class CliqueInERDetector:
def __init__(self, v, p, cs, d, num_run=0):
self._params = {
'vertices': v,
'probability': p,
'clique_size': cs,
'directed': d,
'load_graph': False,
'load_labels': False,
'load_motifs': False
}
self._key_name = f"n_{v}_p_{p}_size_{cs}_{'d' if d else 'ud'})"
self._dir_path = os.path.join(os.path.dirname(__file__), '..',
'graph_calculations', 'pkl',
self._key_name + '_runs',
self._key_name + "_run_" + str(num_run))
self._data = GraphBuilder(self._params, self._dir_path)
self._graph = self._data.graph()
self._labels = self._data.labels()
self._motif_calc = MotifCalculator(self._params,
self._graph,
self._dir_path,
gpu=True,
device=2)
self._motif_matrix = self._motif_calc.motif_matrix(
motif_picking=self._motif_calc.clique_motifs())
# self.detect_clique()
def detect_clique(self):
detector = DetectClique(graph=self._graph,
matrix=self._motif_matrix,
labels=self._labels,
dir_path=self._dir_path)
suspected_vertices = detector.irregular_vertices(to_scale=False)
vertex_label = [(v, self._labels[v]) for v in suspected_vertices]
print(vertex_label)
def _load_other_things(self):
graph_ids = os.listdir(self._head_path)
self._gnxs = []
self._labels_by_run = []
self._all_labels = []
for run in range(len(graph_ids)):
dir_path = os.path.join(self._head_path,
self._key_name + "_run_" + str(run))
data = GraphBuilder(self._params, dir_path)
gnx = data.graph()
self._gnxs.append(gnx)
labels = data.labels()
self._labels_by_run.append(labels)
if type(labels) == dict:
new_labels = [y for x, y in labels.items()]
self._all_labels += new_labels
else:
self._all_labels += labels
self._mp = MotifProbability(self._params['vertices'],
self._params['probability'],
self._params['clique_size'],
self._params['directed'])
self._clique_motifs = self._mp.get_3_clique_motifs(3) + self._mp.get_3_clique_motifs(4) \
if self._motifs_picked is None else self._motifs_picked
def _load_data(self, check):
graph_ids = os.listdir(self._head_path)
if len(graph_ids) == 0:
if self._num_runs == 0:
raise ValueError(
f"No runs of G({self._params['vertices']}, {self._params['probability']}) "
f"with a clique of size {self._params['clique_size']} were saved, "
f"and no new runs were requested.")
self._feature_matrices = []
self._labels = []
motifs_picked = []
for run in range(0, len(graph_ids) + self._num_runs):
dir_path = os.path.join(self._head_path,
self._key_name + "_run_" + str(run))
data = GraphBuilder(self._params, dir_path)
gnx = data.graph()
labels = data.labels()
mc = MotifCalculator(self._params,
gnx,
dir_path,
gpu=True,
device=1)
motifs_picked = [
i for i in range(mc.mp.get_3_clique_motifs(3)[0] + 1)
]
mc.build_all(motifs_picked)
motif_matrix = mc.motif_matrix()
self._feature_matrices.append(motif_matrix)
if type(labels) == dict:
new_labels = [[y for x, y in labels.items()]]
self._labels += new_labels
else:
self._labels += [labels]
self._extra_parameters(motifs=motifs_picked)
self._scale_matrices()
if check == -1: # Training-test split or cross-validation, where in CV the left-out graph index is given.
rand_test_indices = np.random.choice(
len(graph_ids) + self._num_runs,
round((len(graph_ids) + self._num_runs) * 0.2),
replace=False)
train_indices = np.delete(
np.arange(len(graph_ids) + self._num_runs), rand_test_indices)
self._test_features = [
self._feature_matrices[j] for j in rand_test_indices
]
self._test_labels = [self._labels[j] for j in rand_test_indices]
self._training_features = [
self._feature_matrices[j] for j in train_indices
]
self._training_labels = [self._labels[j] for j in train_indices]
else:
one_out = check
train_indices = np.delete(
np.arange(len(graph_ids) + self._num_runs), one_out)
self._test_features = [self._feature_matrices[one_out]]
self._test_labels = [self._labels[one_out]]
self._training_features = [
self._feature_matrices[j] for j in train_indices
]
self._training_labels = [self._labels[j] for j in train_indices]
