def test_propagation():
"""Picklability test for the Propagation kernel."""
train, _ = generate_dataset(n_graphs=100,
r_vertices=(10, 20),
r_connectivity=(0.4, 0.8),
r_weight_edges=(float("1e-5"), 10),
n_graphs_test=40,
random_state=rs,
features=('nl', 4))
propagation_kernel = Propagation(verbose=verbose, normalize=normalize)
propagation_kernel.fit(train)
assert is_picklable(propagation_kernel)
train, _ = generate_dataset(n_graphs=100,
r_vertices=(10, 20),
r_connectivity=(0.4, 0.8),
r_weight_edges=(float("1e-5"), 10),
n_graphs_test=40,
random_state=rs,
features=('na', 5))
propagation_kernel_attr = PropagationAttr(verbose=verbose,
normalize=normalize)
propagation_kernel_attr.fit(train)
assert is_picklable(propagation_kernel_attr)
def test_propagation():
"""Eigenvalue test for the Propagation kernel."""
propagation_kernel = Propagation(verbose=verbose, normalize=normalize)
if verbose:
print_kernel("Propagation", propagation_kernel, dataset_tr, dataset_te)
else:
positive_eig(propagation_kernel, dataset)
propagation_kernel_attr = PropagationAttr(verbose=verbose, normalize=normalize)
if verbose:
print_kernel("Propagation", propagation_kernel_attr, dataset_attr_tr, dataset_attr_te)
else:
positive_eig(propagation_kernel_attr, dataset_attr)
def __init__(self,
kernel,
detector,
labeled=True,
WL_iter=5,
PK_bin_width=1,
LOF_n_neighbors=20,
LOF_n_leaf=30,
**kwargs):
kernels = {
'WL':
WeisfeilerLehman(n_iter=WL_iter,
normalize=True,
base_graph_kernel=VertexHistogram),
'PK':
Propagation(t_max=WL_iter, w=PK_bin_width, normalize=True)
if labeled else PropagationAttr(
t_max=WL_iter, w=PK_bin_width, normalize=True),
}
detectors = {
'OCSVM':
OneClassSVM(kernel='precomputed', nu=0.1),
'LOF':
LocalOutlierFactor(n_neighbors=LOF_n_neighbors,
leaf_size=LOF_n_leaf,
metric='precomputed',
contamination=0.1),
# 'IF': current similarity forest also has problem
}
assert kernel in kernels.keys()
assert detector in detectors.keys()
self.kernel = kernels[kernel]
self.detector = detectors[detector]
self.kernel_name = kernel
self.detector_name = detector
self.labeled = labeled
def test_propagation():
"""Random input test for the Propagation kernel."""
train, test = generate_dataset(n_graphs=100,
r_vertices=(10, 20),
r_connectivity=(0.4, 0.8),
r_weight_edges=(float("1e-5"), 10),
n_graphs_test=40,
random_state=rs,
features=('nl', 4))
propagation_kernel = Propagation(verbose=verbose, normalize=normalize)
try:
propagation_kernel.fit_transform(train)
propagation_kernel.transform(test)
assert True
except Exception as exception:
assert False, exception
train, test = generate_dataset(n_graphs=100,
r_vertices=(10, 20),
r_connectivity=(0.4, 0.8),
r_weight_edges=(float("1e-5"), 10),
n_graphs_test=40,
random_state=rs,
features=('na', 5))
propagation_kernel_attr = PropagationAttr(verbose=verbose,
normalize=normalize)
try:
propagation_kernel_attr.fit_transform(train)
propagation_kernel_attr.transform(test)
assert True
except Exception as exception:
assert False, exception
"GK-RandomWalk":
lambda: RandomWalk(n_jobs=N_JOBS, normalize=NORMALIZING_GRAPH_KERNELS
), # taking too long
"GK-RandomWalkLabeled":
lambda: RandomWalkLabeled(
n_jobs=N_JOBS, normalize=NORMALIZING_GRAPH_KERNELS), # taking too long
"GK-GraphHopper":
lambda: GraphHopper(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-PyramidMatch":
lambda: PyramidMatch(normalize=NORMALIZING_GRAPH_KERNELS), # Error with PG
"GK-LovaszTheta":
lambda: LovaszTheta(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-SvmTheta":
lambda: SvmTheta(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-Propagation":
lambda: Propagation(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-PropagationA":
lambda: PropagationAttr(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-MScLaplacian":
lambda: MultiscaleLaplacian(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-OddSth":
lambda: OddSth(normalize=NORMALIZING_GRAPH_KERNELS),
"GK-SubgraphMatching":
lambda: SubgraphMatching(normalize=NORMALIZING_GRAPH_KERNELS
), # taking too long
}
def test_prediction_on_Grakel_kernels(graphs: pd.DataFrame,
y_column: str,
cv_sets=None,