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):
return numpy.asarray(label_list, dtype=numpy.float32)
# Apply a preprocessor to the dataset.
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[args.method]()
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label,
labels=labels, smiles_col='SMILES')
dataset = parser.parse(args.datafile)['dataset']
# Scale the label values, if necessary.
if args.scale == 'standardize':
scaler = StandardScaler()
scaler.fit(dataset.get_datasets()[-1])
else:
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, _ = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(
args.method, args.unit_num,
args.conv_layers, class_num, label_scaler=scaler)
# Set up the regressor.
device = chainer.get_device(args.device)
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
regressor = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
print('Training...')
run_train(regressor, train, valid=None,
batch_size=args.batchsize, epoch=args.epoch,
out=args.out, extensions_list=None,
device=device, converter=concat_mols,
resume_path=None)
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
# TODO(nakago): ChainerX array cannot be sent to numpy array when internal
# state has gradients.
if hasattr(regressor.predictor.graph_conv, 'reset_state'):
regressor.predictor.graph_conv.reset_state()
regressor.save_pickle(model_path, protocol=args.protocol)
def test_standard_scaler_transform_zero_std():
x = numpy.array([[1, 2], [1, 2], [1, 2]], dtype=numpy.float32)
expect_x_scaled = numpy.array([[0, 0], [0, 0], [0, 0]],
dtype=numpy.float32)
scaler = StandardScaler()
scaler.fit(x)
x_scaled = scaler.transform(x)
assert numpy.allclose(x_scaled, expect_x_scaled)
def test_standard_scaler_transform_zero_std():
x = numpy.array([[1, 2], [1, 2], [1, 2]], dtype=numpy.float32)
expect_x_scaled = numpy.array([[0, 0], [0, 0], [0, 0]],
dtype=numpy.float32)
scaler = StandardScaler()
scaler.fit(x)
x_scaled = scaler.transform(x)
assert numpy.allclose(x_scaled, expect_x_scaled)
def test_standard_scaler_transform_variable(data):
x, expect_x_scaled = data
xvar = Variable(x)
scaler = StandardScaler()
scaler.fit(xvar)
x_scaled = scaler.transform(xvar)
assert isinstance(x_scaled, Variable)
assert numpy.allclose(x_scaled.array, expect_x_scaled)
def test_standard_scaler_transform_variable(data):
x, expect_x_scaled = data
xvar = Variable(x)
scaler = StandardScaler()
scaler.fit(xvar)
x_scaled = scaler.transform(xvar)
assert isinstance(x_scaled, Variable)
assert numpy.allclose(x_scaled.array, expect_x_scaled)
def test_standard_scaler_assert_raises():
x = numpy.array([[0.1, 0.2, 0.3], [0.5, 0.3, 0.1]],
dtype=numpy.float32)
scaler = StandardScaler()
# call transform before fit raises error
with pytest.raises(AttributeError):
scaler.transform(x)
with pytest.raises(AttributeError):
scaler.inverse_transform(x)
def test_standard_scaler_inverse_transform(data, indices):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.fit(x, indices=indices)
x_inverse = scaler.inverse_transform(expect_x_scaled)
if indices is None:
indices = numpy.arange(x.shape[1])
for index in range(x.shape[1]):
if index in indices:
assert numpy.allclose(x_inverse[:, index], x[:, index])
else:
assert numpy.allclose(x_inverse[:, index],
expect_x_scaled[:, index])
def test_standard_scaler_inverse_transform(data, indices):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.fit(x, indices=indices)
x_inverse = scaler.inverse_transform(expect_x_scaled)
if indices is None:
indices = numpy.arange(x.shape[1])
for index in range(x.shape[1]):
if index in indices:
assert numpy.allclose(x_inverse[:, index], x[:, index])
else:
assert numpy.allclose(x_inverse[:, index],
expect_x_scaled[:, index])
def test_standard_scaler_serialize(tmpdir, data, indices):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.fit(x, indices=indices)
scaler_filepath = os.path.join(str(tmpdir), 'scaler.npz')
serializers.save_npz(scaler_filepath, scaler)
scaler2 = StandardScaler()
serializers.load_npz(scaler_filepath, scaler2)
# print('scaler2 attribs:', scaler2.mean, scaler2.std, scaler2.indices)
assert numpy.allclose(scaler.mean, scaler2.mean)
assert numpy.allclose(scaler.std, scaler2.std)
assert scaler.indices == scaler2.indices
def test_standard_scaler_serialize(tmpdir, data, indices):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.fit(x, indices=indices)
scaler_filepath = os.path.join(str(tmpdir), 'scaler.npz')
serializers.save_npz(scaler_filepath, scaler)
scaler2 = StandardScaler()
serializers.load_npz(scaler_filepath, scaler2)
# print('scaler2 attribs:', scaler2.mean, scaler2.std, scaler2.indices)
assert numpy.allclose(scaler.mean, scaler2.mean)
assert numpy.allclose(scaler.std, scaler2.std)
assert scaler.indices == scaler2.indices
def test_standard_scaler_transform_gpu(data):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.to_gpu()
x = cuda.to_gpu(x)
scaler.fit(x)
x_scaled = scaler.transform(x)
assert isinstance(x_scaled, cuda.cupy.ndarray)
assert numpy.allclose(cuda.to_cpu(x_scaled), expect_x_scaled)
def test_standard_scaler_3darray(data, axis):
x, expect_x_scaled = data
s0, s1 = x.shape
if axis == 1:
# feature axis is 1, insert other axis to 2nd axis
x = numpy.broadcast_to(x[:, :, None], (s0, s1, 2))
expect_x_scaled = numpy.broadcast_to(
expect_x_scaled[:, :, None], (s0, s1, 2))
elif axis == 2:
# feature axis is 2, insert other axis to 1st axis
x = numpy.broadcast_to(x[:, None, :], (s0, 3, s1))
expect_x_scaled = numpy.broadcast_to(
expect_x_scaled[:, None, :], (s0, 3, s1))
assert x.ndim == 3
indices = None
scaler = StandardScaler()
scaler.fit(x, indices=indices, axis=axis)
x_scaled = scaler.transform(x, axis=axis)
assert x_scaled.shape == expect_x_scaled.shape
assert numpy.allclose(x_scaled, expect_x_scaled, atol=1e-7)
x_inverse = scaler.inverse_transform(expect_x_scaled, axis=axis)
for index in numpy.arange(x.shape[1]):
assert numpy.allclose(x_inverse[:, index], x[:, index], atol=1e-7)
def test_standard_scaler_assert_raises():
x = numpy.array([[0.1, 0.2, 0.3], [0.5, 0.3, 0.1]], dtype=numpy.float32)
scaler = StandardScaler()
# call transform before fit raises error
with pytest.raises(AttributeError):
scaler.transform(x)
with pytest.raises(AttributeError):
scaler.inverse_transform(x)
def test_standard_scaler_transform_gpu(data):
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.to_gpu()
x = cuda.to_gpu(x)
scaler.fit(x)
x_scaled = scaler.transform(x)
assert isinstance(x_scaled, cuda.cupy.ndarray)
assert numpy.allclose(cuda.to_cpu(x_scaled), expect_x_scaled)
def test_standard_scaler_forward(data):
# test `forward` and `__call__` method.
indices = [0]
x, expect_x_scaled = data
scaler = StandardScaler()
scaler.fit(x, indices=indices)
x_scaled_transform = scaler.transform(x)
x_scaled_forward = scaler.forward(x)
assert numpy.allclose(x_scaled_transform, x_scaled_forward)
if int(chainer.__version__.split('.')[0]) >= 5:
# `__call__` invokes `forward` method from version 5.
# Skip test for chainer v4.
x_scaled_call = scaler(x)
assert numpy.allclose(x_scaled_transform, x_scaled_call)
def test_standard_scaler_fit_transform(data):
x, expect_x_scaled = data
scaler = StandardScaler()
x_scaled = scaler.fit_transform(x)
assert numpy.allclose(x_scaled, expect_x_scaled)
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached dataset from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor, labels=labels,
target_index=target_index)
else:
# Load the entire dataset.
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Scale the label values, if necessary.
if args.scale == 'standardize':
print('Applying standard scaling to the labels.')
scaler = StandardScaler()
scaled_t = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1]
+ (scaled_t,)))
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, valid = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num, scaler)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid, args.batchsize, repeat=False,
shuffle=False)
# Set up the regressor.
device = args.gpu
metrics_fun = {'mae': MeanAbsError(scaler=scaler),
'rmse': RootMeanSqrError(scaler=scaler)}
regressor = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# 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=args.out)
trainer.extend(E.Evaluator(valid_iter, regressor, device=device,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.PrintReport([
'epoch', 'main/loss', 'main/mae', 'main/rmse', 'validation/main/loss',
'validation/main/mae', 'validation/main/rmse', 'elapsed_time']))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.save_pickle(model_path, protocol=args.protocol)
def test_standard_scaler_fit_transform(data):
x, expect_x_scaled = data
scaler = StandardScaler()
x_scaled = scaler.fit_transform(x)
assert numpy.allclose(x_scaled, expect_x_scaled)
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():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached dataset from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor, labels=labels,
target_index=target_index)
else:
# Load the entire dataset.
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Scale the label values, if necessary.
if args.scale == 'standardize':
print('Applying standard scaling to the labels.')
scaler = StandardScaler()
scaled_t = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1]
+ (scaled_t,)))
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, valid = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num, scaler)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid, args.batchsize, repeat=False,
shuffle=False)
# Set up the regressor.
device = args.gpu
metrics_fun = {'mae': MeanAbsError(scaler=scaler),
'rmse': RootMeanSqrError(scaler=scaler)}
regressor = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# 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=args.out)
trainer.extend(E.Evaluator(valid_iter, regressor, device=device,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.PrintReport([
'epoch', 'main/loss', 'main/mae', 'main/rmse', 'validation/main/loss',
'validation/main/mae', 'validation/main/rmse', 'elapsed_time']))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.save_pickle(model_path, protocol=args.protocol)
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached dataset from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor,
labels=labels,
target_index=target_index)
else:
# Load the entire dataset.
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Scale the label values, if necessary.
if args.scale == 'standardize':
print('Fit StandardScaler to the labels.')
scaler = StandardScaler()
scaler.fit(dataset.get_datasets()[-1])
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, valid = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num, scaler)
# Set up the regressor.
device = chainer.get_device(args.device)
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
regressor = Regressor(predictor,
lossfun=F.mean_squared_error,
metrics_fun=metrics_fun,
device=device)
print('Training...')
run_train(regressor,
train,
valid=valid,
batch_size=args.batchsize,
epoch=args.epoch,
out=args.out,
extensions_list=None,
device=device,
converter=concat_mols,
resume_path=None)
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.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):
return numpy.asarray(label_list, dtype=numpy.float32)
# Apply a preprocessor to the dataset.
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[args.method]()
parser = CSVFileParser(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_col='SMILES')
dataset = parser.parse(args.datafile)['dataset']
# Scale the label values, if necessary.
if args.scale == 'standardize':
scaler = StandardScaler()
scaler.fit(dataset.get_datasets()[-1])
else:
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, _ = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(args.method,
args.unit_num,
args.conv_layers,
class_num,
label_scaler=scaler)
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
# Set up the regressor.
device = args.gpu
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
regressor = Regressor(predictor,
lossfun=F.mean_squared_error,
metrics_fun=metrics_fun,
device=device)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# Set up the updater.
updater = training.StandardUpdater(train_iter,
optimizer,
device=device,
converter=concat_mols)
# Set up the trainer.
print('Training...')
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport(
['epoch', 'main/loss', 'main/mae', 'main/rmse', 'elapsed_time']))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.save_pickle(model_path, protocol=args.protocol)