خوارزميات تصنيف الصفحات واستخدام Python لتحقيقها

خوارزمية PageRank مناسبة للصفحات. الصفحات هي رسم بياني ذو اتجاه، ونحن نعلم أن مكونين رئيسيين في الرسم البياني ذو الاتجاه هما العقد والروابط. الصفحة هي العقد، والروابط العكسية هي الروابط، وهي رابط بين عقدتين.

يمكننا اكتشاف أهمية كل صفحة باستخدام PageRank، وهو دقيق. قيمة PageRank تتراوح بين 0 و1.

قيمة PageRank لمفردة واحدة في الصورة تعتمد على قيم PageRank لجميع العقد الموصلة إليها، وتلك العقد تربط بشكل دوري إلى العقد التي نريد تقييمها، ونستخدم طريقة التكرار التجميعي للتحويل إلى PageRank.

مثال على البرنامج

import numpy as np
import scipy as sc
import pandas as pd
from fractions import Fraction
　　　def display_format(my_vector, my_decimal):
　　　　　　return np.round((my_vector).astype(np.float), decimals=my_decimal)
　　　　　　my_dp = Fraction(1,3)
　　　　　　Mat = np.matrix([[0,0,1],
　　　　　　[Fraction(1,2),0,0],
　　　　　　[Fraction(1,2),1,0]])
　　　　　　Ex = np.zeros((3,3))
　　　　　　Ex[:] = my_dp
　　　　　　beta = 0.7
　　　　　　Al = beta * Mat + ((1-beta) * Ex)
　　　　　　r = np.matrix([my_dp, my_dp, my_dp])
　　　　　　r = np.transpose(r)
　　　　　　previous_r = r
　　　for i in range(1,100):
　　　　　　r = Al * r
　　　　　　print (display_format(r,3))
if (previous_r==r).all():
　　　break
previous_r = r
print ("Final:\n", display_format(r,3))
print ("sum", np.sum(r))

نتيجة الخروج

[[0.333]
[0.217]
[0.45]
[[0.415]
[0.217]
[0.368]
[[0.358]
[0.245]
[0.397]]
[[0.378]
[0.225]
[0.397]]
[[0.378]
[0.232]
[0.39]
[[0.373]
[0.232]
[0.395]]
[[0.376]
[0.231]
[0.393]]
[[0.375]
[0.232]
[0.393]]
[[0.375]
[0.231]
[0.394]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
[[0.375]
[0.231]
[0.393]]
Final:
[[0.375]
[0.231]
[0.393]]
sum 0.9999999999999951