def main():
"""Launcher."""
preprocessor = preprocess_method_dict["nfp"]()
dataset = datasets.get_qm9(preprocessor, labels="h**o")
cache_dir = "data/"
if not (os.path.exists(cache_dir)):
os.makedirs(cache_dir)
NumpyTupleDataset.save(cache_dir + "data.npz", dataset)
dataset = NumpyTupleDataset.load(cache_dir + 'data.npz')
train_data_ratio = 0.7
train_data_size = int(len(dataset) * train_data_ratio)
train, validation = split_dataset_random(dataset, train_data_size, 777)
print('train dataset size:', len(train))
print('validation dataset size:', len(validation))
n_unit = 16
conv_layers = 4
model = GraphConvPredictor(NFP(n_unit, n_unit, conv_layers),
MLP(n_unit, 1))
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':
label = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, label))
labels = [label]
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# 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 data from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the newly preprocessed dataset.
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Use a predictor with scaled output labels.
model_path = os.path.join(args.in_dir, args.model_filename)
regressor = Regressor.load_pickle(model_path, device=args.gpu)
scaler = regressor.predictor.scaler
if scaler is not None:
scaled_t = scaler.transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] +
(scaled_t, )))
# Split the dataset into training and testing.
train_data_size = int(len(dataset) * args.train_data_ratio)
_, test = split_dataset_random(dataset, train_data_size, args.seed)
# This callback function extracts only the inputs and discards the labels.
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_fn(x):
if scaler is not None:
scaled_x = scaler.inverse_transform(x)
return scaled_x
else:
return x
# Predict the output labels.
print('Predicting...')
y_pred = regressor.predict(test,
converter=extract_inputs,
postprocess_fn=postprocess_fn)
# Extract the ground-truth labels.
t = concat_mols(test, device=-1)[-1]
original_t = scaler.inverse_transform(t)
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({
'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): original_t[:, i],
})
df = pandas.DataFrame(df_dict)
# Show a prediction/ground truth table with 5 random examples.
print(df.sample(5))
n_eval = 10
for target_label in range(y_pred.shape[1]):
label_name = labels[target_label]
diff = y_pred[:n_eval, target_label] - original_t[:n_eval,
target_label]
print('label_name = {}, y_pred = {}, t = {}, diff = {}'.format(
label_name, y_pred[:n_eval, target_label],
original_t[:n_eval, target_label], diff))
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
regressor,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
# Save the evaluation results.
save_json(os.path.join(args.in_dir, 'eval_result.json'), eval_result)
# Calculate mean abs error for each label
mae = numpy.mean(numpy.abs(y_pred - original_t), axis=0)
eval_result = {}
for i, l in enumerate(labels):
eval_result.update({l: mae[i]})
save_json(os.path.join(args.in_dir, 'eval_result_mae.json'), 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:
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# 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 data from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the newly preprocessed dataset.
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# 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
# Split the dataset into training and testing.
train_data_size = int(len(dataset) * args.train_data_ratio)
_, test = split_dataset_random(dataset, train_data_size, args.seed)
# Use a predictor with scaled output labels.
model_path = os.path.join(args.in_dir, args.model_filename)
regressor = Regressor.load_pickle(model_path, device=args.gpu)
# Replace the default predictor with one that scales the output labels.
scaled_predictor = ScaledGraphConvPredictor(regressor.predictor)
scaled_predictor.scaler = scaler
regressor.predictor = scaled_predictor
# This callback function extracts only the inputs and discards the labels.
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
# Predict the output labels.
print('Predicting...')
y_pred = regressor.predict(test, converter=extract_inputs)
# Extract the ground-truth labels.
t = concat_mols(test, device=-1)[-1]
n_eval = 10
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({
'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): t[:, i],
})
df = pandas.DataFrame(df_dict)
# Show a prediction/ground truth table with 5 random examples.
print(df.sample(5))
for target_label in range(y_pred.shape[1]):
diff = y_pred[:n_eval, target_label] - t[:n_eval, target_label]
print('target_label = {}, y_pred = {}, t = {}, diff = {}'.format(
target_label, y_pred[:n_eval, target_label],
t[:n_eval, target_label], diff))
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
regressor,
converter=concat_mols,
device=args.gpu)()
# Prevents the loss function from becoming a cupy.core.core.ndarray object
# when using the GPU. This hack will be removed as soon as the cause of
# the issue is found and properly fixed.
loss = numpy.asscalar(cuda.to_cpu(eval_result['main/loss']))
eval_result['main/loss'] = loss
print('Evaluation result: ', eval_result)
# Save the evaluation results.
with open(os.path.join(args.in_dir, 'eval_result.json'), 'w') as f:
json.dump(eval_result, f)
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()
# 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)
if data_name == 'qm9':
max_atoms = 9
elif data_name == 'zinc250k':
max_atoms = 38
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
if data_type == 'gcn':
preprocessor = RSGCNPreprocessor(out_size=max_atoms)
elif data_type == 'relgcn':
# preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True, return_is_real_node=False)
preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True)
else:
raise ValueError("[ERROR] Unexpected value data_type={}".format(data_type))
data_dir = "."
os.makedirs(data_dir, exist_ok=True)
if data_name == 'qm9':
dataset = datasets.get_qm9(preprocessor)
elif data_name == 'zinc250k':
dataset = datasets.get_zinc250k(preprocessor)
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
NumpyTupleDataset.save(
os.path.join(data_dir,
'{}_{}_kekulized_ggnp.npz'.format(data_name, data_type)),
dataset)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
label_names = [
'A', 'B', 'C', 'mu', 'alpha', 'h**o', 'lumo', 'gap', 'r2', 'zpve',
'U0', 'U', 'H', 'G', 'Cv'
]
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(description='Regression with QM9.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for regression, '
'empty string means to predict all '
'property at once')
parser.add_argument('--scale',
type=str,
choices=scale_list,
default='standardize',
help='Label scaling method')
parser.add_argument('--batchsize', '-b', type=int, default=32)
parser.add_argument('--gpu', '-g', type=int, default=-1)
parser.add_argument('--in-dir', '-i', type=str, default='result')
parser.add_argument('--seed', '-s', type=int, default=777)
parser.add_argument('--train-data-ratio', '-t', type=float, default=0.7)
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()
seed = args.seed
train_data_ratio = args.train_data_ratio
method = args.method
if args.label:
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
# class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# class_num = len(labels)
# Dataset preparation
dataset = None
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
if os.path.exists(dataset_cache_path):
print('load from cache {}'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
if args.scale == 'standardize':
# Standard Scaler for labels
with open(os.path.join(args.in_dir, 'ss.pkl'), mode='rb') as f:
ss = pickle.load(f)
else:
ss = None
train_data_size = int(len(dataset) * train_data_ratio)
train, val = split_dataset_random(dataset, train_data_size, seed)
regressor = Regressor.load_pickle(os.path.join(args.in_dir,
args.model_filename),
device=args.gpu) # type: Regressor
# 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_fn(x):
if ss is not None:
# Model's output is scaled by StandardScaler,
# so we need to rescale back.
if isinstance(x, Variable):
x = x.data
scaled_x = ss.inverse_transform(cuda.to_cpu(x))
return scaled_x
else:
return x
print('Predicting...')
y_pred = regressor.predict(val,
converter=extract_inputs,
postprocess_fn=postprocess_fn)
print('y_pred.shape = {}, y_pred[:5, 0] = {}'.format(
y_pred.shape, y_pred[:5, 0]))
t = concat_mols(val, device=-1)[-1]
n_eval = 10
# Construct dataframe
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({
'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): t[:, i],
})
df = pandas.DataFrame(df_dict)
# Show random 5 example's prediction/ground truth table
print(df.sample(5))
for target_label in range(y_pred.shape[1]):
diff = y_pred[:n_eval, target_label] - t[:n_eval, target_label]
print('target_label = {}, y_pred = {}, t = {}, diff = {}'.format(
target_label, y_pred[:n_eval, target_label],
t[:n_eval, target_label], diff))
# --- evaluate ---
# To calc loss/accuracy, we can use `Evaluator`, `ROCAUCEvaluator`
print('Evaluating...')
val_iterator = SerialIterator(val, 16, repeat=False, shuffle=False)
eval_result = Evaluator(val_iterator,
regressor,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
label_names = [
'A', 'B', 'C', 'mu', 'alpha', 'h**o', 'lumo', 'gap', 'r2', 'zpve',
'U0', 'U', 'H', 'G', 'Cv'
]
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(description='Regression with QM9.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for regression, '
'empty string means to predict all '
'property at once')
parser.add_argument('--scale',
type=str,
choices=scale_list,
default='standardize',
help='Label scaling method')
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('--seed', '-s', type=int, default=777)
parser.add_argument('--train-data-ratio', '-t', type=float, default=0.7)
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()
seed = args.seed
train_data_ratio = args.train_data_ratio
method = args.method
if args.label:
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())
# Dataset preparation
dataset = None
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
if os.path.exists(dataset_cache_path):
print('load from cache {}'.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:
# only use first 100 for debug
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor,
labels=labels,
target_index=target_index)
else:
dataset = D.get_qm9(preprocessor, labels=labels)
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
if args.scale == 'standardize':
# Standard Scaler for labels
ss = StandardScaler()
labels = ss.fit_transform(dataset.get_datasets()[-1])
else:
ss = None
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] + (labels, )))
train_data_size = int(len(dataset) * train_data_ratio)
train, val = split_dataset_random(dataset, train_data_size, seed)
# Network
n_unit = args.unit_num
conv_layers = args.conv_layers
if method == 'nfp':
print('Train NFP model...')
model = 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...')
model = 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...')
model = 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
model = 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...')
model = 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 = I.SerialIterator(train, args.batchsize)
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
regressor = Regressor(
model,
lossfun=F.mean_squared_error,
metrics_fun={'abs_error': ScaledAbsError(scale=args.scale, ss=ss)},
device=args.gpu)
optimizer = O.Adam()
optimizer.setup(regressor)
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,
regressor,
device=args.gpu,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/abs_error', 'validation/main/loss',
'validation/main/abs_error', 'elapsed_time'
]))
trainer.extend(E.ProgressBar())
trainer.run()
# --- save regressor & standardscaler ---
protocol = args.protocol
regressor.save_pickle(os.path.join(args.out, args.model_filename),
protocol=protocol)
if args.scale == 'standardize':
with open(os.path.join(args.out, 'ss.pkl'), mode='wb') as f:
pickle.dump(ss, f, protocol=protocol)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
label_names = [
'A', 'B', 'C', 'mu', 'alpha', 'h**o', 'lumo', 'gap', 'r2', 'zpve',
'U0', 'U', 'H', 'G', 'Cv'
]
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(description='Regression with QM9.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for regression, '
'empty string means to predict all '
'property at once')
parser.add_argument('--scale',
type=str,
choices=scale_list,
default='standardize',
help='Label scaling method')
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('--seed', '-s', type=int, default=777)
parser.add_argument('--train-data-ratio', '-t', type=float, default=0.7)
args = parser.parse_args()
seed = args.seed
train_data_ratio = args.train_data_ratio
method = args.method
if args.label:
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())
# Dataset preparation
dataset = None
if os.path.exists(cache_dir):
print('load from cache {}'.format(cache_dir))
dataset = NumpyTupleDataset.load(os.path.join(cache_dir, 'data.npz'))
if dataset is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
os.makedirs(cache_dir)
NumpyTupleDataset.save(os.path.join(cache_dir, 'data.npz'), dataset)
if args.scale == 'standardize':
# Standard Scaler for labels
ss = StandardScaler()
labels = ss.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*dataset.get_datasets()[:-1], labels)
train_data_size = int(len(dataset) * train_data_ratio)
train, val = split_dataset_random(dataset, train_data_size, seed)
# Network
n_unit = args.unit_num
conv_layers = args.conv_layers
if method == 'nfp':
print('Train NFP model...')
model = 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...')
model = 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...')
model = 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
model = 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...')
model = 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 = I.SerialIterator(train, args.batchsize)
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
def scaled_abs_error(x0, x1):
if isinstance(x0, Variable):
x0 = cuda.to_cpu(x0.data)
if isinstance(x1, Variable):
x1 = cuda.to_cpu(x1.data)
if args.scale == 'standardize':
scaled_x0 = ss.inverse_transform(cuda.to_cpu(x0))
scaled_x1 = ss.inverse_transform(cuda.to_cpu(x1))
diff = scaled_x0 - scaled_x1
elif args.scale == 'none':
diff = cuda.to_cpu(x0) - cuda.to_cpu(x1)
return numpy.mean(numpy.absolute(diff), axis=0)[0]
classifier = L.Classifier(model,
lossfun=F.mean_squared_error,
accfun=scaled_abs_error)
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
classifier.to_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.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/accuracy', 'validation/main/loss',
'validation/main/accuracy', 'elapsed_time'
]))
trainer.extend(E.ProgressBar())
trainer.run()
def main():
# Parse the arguments.
args = parse_arguments()
device = args.gpu
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
label = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, label))
labels = [label]
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# 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 data from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the newly preprocessed dataset.
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Use a predictor with scaled output labels.
model_path = os.path.join(args.in_dir, args.model_filename)
regressor = Regressor.load_pickle(model_path, device=device)
scaler = regressor.predictor.scaler
if scaler is not None:
original_t = dataset.get_datasets()[-1]
if args.gpu >= 0:
scaled_t = cuda.to_cpu(scaler.transform(
cuda.to_gpu(original_t)))
else:
scaled_t = scaler.transform(original_t)
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] +
(scaled_t,)))
# Split the dataset into training and testing.
train_data_size = int(len(dataset) * args.train_data_ratio)
_, test = split_dataset_random(dataset, train_data_size, args.seed)
# This callback function extracts only the inputs and discards the labels.
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_fn(x):
if scaler is not None:
scaled_x = scaler.inverse_transform(x)
return scaled_x
else:
return x
# Predict the output labels.
print('Predicting...')
y_pred = regressor.predict(
test, converter=extract_inputs,
postprocess_fn=postprocess_fn)
# Extract the ground-truth labels.
t = concat_mols(test, device=device)[-1]
original_t = cuda.to_cpu(scaler.inverse_transform(t))
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): original_t[:, i], })
df = pandas.DataFrame(df_dict)
# Show a prediction/ground truth table with 5 random examples.
print(df.sample(5))
n_eval = 10
for target_label in range(y_pred.shape[1]):
label_name = labels[target_label]
diff = y_pred[:n_eval, target_label] - original_t[:n_eval,
target_label]
print('label_name = {}, y_pred = {}, t = {}, diff = {}'
.format(label_name, y_pred[:n_eval, target_label],
original_t[:n_eval, target_label], diff))
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator, regressor, converter=concat_mols,
device=device)()
print('Evaluation result: ', eval_result)
# Save the evaluation results.
save_json(os.path.join(args.in_dir, 'eval_result.json'), eval_result)
# Calculate mean abs error for each label
mae = numpy.mean(numpy.abs(y_pred - original_t), axis=0)
eval_result = {}
for i, l in enumerate(labels):
eval_result.update({l: mae[i]})
save_json(os.path.join(args.in_dir, 'eval_result_mae.json'), eval_result)
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
if data_type == 'gcn':
preprocessor = RSGCNPreprocessor(out_size=max_atoms)
elif data_type == 'relgcn':
# preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True, return_is_real_node=False)
preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True)
else:
raise ValueError("[ERROR] Unexpected value data_type={}".format(data_type))
#data_dir = "."
#os.makedirs(data_dir, exist_ok=True)
if data_name == 'qm9':
dataset, smiles = datasets.get_qm9(preprocessor, return_smiles=True)
elif data_name == 'zinc250k':
dataset, smiles = datasets.get_zinc250k(preprocessor, return_smiles=True)
elif data_name == 'tox21':
dataset, smiles = datasets.get_tox21(preprocessor, return_smiles=True)
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
to_smiles_txt(
smiles,
os.path.join(args.data_dir, '{}_kekulized_ggnp.txt'.format(data_name)))
NumpyTupleDataset.save(
os.path.join(args.data_dir,
'{}_{}_kekulized_ggnp.npz'.format(data_name, data_type)),
dataset)
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():
args = parse_args()
if args is None:
exit()
# -- properties
database = 'QM9' # dataset name
# -- database specification
atom_types = ['6', '8', '7', '9', '1']
n_max_atom = 9
# -- set data indices
X = np.random.choice(133885, size=args.data_size,
replace=False) # train + test data indices
X_train = X[:args.N] # train data indices
X_test = X[args.N:] # test data indices
# -- bootstrapped data indices
for b in range(args.n_samples):
if args.n_samples is not 1:
X_b = np.concatenate(([
X_train[np.random.choice(range(args.N), size=args.N)], X_test
]),
axis=0)
else:
X_b = X
# -- generate dataset
dataset, dataset_smiles = datasets.get_qm9(
GGNNPreprocessor(kekulize=True),
return_smiles=True,
target_index=X_b)
smils_list = []
atoms_list = []
adjs_list = []
prop_1 = []
prop_2 = []
prop_3 = []
for idx in range(args.data_size):
atom, adj, _ = dataset[idx]
n_atom = len(atom)
# -- smiles
smils_list.append(dataset_smiles[idx])
mol = Chem.MolFromSmiles(dataset_smiles[idx])
# -- adj
adjacency = adj[0] + 2 * adj[1] + 3 * adj[2]
adjacency_append = np.zeros((n_max_atom, n_max_atom)).astype(float)
adjacency_append[:n_atom, :n_atom] = adjacency
adjs_list.append(adjacency_append)
# -- signal
signal = []
for i in range(n_atom):
atom_sig = []
atom_i = mol.GetAtomWithIdx(i)
atom_sig += [
float(str(atom_i.GetAtomicNum()) == x) for x in atom_types
] # one-hot vector of atom types
signal.append(atom_sig)
for i in range(n_max_atom - n_atom): # dummy value for ghost nodes
atom_sig = []
atom_sig += list(np.zeros(len(atom_types) - 1)) + [1.]
signal.append(atom_sig)
atoms_list.append(np.array(signal).T)
# -- properties
prop_1.append(Descriptors.TPSA(mol))
prop_2.append(Descriptors.MolWt(mol))
prop_3.append(Crippen.MolLogP(mol))
signal = np.asarray(atoms_list).transpose([0, 2, 1]).reshape(
-1,
len(atom_sig) * n_max_atom)
# -- store
if args.n_samples is not 1:
data_name = database + '_N_' + str(args.N) + '_' + str(b) + '.data'
else:
data_name = database + '_0.data'
with open(data_name, 'wb') as f:
pickle.dump(smils_list, f)
pickle.dump(signal, f)
pickle.dump(adjs_list, f)
pickle.dump(prop_1, f)
pickle.dump(prop_2, f)
pickle.dump(prop_3, f)
parser.add_argument("-g",
"--gaussianization",
help="choose the gaussianization method 'W'/'N'",
default='N')
args = parser.parse_args()
# =============================================================================
# prepare data
# =============================================================================
num_train = 133885
if not os.path.exists("./qm9.data"):
preprocessor = GGNNPreprocessor()
dataset, dataset_smiles = datasets.get_qm9(preprocessor,
labels=None,
return_smiles=True)
num_of_data = len(dataset)
features = []
adjs = []
for idx in range(num_of_data):
atom, adj, labels = dataset[idx]
if len(atom) < 9:
n_temp = len(atom)
atom_temp = np.zeros(9).astype(int)
atom_temp[:n_temp] = atom
atom_to_append = atom_to_hot(atom_temp)
else:
atom_to_append = atom_to_hot(atom)
if len(atom) < 9:
