def test_autorefs():
"""
Tests that different (base) algorithms yield different citations, that all citations have at least one
reference to a publication and that wrapping the same base algorithms yields the same citations.
"""
pre = pg.preprocessor(assume_immutability=True, normalization="symmetric")
algs = {
"ppr.85": pg.PageRank(.85, preprocessor=pre, tol=1.E-9,
max_iters=1000),
"ppr.99": pg.PageRank(.99, preprocessor=pre, tol=1.E-9,
max_iters=1000),
"hk3": pg.HeatKernel(3, preprocessor=pre, tol=1.E-9, max_iters=1000),
"hk5": pg.HeatKernel(5, preprocessor=pre, tol=1.E-9, max_iters=1000),
"hk5'": pg.HeatKernel(5, preprocessor=pre, tol=1.E-9, max_iters=1000),
}
algs = algs | pg.create_variations(
algs, {
"+Sweep": pg.Sweep,
"+SO": pg.SeedOversampling,
"+BSO": pg.BoostedSeedOversampling
})
citations = set()
for alg in algs.values():
citation = alg.cite()
assert "\\cite{" in citation
citations.add(citation)
assert len(citations) == len(algs) - 4
def test_unsupervised_vs_auc():
def loader():
return pg.load_datasets_multiple_communities(["graph9"])
algorithms = pg.create_variations(pg.create_many_filters(), pg.create_many_variation_types())
time_scores = pg.benchmark_scores(pg.benchmark(algorithms, loader(), pg.Time))
assert sum(time_scores) > 0
measures = {"AUC": lambda ground_truth, exlude: pg.MultiSupervised(pg.AUC, ground_truth, exlude),
"NDCG": lambda ground_truth, exlude: pg.MultiSupervised(pg.NDCG, ground_truth, exlude),
"Density": lambda graph: pg.MultiUnsupervised(pg.Density, graph),
"Conductance": lambda graph: pg.MultiUnsupervised(pg.Conductance(autofix=True).as_unsupervised_method(), graph),
"Modularity": lambda graph: pg.MultiUnsupervised(pg.Modularity(max_positive_samples=5).as_unsupervised_method(), graph),
"CCcos": lambda graph: pg.ClusteringCoefficient(graph, similarity="cos", max_positive_samples=5),
"CCdot": lambda graph: pg.ClusteringCoefficient(graph, similarity="dot", max_positive_samples=5),
"LinkAUCcos": lambda graph: pg.LinkAssessment(graph, similarity="cos", max_positive_samples=5),
"LinkAUCdot": lambda graph: pg.LinkAssessment(graph, similarity="dot", max_positive_samples=5),
"HopAUCcos": lambda graph: pg.LinkAssessment(graph, similarity="cos", hops=2, max_positive_samples=5),
"HopAUCdot": lambda graph: pg.LinkAssessment(graph, similarity="dot", hops=2, max_positive_samples=5),
}
scores = {}#measure: pg.benchmark_scores(pg.benchmark(algorithms, loader(), measures[measure])) for measure in measures}
for measure in measures: # do this as a for loop, because pytest becomes a little slow above list comprehension
scores[measure] = pg.benchmark_scores(pg.benchmark(algorithms, loader(), measures[measure]))
supervised = {"AUC", "NDCG"}
evaluations = dict()
for measure in measures:
evaluations[measure] = abs(pg.SpearmanCorrelation(scores["AUC"])(scores[measure]))
#for measure in measures:
# print(measure, evaluations[measure])
assert max([evaluations[measure] for measure in measures if measure not in supervised]) == evaluations["LinkAUCdot"]
def test_algorithm_selection():
for _ in supported_backends():
_, graph, communities = next(
pg.load_datasets_multiple_communities(["bigraph"],
max_group_number=3))
train, test = pg.split(communities,
0.05) # 5% of community members are known
algorithms = pg.create_variations(pg.create_demo_filters(),
pg.Normalize)
supervised_algorithm = pg.AlgorithmSelection(algorithms.values(),
measure=pg.AUC,
tuning_backend="numpy")
print(supervised_algorithm.cite())
modularity_algorithm = pg.AlgorithmSelection(
algorithms.values(),
fraction_of_training=1,
measure=pg.Modularity().as_supervised_method(),
tuning_backend="numpy")
supervised_aucs = list()
modularity_aucs = list()
for seeds, members in zip(train.values(), test.values()):
measure = pg.AUC(members, exclude=seeds)
supervised_aucs.append(measure(supervised_algorithm(graph, seeds)))
modularity_aucs.append(measure(modularity_algorithm(graph, seeds)))
assert abs(
sum(supervised_aucs) / len(supervised_aucs) -
sum(modularity_aucs) / len(modularity_aucs)) < 0.05
"facebook0", "facebook686", "log4j", "ant", "eucore", "citeseer", "dblp"
]
seed_fractions = [0.3, 0.5]
pre = pg.preprocessor(assume_immutability=True, normalization="symmetric")
filters = {
"ppr0.85":
pg.PageRank(alpha=0.85, preprocessor=pre, max_iters=10000, tol=1.E-6),
"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,
import pygrank as pg
datasets = ["EUCore", "Amazon"]
pre = pg.preprocessor(assume_immutability=True, normalization="symmetric")
algs = {
"ppr.85": pg.PageRank(.85, preprocessor=pre, tol=1.E-9, max_iters=1000),
"ppr.99": pg.PageRank(.99, preprocessor=pre, tol=1.E-9, max_iters=1000),
"hk3": pg.HeatKernel(3, preprocessor=pre, tol=1.E-9, max_iters=1000),
"hk5": pg.HeatKernel(5, preprocessor=pre, tol=1.E-9, max_iters=1000),
}
algs = algs | pg.create_variations(algs, {"+Sweep": pg.Sweep})
loader = pg.load_datasets_one_community(datasets)
algs["tuned"] = pg.ParameterTuner(preprocessor=pre, tol=1.E-9, max_iters=1000)
algs["selected"] = pg.AlgorithmSelection(
pg.create_demo_filters(preprocessor=pre, tol=1.E-9,
max_iters=1000).values())
algs["tuned+Sweep"] = pg.ParameterTuner(
ranker_generator=lambda params: pg.Sweep(
pg.GenericGraphFilter(
params, preprocessor=pre, tol=1.E-9, max_iters=1000)))
for alg in algs.values():
print(alg.cite()) # prints a list of algorithm citations
pg.benchmark_print(pg.benchmark(algs, loader, pg.AUC, fraction_of_training=.5),
delimiter=" & ",
end_line="\\\\")
import pygrank as pg
loader = list(pg.load_datasets_multiple_communities(["bigraph", "cora", "citeseer"]))
algorithms = pg.create_variations(pg.create_demo_filters(), pg.create_many_variation_types())
algorithms = pg.create_variations(algorithms, pg.Normalize) # add normalization to all algorithms
print("Algorithms", len(algorithms))
measures = {"AUC": lambda ground_truth, exlude: pg.MultiSupervised(pg.AUC, ground_truth, exlude),
"NDCG": lambda ground_truth, exlude: pg.MultiSupervised(pg.NDCG, ground_truth, exlude),
"Density": lambda graph: pg.MultiUnsupervised(pg.Density, graph),
"Modularity": lambda graph: pg.MultiUnsupervised(pg.Modularity, graph),
"LinkCC": lambda graph: pg.ClusteringCoefficient(graph, similarity="dot"),
"LinkAUCcos": lambda graph: pg.LinkAssessment(graph, similarity="cos"),
"HopAUCdot": lambda graph: pg.LinkAssessment(graph, similarity="dot", hops=2),
}
scores = {measure: pg.benchmark_scores(pg.benchmark(algorithms, loader, measures[measure])) for measure in measures}
evaluations_vs_auc = dict()
evaluations_vs_ndcg = dict()
for measure in measures:
evaluations_vs_auc[measure] = abs(pg.SpearmanCorrelation(scores["AUC"])(scores[measure]))
evaluations_vs_ndcg[measure] = abs(pg.SpearmanCorrelation(scores["NDCG"])(scores[measure]))
pg.benchmark_print([("Measure", "AUC corr", "NDCG corr")]
+ [(measure, evaluations_vs_auc[measure], evaluations_vs_ndcg[measure]) for measure in measures])
import pygrank as pg
_, graph, community = next(pg.load_datasets_one_community(["EUCore"]))
algorithm = pg.HeatKernel(
t=5, # the number of hops away HeatKernel places maximal importance on
normalization="symmetric",
renormalize=True)
personalization = {node: 1.
for node in community} # ignored nodes assumed to be zeroes
algorithms = {
"HK5": algorithm,
"HK5+Oversampling": pg.SeedOversampling(algorithm)
}
algorithms = algorithms | pg.create_variations(algorithms,
{"+Sweep": pg.Sweep})
algorithms = pg.create_variations(algorithms, {"": pg.Normalize})
measure = pg.Conductance()
for algorithm_name, algorithm in algorithms.items():
scores = algorithm(graph,
personalization) # returns a dict-like pg.GraphSignal
print(algorithm_name, measure(scores))
import pygrank as pg
_, graph, communities = next(
pg.load_datasets_multiple_communities(["EUCore"], max_group_number=3))
train, test = pg.split(communities, 0.05) # 5% of community members are known
algorithms = pg.create_variations(pg.create_demo_filters(), pg.Normalize)
supervised_algorithm = pg.AlgorithmSelection(algorithms.values(),
measure=pg.AUC)
print(supervised_algorithm.cite())
modularity_algorithm = pg.AlgorithmSelection(
algorithms.values(),
fraction_of_training=1,
measure=pg.Modularity().as_supervised_method())
linkauc_algorithm = None
best_evaluation = 0
linkAUC = pg.LinkAssessment(
graph, similarity="cos",
hops=1) # LinkAUC, because emails systemically exhibit homophily
for algorithm in algorithms.values():
evaluation = linkAUC.evaluate({
community: algorithm(graph, seeds)
for community, seeds in train.items()
})
if evaluation > best_evaluation:
best_evaluation = evaluation
linkauc_algorithm = algorithm
supervised_aucs = list()
modularity_aucs = list()
linkauc_aucs = list()
