def check_invalid_key(self, gpu, label_key):
link = Classifier(links.Linear(10, 3), label_key=label_key)
if gpu:
link.to_gpu()
x = chainer.Variable(link.xp.asarray(self.x))
with pytest.raises(ValueError):
link(x)
def check_predict_proba(self, device):
clf = Classifier(self.predictor, device=device)
actual_y = clf.predict_proba(self.x)
assert actual_y.shape == (3, 2)
assert actual_y.dtype == numpy.float32
assert numpy.alltrue(0 <= actual_y)
assert numpy.alltrue(actual_y <= 1.)
actual_t = numpy.argmax(actual_y, axis=1)
assert numpy.alltrue(actual_t == self.t)
def check_call(self, gpu, label_key, args, kwargs, model_args,
model_kwargs, metrics_fun, compute_metrics):
init_kwargs = {'label_key': label_key}
if metrics_fun is not None:
init_kwargs['metrics_fun'] = metrics_fun
link = Classifier(chainer.Link(), **init_kwargs)
if gpu:
xp = cuda.cupy
link.to_gpu()
else:
xp = numpy
link.compute_metrics = compute_metrics
y = chainer.Variable(self.y)
link.predictor = mock.MagicMock(return_value=y)
loss = link(*args, **kwargs)
link.predictor.assert_called_with(*model_args, **model_kwargs)
assert hasattr(link, 'y')
assert link.y is not None
assert hasattr(link, 'loss')
xp.testing.assert_allclose(link.loss.data, loss.data)
assert hasattr(link, 'metrics')
if compute_metrics:
assert link.metrics is not None
else:
assert link.metrics is None
def test_report_key(self, metrics_fun, compute_metrics):
repo = chainer.Reporter()
link = Classifier(predictor=DummyPredictor(), metrics_fun=metrics_fun)
link.compute_metrics = compute_metrics
repo.add_observer('target', link)
with repo:
observation = {}
with reporter.report_scope(observation):
link(self.x, self.t)
# print('observation ', observation)
actual_keys = set(observation.keys())
if compute_metrics:
if metrics_fun is None:
assert set(['target/loss']) == actual_keys
elif isinstance(metrics_fun, dict):
assert set(['target/loss', 'target/user_key']) == actual_keys
elif callable(metrics_fun):
assert set(['target/loss', 'target/accuracy']) == actual_keys
else:
raise TypeError()
else:
assert set(['target/loss']) == actual_keys
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')
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)
def main():
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
dataset_names = list(molnet_default_config.keys())
parser = argparse.ArgumentParser(description='molnet example')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
default='',
help='target label for regression, empty string means '
'to predict all property at once')
parser.add_argument('--conv-layers', '-c', type=int, default=4)
parser.add_argument('--batchsize', '-b', type=int, default=32)
parser.add_argument('--gpu', '-g', type=int, default=-1)
parser.add_argument('--out', '-o', type=str, default='result')
parser.add_argument('--epoch', '-e', type=int, default=20)
parser.add_argument('--unit-num', '-u', type=int, default=16)
parser.add_argument('--dataset',
'-d',
type=str,
choices=dataset_names,
default='bbbp')
parser.add_argument('--protocol', type=int, default=2)
parser.add_argument('--model-filename', type=str, default='regressor.pkl')
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()
dataset_name = args.dataset
method = args.method
num_data = args.num_data
n_unit = args.unit_num
conv_layers = args.conv_layers
print('Use {} dataset'.format(dataset_name))
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'])
# Dataset preparation
def get_dataset_paths(cache_dir, num_data):
filepaths = []
for filetype in ['train', 'valid', 'test']:
filename = filetype + '_data'
if num_data >= 0:
filename += '_' + str(num_data)
filename += '.npz'
filepath = os.path.join(cache_dir, filename)
filepaths.append(filepath)
return filepaths
filepaths = get_dataset_paths(cache_dir, num_data)
if all([os.path.exists(fpath) for fpath in filepaths]):
datasets = []
for fpath in filepaths:
print('load from cache {}'.format(fpath))
datasets.append(NumpyTupleDataset.load(fpath))
else:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
# only use first 100 for debug if num_data >= 0
target_index = numpy.arange(num_data) if num_data >= 0 else None
datasets = D.molnet.get_molnet_dataset(dataset_name,
preprocessor,
labels=labels,
target_index=target_index)
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
datasets = datasets['dataset']
for i, fpath in enumerate(filepaths):
NumpyTupleDataset.save(fpath, datasets[i])
train, val, _ = datasets
# Network
if method == 'nfp':
print('Train NFP model...')
predictor = GraphConvPredictor(
NFP(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'ggnn':
print('Train GGNN model...')
predictor = GraphConvPredictor(
GGNN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'schnet':
print('Train SchNet model...')
predictor = GraphConvPredictor(
SchNet(out_dim=class_num, hidden_dim=n_unit, n_layers=conv_layers),
None)
elif method == 'weavenet':
print('Train WeaveNet model...')
n_atom = 20
n_sub_layer = 1
weave_channels = [50] * conv_layers
predictor = GraphConvPredictor(
WeaveNet(weave_channels=weave_channels,
hidden_dim=n_unit,
n_sub_layer=n_sub_layer,
n_atom=n_atom), MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'rsgcn':
print('Train RSGCN model...')
predictor = GraphConvPredictor(
RSGCN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
else:
raise ValueError('[ERROR] Invalid method {}'.format(method))
train_iter = iterators.SerialIterator(train, args.batchsize)
val_iter = iterators.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
metrics_fun = molnet_default_config[dataset_name]['metrics']
loss_fun = molnet_default_config[dataset_name]['loss']
task_type = molnet_default_config[dataset_name]['task_type']
if task_type == 'regression':
model = Regressor(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=args.gpu)
# TODO(nakago): 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 NotImplementedError(
'Not implemented task_type = {}'.format(task_type))
optimizer = optimizers.Adam()
optimizer.setup(model)
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, model, device=args.gpu, converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
print_report_targets = ['epoch', 'main/loss', 'validation/main/loss']
if metrics_fun is not None and type(metrics_fun) == dict:
for m_k in metrics_fun.keys():
print_report_targets.append('main/' + m_k)
print_report_targets.append('validation/main/' + m_k)
if task_type == 'classification':
# Evaluation for train data takes time, skip for now.
# trainer.extend(ROCAUCEvaluator(
# train_iter, model, device=args.gpu, eval_func=predictor,
# converter=concat_mols, name='train', raise_value_error=False))
# print_report_targets.append('train/main/roc_auc')
trainer.extend(
ROCAUCEvaluator(val_iter,
model,
device=args.gpu,
eval_func=predictor,
converter=concat_mols,
name='val',
raise_value_error=False))
print_report_targets.append('val/main/roc_auc')
print_report_targets.append('elapsed_time')
trainer.extend(E.PrintReport(print_report_targets))
trainer.extend(E.ProgressBar())
trainer.run()
# --- save model ---
protocol = args.protocol
model.save_pickle(os.path.join(args.out, args.model_filename),
protocol=protocol)
def test_predict_gpu(self):
clf = Classifier(self.predictor, device=0)
actual_t = clf.predict(self.x)
assert numpy.alltrue(actual_t == self.t)
def main():
parser = argparse.ArgumentParser(
description='Predict with a trained model.')
parser.add_argument('--in-dir', '-i', type=str, default='result',
help='Path to the result directory of the training '
'script.')
parser.add_argument('--batchsize', '-b', type=int, default=128,
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('--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()
with open(os.path.join(args.in_dir, 'config.json'), 'r') as i:
config = json.loads(i.read())
method = config['method']
labels = config['labels']
_, test, _ = data.load_dataset(method, labels, num_data=args.num_data)
y_test = test.get_datasets()[-1]
# Load pretrained model
clf = Classifier.load_pickle(
os.path.join(args.in_dir, args.model_filename),
device=args.gpu) # type: Classifier
# ---- predict ---
print('Predicting...')
# We need to feed only input features `x` to `predict`/`predict_proba`.
# This converter extracts only inputs (x1, x2, ...) from the features which
# consist of input `x` and label `t` (x1, x2, ..., t).
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_pred(x):
x_array = cuda.to_cpu(x.data)
return numpy.where(x_array > 0, 1, 0)
y_pred = clf.predict(test, converter=extract_inputs,
postprocess_fn=postprocess_pred)
y_proba = clf.predict_proba(test, converter=extract_inputs,
postprocess_fn=F.sigmoid)
# `predict` method returns the prediction label (0: non-toxic, 1:toxic)
print('y_pread.shape = {}, y_pred[:5, 0] = {}'
.format(y_pred.shape, y_pred[:5, 0]))
# `predict_proba` method returns the probability to be toxic
print('y_proba.shape = {}, y_proba[:5, 0] = {}'
.format(y_proba.shape, y_proba[:5, 0]))
# --- predict end ---
if y_pred.ndim == 1:
y_pred = y_pred[:, None]
if y_pred.shape != y_test.shape:
raise RuntimeError('The shape of the prediction result array and '
'that of the ground truth array do not match. '
'Contents of the input directory may be corrupted '
'or modified.')
statistics = []
for t, p in six.moves.zip(y_test.T, y_pred.T):
idx = t != -1
n_correct = (t[idx] == p[idx]).sum()
n_total = len(t[idx])
accuracy = float(n_correct) / n_total
statistics.append([n_correct, n_total, accuracy])
print('{:>6} {:>8} {:>8} {:>8}'
.format('TaskID', 'Correct', 'Total', 'Accuracy'))
for idx, (n_correct, n_total, accuracy) in enumerate(statistics):
print('task{:>2} {:>8} {:>8} {:>8.4f}'
.format(idx, n_correct, n_total, accuracy))
prediction_result_file = 'prediction.npz'
print('Save prediction result to {}'.format(prediction_result_file))
numpy.savez_compressed(prediction_result_file, y_pred)
# --- evaluate ---
# To calc loss/accuracy, we can use `Evaluator`, `ROCAUCEvaluator`
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(
test_iterator, clf, converter=concat_mols, device=args.gpu)()
print('Evaluation result: ', eval_result)
rocauc_result = ROCAUCEvaluator(
test_iterator, clf, converter=concat_mols, device=args.gpu,
eval_func=clf.predictor, name='test', ignore_labels=-1)()
print('ROCAUC Evaluation result: ', rocauc_result)
with open(os.path.join(args.in_dir, 'eval_result.json'), 'w') as f:
json.dump(rocauc_result, f)
def main():
args = parse_arguments()
generate_drug_list = True if args.generate_drug_list == 'True' else False
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 test dataset...')
preprocessor = preprocess_method_dict['ggnn']()
parser = CSVFileParserForPair(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_cols=['smiles_1', 'smiles_2'])
test_dict = parser.parse(args.test_datafile,
return_smiles_pair_original=True)
test = test_dict['dataset']
# test_smiles_pairs = test_dict['smiles_pair_original']
from chainer.iterators import SerialIterator
test_iter = SerialIterator(test, 64, repeat=False, shuffle=False)
out = 'output' + '/' + args.out
model_path = os.path.join(out, args.model_filename)
# `load_pickle` is static method, call from Class to get an instance
print('model_path: {}'.format(model_path))
from chainer_chemistry.models.prediction import Classifier
model = Classifier.load_pickle(model_path, args.gpu)
if args.gpu >= 0:
model.to_gpu(args.gpu)
else:
model.to_cpu()
snapshot_path = os.path.join(out, args.snapshot)
try:
chainer.serializers.load_npz(snapshot_path, model)
except KeyError as e:
print(e)
def eval_func(atoms_1, adj_1, atoms_2, adj_2):
sample = [
(atoms_1, adj_1),
(atoms_2, adj_2),
]
sample = concat_mols(sample)
atoms_1, adj_1 = sample[0]
atoms_2, adj_2 = sample[1]
print(atoms_1, adj_1)
print('shape 1:', atoms_1.shape, adj_1.shape)
print('shape 2:', atoms_2.shape, adj_2.shape)
pred, _ = model.predictor.predict(atoms_1, adj_1, atoms_2, adj_2)
return pred
evaluator = MyEvaluator(
test_iter,
model,
converter=concat_mols,
device=args.gpu,
eval_func=model.predictor.predict,
# eval_func=eval_func,
# mediate_func=models.predictor.mediate_output,
name='test',
ignore_labels=-1)
e1_total, e2_total = evaluator.generate_representations()
y_total, t_total = evaluator.generate_y_and_t()
# print('test_datafile: {}'.format(args.test_datafile))
test_filename = os.path.basename(args.test_datafile).split('.')[0]
# print('test_filename: {}'.format(test_filename))
dst_repre_filename = test_filename + '_e' + '.csv'
dst_repre_filepath = os.path.join(out, dst_repre_filename)
add_representations(args.test_datafile,
dst_repre_filepath,
e1_total,
e2_total,
generate_drug_list=generate_drug_list)
dst_filename = test_filename + '_e_y' + '.csv'
dst_filepath = os.path.join(out, dst_filename)
add_reprensentations_and_y(args.test_datafile, dst_filepath, e1_total,
e2_total, y_total)
perf_dict = dict()
for metric in [
'roc_auc', 'prc_auc', 'accuracy', 'precision', 'recall', 'f1'
]:
result = evaluator.compuate(metric=metric)
perf_dict[metric] = result
print('{}: {}'.format(metric, result))
with open(os.path.join(ROOT_PATH, 'eval_result.json'), 'w') as f:
json.dump(perf_dict, f)
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():
parser = argparse.ArgumentParser(
description='Predict with a trained model.')
parser.add_argument('--in-dir',
'-i',
type=str,
default='result',
help='Path to the result directory of the training '
'script.')
parser.add_argument('--batchsize',
'-b',
type=int,
default=128,
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('--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()
with open(os.path.join(args.in_dir, 'config.json'), 'r') as i:
config = json.loads(i.read())
method = config['method']
labels = config['labels']
_, test, _ = data.load_dataset(method, labels, num_data=args.num_data)
y_test = test.get_datasets()[-1]
# Load pretrained model
clf = Classifier.load_pickle(os.path.join(args.in_dir,
args.model_filename),
device=args.gpu) # type: Classifier
# ---- predict ---
print('Predicting...')
# We need to feed only input features `x` to `predict`/`predict_proba`.
# This converter extracts only inputs (x1, x2, ...) from the features which
# consist of input `x` and label `t` (x1, x2, ..., t).
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_pred(x):
x_array = cuda.to_cpu(x.data)
return numpy.where(x_array > 0, 1, 0)
y_pred = clf.predict(test,
converter=extract_inputs,
postprocess_fn=postprocess_pred)
y_proba = clf.predict_proba(test,
converter=extract_inputs,
postprocess_fn=F.sigmoid)
# `predict` method returns the prediction label (0: non-toxic, 1:toxic)
print('y_pread.shape = {}, y_pred[:5, 0] = {}'.format(
y_pred.shape, y_pred[:5, 0]))
# `predict_proba` method returns the probability to be toxic
print('y_proba.shape = {}, y_proba[:5, 0] = {}'.format(
y_proba.shape, y_proba[:5, 0]))
# --- predict end ---
if y_pred.ndim == 1:
y_pred = y_pred[:, None]
if y_pred.shape != y_test.shape:
raise RuntimeError('The shape of the prediction result array and '
'that of the ground truth array do not match. '
'Contents of the input directory may be corrupted '
'or modified.')
statistics = []
for t, p in six.moves.zip(y_test.T, y_pred.T):
idx = t != -1
n_correct = (t[idx] == p[idx]).sum()
n_total = len(t[idx])
accuracy = float(n_correct) / n_total
statistics.append([n_correct, n_total, accuracy])
print('{:>6} {:>8} {:>8} {:>8}'.format('TaskID', 'Correct', 'Total',
'Accuracy'))
for idx, (n_correct, n_total, accuracy) in enumerate(statistics):
print('task{:>2} {:>8} {:>8} {:>8.4f}'.format(idx, n_correct, n_total,
accuracy))
prediction_result_file = 'prediction.npz'
print('Save prediction result to {}'.format(prediction_result_file))
numpy.savez_compressed(prediction_result_file, y_pred)
# --- evaluate ---
# To calc loss/accuracy, we can use `Evaluator`, `ROCAUCEvaluator`
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
clf,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
rocauc_result = ROCAUCEvaluator(test_iterator,
clf,
converter=concat_mols,
device=args.gpu,
eval_func=clf.predictor,
name='test',
ignore_labels=-1)()
print('ROCAUC Evaluation result: ', rocauc_result)
with open(os.path.join(args.in_dir, 'eval_result.json'), 'w') as f:
json.dump(rocauc_result, f)
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
if args.label:
labels = args.label
cache_dir = os.path.join(
'input', '{}_{}_{}'.format(dataset_name, method, labels))
else:
labels = None
cache_dir = os.path.join('input',
'{}_{}_all'.format(dataset_name, method))
# Load the cached dataset.
filename = dataset_part_filename('test', num_data)
path = os.path.join(cache_dir, filename)
if os.path.exists(path):
print('Loading cached dataset from {}.'.format(path))
test = NumpyTupleDataset.load(path)
else:
_, _, test = download_entire_dataset(dataset_name, num_data, labels,
method, cache_dir)
# Model-related data is stored this directory.
model_dir = os.path.join(args.in_dir, os.path.basename(cache_dir))
model_filename = {
'classification': 'classifier.pkl',
'regression': 'regressor.pkl'
}
task_type = molnet_default_config[dataset_name]['task_type']
model_path = os.path.join(model_dir, model_filename[task_type])
print("model_path=" + model_path)
print('Loading model weights from {}...'.format(model_path))
if task_type == 'classification':
model = Classifier.load_pickle(model_path, device=args.gpu)
elif task_type == 'regression':
model = Regressor.load_pickle(model_path, device=args.gpu)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# Re-load the best-validation score snapshot
# serializers.load_npz(os.path.join(
# model_dir, "best_val_" + model_filename[task_type]), model)
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
model,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
# Add more stats
if task_type == 'regression':
# loss = cuda.to_cpu(numpy.array(eval_result['main/loss']))
# eval_result['main/loss'] = loss
# convert to native values..
for k, v in eval_result.items():
eval_result[k] = float(v)
elif task_type == "classification":
# For Classifier, we do not equip the model with ROC-AUC evalation function
# use a seperate ROC-AUC Evaluator here
rocauc_result = ROCAUCEvaluator(test_iterator,
model,
converter=concat_mols,
device=args.gpu,
eval_func=model.predictor,
name='test',
ignore_labels=-1)()
print('ROCAUC Evaluation result: ', rocauc_result)
save_json(os.path.join(model_dir, 'rocauc_result.json'), rocauc_result)
else:
print('[WARNING] unknown task_type {}.'.format(task_type))
# Save the evaluation results.
save_json(os.path.join(model_dir, 'eval_result.json'), eval_result)
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():
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
if args.label:
labels = args.label
cache_dir = os.path.join(
'input', '{}_{}_{}'.format(dataset_name, method, labels))
else:
labels = None
cache_dir = os.path.join('input',
'{}_{}_all'.format(dataset_name, method))
# Load the cached dataset.
filename = dataset_part_filename('test', num_data)
path = os.path.join(cache_dir, filename)
if os.path.exists(path):
print('Loading cached dataset from {}.'.format(path))
test = NumpyTupleDataset.load(path)
else:
_, _, test = download_entire_dataset(dataset_name, num_data, labels,
method, cache_dir)
# # Load the standard scaler parameters, if necessary.
# if args.scale == 'standardize':
# scaler_path = os.path.join(args.in_dir, 'scaler.pkl')
# print('Loading scaler parameters from {}.'.format(scaler_path))
# with open(scaler_path, mode='rb') as f:
# scaler = pickle.load(f)
# else:
# print('No standard scaling was selected.')
# scaler = None
# Model-related data is stored this directory.
model_dir = os.path.join(args.in_dir, os.path.basename(cache_dir))
model_filename = {
'classification': 'classifier.pkl',
'regression': 'regressor.pkl'
}
task_type = molnet_default_config[dataset_name]['task_type']
model_path = os.path.join(model_dir, model_filename[task_type])
print('Loading model weights from {}...'.format(model_path))
if task_type == 'classification':
model = Classifier.load_pickle(model_path, device=args.gpu)
elif task_type == 'regression':
model = Regressor.load_pickle(model_path, device=args.gpu)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# # Replace the default predictor with one that scales the output labels.
# scaled_predictor = ScaledGraphConvPredictor(model.predictor)
# scaled_predictor.scaler = scaler
# model.predictor = scaled_predictor
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
model,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
# Save the evaluation results.
with open(os.path.join(model_dir, 'eval_result.json'), 'w') as f:
json.dump(eval_result, f)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn', 'relgcn',
'relgat']
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, 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.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():
label_names = D.get_tox21_label_names()
parser = argparse.ArgumentParser(
description='Predict with a trained model.')
parser.add_argument('--in-dir',
'-i',
type=str,
default='result',
help='Path to the result directory of the training '
'script.')
parser.add_argument('--trainer-snapshot',
'-s',
type=str,
default='',
help='Path to the snapshot file of the Chainer '
'trainer from which serialized model parameters '
'are extracted. If it is not specified, this '
'script searches the training result directory '
'for the latest snapshot, assuming that '
'the naming convension of snapshot files is '
'`snapshot_iter_N` where N is the number of '
'iterations, which is the default configuration '
'of Chainer.')
parser.add_argument('--batchsize',
'-b',
type=int,
default=128,
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.')
args = parser.parse_args()
with open(os.path.join(args.in_dir, 'config.json'), 'r') as i:
config = json.loads(i.read())
method = config['method']
labels = config['labels']
if labels:
class_num = len(labels) if isinstance(labels, list) else 1
else:
class_num = len(label_names)
_, test, _ = data.load_dataset(method, labels)
y_test = test.get_datasets()[-1]
# Load pretrained model
predictor_ = predictor.build_predictor(method, config['unit_num'],
config['conv_layers'], class_num)
snapshot_file = args.trainer_snapshot
if not snapshot_file:
snapshot_file = _find_latest_snapshot(args.in_dir)
print('Loading pretrained model parameters from {}'.format(snapshot_file))
chainer.serializers.load_npz(snapshot_file, predictor_,
'updater/model:main/predictor/')
clf = Classifier(predictor=predictor_,
device=args.gpu,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy)
# ---- predict ---
print('Predicting...')
# We need to feed only input features `x` to `predict`/`predict_proba`.
# This converter extracts only inputs (x1, x2, ...) from the features which
# consist of input `x` and label `t` (x1, x2, ..., t).
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_pred(x):
x_array = cuda.to_cpu(x.data)
return numpy.where(x_array > 0, 1, 0)
y_pred = clf.predict(test,
converter=extract_inputs,
postprocess_fn=postprocess_pred)
y_proba = clf.predict_proba(test,
converter=extract_inputs,
postprocess_fn=F.sigmoid)
# `predict` method returns the prediction label (0: non-toxic, 1:toxic)
print('y_pread.shape = {}, y_pred[:5, 0] = {}'.format(
y_pred.shape, y_pred[:5, 0]))
# `predict_proba` method returns the probability to be toxic
print('y_proba.shape = {}, y_proba[:5, 0] = {}'.format(
y_proba.shape, y_proba[:5, 0]))
# --- predict end ---
if y_pred.ndim == 1:
y_pred = y_pred[:, None]
if y_pred.shape != y_test.shape:
raise RuntimeError('The shape of the prediction result array and '
'that of the ground truth array do not match. '
'Contents of the input directory may be corrupted '
'or modified.')
statistics = []
for t, p in six.moves.zip(y_test.T, y_pred.T):
idx = t != -1
n_correct = (t[idx] == p[idx]).sum()
n_total = len(t[idx])
accuracy = float(n_correct) / n_total
statistics.append([n_correct, n_total, accuracy])
print('{:>6} {:>8} {:>8} {:>8}'.format('TaskID', 'Correct', 'Total',
'Accuracy'))
for idx, (n_correct, n_total, accuracy) in enumerate(statistics):
print('task{:>2} {:>8} {:>8} {:>8.4f}'.format(idx, n_correct, n_total,
accuracy))
prediction_result_file = 'prediction.npz'
print('Save prediction result to {}'.format(prediction_result_file))
numpy.savez_compressed(prediction_result_file, y_pred)
# --- evaluate ---
# To calc loss/accuracy, we can use `Evaluator`, `ROCAUCEvaluator`
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
clf,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
rocauc_result = ROCAUCEvaluator(test_iterator,
clf,
converter=concat_mols,
device=args.gpu,
eval_func=predictor_,
name='test',
ignore_labels=-1)()
print('ROCAUC Evaluation result: ', rocauc_result)
def main():
# Supported preprocessing/network list
method_list = [
'nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn', 'relgcn', 'relgat'
]
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
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=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.
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
extensions_list.append(
ROCAUCEvaluator(val_iter,
classifier,
eval_func=predictor_,
device=device,
converter=concat_mols,
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=concat_mols,
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
if args.label:
labels = args.label
cache_dir = os.path.join(
'input', '{}_{}_{}'.format(dataset_name, method, labels))
else:
labels = None
cache_dir = os.path.join('input',
'{}_{}_all'.format(dataset_name, method))
# Load the cached dataset.
filename = dataset_part_filename('test', num_data)
path = os.path.join(cache_dir, filename)
if os.path.exists(path):
print('Loading cached dataset from {}.'.format(path))
test = NumpyTupleDataset.load(path)
else:
_, _, test = download_entire_dataset(dataset_name, num_data, labels,
method, cache_dir)
# # Load the standard scaler parameters, if necessary.
# if args.scale == 'standardize':
# scaler_path = os.path.join(args.in_dir, 'scaler.pkl')
# print('Loading scaler parameters from {}.'.format(scaler_path))
# with open(scaler_path, mode='rb') as f:
# scaler = pickle.load(f)
# else:
# print('No standard scaling was selected.')
# scaler = None
# Model-related data is stored this directory.
model_dir = os.path.join(args.in_dir, os.path.basename(cache_dir))
model_filename = {
'classification': 'classifier.pkl',
'regression': 'regressor.pkl'
}
task_type = molnet_default_config[dataset_name]['task_type']
model_path = os.path.join(model_dir, model_filename[task_type])
print("model_path=" + model_path)
print('Loading model weights from {}...'.format(model_path))
if task_type == 'classification':
model = Classifier.load_pickle(model_path, device=args.gpu)
elif task_type == 'regression':
model = Regressor.load_pickle(model_path, device=args.gpu)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# Proposed by Ishiguro
# ToDo: consider go/no-go with following modification
# Re-load the best-validation score snapshot
serializers.load_npz(
os.path.join(model_dir, "best_val_" + model_filename[task_type]),
model)
# # Replace the default predictor with one that scales the output labels.
# scaled_predictor = ScaledGraphConvPredictor(model.predictor)
# scaled_predictor.scaler = scaler
# model.predictor = scaled_predictor
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
model,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
# Proposed by Ishiguro: add more stats
# ToDo: considre go/no-go with the following modification
if task_type == 'regression':
# loss = cuda.to_cpu(numpy.array(eval_result['main/loss']))
# eval_result['main/loss'] = loss
# convert to native values..
for k, v in eval_result.items():
eval_result[k] = float(v)
save_json(os.path.join(args.in_dir, 'eval_result.json'), eval_result)
elif task_type == "classification":
# For Classifier, we do not equip the model with ROC-AUC evalation function
# use a seperate ROC-AUC Evaluator here
rocauc_result = ROCAUCEvaluator(test_iterator,
model,
converter=concat_mols,
device=args.gpu,
eval_func=model.predictor,
name='test',
ignore_labels=-1)()
print('ROCAUC Evaluation result: ', rocauc_result)
save_json(os.path.join(args.in_dir, 'eval_result.json'), rocauc_result)
else:
pass
# Save the evaluation results.
save_json(os.path.join(model_dir, 'eval_result.json'), eval_result)
def setup_class(cls):
cls.link = Classifier(links.Linear(10, 3))
cls.x = numpy.random.uniform(-1, 1, (5, 10)).astype(numpy.float32)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn', 'attention']
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
print("labels : ", labels)
print("num_data : ", args.num_data)
train, val, _ = data.load_dataset(method, labels, num_data=args.num_data)
#train data : 11757
#len(train[0]) : 3
#len(train[0][0]) : 34
#len(train[0][1]) : 34
#len(train[0][1][0]) : 34
#len(train[0][1]) : 12 ?
#import pdb;pdb.set_trace()
#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,
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.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 test_invalid_label_key_type(self):
with pytest.raises(TypeError):
Classifier(links.Linear(10, 3), label_key=None)
def main():
args = parse_arguments()
generate_drug_list = True if args.generate_drug_list == 'True' else False
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 test dataset...')
preprocessor = preprocess_method_dict['ggnn']()
parser = CSVFileParserForPair(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_cols=['smiles_1', 'smiles_2'])
test_dict = parser.parse(args.test_datafile,
return_smiles_pair_original=True)
test = test_dict['dataset']
# test_smiles_pairs = test_dict['smiles_pair_original']
from chainer.iterators import SerialIterator
test_iter = SerialIterator(test, 1, repeat=False, shuffle=False)
out = 'output' + '/' + args.out
model_path = os.path.join(out, args.model_filename)
# `load_pickle` is static method, call from Class to get an instance
print('model_path: {}'.format(model_path))
model = Classifier.load_pickle(model_path, args.gpu)
if args.gpu >= 0:
model.to_gpu(args.gpu)
else:
model.to_cpu()
snapshot_path = os.path.join(out, args.snapshot)
try:
chainer.serializers.load_npz(snapshot_path, model)
except KeyError as e:
print(e)
evaluator = MyEvaluator(
test_iter,
model,
converter=concat_mols,
device=args.gpu,
eval_func=model.predictor.predict,
# mediate_func=models.predictor.mediate_output,
name='test',
ignore_labels=-1)
e1_total, e2_total = evaluator.generate_representations()
y_total, t_total = evaluator.generate_y_and_t()
# print('test_datafile: {}'.format(args.test_datafile))
test_filename = os.path.basename(args.test_datafile).split('.')[0]
# print('test_filename: {}'.format(test_filename))
dst_repre_filename = test_filename + '_e' + '.csv'
dst_repre_filepath = os.path.join(out, dst_repre_filename)
add_representations(args.test_datafile,
dst_repre_filepath,
e1_total,
e2_total,
generate_drug_list=generate_drug_list)
dst_filename = test_filename + '_e_y' + '.csv'
dst_filepath = os.path.join(out, dst_filename)
add_reprensentations_and_y(args.test_datafile, dst_filepath, e1_total,
e2_total, y_total)
perf_dict = dict()
for metric in [
'roc_auc', 'prc_auc', 'accuracy', 'precision', 'recall', 'f1'
]:
result = evaluator.compuate(metric=metric)
perf_dict[metric] = result
print('{}: {}'.format(metric, result))
with open(os.path.join(ROOT_PATH, 'eval_result.json'), 'w') as f:
json.dump(perf_dict, f)
def eval_func(atoms_1, adj_1, atoms_2, adj_2, label):
sample = [
(atoms_1, adj_1),
(atoms_2, adj_2),
]
sample = concat_mols(sample)
atoms_1, adj_1 = sample[0]
atoms_2, adj_2 = sample[1]
print(atoms_1, adj_1)
print('shape 1:', atoms_1.shape, adj_1.shape)
print('shape 2:', atoms_2.shape, adj_2.shape)
pred, _ = model.predictor.predict(atoms_1, adj_1, atoms_2, adj_2)
return pred
calculator = IntegratedGradientsCalculator(
model.predictor,
steps=5,
eval_fun=eval_func,
target_extractor=VariableMonitorLinkHook(
model.predictor.graph_conv.embed, timing='post'),
device=args.gpu)
M = 1
# 2. compute
# saliency_samples_vanilla = calculator.compute(
# test, M=1, converter=concat_mols)
# saliency_samples_smooth = calculator.compute(
# test, M=M, converter=concat_mols, noise_sampler=GaussianNoiseSampler())
saliency_samples_bayes = calculator.compute(test,
M=M,
converter=concat_mols,
train=True)
visualizer = SmilesVisualizer()
smiles = list(pd.read_csv(args.test_datafile, index_col=0)['smiles_2'])
# from IPython.display import display, HTML
def sv_visualize(i, ratio, method, view):
# saliency_vanilla = calculator.aggregate(
# saliency_samples_vanilla, ch_axis=3, method=method)
# saliency_smooth = calculator.aggregate(
# saliency_samples_smooth, ch_axis=3, method=method)
saliency_bayes = calculator.aggregate(saliency_samples_bayes,
ch_axis=3,
method=method)
scaler = abs_max_scaler
if view == 'view':
# svg_vanilla = visualizer.visualize(saliency_vanilla[i], smiles[i], visualize_ratio=ratio, scaler=scaler)
# svg_smooth = visualizer.visualize(saliency_smooth[i], smiles[i], visualize_ratio=ratio, scaler=scaler)
svg_bayes = visualizer.visualize(saliency_bayes[i],
smiles[i],
visualize_ratio=ratio,
scaler=scaler)
# display(svg_bayes)
elif view == 'save':
if not os.path.exists('results'):
os.makedirs('results')
# visualizer.visualize(saliency_vanilla[i], smiles[i], visualize_ratio=ratio, scaler=scaler,
# save_filepath='results/{}_vanilla.png'.format(i))
# visualizer.visualize(saliency_smooth[i], smiles[i], visualize_ratio=ratio, scaler=scaler,
# save_filepath='results/{}_smooth.png'.format(i))
visualizer.visualize(
saliency_bayes[i],
smiles[i],
visualize_ratio=ratio,
scaler=scaler,
save_filepath='results/{}_bayes.svg'.format(i))
print('saved {}-th result!'.format(i))
else:
print(view, 'not supported')
sv_visualize(i=2, ratio=0.7, method='raw', view='save')
def test_predict_cpu(self):
clf = Classifier(self.predictor)
actual_t = clf.predict(self.x)
assert actual_t.shape == (3, )
assert actual_t.dtype == numpy.int32
assert numpy.alltrue(actual_t == self.t)
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.
scaler = None
if args.scale == 'standardize':
if task_type == 'regression':
print('Applying standard scaling to the labels.')
scaler = fit_scaler(dataset_parts)
else:
print('Label scaling is not available for classification tasks.')
else:
print('No label scaling was selected.')
# Set up the predictor.
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()
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=device,
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=device, converter=concat_mols))
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)
# 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, 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():
# 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)