def test_fair_heuristics():
H = pg.PageRank(assume_immutability=True, normalization="symmetric")
algorithms = {
"FairO": lambda G, p, s: pg.Normalize(pg.AdHocFairness(H, method="O")).rank(G, sensitive=s),
"FairB": lambda G, p, s: pg.Normalize()(pg.AdHocFairness("B").transform(H.rank(G, p), sensitive=s)),
"LFPRN": lambda G, p, s: pg.Normalize()(pg.LFPR().rank(G, p, sensitive=s)),
"LFPRP": lambda G, p, s: pg.Normalize()(pg.LFPR(redistributor="original").rank(G, p, sensitive=s)),
"FairWalk": lambda G, p, s: pg.FairWalk(H).rank(G, p, sensitive=s)
}
import networkx as nx
_, graph, groups = next(pg.load_datasets_multiple_communities(["bigraph"], graph_api=nx))
# TODO: networx needed due to edge weighting by some algorithms
labels = pg.to_signal(graph, groups[0])
sensitive = pg.to_signal(graph, groups[1])
for name, algorithm in algorithms.items():
ranks = algorithm(graph, labels, sensitive)
if name == "FairWalk":
assert pg.pRule(sensitive)(ranks) > 0.6 # TODO: Check why fairwalk fails by that much and increase the limit.
else:
assert pg.pRule(sensitive)(ranks) > 0.98
sensitive = 1 - sensitive.np
for name, algorithm in algorithms.items():
ranks = algorithm(graph, labels, sensitive)
if name == "FairWalk":
assert pg.pRule(sensitive)(ranks) > 0.6
else:
assert pg.pRule(sensitive)(ranks) > 0.98
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_fair_heuristics():
H = pg.PageRank(assume_immutability=True, normalization="symmetric")
algorithms = {
"FairO":
lambda G, p, s: pg.Normalize(pg.AdHocFairness(H, method="O")).rank(
G, sensitive=s),
"FairB":
lambda G, p, s: pg.Normalize()
(pg.AdHocFairness("B").transform(H.rank(G, p), sensitive=s)),
"FairWalk":
lambda G, p, s: pg.FairWalk(H).rank(G, p, sensitive=s)
}
_, graph, groups = next(pg.load_datasets_multiple_communities(["bigraph"]))
labels = pg.to_signal(graph, groups[0])
sensitive = pg.to_signal(graph, groups[1])
for algorithm in algorithms.values():
ranks = algorithm(graph, labels, sensitive)
assert pg.pRule(sensitive)(
ranks
) > 0.6 # TODO: Check why fairwalk fails by that much and increase the limit.
sensitive = 1 - sensitive.np
for algorithm in algorithms.values():
ranks = algorithm(graph, labels, sensitive)
assert pg.pRule(sensitive)(ranks) > 0.6
def test_invalid_fairness_arguments():
_, graph, groups = next(pg.load_datasets_multiple_communities(["bigraph"]))
labels = pg.to_signal(graph, groups[0])
sensitive = pg.to_signal(graph, groups[1])
H = pg.PageRank(assume_immutability=True, normalization="symmetric")
with pytest.raises(Exception):
# this tests that a deprecated way of applying fairwalk actually raises an exception
pg.AdHocFairness(H, method="FairWalk").rank(graph, labels, sensitive=sensitive)
with pytest.raises(Exception):
pg.FairPersonalizer(H, parity_type="universal").rank(graph, labels, sensitive=sensitive)
with pytest.raises(Exception):
pg.FairWalk(None).transform(H.rank(graph, labels), sensitive=sensitive)
"ppr0.99":
pg.PageRank(alpha=0.99, preprocessor=pre, max_iters=10000, tol=1.E-6),
"hk3":
pg.HeatKernel(t=3, preprocessor=pre, max_iters=10000, tol=1.E-6),
"hk7":
pg.HeatKernel(t=7, preprocessor=pre, max_iters=10000, tol=1.E-6),
}
filters = pg.create_variations(filters, {"": pg.Tautology, "+Sweep": pg.Sweep})
for name, filter in filters.items():
print("=====", name, "=====")
algorithms = {
"None":
filter,
"Mult":
pg.AdHocFairness(filter, "B"),
"LFPRO":
pg.AdHocFairness(filter, "O"),
#"FBuck-C": pg.FairPersonalizer(filter, .8, pRule_weight=10, max_residual=1, error_type=pg.Mabs, parameter_buckets=0),
"FPers-C":
pg.FairPersonalizer(filter,
.8,
pRule_weight=10,
max_residual=0,
error_type=pg.Mabs,
error_skewing=True,
parity_type="impact"),
"Fest-C":
pg.FairPersonalizer(filter,
.8,
pRule_weight=10,