def test_sample_pagerank(self):
# Test Corpus 0
corpus = pr.crawl("corpus0")
ranks = pr.iterate_pagerank(corpus, pr.DAMPING)
rankSum = 0
for rank in ranks.values():
rankSum += rank
self.assertAlmostEqual(rankSum, 1, 1)
# Test Corpus 1
corpus = pr.crawl("corpus1")
ranks = pr.iterate_pagerank(corpus, pr.DAMPING)
rankSum = 0
for rank in ranks.values():
rankSum += rank
self.assertAlmostEqual(rankSum, 1, 1)
# Test Corpus 2
corpus = pr.crawl("corpus2")
ranks = pr.iterate_pagerank(corpus, pr.DAMPING)
rankSum = 0
for rank in ranks.values():
rankSum += rank
self.assertAlmostEqual(rankSum, 1, 1)
def test_iterate_pagerank():
assert pagerank.iterate_pagerank(pagerank.crawl("corpus0"),
DAMPING) == ITERATION_PAGE_RANKS_0
assert pagerank.iterate_pagerank(pagerank.crawl("corpus1"),
DAMPING) == ITERATION_PAGE_RANKS_1
assert pagerank.iterate_pagerank(pagerank.crawl("corpus2"),
DAMPING) == ITERATION_PAGE_RANKS_2
def test_iterate_pagerank(self):
corpus = {
"1.html": {"2.html", "3.html"},
"2.html": {"3.html"},
"3.html": {"2.html"}
}
damping_factor = 0.85
result = iterate_pagerank(corpus, damping_factor)
self.assertEqual(1, round(sum(result.values()), 4))
def test_iterate_pagerank_corpus0(self):
corpus = {
"1.html": {"2.html"},
"2.html": {"1.html", "3.html"},
"3.html": {"2.html", "4.html"},
"4.html": {"2.html"}
}
damping_factor = 0.85
result = iterate_pagerank(corpus, damping_factor)
self.assertEqual(1, round(sum(result.values()), 4))
self.assertEqual(0.2202, round(result["1.html"], 4))
self.assertEqual(0.4289, round(result["2.html"], 4))
self.assertEqual(0.2202, round(result["3.html"], 4))
self.assertEqual(0.1307, round(result["4.html"], 4))
import os
import random
import re
import sys
import pagerank
if len(sys.argv) != 2:
sys.exit("Usage: python pagerank.py corpus")
corpus = pagerank.crawl(sys.argv[1])
# Test sampling
# print(pagerank.sample_pagerank(corpus, 0.8, 100))
# Test iteration
print(pagerank.iterate_pagerank(corpus, 0.8))
import pagerank as pr
my_dicy = {
"1.html": {"2.html", "3.html"},
"2.html": {"3.html"},
"3.html": {"2.html"}}
pr.iterate_pagerank(my_dicy, 0.85)
from pagerank import transition_model, sample_pagerank, iterate_pagerank
corpus = {
"1.html": {"2.html", "3.html"},
"2.html": {"3.html"},
"3.html": {"2.html"}
}
page = "1.html"
damp = 0.85
transition_model(corpus, page, damp)
print(sample_pagerank(corpus, 0.85, 5000))
print(iterate_pagerank(corpus, 0.85))
def testIteratePagerank(self):
pagerank_3 = pr.iterate_pagerank(self.corpus_3, DAMPING)
self.assertEqual(pagerank_3, {'1.html': 0.232539658203125, '2.html': 0.43412700846354163, '3.html': 0.3333333333333333})