def test_absorbing_vs_pagerank():
graph = next(pg.load_datasets_graph(["graph9"]))
personalization = {"A": 1, "B": 1}
for _ in supported_backends():
pagerank_result = pg.PageRank(normalization='col').rank(graph, personalization)
absorbing_result = pg.AbsorbingWalks(0.85, normalization='col', max_iters=1000).rank(graph, personalization)
assert pg.Mabs(pagerank_result)(absorbing_result) < pg.epsilon()
def test_convergence_string_conversion():
# TODO: make convergence trackable from wrapping objects
graph = next(pg.load_datasets_graph(["graph5"]))
ranker = pg.PageRank() >> pg.Normalize()
ranker(graph)
assert str(ranker.convergence.iteration) + " iterations" in str(
ranker.convergence)
def test_separate_normalization():
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
algorithm = pg.PageRank(
preserve_norm=False) + pg.SeparateNormalization(["A", "B"])
ranks = algorithm(graph, {"A": 2})
assert abs(ranks["A"] + ranks["B"] - 1) < pg.epsilon()
def test_pagerank_vs_networkx():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
ranker = pg.Normalize("sum", pg.PageRank(normalization='col', tol=1.E-9))
test_result = ranker(graph)
test_result2 = nx.pagerank(graph, tol=1.E-9)
# TODO: assert that 2.5*epsilon is indeed a valid limit
assert pg.Mabs(test_result)(test_result2) < 2.5*pg.epsilon()
def test_ordinals():
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
test_result = pg.Ordinals(
pg.Ordinals(pg.Ordinals(pg.PageRank(normalization='col')))).rank(
graph,
{"A": 1}) # three ordinal transformations are the same as one
assert test_result["A"] == 1
def test_norm_maintain():
# TODO: investigate that 2.5*epsilon is truly something to be expected
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
prior = pg.to_signal(graph, {"A": 2})
posterior = pg.MabsMaintain(pg.Normalize(pg.PageRank(),
"range")).rank(prior)
assert abs(pg.sum(pg.abs(posterior.np)) - 2) < 2.5 * pg.epsilon()
def test_completion():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
pg.PageRank().rank(graph)
pg.HeatKernel().rank(graph)
pg.AbsorbingWalks().rank(graph)
pg.HeatKernel().rank(graph)
assert True
def test_kernel_locality():
graph = next(pg.load_datasets_graph(["graph9"]))
personalization = {"A": 1, "B": 1}
for _ in supported_backends():
for kernel_algorithm in [pg.HeatKernel, pg.BiasedKernel]:
pagerank_result = pg.Normalize("sum", pg.PageRank(max_iters=1000)).rank(graph, personalization)
kernel_result = pg.Normalize("sum", kernel_algorithm(max_iters=1000)).rank(graph, personalization)
assert pagerank_result['A'] < kernel_result['A']
assert pagerank_result['I'] > kernel_result['I']
def test_signal_init():
for backend in supported_backends():
with pytest.raises(Exception):
pg.GraphSignal([1, 2, 3], [1, 2])
signal = pg.GraphSignal(next(pg.load_datasets_graph(["graph9"])), {"A": 1, "B": 2})
if backend != "tensorflow":
del signal["A"]
assert signal["A"] == 0
assert signal["B"] == 2
def test_subgraph():
graph = next(pg.load_datasets_graph(["graph9"]))
signal1 = pg.to_signal(graph, {"A": 1, "B": 1, "C": 1, "D": 1, "E": 0.5})
assert "L" in signal1
signal2 = pg.Subgraph().rank(signal1)
assert signal2["E"] == 0.5
assert "L" not in signal2
signal3 = signal2 >> pg.Supergraph()
assert "L" in signal3
def test_correlation_compliance():
graph = next(pg.load_datasets_graph(["graph5"]))
# TODO: Make spearman and pearson correlation support tensorflow
alg1 = pg.PageRank(alpha=0.5)
alg2 = pg.PageRank(alpha=0.99)
pearson_ordinals = pg.PearsonCorrelation(pg.Ordinals(alg1)(graph))(
pg.Ordinals(alg2)(graph))
spearman = pg.SpearmanCorrelation(alg1(graph))(alg2(graph))
assert pearson_ordinals == spearman
def test_stream_diff():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
ranks1 = pg.GenericGraphFilter(
[0, 0, 1], max_iters=4, error_type="iters") | pg.to_signal(
graph, {"A": 1})
ranks2 = pg.GenericGraphFilter(
[1, 1, 1], tol=None) & ~pg.GenericGraphFilter(
[1, 1], tol=None) | pg.to_signal(graph, {"A": 1})
assert pg.Mabs(ranks1)(ranks2) < pg.epsilon()
def test_completion():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
pg.PageRank().rank(graph)
pg.PageRank(normalization="both").rank(graph)
pg.HeatKernel().rank(graph)
pg.AbsorbingWalks().rank(graph)
pg.SymmetricAbsorbingRandomWalks().rank(graph)
pg.HeatKernel().rank(graph)
assert True
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_quotient():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
test_result = pg.PageRank(normalization='symmetric',
tol=max(1.E-9, pg.epsilon()),
use_quotient=True).rank(graph)
norm_result = pg.PageRank(normalization='symmetric',
tol=max(1.E-9, pg.epsilon()),
use_quotient=pg.Normalize("sum")).rank(graph)
assert pg.Mabs(test_result)(norm_result) < pg.epsilon()
def test_abstract_filter_types():
graph = next(pg.load_datasets_graph(["graph5"]))
with pytest.raises(Exception):
pg.GraphFilter().rank(graph)
with pytest.raises(Exception):
pg.RecursiveGraphFilter().rank(graph)
with pytest.raises(Exception):
pg.ClosedFormGraphFilter().rank(graph)
with pytest.raises(Exception):
pg.Tuner().rank(graph)
def test_lanczos_speedup():
graph = next(pg.load_datasets_graph(["bigraph"]))
for _ in supported_backends():
for algorithm in [pg.HeatKernel]:
result = pg.Normalize(algorithm(normalization='symmetric')).rank(
graph, {"0": 1})
result_lanczos = pg.Normalize(
algorithm(normalization='symmetric',
krylov_dims=5)).rank(graph, {"0": 1})
assert pg.Mabs(result)(result_lanczos) < 0.01
def test_tautology():
graph = next(pg.load_datasets_graph(["bigraph"]))
r = pg.PageRank().rank(graph)
tr = pg.Tautology(pg.PageRank()).rank(graph)
rt = pg.Tautology().transform(r)
for u in graph:
assert r[u] == rt[u]
assert r[u] == tr[u]
u = pg.Tautology().rank(graph)
assert float(sum(u.np)) == len(graph)
def test_remove_edges():
graph = next(pg.load_datasets_graph(["graph5"]))
assert graph.has_edge("A", "B")
assert graph.has_edge("C", "D")
pg.remove_intra_edges(graph, {
"community1": ["A", "B"],
"community2": ["D", "C"]
})
assert graph.has_edge("B", "C")
assert not graph.has_edge("A", "B")
assert not graph.has_edge("C", "D")
def test_automatic_graph_casting():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
signal = pg.to_signal(graph, {"A": 1})
test_result1 = pg.PageRank(normalization='col').rank(signal, signal)
test_result2 = pg.PageRank(normalization='col').rank(personalization=signal)
assert pg.Mabs(test_result1)(test_result2) < pg.epsilon()
with pytest.raises(Exception):
pg.PageRank(normalization='col').rank(personalization={"A": 1})
with pytest.raises(Exception):
pg.PageRank(normalization='col').rank(graph.copy(), signal)
def test_stream():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
ranks1 = pg.Normalize(
pg.PageRank(0.85,
tol=pg.epsilon(),
max_iters=1000,
use_quotient=False)).rank(graph, {"A": 1})
ranks2 = pg.to_signal(graph, {"A": 1}) >> pg.PageRank(
0.85, tol=pg.epsilon(),
max_iters=1000) + pg.Tautology() >> pg.Normalize()
assert pg.Mabs(ranks1)(ranks2) < pg.epsilon()
def test_pagerank_vs_networkx():
graph = next(pg.load_datasets_graph(["graph9"], graph_api=nx))
graph = graph.to_directed()
# graph_api needed so that nx.pagerank can perform internal computations
for _ in supported_backends():
ranker = pg.Normalize("sum", pg.PageRank(normalization='col'))
test_result2 = nx.pagerank(graph)
test_result = ranker(graph)
print(test_result)
print(test_result2)
# TODO: assert that 2.5*epsilon is indeed a valid limit
assert pg.Mabs(test_result)(test_result2) < 2.5 * pg.epsilon()
def test_sequential():
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
prior = pg.to_signal(graph, {"A": 2})
posterior1 = pg.Normalize(pg.PageRank(), "range").rank(prior)
posterior2 = pg.Normalize("range")(pg.PageRank()(prior))
posterior3 = pg.Sequential(pg.PageRank(),
pg.Normalize("range")).rank(prior)
assert pg.sum(pg.abs(posterior1 - posterior2)) < pg.epsilon(
) # TODO: investigate when not exactly zero
assert pg.sum(pg.abs(posterior1 - posterior3)) < pg.epsilon(
) # TODO: investigate when not exactly zero
def test_filter_stream():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
test_result = pg.Normalize(
pg.PageRank(normalization='symmetric',
tol=max(1.E-9, pg.epsilon()),
use_quotient=True)).rank(graph)
norm_result = pg.PageRank(tol=max(1.E-9, pg.epsilon())) \
+ pg.preprocessor(normalization='symmetric') \
+ pg.Normalize("sum") \
>> pg.Normalize() \
| pg.to_signal(graph, {v: 1 for v in graph})
assert pg.Mabs(test_result)(norm_result) < pg.epsilon()
def test_remove_edges():
import networkx as nx
graph = next(pg.load_datasets_graph(["graph5"], graph_api=nx))
# TODO: make removing edges possible for fastgraph
assert graph.has_edge("A", "B")
assert graph.has_edge("C", "D")
pg.remove_intra_edges(graph, {
"community1": ["A", "B"],
"community2": ["D", "C"]
})
assert graph.has_edge("B", "C")
assert not graph.has_edge("A", "B")
assert not graph.has_edge("C", "D")
def test_venuerank():
graph = next(pg.load_datasets_graph(["bigraph"]))
for _ in supported_backends():
venuerank = pg.PageRank(alpha=0.85,
max_iters=10000,
converge_to_eigenvectors=True,
tol=1.E-12)
venuerank_result = venuerank.rank(graph)
small_restart = pg.PageRank(alpha=0.99, max_iters=10000, tol=1.E-12)
small_restart_result = small_restart.rank(graph)
#assert venuerank.convergence.iteration < small_restart.convergence.iteration / 2
corr = pg.SpearmanCorrelation(pg.Ordinals()(venuerank_result))(
pg.Ordinals()(small_restart_result))
assert corr > 0.99
def test_normalize():
import networkx as nx
graph = next(pg.load_datasets_graph(["graph5"]))
for _ in supported_backends():
assert float(
pg.sum(
pg.Normalize("range").transform(
pg.to_signal(nx.Graph([("A", "B")]), [2, 2])).np)) == 4
r = pg.Normalize(pg.PageRank(), "range").rank(graph)
assert pg.min(r.np) == 0
assert pg.max(r.np) == 1
r = pg.Normalize(pg.PageRank(), "sum").rank(graph)
assert abs(pg.sum(r.np) - 1) < pg.epsilon()
with pytest.raises(Exception):
pg.Normalize(pg.PageRank(), "unknown").rank(graph)
def test_custom_runs():
graph = next(pg.load_datasets_graph(["graph9"]))
for _ in supported_backends():
ranks1 = pg.Normalize(
pg.PageRank(0.85,
tol=pg.epsilon(),
max_iters=1000,
use_quotient=False)).rank(graph, {"A": 1})
ranks2 = pg.Normalize(
pg.GenericGraphFilter([0.85**i * len(graph) for i in range(80)],
tol=pg.epsilon())).rank(graph, {"A": 1})
ranks3 = pg.Normalize(
pg.LowPassRecursiveGraphFilter([0.85 for _ in range(80)],
tol=pg.epsilon())).rank(
graph, {"A": 1})
assert pg.Mabs(ranks1)(ranks2) < 1.E-6
assert pg.Mabs(ranks1)(ranks3) < 1.E-6
def test_optimization_dict():
pg.load_backend("numpy")
from timeit import default_timer as time
graph = next(pg.load_datasets_graph(["bigraph"]))
personalization = {str(i): 1 for i in range(200)}
preprocessor = pg.preprocessor(assume_immutability=True)
preprocessor(graph)
tic = time()
for _ in range(10):
pg.ParameterTuner(preprocessor=preprocessor, tol=1.E-9).rank(graph, personalization)
unoptimized = time()-tic
optimization = dict()
tic = time()
for _ in range(10):
pg.ParameterTuner(optimization_dict=optimization, preprocessor=preprocessor, tol=1.E-9).rank(graph, personalization)
optimized = time() - tic
assert len(optimization) == 20
assert unoptimized > optimized
def test_fastgraph():
for graph_api in [pg.fastgraph, nx]:
graph = next(pg.load_datasets_graph(["graph5"], graph_api=graph_api))
assert graph.has_edge("A", "B")
assert not graph.has_edge("A", "E")
graph.add_edge("A", "E")
assert graph.has_edge("A", "E")
assert graph.has_edge(
"E", "A") # checks that undirected is the default mode
prev_count = graph.number_of_edges()
graph.remove_edge("A", "E")
assert graph.number_of_edges() == prev_count - 1
sparse = graph.to_scipy_sparse_array() if isinstance(
graph, pg.Graph) else nx.to_scipy_sparse_matrix(
graph, weight="weight", dtype=float)
assert pg.sum(sparse) == 14
assert not graph.has_edge("A", "E")
assert not graph.has_edge("E", "A")
graph.add_edge("A", "E")
assert graph.has_edge("A", "E")
graph.add_edge("Y", "Z")
assert graph.has_edge("Y", "Z")
