numpy import array

A = loadmat('A.mat')['A'].astype('int32')

outlinks = Series(array(A.sum(1).flatten())[0])
inlinks = Series(array(A.sum(0).flatten())[0])

outlinks.describe()

outlinks.hist(bins=20);

log(outlinks+1).hist(bins=20, log=True)

outlinks.hist(normed=True, cumulative=True, bins=30, histtype='step')
ylim(.94,1)

ecdf = sm.distributions.ECDF(outlinks)

x = linspace(min(outlinks), max(outlinks))
y = ecdf(x)
step(log(x+1), y)
ylim(.9,1);

inlinks.describe()

inlinks.hist(bins=20)

log(inlinks+1).hist(bins=20, log=True)

ecdf = sm.distributions.ECDF(inlinks)
x = linspace(min(inlinks), max(inlinks))
y = ecdf(x)
step(log(x+1), y)
ylim(.95, 1);