def create_H(args):
source_dataset = Dataset(args.source_dataset)
target_dataset = Dataset(args.target_dataset)
src_degrees = np.array(source_dataset.get_nodes_degrees())
trg_degrees = np.array(target_dataset.get_nodes_degrees())
# import pdb
# pdb.set_trace()
# src_degrees = src_degrees/src_degrees.max()
# trg_degrees = trg_degrees/trg_degrees.max()
#
# distance_matrix = np.zeros((len(src_degrees), len(trg_degrees)))
# for src_idx, src_deg in enumerate(src_degrees):
# for trg_idx, trg_deg in enumerate(trg_degrees):
# distance_matrix[src_idx,trg_idx] = np.abs(src_deg-trg_deg)
# max_distance = distance_matrix.max()
# H = 1-distance_matrix/max_distance
# H = H.T
H = np.zeros((len(trg_degrees), len(src_degrees)))
for i in range(H.shape[0]):
H[i, :] = np.abs(trg_degrees[i] - src_degrees) / max(
[src_degrees.max(), trg_degrees[i]])
H = H / H.sum()
# H = np.zeros((len(trg_degrees),len(src_degrees)))
# for i, trg_deg in enumerate(trg_degrees):
# for j, src_deg in enumerate(src_degrees):
# H[i,j]=1-min([src_deg,trg_deg])/max([src_deg,trg_deg])
# idxs_trg = np.random.choice(H.shape[0],2000000,replace=True)
# idxs_src = np.random.choice(H.shape[1],2000000,replace=True)
# H[idxs_trg,idxs_src]=0
print("H shape: ", H.shape)
if not os.path.exists(args.out_dir):
os.makedirs(args.out_dir)
np.save(args.out_dir + "/H2.npy", H)
print("H has been saved to ", args.out_dir)
file.write(json.dumps(res))
if __name__ == "__main__":
args = parse_args()
source_dataset = Dataset(args.source_dataset)
target_dataset = Dataset(args.target_dataset)
groundtruth = graph_utils.load_gt(args.groundtruth, source_dataset.id2idx,
target_dataset.id2idx, 'dict')
source_groundtruth_nodes = list(groundtruth.keys())
target_groundtruth_nodes = list(groundtruth.values())
source_idx2id = {v: k for k, v in source_dataset.id2idx.items()}
target_idx2id = {v: k for k, v in target_dataset.id2idx.items()}
source_gt_id = [source_idx2id[node] for node in source_groundtruth_nodes]
target_gt_id = [target_idx2id[node] for node in target_groundtruth_nodes]
source_care_deg = source_dataset.get_nodes_degrees(
)[source_groundtruth_nodes]
target_care_deg = target_dataset.get_nodes_degrees(
)[target_groundtruth_nodes]
print("Number of nodes in groundtruth: {}".format(len(groundtruth)))
print("Num source nodes: {}".format(len(source_dataset.G.nodes())))
print("Num target nodes: {}".format(len(target_dataset.G.nodes())))
# print("Source care deg: {}".format(source_care_deg))
# print("Source care deg: {}".format(target_care_deg))
G1 = filter_nodes(source_dataset.G, source_gt_id, 1)
G2 = filter_nodes(target_dataset.G, target_gt_id, 1)
# save G
source_node_left = G1.nodes()
target_node_left = G2.nodes()
# save id2idx
source_id2idx = {
