def main():
# Parse the arguments.
args = parse_arguments()
augment = False if args.augment == 'False' else True
multi_gpu = False if args.multi_gpu == 'False' else True
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label(label_list):
label_arr = np.asarray(label_list, dtype=np.int32)
return label_arr
# Apply a preprocessor to the dataset.
logging.info('Preprocess train dataset and test dataset...')
preprocessor = preprocess_method_dict[args.method]()
parser = CSVFileParserForPair(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_cols=['smiles_1', 'smiles_2'])
train = parser.parse(args.train_datafile)['dataset']
test = parser.parse(args.valid_datafile)['dataset']
if augment:
logging.info('Utilizing data augmentation in train set')
train = augment_dataset(train)
num_train = train.get_datasets()[0].shape[0]
num_test = test.get_datasets()[0].shape[0]
logging.info('Train/test split: {}/{}'.format(num_train, num_test))
if len(args.net_hidden_dims):
net_hidden_dims = tuple([
int(net_hidden_dim)
for net_hidden_dim in args.net_hidden_dims.split(',')
])
else:
net_hidden_dims = ()
weight_tying = False if args.weight_tying == 'False' else True
fp_batch_normalization = True if args.fp_bn == 'True' else False
predictor = set_up_predictor(
method=args.method,
fp_hidden_dim=args.fp_hidden_dim,
fp_out_dim=args.fp_out_dim,
conv_layers=args.conv_layers,
concat_hidden=args.concat_hidden,
fp_dropout_rate=args.fp_dropout_rate,
fp_batch_normalization=fp_batch_normalization,
net_hidden_dims=net_hidden_dims,
class_num=class_num,
sim_method=args.sim_method,
weight_typing=weight_tying,
symmetric=args.symmetric,
attn_model=args.attn,
)
if args.train_pos_neg_ratio != -1.:
# Set up the iterator.
train_dataset = train.get_datasets()
atoms1_train, adjs1_train, atoms2_train, adjs2_train, labels_train = train_dataset
labels_train = np.squeeze(labels_train)
train_dataset_arr = np.concatenate([
item[:, None] if len(item.shape) == 1 else item
for item in list(train_dataset)
],
axis=1)
pos_train_dataset_arr = train_dataset_arr[labels_train == 1]
num_pos_train = pos_train_dataset_arr.shape[0]
pos_train_indices = np.arange(0, num_pos_train)
neg_train_dataset_arr = train_dataset_arr[labels_train == 0]
num_neg_train = neg_train_dataset_arr.shape[0]
pos_neg_train_ratio = args.train_pos_neg_ratio
num_pos_train = int(pos_neg_train_ratio * num_neg_train)
np.random.seed(777)
np.random.shuffle(pos_train_indices)
pos_train_indices = pos_train_indices[:num_pos_train]
pos_train_dataset_arr = pos_train_dataset_arr[pos_train_indices]
new_train_dataset_arr = np.concatenate(
(pos_train_dataset_arr, neg_train_dataset_arr), axis=0)
atoms1_train, adjs1_train = new_train_dataset_arr[:,
0], new_train_dataset_arr[:,
1]
atoms2_train, adjs2_train = new_train_dataset_arr[:,
2], new_train_dataset_arr[:,
3]
labels_train = new_train_dataset_arr[:, 4].astype(np.int32)
labels_train = np.expand_dims(labels_train, axis=1)
train = NumpyTupleDataset(atoms1_train, adjs1_train, atoms2_train,
adjs2_train, labels_train)
num_train = train.get_datasets()[0].shape[0]
num_test = test.get_datasets()[0].shape[0]
logging.info('Train pos-neg ratio is {:.4f}'.format(
args.train_pos_neg_ratio))
logging.info('Train/test number is {}/{}'.format(num_train, num_test))
# if args.loss_func == 'hinge':
# modify_dataset_for_hinge(train)
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
test_iter = SerialIterator(test,
args.batchsize,
repeat=False,
shuffle=False)
metrics_fun = {'accuracy': F.binary_accuracy}
loss_func = F.sigmoid_cross_entropy
if args.loss_func == 'hinge':
logging.info('Loss function is {}'.format(args.loss_func))
loss_func = F.hinge
metrics_fun = {'accuracy': F.accuracy}
classifier = Classifier(predictor,
lossfun=loss_func,
metrics_fun=metrics_fun,
device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam(alpha=args.learning_rate,
weight_decay_rate=args.weight_decay_rate)
# optimizer = optimizers.Adam()
# optimizer = optimizers.SGD(lr=args.learning_rate)
optimizer.setup(classifier)
# add regularization
if args.max_norm > 0:
optimizer.add_hook(
chainer.optimizer.GradientClipping(threshold=args.max_norm))
if args.l2_rate > 0:
optimizer.add_hook(chainer.optimizer.WeightDecay(rate=args.l2_rate))
if args.l1_rate > 0:
optimizer.add_hook(chainer.optimizer.Lasso(rate=args.l1_rate))
# Set up the updater.
if multi_gpu:
logging.info('Using multiple GPUs')
updater = training.ParallelUpdater(train_iter,
optimizer,
devices={
'main': 0,
'second': 1
},
converter=concat_mols)
else:
logging.info('Using single GPU')
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
# Set up the trainer.
logging.info('Training...')
# add stop_trigger parameter
early_stop = triggers.EarlyStoppingTrigger(monitor='validation/main/loss',
patients=10,
max_trigger=(500, 'epoch'))
out = 'output' + '/' + args.out
trainer = training.Trainer(updater, stop_trigger=early_stop, out=out)
# trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
E.Evaluator(test_iter,
classifier,
device=args.gpu,
converter=concat_mols))
train_eval_iter = SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
AccuracyEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_acc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
AccuracyEvaluator(test_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_acc',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_roc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(test_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_roc',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
PRCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_prc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
PRCAUCEvaluator(test_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_prc',
pos_labels=1,
ignore_labels=-1))
# trainer.extend(PrecisionEvaluator(
# train_eval_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='train_p',
# pos_labels=1, ignore_labels=-1, raise_value_error=False))
# # extension name='validation' is already used by `Evaluator`,
# # instead extension name `val` is used.
# trainer.extend(PrecisionEvaluator(
# val_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='val_p',
# pos_labels=1, ignore_labels=-1))
#
# trainer.extend(RecallEvaluator(
# train_eval_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='train_r',
# pos_labels=1, ignore_labels=-1, raise_value_error=False))
# # extension name='validation' is already used by `Evaluator`,
# # instead extension name `val` is used.
# trainer.extend(RecallEvaluator(
# val_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='val_r',
# pos_labels=1, ignore_labels=-1))
trainer.extend(
F1Evaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_f',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
F1Evaluator(test_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_f',
pos_labels=1,
ignore_labels=-1))
# apply shift strategy to learning rate every 10 epochs
# trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate), trigger=(10, 'epoch'))
if args.exp_shift_strategy == 1:
trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate),
trigger=triggers.ManualScheduleTrigger(
[10, 20, 30, 40, 50, 60], 'epoch'))
elif args.exp_shift_strategy == 2:
trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate),
trigger=triggers.ManualScheduleTrigger(
[5, 10, 15, 20, 25, 30], 'epoch'))
elif args.exp_shift_strategy == 3:
trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate),
trigger=triggers.ManualScheduleTrigger(
[5, 10, 15, 20, 25, 30, 40, 50, 60, 70], 'epoch'))
else:
raise ValueError('No such strategy to adapt learning rate')
# # observation of learning rate
trainer.extend(E.observe_lr(), trigger=(1, 'iteration'))
entries = [
'epoch',
'main/loss',
'train_acc/main/accuracy',
'train_roc/main/roc_auc',
'train_prc/main/prc_auc',
# 'train_p/main/precision', 'train_r/main/recall',
'train_f/main/f1',
'validation/main/loss',
'val_acc/main/accuracy',
'val_roc/main/roc_auc',
'val_prc/main/prc_auc',
# 'val_p/main/precision', 'val_r/main/recall',
'val_f/main/f1',
'lr',
'elapsed_time'
]
trainer.extend(E.PrintReport(entries=entries))
# change from 10 to 2 on Mar. 1 2019
trainer.extend(E.snapshot(), trigger=(2, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.ProgressBar())
trainer.extend(
E.PlotReport(['main/loss', 'validation/main/loss'],
'epoch',
file_name='loss.png'))
trainer.extend(
E.PlotReport(['train_acc/main/accuracy', 'val_acc/main/accuracy'],
'epoch',
file_name='accuracy.png'))
if args.resume:
resume_path = os.path.join(out, args.resume)
logging.info(
'Resume training according to snapshot in {}'.format(resume_path))
chainer.serializers.load_npz(resume_path, trainer)
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(out, args.model_filename)
logging.info('Saving the trained models to {}...'.format(model_path))
classifier.save_pickle(model_path, protocol=args.protocol)
def main():
args = parse_arguments()
# Set up some useful variables that will be used later on.
dataset_name = args.dataset
method = args.method
num_data = args.num_data
n_unit = args.unit_num
conv_layers = args.conv_layers
if method == 'node2vec':
fname = args.modelpath.split('/')[-1].rsplit('.', 1)[0]
r, p, q = fname.split('-')[-3:]
r, p, q = int(r[1:]), float(p[1:]), float(q[1:])
print(args.modelpath)
print(f"r={r}, p={p}, q={q}")
task_type = molnet_default_config[dataset_name]['task_type']
model_filename = {
'classification': 'classifier.pkl',
'regression': 'regressor.pkl'
}
print('Using dataset: {}...'.format(dataset_name))
# Set up some useful variables that will be used later on.
if args.label:
labels = args.label
if method == 'node2vec':
cache_dir = os.path.join(
args.datadir,
'{}_{}_r{}_p{}_q{}_{}'.format(dataset_name, method, r, p, q,
labels))
else:
cache_dir = os.path.join(
args.datadir, '{}_{}_{}'.format(dataset_name, method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
if method == 'node2vec':
cache_dir = os.path.join(
args.datadir,
'{}_{}_r{}_p{}_q{}_all'.format(dataset_name, method, r, p, q))
else:
cache_dir = os.path.join(args.datadir,
'{}_{}_all'.format(dataset_name, method))
class_num = len(molnet_default_config[args.dataset]['tasks'])
# Load the train and validation parts of the dataset.
filenames = [
dataset_part_filename(p, num_data) for p in ['train', 'valid']
]
paths = [os.path.join(cache_dir, f) for f in filenames]
if all([os.path.exists(path) for path in paths]):
dataset_parts = []
for path in paths:
print('Loading cached dataset from {}.'.format(path))
dataset_parts.append(NumpyTupleDataset.load(path))
else:
dataset_parts = download_entire_dataset(dataset_name,
num_data,
labels,
method,
cache_dir,
modelpath=args.modelpath)
# Scale the label values, if necessary.
scaler = None
if args.scale == 'standardize':
if task_type == 'regression':
print('Applying standard scaling to the labels.')
scaler, dataset_parts = fit_scaler(dataset_parts)
else:
print('Label scaling is not available for classification tasks.')
else:
print('No label scaling was selected.')
train, valid = dataset_parts[0], dataset_parts[1]
# Set up the predictor.
if method == 'node2vec':
predictor = MLP(class_num, n_unit)
else:
predictor = set_up_predictor(method,
n_unit,
conv_layers,
class_num,
label_scaler=scaler)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid,
args.batchsize,
repeat=False,
shuffle=False)
# Load metrics for the current dataset.
metrics = molnet_default_config[dataset_name]['metrics']
metrics_fun = {
k: v
for k, v in metrics.items() if isinstance(v, types.FunctionType)
}
loss_fun = molnet_default_config[dataset_name]['loss']
device = chainer.get_device(args.device)
if task_type == 'regression':
model = Regressor(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=device)
elif task_type == 'classification':
model = Classifier(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=device)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# Set up the optimizer.
optimizer = optimizers.Adam(0.0005)
optimizer.setup(model)
# Save model-related output to this directory.
if not os.path.exists(args.out):
os.makedirs(args.out)
save_json(os.path.join(args.out, 'args.json'), vars(args))
model_dir = os.path.join(args.out, os.path.basename(cache_dir))
if not os.path.exists(model_dir):
os.makedirs(model_dir)
# save scaler
if args.scale == 'standardize' and task_type == 'regression':
pkl.dump(scaler,
open(os.path.join(cache_dir, 'standatdize_scaler.pkl'), 'wb'))
# Set up the updater.
if method == 'node2vec':
converter = converter_method_dict['nfp'] # concat_mols
else:
converter = converter_method_dict[method]
updater = training.StandardUpdater(train_iter,
optimizer,
device=device,
converter=converter)
# Set up the trainer.
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=model_dir)
trainer.extend(
E.Evaluator(valid_iter, model, device=device, converter=converter))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
# TODO: consider go/no-go of the following block
# (i) more reporting for val/evalutaion
# (ii) best validation score snapshot
if task_type == 'regression':
metric_name_list = list(metrics.keys())
if 'RMSE' in metric_name_list:
trainer.extend(E.snapshot_object(
model, "best_val_" + model_filename[task_type]),
trigger=training.triggers.MinValueTrigger(
'validation/main/RMSE'))
elif 'MAE' in metric_name_list:
trainer.extend(E.snapshot_object(
model, "best_val_" + model_filename[task_type]),
trigger=training.triggers.MinValueTrigger(
'validation/main/MAE'))
else:
print("[WARNING] No validation metric defined?")
elif task_type == 'classification':
train_eval_iter = iterators.SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
if dataset_name in ['muv', 'pcba']:
trainer.extend(
PRCAUCEvaluator(train_eval_iter,
predictor,
eval_func=predictor,
device=device,
converter=converter,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
PRCAUCEvaluator(valid_iter,
predictor,
eval_func=predictor,
device=device,
converter=converter,
name='val',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
trainer.extend(
E.snapshot_object(model,
"best_val_" + model_filename[task_type]),
trigger=training.triggers.MaxValueTrigger('val/main/prc_auc'))
else:
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
predictor,
eval_func=predictor,
device=device,
converter=converter,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(valid_iter,
predictor,
eval_func=predictor,
device=device,
converter=converter,
name='val',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
trainer.extend(
E.snapshot_object(model,
"best_val_" + model_filename[task_type]),
trigger=training.triggers.MaxValueTrigger('val/main/roc_auc'))
else:
raise NotImplementedError(
'Not implemented task_type = {}'.format(task_type))
trainer.extend(AutoPrintReport())
trainer.extend(E.ProgressBar())
trainer.run()
# Save the model's parameters.
model_path = os.path.join(model_dir, model_filename[task_type])
print('Saving the trained model to {}...'.format(model_path))
model.save_pickle(model_path, protocol=args.protocol)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
label_names = D.get_tox21_label_names()
iterator_type = ['serial', 'balanced']
parser = argparse.ArgumentParser(
description='Multitask Learning with Tox21.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp',
help='graph convolution model to use '
'as a predictor.')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for logistic '
'regression. Use all labels if this option '
'is not specified.')
parser.add_argument('--iterator-type',
type=str,
choices=iterator_type,
default='serial',
help='iterator type. If `balanced` '
'is specified, data is sampled to take same number of'
'positive/negative labels during training.')
parser.add_argument('--eval-mode',
type=int,
default=1,
help='Evaluation mode.'
'0: only binary_accuracy is calculated.'
'1: binary_accuracy and ROC-AUC score is calculated')
parser.add_argument('--conv-layers',
'-c',
type=int,
default=4,
help='number of convolution layers')
parser.add_argument('--batchsize',
'-b',
type=int,
default=32,
help='batch size')
parser.add_argument('--gpu',
'-g',
type=int,
default=-1,
help='GPU ID to use. Negative value indicates '
'not to use GPU and to run the code in CPU.')
parser.add_argument('--out',
'-o',
type=str,
default='result',
help='path to output directory')
parser.add_argument('--epoch',
'-e',
type=int,
default=10,
help='number of epochs')
parser.add_argument('--unit-num',
'-u',
type=int,
default=16,
help='number of units in one layer of the model')
parser.add_argument('--resume',
'-r',
type=str,
default='',
help='path to a trainer snapshot')
parser.add_argument('--frequency',
'-f',
type=int,
default=-1,
help='Frequency of taking a snapshot')
parser.add_argument('--protocol',
type=int,
default=2,
help='protocol version for pickle')
parser.add_argument('--model-filename',
type=str,
default='classifier.pkl',
help='file name for pickled model')
parser.add_argument('--num-data',
type=int,
default=-1,
help='Number of data to be parsed from parser.'
'-1 indicates to parse all data.')
args = parser.parse_args()
method = args.method
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
class_num = len(label_names)
# Dataset preparation
train, val, _ = data.load_dataset(method, labels, num_data=args.num_data)
# Network
predictor_ = predictor.build_predictor(method, args.unit_num,
args.conv_layers, class_num)
iterator_type = args.iterator_type
if iterator_type == 'serial':
train_iter = I.SerialIterator(train, args.batchsize)
elif iterator_type == 'balanced':
if class_num > 1:
raise ValueError('BalancedSerialIterator can be used with only one'
'label classification, please specify label to'
'be predicted by --label option.')
train_iter = BalancedSerialIterator(train,
args.batchsize,
train.features[:, -1],
ignore_labels=-1)
train_iter.show_label_stats()
else:
raise ValueError('Invalid iterator type {}'.format(iterator_type))
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
classifier = Classifier(predictor_,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=args.gpu)
optimizer = O.Adam()
optimizer.setup(classifier)
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
E.Evaluator(val_iter,
classifier,
device=args.gpu,
converter=concat_mols))
trainer.extend(E.LogReport())
eval_mode = args.eval_mode
if eval_mode == 0:
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'validation/main/loss',
'validation/main/accuracy', 'elapsed_time'
]))
elif eval_mode == 1:
train_eval_iter = I.SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor_,
device=args.gpu,
converter=concat_mols,
name='train',
pos_labels=1,
ignore_labels=-1))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=predictor_,
device=args.gpu,
converter=concat_mols,
name='val',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'train/main/roc_auc',
'validation/main/loss', 'validation/main/accuracy',
'val/main/roc_auc', 'elapsed_time'
]))
else:
raise ValueError('Invalid accfun_mode {}'.format(eval_mode))
trainer.extend(E.ProgressBar(update_interval=10))
frequency = args.epoch if args.frequency == -1 else max(1, args.frequency)
trainer.extend(E.snapshot(), trigger=(frequency, 'epoch'))
if args.resume:
chainer.serializers.load_npz(args.resume, trainer)
trainer.run()
config = {
'method': args.method,
'conv_layers': args.conv_layers,
'unit_num': args.unit_num,
'labels': args.label
}
with open(os.path.join(args.out, 'config.json'), 'w') as o:
o.write(json.dumps(config))
classifier.save_pickle(os.path.join(args.out, args.model_filename),
protocol=args.protocol)
def main():
# Parse the arguments.
args = parse_arguments()
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label(label_list):
label_arr = np.asarray(label_list, dtype=np.int32)
return label_arr
# Apply a preprocessor to the dataset.
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[args.method]()
parser = CSVFileParserForPair(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_cols=['smiles_1', 'smiles_2'])
dataset = parser.parse(args.datafile)['dataset']
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, val = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
# def set_up_predictor(method, fp_hidden_dim, fp_out_dim, conv_layers, net_hidden_num, class_num, net_layers):
# predictor = set_up_predictor(args.method, args.unit_num,
# args.conv_layers, class_num)
if len(args.net_hidden_dims):
net_hidden_dims = tuple([
int(net_hidden_dim)
for net_hidden_dim in args.net_hidden_dims.split(',')
])
else:
net_hidden_dims = ()
predictor = set_up_predictor(method=args.method,
fp_hidden_dim=args.fp_hidden_dim,
fp_out_dim=args.fp_out_dim,
conv_layers=args.conv_layers,
concat_hidden=args.concat_hidden,
fp_dropout_rate=args.fp_dropout_rate,
net_hidden_dims=net_hidden_dims,
class_num=class_num,
sim_method=args.sim_method)
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
val_iter = SerialIterator(val, args.batchsize, repeat=False, shuffle=False)
metrics_fun = {'accuracy': F.binary_accuracy}
classifier = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=metrics_fun,
device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam(alpha=args.learning_rate,
weight_decay_rate=args.weight_decay_rate)
# optimizer = optimizers.Adam()
# optimizer = optimizers.SGD(lr=args.learning_rate)
optimizer.setup(classifier)
# Set up the updater.
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
# Set up the trainer.
print('Training...')
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
E.Evaluator(val_iter,
classifier,
device=args.gpu,
converter=concat_mols))
train_eval_iter = SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
AccuracyEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_acc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
AccuracyEvaluator(val_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_acc',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_roc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_roc',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
PRCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_prc',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
PRCAUCEvaluator(val_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_prc',
pos_labels=1,
ignore_labels=-1))
# trainer.extend(PrecisionEvaluator(
# train_eval_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='train_p',
# pos_labels=1, ignore_labels=-1, raise_value_error=False))
# # extension name='validation' is already used by `Evaluator`,
# # instead extension name `val` is used.
# trainer.extend(PrecisionEvaluator(
# val_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='val_p',
# pos_labels=1, ignore_labels=-1))
#
# trainer.extend(RecallEvaluator(
# train_eval_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='train_r',
# pos_labels=1, ignore_labels=-1, raise_value_error=False))
# # extension name='validation' is already used by `Evaluator`,
# # instead extension name `val` is used.
# trainer.extend(RecallEvaluator(
# val_iter, classifier, eval_func=predictor,
# device=args.gpu, converter=concat_mols, name='val_r',
# pos_labels=1, ignore_labels=-1))
trainer.extend(
F1Evaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train_f',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
F1Evaluator(val_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val_f',
pos_labels=1,
ignore_labels=-1))
# apply shift strategy to learning rate every 10 epochs
# trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate), trigger=(10, 'epoch'))
trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate),
trigger=triggers.ManualScheduleTrigger([10, 20, 30, 40, 50],
'epoch'))
# # observation of learning rate
trainer.extend(E.observe_lr(), trigger=(1, 'iteration'))
entries = [
'epoch',
'main/loss',
'train_acc/main/accuracy',
'train_roc/main/roc_auc',
'train_prc/main/prc_auc',
# 'train_p/main/precision', 'train_r/main/recall',
'train_f/main/f1',
'validation/main/loss',
'val_acc/main/accuracy',
'val_roc/main/roc_auc',
'val_prc/main/prc_auc',
# 'val_p/main/precision', 'val_r/main/recall',
'val_f/main/f1',
'lr',
'elapsed_time'
]
trainer.extend(E.PrintReport(entries=entries))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.ProgressBar())
if args.resume:
resume_path = os.path.join(args.out, args.resume)
logging.info(
'Resume training according to snapshot in {}'.format(resume_path))
chainer.serializers.load_npz(resume_path, trainer)
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained models to {}...'.format(model_path))
classifier.save_pickle(model_path, protocol=args.protocol)
def main():
# Parse the arguments.
args = parse_arguments()
if args['label']:
labels = args['label']
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label(label_list):
label_arr = np.asarray(label_list, dtype=np.int32)
return label_arr
# Apply a preprocessor to the dataset.
logging.info('Preprocess train dataset and valid dataset...')
if args['method'] == 'relgcn':
preprocessor = preprocess_method_dict['ggnn']()
# preprocessor = preprocess_method_dict['rsgcn']()
elif args['method'] == 'mpnn':
preprocessor = preprocess_method_dict['ggnn']()
else:
preprocessor = preprocess_method_dict[args['method']]()
parser = CSVFileParserForPair(preprocessor, postprocess_label=postprocess_label,
labels=labels, smiles_cols=['smiles_1', 'smiles_2'])
train = parser.parse(args['train_datafile'])['dataset']
valid = parser.parse(args['valid_datafile'])['dataset']
if args['augment']:
logging.info('Utilizing data augmentation in train set')
train = augment_dataset(train)
num_train = train.get_datasets()[0].shape[0]
num_valid = valid.get_datasets()[0].shape[0]
logging.info('Train/test split: {}/{}'.format(num_train, num_valid))
if len(args['net_hidden_dims']):
net_hidden_dims = tuple([int(net_hidden_dim) for net_hidden_dim in args['net_hidden_dims'].split(',')])
else:
net_hidden_dims = ()
predictor = set_up_predictor(method=args['method'],
fp_hidden_dim=args['fp_hidden_dim'],
fp_out_dim=args['fp_out_dim'],
conv_layers=args['conv_layers'],
concat_hidden=args['concat_hidden'],
fp_dropout_rate=args['fp_dropout_rate'],
fp_batch_normalization=args['fp_batch_normalization'],
net_hidden_dims=net_hidden_dims, class_num=class_num,
sim_method=args['sim_method'], weight_typing=args['weight_tying'],
symmetric=args['symmetric'],
)
train_iter = SerialIterator(train, args['batchsize'])
test_iter = SerialIterator(valid, args['batchsize'],
repeat=False, shuffle=False)
metrics_fun = {'accuracy': F.binary_accuracy}
classifier = Classifier(predictor, lossfun=F.sigmoid_cross_entropy,
metrics_fun=metrics_fun, device=args['gpu'])
# Set up the optimizer.
optimizer = optimizers.Adam(alpha=args['learning_rate'], weight_decay_rate=args['weight_decay_rate'])
# optimizer = optimizers.Adam()
# optimizer = optimizers.SGD(lr=args.learning_rate)
optimizer.setup(classifier)
# add regularization
if args['max_norm'] > 0:
optimizer.add_hook(chainer.optimizer.GradientClipping(threshold=args['max_norm']))
if args['l2_rate'] > 0:
optimizer.add_hook(chainer.optimizer.WeightDecay(rate=args['l2_rate']))
if args['l1_rate'] > 0:
optimizer.add_hook(chainer.optimizer.Lasso(rate=args['l1_rate']))
updater = training.StandardUpdater(train_iter, optimizer, device=args['gpu'],
converter=concat_mols)
# Set up the trainer.
logging.info('Training...')
# add stop_trigger parameter
early_stop = triggers.EarlyStoppingTrigger(monitor='validation/main/loss', patients=10, max_trigger=(500, 'epoch'))
out = 'output' + '/' + args['out']
trainer = training.Trainer(updater, stop_trigger=early_stop, out=out)
trainer.extend(E.Evaluator(test_iter, classifier,
device=args['gpu'], converter=concat_mols))
train_eval_iter = SerialIterator(train, args['batchsize'],
repeat=False, shuffle=False)
trainer.extend(AccuracyEvaluator(
train_eval_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='train_acc',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(AccuracyEvaluator(
test_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='val_acc',
pos_labels=1, ignore_labels=-1))
trainer.extend(ROCAUCEvaluator(
train_eval_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='train_roc',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(ROCAUCEvaluator(
test_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='val_roc',
pos_labels=1, ignore_labels=-1))
trainer.extend(PRCAUCEvaluator(
train_eval_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='train_prc',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(PRCAUCEvaluator(
test_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='val_prc',
pos_labels=1, ignore_labels=-1))
trainer.extend(F1Evaluator(
train_eval_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='train_f',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(F1Evaluator(
test_iter, classifier, eval_func=predictor,
device=args['gpu'], converter=concat_mols, name='val_f',
pos_labels=1, ignore_labels=-1))
# apply shift strategy to learning rate every 10 epochs
# trainer.extend(E.ExponentialShift('alpha', args.exp_shift_rate), trigger=(10, 'epoch'))
if args['exp_shift_strategy']== 1:
trainer.extend(E.ExponentialShift('alpha', args['exp_shift_rate']),
trigger=triggers.ManualScheduleTrigger([10, 20, 30, 40, 50, 60], 'epoch'))
elif args['exp_shift_strategy'] == 2:
trainer.extend(E.ExponentialShift('alpha', args['exp_shift_rate']),
trigger=triggers.ManualScheduleTrigger([5, 10, 15, 20, 25, 30], 'epoch'))
elif args['exp_shift_strategy'] == 3:
trainer.extend(E.ExponentialShift('alpha', args['exp_shift_rate']),
trigger=triggers.ManualScheduleTrigger([5, 10, 15, 20, 25, 30, 40, 50, 60, 70], 'epoch'))
else:
raise ValueError('No such strategy to adapt learning rate')
# # observation of learning rate
trainer.extend(E.observe_lr(), trigger=(1, 'iteration'))
entries = [
'epoch',
'main/loss', 'train_acc/main/accuracy', 'train_roc/main/roc_auc', 'train_prc/main/prc_auc',
# 'train_p/main/precision', 'train_r/main/recall',
'train_f/main/f1',
'validation/main/loss', 'val_acc/main/accuracy', 'val_roc/main/roc_auc', 'val_prc/main/prc_auc',
# 'val_p/main/precision', 'val_r/main/recall',
'val_f/main/f1',
'lr',
'elapsed_time']
trainer.extend(E.PrintReport(entries=entries))
# change from 10 to 2 on Mar. 1 2019
trainer.extend(E.snapshot(), trigger=(2, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.ProgressBar())
trainer.extend(E.PlotReport(['main/loss', 'validation/main/loss'], 'epoch', file_name='loss.png'))
trainer.extend(E.PlotReport(['train_acc/main/accuracy', 'val_acc/main/accuracy'], 'epoch', file_name='accuracy.png'))
if args['resume']:
resume_path = os.path.join(out, args['resume'])
logging.info('Resume training according to snapshot in {}'.format(resume_path))
chainer.serializers.load_npz(resume_path, trainer)
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(out, args['model_filename'])
logging.info('Saving the trained models to {}...'.format(model_path))
classifier.save_pickle(model_path, protocol=args['protocol'])
def main():
# Parse the arguments.
args = parse_arguments()
gpu = False
if args.gpu >= 0:
import cupy
gpu = True
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label(label_list):
if gpu:
return cupy.asarray(label_list, dtype=cupy.int32)
else:
return numpy.asarray(label_list, dtype=numpy.int32)
# Apply a preprocessor to the dataset.
print('Preprocessing dataset...')
preprocessor = set_up_preprocessor(args.method, args.max_atoms)
parser = CSVFileParser(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_col='SMILES')
train = parser.parse(args.train_datafile)['dataset']
# Validation
preprocessor = set_up_preprocessor(args.method, args.max_atoms)
parser = CSVFileParser(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_col='SMILES')
val = parser.parse(args.val_datafile)['dataset']
# Set up the predictor.
predictor = set_up_predictor(args.method,
args.unit_num,
args.conv_layers,
class_num,
max_atoms=args.max_atoms)
if gpu:
predictor = predictor.to_gpu()
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
val_iter = SerialIterator(val, args.batchsize, repeat=False, shuffle=False)
# Set up the classifier.
classifier = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(classifier)
optimizer.add_hook(chainer.optimizer.WeightDecay(rate=args.l2reg))
# Set up the updater.
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
# Set up the trainer.
print('Training...')
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
#metrics
trainer.extend(E.Evaluator(val_iter, classifier))
train_eval_iter = SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val',
pos_labels=1,
ignore_labels=-1))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'train/main/roc_auc',
'validation/main/loss', 'validation/main/accuracy',
'val/main/roc_auc', 'elapsed_time'
]))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the classifier's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
classifier.save_pickle(model_path, protocol=args.protocol)
def main():
parser = argparse.ArgumentParser(
description='Imbalanced MNIST classification')
parser.add_argument('--eval-mode',
type=int,
default=1,
help='Evaluation mode.'
'0: only binary_accuracy is calculated.'
'1: binary_accuracy and ROC-AUC score is calculated')
parser.add_argument('--batchsize',
'-b',
type=int,
default=100,
help='batch size')
parser.add_argument('--gpu',
'-g',
type=int,
default=-1,
help='GPU ID to use. Negative value indicates '
'not to use GPU and to run the code in CPU.')
parser.add_argument('--out',
'-o',
type=str,
default='result',
help='path to output directory')
parser.add_argument('--epoch',
'-e',
type=int,
default=10,
help='number of epochs')
parser.add_argument('--resume',
'-r',
type=str,
default='',
help='path to a trainer snapshot')
parser.add_argument('--frequency',
'-f',
type=int,
default=-1,
help='Frequency of taking a snapshot')
parser.add_argument('--protocol',
type=int,
default=2,
help='protocol version for pickle')
parser.add_argument('--model-filename',
type=str,
default='classifier.pkl',
help='file name for pickled model')
parser.add_argument('--updater-type', type=str, default='standard')
parser.add_argument('--sampling-size', type=int, default=32)
parser.add_argument('--optimizer-type', type=str, default='Adam')
parser.add_argument('--alpha', type=str, default='0.001')
args = parser.parse_args()
# Dataset preparation
train, train_val, val = get_binary_imbalanced_data()
train_iter = iterators.SerialIterator(train, args.batchsize)
val_iter = iterators.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
model = LeNet(n_class=1, binary=True)
classifier = Classifier(model,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=args.gpu)
if args.optimizer_type == 'Adam':
optimizer = optimizers.Adam()
else:
optimizer = optimizers.SGD(lr=1e-3)
optimizer.setup(classifier)
updater_type = args.updater_type
if updater_type == 'standard':
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu)
elif updater_type == 'proposed':
updater = Proposed(train_iter,
optimizer,
device=args.gpu,
sampling_size=args.sampling_size)
elif updater_type == 'LRE':
x, t = chainer.dataset.concat_examples(train)
train_val_iter = iterators.SerialIterator(train_val, len(train_val))
updater = LRE({
'main': train_iter,
'val': train_val_iter
},
optimizer,
device=args.gpu,
alpha=args.alpha)
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(E.Evaluator(val_iter, classifier, device=args.gpu))
trainer.extend(E.LogReport())
eval_mode = args.eval_mode
if eval_mode == 0:
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'validation/main/loss',
'validation/main/accuracy', 'elapsed_time'
]))
elif eval_mode == 1:
train_eval_iter = iterators.SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=model,
device=args.gpu,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=model,
device=args.gpu,
name='val',
pos_labels=1,
ignore_labels=-1))
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'train/main/roc_auc',
'validation/main/loss', 'validation/main/accuracy',
'val/main/roc_auc', 'elapsed_time'
]))
else:
raise ValueError('Invalid accfun_mode {}'.format(eval_mode))
trainer.extend(E.ProgressBar(update_interval=10))
frequency = args.epoch if args.frequency == -1 else max(1, args.frequency)
trainer.extend(E.snapshot(), trigger=(frequency, 'epoch'))
if args.resume:
chainer.serializers.load_npz(args.resume, trainer)
trainer.run()
classifier.save_pickle(os.path.join(args.out, args.model_filename),
protocol=args.protocol)
def main():
# Parse the arguments.
args = parse_arguments()
args.out = os.path.join(args.out, args.method)
save_args(args, args.out)
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label_float(label_list):
return numpy.asarray(label_list, dtype=numpy.float32)
def postprocess_label_int(label_list):
return numpy.asarray(label_list, dtype=numpy.int64)
# Apply a preprocessor to the dataset.
if args.train:
## training data
fn,ext = os.path.splitext(args.train)
if ext==".npz":
print('Loading training dataset...')
train = NumpyTupleDataset.load(args.train)
else:
print('Preprocessing training dataset...')
preprocessor = preprocess_method_dict[args.method]()
if args.classification:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_int,labels=labels, smiles_col='SMILES')
else:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_float,labels=labels, smiles_col='SMILES')
train = parser.parse(args.train)['dataset']
NumpyTupleDataset.save(os.path.join(args.out,os.path.split(fn)[1]), train)
# Scale the label values, if necessary.
if args.scale == 'standardize':
scaler = StandardScaler()
scaler.fit(train.get_datasets()[-1])
else:
scaler = None
## test data
fn,ext = os.path.splitext(args.val)
if ext==".npz":
print('Loading test dataset...')
test = NumpyTupleDataset.load(args.val)
else:
print('Preprocessing test dataset...')
preprocessor = preprocess_method_dict[args.method]()
if args.classification:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_int,labels=labels, smiles_col='SMILES')
else:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_float,labels=labels, smiles_col='SMILES')
test = parser.parse(args.val)['dataset']
NumpyTupleDataset.save(os.path.join(args.out,os.path.split(fn)[1]), test)
# Set up the model.
device = chainer.get_device(args.device)
converter = converter_method_dict[args.method]
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
if args.classification:
if args.load_model:
model = Classifier.load_pickle(args.load_model, device=device)
print("model file loaded: ",args.load_model)
else:
predictor = set_up_predictor(args.method, args.unit_num, args.conv_layers, class_num)
model = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=device)
else:
if args.load_model:
model = Regressor.load_pickle(args.load_model, device=device)
print("model file loaded: ",args.load_model)
else:
predictor = set_up_predictor(
args.method+args.method_suffix, args.unit_num,
args.conv_layers, class_num, label_scaler=scaler)
model = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
if args.train:
if args.balanced_iter:
train = BalancedSerialIterator(train, args.batchsize, train.features[:, -1], ignore_labels=-1)
train.show_label_stats()
print('Training...')
log_keys = ['main/mae','main/rmse','validation/main/mae','validation/main/rmse','validation/main/roc_auc']
extensions_list = [extensions.PlotReport(log_keys, 'iteration', trigger=(100, 'iteration'), file_name='loss.png')]
if args.eval_roc and args.classification:
extensions_list.append(ROCAUCEvaluator(
test, model, eval_func=predictor,
device=device, converter=converter, name='validation',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
save_json(os.path.join(args.out, 'args.json'), vars(args))
run_train(model, train, valid=test,
batch_size=args.batchsize, epoch=args.epoch,
out=args.out, extensions_list=extensions_list,
device=device, converter=converter) #, resume_path=args.resume)
# Save the model's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
if hasattr(model.predictor.graph_conv, 'reset_state'):
model.predictor.graph_conv.reset_state()
model.save_pickle(model_path, protocol=args.protocol)
## prediction
it = SerialIterator(test, args.batchsize, repeat=False, shuffle=False)
result = []
for batch in it:
in_arrays = convert._call_converter(converter, batch, device)
with chainer.using_config('train', False), chainer.function.no_backprop_mode():
if isinstance(in_arrays, tuple):
res = model(*in_arrays)
elif isinstance(in_arrays, dict):
res = model(**in_arrays)
else:
res = model(in_arrays)
result.extend(model.y.array.get())
numpy.savetxt(os.path.join(args.out,"result.csv"), numpy.array(result))
eval_result = Evaluator(it, model, converter=converter,device=device)()
print('Evaluation result: ', eval_result)
def main():
# Supported preprocessing/network list
method_list = [
'nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn', 'relgcn', 'relgat',
'megnet'
]
label_names = D.get_tox21_label_names()
iterator_type = ['serial', 'balanced']
parser = argparse.ArgumentParser(
description='Multitask Learning with Tox21.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp',
help='graph convolution model to use '
'as a predictor.')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for logistic '
'regression. Use all labels if this option '
'is not specified.')
parser.add_argument('--iterator-type',
type=str,
choices=iterator_type,
default='serial',
help='iterator type. If `balanced` '
'is specified, data is sampled to take same number of'
'positive/negative labels during training.')
parser.add_argument('--eval-mode',
type=int,
default=1,
help='Evaluation mode.'
'0: only binary_accuracy is calculated.'
'1: binary_accuracy and ROC-AUC score is calculated')
parser.add_argument('--conv-layers',
'-c',
type=int,
default=4,
help='number of convolution layers')
parser.add_argument('--batchsize',
'-b',
type=int,
default=32,
help='batch size')
parser.add_argument(
'--device',
type=str,
default='-1',
help='Device specifier. Either ChainerX device specifier or an '
'integer. If non-negative integer, CuPy arrays with specified '
'device id are used. If negative integer, NumPy arrays are used')
parser.add_argument('--out',
'-o',
type=str,
default='result',
help='path to output directory')
parser.add_argument('--epoch',
'-e',
type=int,
default=10,
help='number of epochs')
parser.add_argument('--unit-num',
'-u',
type=int,
default=16,
help='number of units in one layer of the model')
parser.add_argument('--resume',
'-r',
type=str,
default='',
help='path to a trainer snapshot')
parser.add_argument('--frequency',
'-f',
type=int,
default=-1,
help='Frequency of taking a snapshot')
parser.add_argument('--protocol',
type=int,
default=2,
help='protocol version for pickle')
parser.add_argument('--model-filename',
type=str,
default='classifier.pkl',
help='file name for pickled model')
parser.add_argument('--num-data',
type=int,
default=-1,
help='Number of data to be parsed from parser.'
'-1 indicates to parse all data.')
args = parser.parse_args()
method = args.method
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
class_num = len(label_names)
# Dataset preparation
train, val, _ = data.load_dataset(method, labels, num_data=args.num_data)
# Network
predictor_ = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num)
iterator_type = args.iterator_type
if iterator_type == 'serial':
train_iter = I.SerialIterator(train, args.batchsize)
elif iterator_type == 'balanced':
if class_num > 1:
raise ValueError('BalancedSerialIterator can be used with only one'
'label classification, please specify label to'
'be predicted by --label option.')
train_iter = BalancedSerialIterator(train,
args.batchsize,
train.features[:, -1],
ignore_labels=-1)
train_iter.show_label_stats()
else:
raise ValueError('Invalid iterator type {}'.format(iterator_type))
device = chainer.get_device(args.device)
classifier = Classifier(predictor_,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=device)
extensions_list = []
eval_mode = args.eval_mode
converter = converter_method_dict[method]
if eval_mode == 1:
train_eval_iter = I.SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
extensions_list.append(
ROCAUCEvaluator(train_eval_iter,
classifier,
eval_func=predictor_,
device=device,
converter=converter,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
extensions_list.append(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=predictor_,
device=device,
converter=converter,
name='val',
pos_labels=1,
ignore_labels=-1))
run_train(classifier,
train_iter,
valid=val,
batch_size=args.batchsize,
epoch=args.epoch,
out=args.out,
device=device,
converter=converter,
extensions_list=extensions_list,
resume_path=args.resume)
# frequency = args.epoch if args.frequency == -1 else max(1, args.frequency)
# trainer.extend(E.snapshot(), trigger=(frequency, 'epoch'))
# trainer.run()
config = {
'method': args.method,
'conv_layers': args.conv_layers,
'unit_num': args.unit_num,
'labels': args.label
}
save_json(os.path.join(args.out, 'config.json'), config)
classifier.save_pickle(os.path.join(args.out, args.model_filename),
protocol=args.protocol)
def main():
args = parse_arguments()
# Set up some useful variables that will be used later on.
dataset_name = args.dataset
method = args.method
num_data = args.num_data
n_unit = args.unit_num
conv_layers = args.conv_layers
task_type = molnet_default_config[dataset_name]['task_type']
model_filename = {
'classification': 'classifier.pkl',
'regression': 'regressor.pkl'
}
print('Using dataset: {}...'.format(dataset_name))
# Set up some useful variables that will be used later on.
if args.label:
labels = args.label
cache_dir = os.path.join(
'input', '{}_{}_{}'.format(dataset_name, method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input',
'{}_{}_all'.format(dataset_name, method))
class_num = len(molnet_default_config[args.dataset]['tasks'])
# Load the train and validation parts of the dataset.
filenames = [
dataset_part_filename(p, num_data) for p in ['train', 'valid']
]
paths = [os.path.join(cache_dir, f) for f in filenames]
if all([os.path.exists(path) for path in paths]):
dataset_parts = []
for path in paths:
print('Loading cached dataset from {}.'.format(path))
dataset_parts.append(NumpyTupleDataset.load(path))
else:
dataset_parts = download_entire_dataset(dataset_name, num_data, labels,
method, cache_dir)
train, valid = dataset_parts[0], dataset_parts[1]
# # Scale the label values, if necessary.
# if args.scale == 'standardize':
# if task_type == 'regression':
# print('Applying standard scaling to the labels.')
# datasets, scaler = standardize_dataset_labels(datasets)
# else:
# print('Label scaling is not available for classification tasks.')
# else:
# print('No label scaling was selected.')
# scaler = None
# Set up the predictor.
predictor = set_up_predictor(method, n_unit, conv_layers, class_num)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid,
args.batchsize,
repeat=False,
shuffle=False)
# Load metrics for the current dataset.
metrics = molnet_default_config[dataset_name]['metrics']
metrics_fun = {
k: v
for k, v in metrics.items() if isinstance(v, types.FunctionType)
}
loss_fun = molnet_default_config[dataset_name]['loss']
if task_type == 'regression':
model = Regressor(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=args.gpu)
# TODO: Use standard scaler for regression task
elif task_type == 'classification':
model = Classifier(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=args.gpu)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(model)
# Save model-related output to this directory.
model_dir = os.path.join(args.out, os.path.basename(cache_dir))
if not os.path.exists(model_dir):
os.makedirs(model_dir)
# Set up the updater.
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
# Set up the trainer.
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=model_dir)
trainer.extend(
E.Evaluator(valid_iter, model, device=args.gpu, converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
# Report various metrics.
print_report_targets = ['epoch', 'main/loss', 'validation/main/loss']
for metric_name, metric_fun in metrics.items():
if isinstance(metric_fun, types.FunctionType):
print_report_targets.append('main/' + metric_name)
print_report_targets.append('validation/main/' + metric_name)
elif issubclass(metric_fun, BatchEvaluator):
trainer.extend(
metric_fun(valid_iter,
model,
device=args.gpu,
eval_func=predictor,
converter=concat_mols,
name='val',
raise_value_error=False))
print_report_targets.append('val/main/' + metric_name)
else:
raise TypeError('{} is not a supported metrics function.'.format(
type(metrics_fun)))
print_report_targets.append('elapsed_time')
# Augmented by Ishiguro
# ToDo: consider go/no-go of the following block
# (i) more reporting for val/evalutaion
# (ii) best validation score snapshot
if task_type == 'regression':
if 'RMSE' in metric_name:
trainer.extend(E.snapshot_object(
model, "best_val_" + model_filename[task_type]),
trigger=training.triggers.MinValueTrigger(
'validation/main/RMSE'))
elif 'MAE' in metric_name:
trainer.extend(E.snapshot_object(
model, "best_val_" + model_filename[task_type]),
trigger=training.triggers.MinValueTrigger(
'validation/main/MAE'))
else:
print("No validation metric defined?")
assert (False)
elif task_type == 'classification':
train_eval_iter = iterators.SerialIterator(train,
args.batchsize,
repeat=False,
shuffle=False)
trainer.extend(
ROCAUCEvaluator(train_eval_iter,
predictor,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='train',
pos_labels=1,
ignore_labels=-1,
raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(
ROCAUCEvaluator(valid_iter,
predictor,
eval_func=predictor,
device=args.gpu,
converter=concat_mols,
name='val',
pos_labels=1,
ignore_labels=-1))
print_report_targets.append('train/main/roc_auc')
print_report_targets.append('validation/main/loss')
print_report_targets.append('val/main/roc_auc')
trainer.extend(
E.snapshot_object(model, "best_val_" + model_filename[task_type]),
trigger=training.triggers.MaxValueTrigger('val/main/roc_auc'))
else:
raise NotImplementedError(
'Not implemented task_type = {}'.format(task_type))
trainer.extend(E.PrintReport(print_report_targets))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the model's parameters.
model_path = os.path.join(model_dir, model_filename[task_type])
print('Saving the trained model to {}...'.format(model_path))
model.save_pickle(model_path, protocol=args.protocol)