def build_model(rand_test_indices, train_indices,traint,testt, labels ,X, adj_tr, adj_te, in_features,
hid_features,out_features,ds_name, activation, optimizer, epochs, dropout, lr, l2_pen,
beta, gamma, dumping_name, GS,is_nni=False):
optim_name="SGD"
if optimizer==optim.Adam:
optim_name = "Adam"
conf = {"in_features":in_features, "hid_features": hid_features, "out_features":out_features,"ds_name":ds_name,
"dropout": dropout, "lr": lr, "weight_decay": l2_pen,
"beta": beta, "gamma": gamma,
#"training_mat": training_data, "training_labels": training_labels,
# "test_mat": test_data, "test_labels": test_labels,
"train_ind": train_indices, "test_ind": rand_test_indices, "traint":traint,"testt":testt, "labels":labels, "X":X,
"adj_tr": adj_tr,"adj_te": adj_te,
"optimizer": optimizer, "epochs": epochs, "activation": activation,"optim_name":optim_name}
products_path = os.path.join(os.getcwd(), "logs", dumping_name, time.strftime("%Y%m%d_%H%M%S"))
if not os.path.exists(products_path):
os.makedirs(products_path)
logger = multi_logger([
PrintLogger("MyLogger", level=logging.DEBUG),
FileLogger("results_%s" % dumping_name, path=products_path, level=logging.INFO)], name=None)
data_logger = CSVLogger("results_%s" % dumping_name, path=products_path)
data_logger.info("model_name", "loss", "acc")
runner = ModelRunner(conf, GS,logger=logger, data_logger=data_logger, is_nni=is_nni)
return runner
def build_model(training_data, training_labels, test_data, test_labels, adjacency_matrices,
hid_features, activation, optimizer, epochs, dropout, lr, l2_pen, temporal_pen,
dumping_name, feature_matrices, is_nni=False):
optim_name="SGD"
if optimizer==optim.Adam:
optim_name = "Adam"
conf = {"hid_features": hid_features, "dropout": dropout, "lr": lr, "weight_decay": l2_pen,
"temporal_pen": temporal_pen,
"training_mat": training_data, "training_labels": training_labels,
"test_mat": test_data, "test_labels": test_labels, "adj_matrices": adjacency_matrices,
"optimizer": optimizer, "epochs": epochs, "feature_matrices": feature_matrices, "activation": activation,"optim_name":optim_name}
products_path = os.path.join(os.getcwd(), "logs", dumping_name, time.strftime("%Y%m%d_%H%M%S"))
if not os.path.exists(products_path):
os.makedirs(products_path)
logger = multi_logger([
PrintLogger("MyLogger", level=logging.DEBUG),
FileLogger("results_%s" % dumping_name, path=products_path, level=logging.INFO)], name=None)
data_logger = CSVLogger("results_%s" % dumping_name, path=products_path)
data_logger.info("model_name", "loss", "acc")
##
logger.info('STARTING with lr= {:.4f} '.format(lr) + ' dropout= {:.4f} '.format(dropout)+ ' regulariztion_l2_pen= {:.4f} '.format(l2_pen)
+ ' temporal_pen= {:.10f} '.format(temporal_pen)+ ' optimizer= %s ' %optim_name)
logger.debug('STARTING with lr= {:.4f} '.format(lr) + ' dropout= {:.4f} '.format(dropout) + ' regulariztion_l2_pen= {:.4f} '.format(l2_pen)
+ ' temporal_pen= {:.10f} '.format(temporal_pen) + ' optimizer= %s ' %optim_name)
##
runner = ModelRunner(conf, logger=logger, data_logger=data_logger, is_nni=is_nni)
return runner
def main_clean():
args = parse_args()
dataset = "citeseer"
seed = random.randint(1, 1000000000)
# "feat_type": "neighbors",
conf = {
"kipf": {
"hidden": args.hidden,
"dropout": args.dropout,
"lr": args.lr,
"weight_decay": args.weight_decay
},
"hidden_layers": [16],
"multi_hidden_layers": [100, 35],
"dropout": 0.6,
"lr": 0.01,
"weight_decay": 0.001,
"dataset": dataset,
"epochs": args.epochs,
"cuda": args.cuda,
"fastmode": args.fastmode,
"seed": seed
}
init_seed(conf['seed'], conf['cuda'])
dataset_path = os.path.join(PROJ_DIR, "data", dataset)
products_path = os.path.join(CUR_DIR, "logs", args.prefix + dataset,
time.strftime("%Y_%m_%d_%H_%M_%S"))
if not os.path.exists(products_path):
os.makedirs(products_path)
logger = multi_logger([
PrintLogger("IdansLogger", level=logging.DEBUG),
FileLogger("results_%s" % conf["dataset"],
path=products_path,
level=logging.INFO),
FileLogger("results_%s_all" % conf["dataset"],
path=products_path,
level=logging.DEBUG),
],
name=None)
data_logger = CSVLogger("results_%s" % conf["dataset"], path=products_path)
data_logger.info("model_name", "loss", "acc", "train_p")
runner = ModelRunner(dataset_path,
conf,
logger=logger,
data_logger=data_logger)
# execute_runner(runner, logger, 5, num_iter=30)
for train_p in range(5, 90, 10):
execute_runner(runner, logger, train_p, num_iter=10)
logger.info("Finished")
def build_model(training_data,
training_adj,
training_labels,
test_data,
test_adj,
test_labels,
optimizer,
epochs,
lr,
l2_pen,
class_weights,
graph_params,
dumping_name,
iterations,
is_nni=False):
conf = {
"lr": lr,
"weight_decay": l2_pen,
"training_mat": training_data,
"training_adj": training_adj,
"training_labels": training_labels,
"test_mat": test_data,
"test_adj": test_adj,
"test_labels": test_labels,
"optimizer": optimizer,
"epochs": epochs,
"iterations": iterations
}
products_path = os.path.join(os.getcwd(), "logs", dumping_name,
time.strftime("%Y%m%d_%H%M%S"))
if not os.path.exists(products_path):
os.makedirs(products_path)
logger = multi_logger([
PrintLogger("MyLogger", level=logging.DEBUG),
FileLogger(
"results_" + dumping_name, path=products_path, level=logging.INFO)
],
name=None)
data_logger = CSVLogger("results_" + dumping_name, path=products_path)
data_logger.info("model_name", "loss", "acc", "auc")
runner = ModelRunner(conf,
logger=logger,
data_logger=data_logger,
weights=class_weights,
graph_params=graph_params,
is_nni=is_nni)
return runner
def set_logs(data_name):
grid_outputs_folder = time.strftime("%Y%m%d_%H%M%S")
res_path = os.path.join(os.getcwd(), "dataset", data_name, "grid",
grid_outputs_folder)
if not os.path.exists(res_path):
os.makedirs(res_path)
grid_logger = CSVLogger("results_%s" % 'grid' +
time.strftime("%Y%m%d_%H%M%S"),
path=res_path)
grid_logger_avg = CSVLogger("results_%s" % 'grid_it_avg' +
time.strftime("%Y%m%d_%H%M%S"),
path=res_path)
grid_logger.info("data_name", "weights", "iteration", "total_it", "lr",
"do", "wd", "hid_size", "temp_pen", "epochs",
"best_epoch", "train_loss", "train_temp_loss",
"total_train_loss", "train_f1_macro", "train_f1_micro",
"val_loss", "val_temp_loss", "total_val_loss",
"val_f1_macro", "val_f1_micro", "test_loss",
"test_temp_loss", "total_test_loss", "test_f1_macro",
"test_f1_micro", "diag_sum", "diag_elements")
grid_logger_avg.info(
"data_name", "weights", "iterations", "lr", "do", "hid_size", "wd",
"temp_pen", "epochs", "train_loss", "train_temp_loss",
"total_train_loss", "train_f1_macro_mean", "train_f1_macro_std",
"train_f1_micro_mean", "train_f1_micro_std", "val_loss",
"val_temp_loss", "total_val_loss", "val_f1_macro_mean",
"val_f1_macro_std", "val_f1_micro_mean", "val_f1_micro_std",
"test_loss", "test_temp_loss", "total_test_loss", "test_f1_macro_mean",
"test_f1_macro_std", "test_f1_micro_mean", "test_f1_micro_std",
"diag_sum", "diag_elements")
return grid_logger, grid_logger_avg
def get_loggers(name, products_path, is_debug=True, set_titles=True):
logger = multi_logger([
PrintLogger("IdansLogger",
level=logging.DEBUG if is_debug else logging.INFO),
FileLogger("results_%s" % name, path=products_path,
level=logging.INFO),
FileLogger(
"results_%s_all" % name, path=products_path, level=logging.DEBUG),
],
name=None)
data_logger = CSVLogger("results_%s" % name, path=products_path)
if set_titles:
data_logger.set_titles("feat_type", "year", "loss_val", "loss_test",
"acc", "auc_test", "train_p", "norm_adj",
"epoch")
logger.dump_location()
data_logger.dump_location()
return logger, data_logger
def main():
args = parse_args()
dataset = "cora" # args.dataset
seed = random.randint(1, 1000000000)
conf = {
"kipf": {
"hidden": 16,
"dropout": 0.5,
"lr": 0.01,
"weight_decay": 5e-4
},
"hidden_layers": [16],
"multi_hidden_layers": [100, 20],
"dropout": 0.6,
"lr": 0.01,
"weight_decay": 0.001,
"dataset": dataset,
"epochs": args.epochs,
"cuda": args.cuda,
"fastmode": args.fastmode,
"seed": seed
}
init_seed(conf['seed'], conf['cuda'])
dataset_path = os.path.join(PROJ_DIR, "data", dataset)
products_path = os.path.join(CUR_DIR, "logs", dataset,
time.strftime("%Y_%m_%d_%H_%M_%S"))
if not os.path.exists(products_path):
os.makedirs(products_path)
logger = multi_logger([
PrintLogger("IdansLogger", level=logging.INFO),
FileLogger("results_%s" % conf["dataset"],
path=products_path,
level=logging.INFO),
FileLogger("results_%s_all" % conf["dataset"],
path=products_path,
level=logging.DEBUG),
],
name=None)
data_logger = CSVLogger("results_%s" % conf["dataset"], path=products_path)
data_logger.set_titles("model_name", "loss", "acc", "train_p", "norm_adj",
"feat_type")
num_iter = 5
for norm_adj in [True, False]:
conf["norm_adj"] = norm_adj
runner = ModelRunner(products_path,
dataset_path,
conf,
logger=logger,
data_logger=data_logger)
for train_p in chain([1], range(5, 90, 10)):
conf["train_p"] = train_p
train_p /= 100
val_p = test_p = (1 - train_p) / 2.
train_p /= (val_p + train_p)
runner.loader.split_test(test_p)
for ft, feat_type in enumerate(
["combined", "neighbors", "features"]):
conf["feat_type"] = feat_type
results = [
runner.run(train_p, feat_type) for _ in range(num_iter)
]
conf_path = os.path.join(
runner.products_path, "t%d_n%d_ft%d.pkl" % (
conf["train_p"],
norm_adj,
ft,
))
pickle.dump({
"res": results,
"conf": conf
}, open(conf_path, "wb"))
logger.info("Finished")
gtc = GCNTemporalCommunities(nni=params['is_nni'])
gtc.load_data()
gtc.prep_trial(params, grid_logger, grid_logger_avg)
if __name__ == "__main__":
pr = cProfile.Profile()
pr.enable()
grid_outputs_folder = time.strftime("%Y%m%d_%H%M%S")
res_path = os.path.join(os.getcwd(), "dataset", Dataset_name, "grid", grid_outputs_folder)
if not os.path.exists(res_path):
os.makedirs(res_path)
grid_logger = CSVLogger("results_%s" % 'grid' + time.strftime("%Y%m%d_%H%M%S"), path=res_path)
grid_logger_avg = CSVLogger("results_%s" % 'grid_it_avg' + time.strftime("%Y%m%d_%H%M%S"), path=res_path)
grid_logger.info("iteration", "total_it", "lr", "do", "hid_size", "wd", "temp_pen", "epochs",
"train_reg_loss", "train_temp_loss", "total_train_loss", "train_acc_f1_macro", "train_f1_micro",
"test_reg_loss", "test_temp_loss", "total_test_loss", "test_f1_macro", "test_f1_micro")
grid_logger_avg.info("iterations", "lr", "do", "hid_size", "wd", "temp_pen", "epochs",
"train_reg_loss", "train_temp_loss", "total_train_loss", "train_f1_macro", "train_f1_micro",
"test_reg_loss", "test_temp_loss", "total_test_loss", "test_f1_macro", "test_f1_micro")
num_of_grids = len(LR) * len(Hid_size) * len(Regularization) * len(Temporal_pen) * len(Dropout)
grid_counter = 0
configurations = list(product(*[LR, Hid_size, Regularization, Temporal_pen, Dropout]))
for LR, Hid_size, Regularization, Temporal_pen, Dropout in configurations:
grid_counter += 1