def test_rank_results(self):
from pygrank.algorithms.pagerank import PageRank as Ranker
from pygrank.algorithms.utils import preprocessor
G = create_test_graph()
test_result = Ranker(to_scipy=preprocessor('col')).rank(G)
nx_result = nx.pagerank_scipy(G)
abs_diffs = sum(abs(test_result[v]-nx_result[v]) for v in nx_result.keys())/len(nx_result)
self.assertAlmostEqual(abs_diffs, 0, places=16, msg="PageRank compliance with nx results")
def test_immutability_speedup(self):
from pygrank.algorithms.pagerank import PageRank as Ranker
from pygrank.algorithms.utils import preprocessor
import scipy.stats
nx_time = list()
test_time = list()
repeats = 50
G = create_test_graph()
ranker = Ranker(to_scipy=preprocessor('col'))
tic = time.clock()
for _ in range(repeats):
ranker.rank(G)
unhashed_time = time.clock()-tic
ranker = Ranker(to_scipy=preprocessor('col', assume_immutability=True))
tic = time.clock()
for _ in range(repeats):
ranker.rank(G)
hashed_time = time.clock()-tic
self.assertLessEqual(hashed_time, unhashed_time, msg="Hashing speedup")
def test_rank_time(self):
from pygrank.algorithms.pagerank import PageRank as ranker
from pygrank.algorithms.utils import preprocessor
import scipy.stats
nx_time = list()
test_time = list()
repeats = 50
for _ in range(repeats):
G = create_test_graph()
tic = time.clock()
ranker(to_scipy=preprocessor('col')).rank(G)
test_time.append(time.clock()-tic)
tic = time.clock()
nx.pagerank_scipy(G)
nx_time.append(time.clock()-tic)
self.assertLessEqual(scipy.stats.ttest_ind(nx_time, test_time)[1], 0.001, msg="PageRank time comparable to nx with p-value<0.001")
from scipy.stats import rankdata
ranks = rankdata(ranks)
ground_truth = rankdata(ground_truth)
plt.scatter(ground_truth, ranks)
plt.grid()
plt.show()
# CHANGE THE FOLLOWING BLOCK TO SELECT DATASET
specific_ids = [1723] # community ids
dataset = 'snap_amazon' # dataset
dataset_name = dataset
G, groups = import_SNAP_data(dataset, specific_ids=specific_ids)#left one is amazon, right is dblp
pre = preprocessor('col', assume_immutability=True) # a preprocessor that hashes the outcome of normalization for faster running time of the same algoriths
pre(G) # run once the preprocessor to not affect potential time measurements
result_spearmans = ""
result_iterations = ""
for group_number in range(len(groups)):
for alpha in [0.85, 0.90, 0.95, 0.99, 0.995, 0.999]:
result_spearmans += dataset_name+"-"+str(specific_ids[group_number])+" & & "+(str(alpha)[1:])
result_iterations += dataset_name+"-"+str(specific_ids[group_number])+" & & "+(str(alpha)[1:])
seeds = {v:1 for v in groups[group_number]}
ground_truth_ranker = PageRank(alpha=alpha, to_scipy=pre, tol=1.E-20, max_iters=30000, use_quotient=False)
ground_truth_ranks = ground_truth_ranker.rank(G, seeds)
result_iterations += " & "+str(ground_truth_ranker.convergence.iteration)
print("Found ground truth ranks ("+str(ground_truth_ranker.convergence.iteration)+" iterations)")
compared_rankers = list()
max_iters = 10000
for dataset_name in datasets:
G, groups = import_SNAP_data(
dataset_name,
min_group_size=5000) #12000 for dblp, 5000 for amazon
group_sets = [set(group) for group in groups.values()]
for group in group_sets:
print(len(group))
count = sum(
1 for u, v in G.edges()
if sum(1 for group in group_sets if u in group and v in group) > 0)
print('Homophily', count / float(G.number_of_edges()))
seeds = [0.001, 0.01, 0.1, 0.25, 0.5]
print('Number of groups', len(groups))
for seed in seeds:
pre = preprocessor('col', assume_immutability=True)
preL = preprocessor('symmetric', assume_immutability=True)
pre(G)
tol = 1.E-6
base_algorithms = {
"PPRL 0.85":
pygrank.algorithms.pagerank.PageRank(alpha=0.85,
to_scipy=preL,
max_iters=max_iters,
tol=tol),
"PPRL 0.90":
pygrank.algorithms.pagerank.PageRank(alpha=0.9,
to_scipy=preL,
max_iters=max_iters,
tol=tol),
"PPRL 0.95":