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_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_sample_pagerank():
random.seed(1)
assert pagerank.sample_pagerank(pagerank.crawl("corpus0"), DAMPING,
SAMPLES) == PAGE_RANKS_0
assert pagerank.sample_pagerank(pagerank.crawl("corpus1"), DAMPING,
SAMPLES) == PAGE_RANKS_1
result2 = pagerank.sample_pagerank(pagerank.crawl("corpus2"), DAMPING,
SAMPLES)
assert result2 == PAGE_RANKS_2
assert sum(list(
result2.values())) == 1 # Confirm result is properely normalized
# Confirm that process is pseudoRandom
assert pagerank.sample_pagerank(pagerank.crawl("corpus2"), DAMPING,
SAMPLES) != result2
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))
def test_crawl():
assert pagerank.crawl() == CRAWL0
assert pagerank.crawl("corpus0") == CRAWL0
assert pagerank.crawl("corpus1") == CRAWL1
from pagerank import transition_model, crawl
if len(sys.argv) != 2:
sys.exit("Usage: python pagerank.py corpus")
corpus = crawl(sys.argv[1])
print(corpus)
trans = transition_model(corpus, "1.html", 0.85)
print(trans)