parser.add_argument("--epochs",
type=int,
default=10,
help="Number of epochs during training")
parser.add_argument("--classifier",
type=str,
default='SVM',
choices={'NN', 'SVM'},
help="Downstream Classifier")
parser.add_argument("--seed", type=int, default=0, help="Random Seed")
args = parser.parse_args()
np.random.seed(args.seed)
torch.manual_seed(args.seed)
data_path = f'Datasets/{args.data_name}'
db = Database.load_csv(data_path)
model_dir = f'models/{args.data_name}/{args.kernel}_{args.depth}_{args.dim}_{args.num_samples}_{args.epochs}_{args.batch_size}_{args.seed}'
os.makedirs(model_dir, exist_ok=True)
sample_fct = ek_utlis.ek_sample_fct if args.kernel == 'EK' else mmd_utils.mmd_sample_fct
Y, rows = db.get_labels()
scores = []
split = StratifiedShuffleSplit(train_size=0.9, random_state=0, n_splits=10)
for i, (train_index, test_index) in enumerate(split.split(rows, Y)):
samples = get_samples(db, args.depth, args.num_samples, sample_fct)
row_idx = {r: i for i, r in enumerate(rows)}
scheme_idx = {s: i for i, s in enumerate(samples.keys())}
def compute_embedding(db):
G = db.get_row_val_graph_reg()
embedding, model = get_node2vec_embedding_new(G, epochs=5)
return embedding, model
if __name__ == "__main__":
name = 'mutagenesis'
embedding_name = 'testn3.pckl'
path = f'Datasets/{name}'
embedding_path = f'Embeddings/{name}/{embedding_name}'
db = Database.load_csv(path)
Y, rows = db.get_labels()
scores = []
split = StratifiedShuffleSplit(train_size=0.9, random_state=0, n_splits=10)
for i, (train_index, test_index) in enumerate(split.split(rows, Y)):
embedding, _ = io_utils.load_or_compute(f'{embedding_path}_{i}',
lambda: compute_embedding(db))
X_train = np.float32([embedding[rows[j]] for j in train_index])
X_test = np.float32([embedding[rows[j]] for j in test_index])
Y_train, Y_test = [Y[i]
for i in train_index], [Y[i] for i in test_index]
clf = SVC(kernel='rbf', C=1.0)
