label = data[0].to_numpy()
dataset = data.drop(columns=[0]).to_numpy()
model = UnsupervisedModel(
dataset,
dataset.shape[-1],
config["output"],
error=0.001,
# error=config["output"],
max_epochs=config["max_epochs"],
lr=float(config["lr"]),
algorithm=config["algorithm"],
normalize=True,
normal_params=(config["normal_params"]["mean"],
config["normal_params"]["var"]))
train = True
model_name = config["model_name"] + "_" + config["algorithm"]
for f in glob.glob("*.npy"):
if model_name + ".npy" == f:
train = False
break
if train or config["force_train"]:
print(model)
model.train()
model.save_model(model_name)
model.plot_convergence(save=True, filename='sanger_ort.png')
else:
model.load_model(model_name)
plot_data(model, dataset, label)
def main():
parser = argparse.ArgumentParser(
description='Arguments for unsupervised GraphSAGE model.')
parser.add_argument('train_prefix',
help='Name of the object file that stores the ' +
'training data.')
parser.add_argument("model_name",
choices=[
"graphsage_mean", "gcn", "graphsage_seq",
"graphsage_maxpool", "graphsage_meanpool"
],
help="Model names.")
parser.add_argument('--model_size',
choices=["small", "big"],
default="small",
help="Can be big or small; model specific def'ns")
parser.add_argument('--learning_rate',
type=float,
default=0.00001,
help='Initial learning rate.')
parser.add_argument('--epochs',
type=int,
default=10,
help='Number of epochs to train.')
parser.add_argument('--dropout',
type=float,
default=0.0,
help='Dropout rate (1 - keep probability).')
parser.add_argument('--weight_decay',
type=float,
default=0.0,
help='Weight for l2 loss on embedding matrix.')
parser.add_argument('--max_degree',
type=int,
default=100,
help='Maximum node degree.')
parser.add_argument('--samples_1',
type=int,
default=25,
help='Number of samples in layer 1.')
parser.add_argument('--samples_2',
type=int,
default=10,
help='Number of users samples in layer 2.')
parser.add_argument('--dim_1',
type=int,
default=128,
help='Size of output dim ' +
'(final is 2x this, if using concat)')
parser.add_argument('--dim_2',
type=int,
default=128,
help='Size of output dim ' +
'(final is 2x this, if using concat)')
parser.add_argument('--random_context',
action="store_false",
default=True,
help='Whether to use random context or direct ' +
'edges.')
parser.add_argument('--neg_sample_size',
type=int,
default=20,
help='Number of negative samples.')
parser.add_argument('--batch_size',
type=int,
default=512,
help='Minibatch size.')
parser.add_argument('--identity_dim',
type=int,
default=0,
help='Set to positive value to use identity ' +
'embedding features of that dimension.')
parser.add_argument('--save_embeddings',
action="store_false",
default=True,
help='Whether to save embeddings for all nodes ' +
'after training')
parser.add_argument('--base_log_dir',
default='../../../data/processed/graphsage/',
help='Base directory for logging and saving ' +
'embeddings')
parser.add_argument('--validate_iter',
type=int,
default=5000,
help='How often to run a validation minibatch.')
parser.add_argument('--validate_batch_size',
type=int,
default=256,
help='How many nodes per validation sample.')
parser.add_argument('--gpu',
type=int,
default=0,
help='Which gpu to use.')
parser.add_argument('--print_every',
type=int,
default=50,
help='How often to print training info.')
parser.add_argument('--max_total_steps',
type=int,
default=10**10,
help='Maximum total number of iterations.')
parser.add_argument('--log_device_placement',
action="store_true",
default=False,
help='Whether to log device placement.')
args = parser.parse_args()
print("Starting...")
print("Loading training data..")
train_data = load_data(args.train_prefix, load_walks=True)
print("Done loading training data..\n")
from unsupervised_model import UnsupervisedModel
model = UnsupervisedModel(
args.train_prefix, args.model_name, args.model_size,
args.learning_rate, args.epochs, args.dropout, args.weight_decay,
args.max_degree, args.samples_1, args.samples_2, args.dim_1,
args.dim_2, args.random_context, args.neg_sample_size,
args.batch_size, args.identity_dim, args.save_embeddings,
args.base_log_dir, args.validate_iter, args.validate_batch_size,
args.gpu, args.print_every, args.max_total_steps,
args.log_device_placement)
model.train(train_data)
print("Finished.")