def test_transform():
import math
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
r1 = pg.Normalize(pg.PageRank(), "sum").rank(graph)
r2 = pg.Transformer(pg.PageRank(), lambda x: x / pg.sum(x)).rank(graph)
assert pg.Mabs(r1)(r2) < pg.epsilon()
r1 = pg.Transformer(math.exp).transform(pg.PageRank()(graph))
r2 = pg.Transformer(pg.PageRank(), pg.exp).rank(graph)
assert pg.Mabs(r1)(r2) < pg.epsilon()
def test_sweep_streaming():
_, graph, group = next(pg.load_datasets_one_community(["bigraph"]))
for _ in supported_backends():
training, evaluation = pg.split(list(group), training_samples=0.1)
auc1 = pg.AUC({v: 1
for v in evaluation}, exclude=training).evaluate(
(pg.PageRank() >> pg.Sweep()).rank(
graph, {v: 1
for v in training}))
auc2 = pg.AUC({v: 1
for v in evaluation},
exclude=training).evaluate(pg.PageRank().rank(
graph, {v: 1
for v in training}))
auc3 = pg.AUC(
{v: 1
for v in evaluation}, exclude=training).evaluate(
pg.PageRank() >> pg.Transformer(pg.log) >> pg.LinearSweep()
| pg.to_signal(graph, {v: 1
for v in training}))
assert auc1 > auc2
assert abs(auc1 - auc3) < pg.epsilon()
with pytest.raises(Exception):
pg.Sweep() << "a"
def test_explicit_citations():
assert "unknown node ranking algorithm" == pg.NodeRanking().cite()
assert "with parameters tuned \cite{krasanakis2021pygrank}" in pg.ParameterTuner(
lambda params: pg.PageRank(params[0])).cite()
assert "Postprocessor" in pg.Postprocessor().cite()
assert pg.PageRank().cite() in pg.AlgorithmSelection().cite()
assert "krasanakis2021pygrank" in pg.ParameterTuner().cite()
assert "ortega2018graph" in pg.ParameterTuner().cite()
assert pg.HeatKernel().cite() in pg.SeedOversampling(pg.HeatKernel()).cite()
assert pg.AbsorbingWalks().cite() in pg.BoostedSeedOversampling(pg.AbsorbingWalks()).cite()
assert "krasanakis2018venuerank" in pg.BiasedKernel(converge_to_eigenvectors=True).cite()
assert "yu2021chebyshev" in pg.HeatKernel(coefficient_type="chebyshev").cite()
assert "susnjara2015accelerated" in pg.HeatKernel(krylov_dims=5).cite()
assert "krasanakis2021pygrank" in pg.GenericGraphFilter(optimization_dict=dict()).cite()
assert "tautology" in pg.Tautology().cite()
assert pg.PageRank().cite() == pg.Tautology(pg.PageRank()).cite()
assert "mabs" in pg.MabsMaintain(pg.PageRank()).cite()
assert "max normalization" in pg.Normalize(pg.PageRank()).cite()
assert "[0,1] range" in pg.Normalize(pg.PageRank(), "range").cite()
assert "ordinal" in pg.Ordinals(pg.PageRank()).cite()
assert "exp" in pg.Transformer(pg.PageRank()).cite()
assert "0.5" in pg.Threshold(pg.PageRank(), 0.5).cite()
assert "andersen2007local" in pg.Sweep(pg.PageRank()).cite()
assert pg.HeatKernel().cite() in pg.Sweep(pg.PageRank(), pg.HeatKernel()).cite()
assert "LFPRO" in pg.AdHocFairness("O").cite()
assert "LFPRO" in pg.AdHocFairness(pg.PageRank(), "LFPRO").cite()
assert "multiplicative" in pg.AdHocFairness(pg.PageRank(), "B").cite()
assert "multiplicative" in pg.AdHocFairness(pg.PageRank(), "mult").cite()
assert "tsioutsiouliklis2020fairness" in pg.AdHocFairness().cite()
assert "rahman2019fairwalk" in pg.FairWalk(pg.PageRank()).cite()
assert "krasanakis2020prioredit" in pg.FairPersonalizer(pg.PageRank()).cite()
def test_postprocessor_citations():
assert pg.Tautology(pg.PageRank()).cite() == pg.PageRank().cite()
assert pg.Normalize(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.Normalize(pg.PageRank(), "sum").cite() != pg.Normalize(pg.PageRank(), "range").cite()
assert pg.Ordinals(pg.PageRank()).cite() != pg.Normalize(pg.PageRank(), "sum").cite()
assert pg.Transformer(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.Threshold(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.Sweep(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.BoostedSeedOversampling(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.SeedOversampling(pg.PageRank()).cite() != pg.PageRank().cite()
assert pg.SeedOversampling(pg.PageRank(), method="safe").cite() \
!= pg.SeedOversampling(pg.PageRank(), method="top").cite()
assert pg.BoostedSeedOversampling(pg.PageRank(), objective="partial").cite() \
!= pg.BoostedSeedOversampling(pg.PageRank(), objective="naive").cite()
assert pg.BoostedSeedOversampling(pg.PageRank(), oversample_from_iteration="previous").cite() \
!= pg.BoostedSeedOversampling(pg.PageRank(), oversample_from_iteration="original").cite()
def test_sweep():
_, graph, group = next(pg.load_datasets_one_community(["bigraph"]))
for _ in supported_backends():
training, evaluation = pg.split(list(group), training_samples=0.1)
auc1 = pg.AUC({v: 1
for v in evaluation}, exclude=training).evaluate(
pg.Sweep(pg.PageRank()).rank(
graph, {v: 1
for v in training}))
auc2 = pg.AUC({v: 1
for v in evaluation},
exclude=training).evaluate(pg.PageRank().rank(
graph, {v: 1
for v in training}))
auc3 = pg.AUC({v: 1
for v in evaluation}, exclude=training).evaluate(
pg.LinearSweep(pg.Transformer(
pg.PageRank(),
pg.log)).rank(graph, {v: 1
for v in training}))
assert auc1 > auc2
assert auc1 == auc3