def download_entire_dataset(dataset_name, num_data, labels, method, cache_dir):
"""Downloads the train/valid/test parts of a dataset and stores them in the
cache directory.
Args:
dataset_name: Dataset to be downloaded.
num_data: Amount of data samples to be parsed from the dataset.
labels: Target labels for regression.
method: Method name. See `parse_arguments`.
cache_dir: Directory to store the dataset to.
"""
print('Downloading {}...'.format(dataset_name))
preprocessor = preprocess_method_dict[method]()
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data) if num_data >= 0 else None
dataset_parts = D.molnet.get_molnet_dataset(dataset_name, preprocessor,
labels=labels,
target_index=target_index)
dataset_parts = dataset_parts['dataset']
# Cache the downloaded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
for i, part in enumerate(['train', 'valid', 'test']):
filename = dataset_part_filename(part, num_data)
path = os.path.join(cache_dir, filename)
NumpyTupleDataset.save(path, dataset_parts[i])
return dataset_parts
def download_entire_dataset(dataset_name, num_data, labels, method, cache_dir):
"""Downloads the train/valid/test parts of a dataset and stores them in the
cache directory.
Args:
dataset_name: Dataset to be downloaded.
num_data: Amount of data samples to be parsed from the dataset.
labels: Target labels for regression.
method: Method name. See `parse_arguments`.
cache_dir: Directory to store the dataset to.
"""
print('Downloading {}...'.format(dataset_name))
preprocessor = preprocess_method_dict[method]()
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data) if num_data >= 0 else None
dataset_parts = D.molnet.get_molnet_dataset(dataset_name,
preprocessor,
labels=labels,
target_index=target_index)
dataset_parts = dataset_parts['dataset']
# Cache the downloaded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
for i, part in enumerate(['train', 'valid', 'test']):
filename = dataset_part_filename(part, num_data)
path = os.path.join(cache_dir, filename)
NumpyTupleDataset.save(path, dataset_parts[i])
return dataset_parts
def test_save_load(self, data):
tmp_cache_path = os.path.join(tempfile.mkdtemp(), 'tmp.npz')
dataset = NumpyTupleDataset(*data)
NumpyTupleDataset.save(tmp_cache_path, dataset)
assert os.path.exists(tmp_cache_path)
load_dataset = NumpyTupleDataset.load(tmp_cache_path)
os.remove(tmp_cache_path)
assert len(dataset._datasets) == len(load_dataset._datasets)
for a, d in six.moves.zip(dataset._datasets, load_dataset._datasets):
numpy.testing.assert_array_equal(a, d)
def fit_scaler(datasets):
"""Standardizes (scales) the dataset labels.
Args:
datasets: Tuple containing the datasets.
Returns:
Datasets with standardized labels and the scaler object.
"""
scaler = StandardScaler()
# Collect all labels in order to apply scaling over the entire dataset.
labels = None
offsets = []
for dataset in datasets:
if labels is None:
labels = dataset.get_datasets()[-1]
else:
labels = numpy.vstack([labels, dataset.get_datasets()[-1]])
offsets.append(len(labels))
scaler.fit(labels)
scaled_datasets = []
for dataset in datasets:
x, y = dataset.get_datasets()
yy = scaler.transform(y)
scaled_datasets.append(NumpyTupleDataset(x, yy))
return scaler, scaled_datasets
def test_get_item_integer_index(self, data, index):
dataset = NumpyTupleDataset(*data)
actual = dataset[index]
assert len(actual) == len(data)
for a, d in six.moves.zip(actual, data):
numpy.testing.assert_array_equal(a, d[index])
def augment_dataset(dataset):
dataset_tuple = dataset.get_datasets()
feat1, feat2, labels = dataset_tuple
new_feat1 = np.concatenate((feat1, feat2), axis=0)
new_feat2 = np.concatenate((feat2, feat1), axis=0)
new_labels = np.concatenate((labels, labels), axis=0)
new_dataset = NumpyTupleDataset(new_feat1, new_feat2, new_labels)
return new_dataset
def augment_dataset(dataset):
dataset_tuple = dataset.get_datasets()
atoms1, adjs1, atoms2, adjs2, labels = dataset_tuple
new_atoms1 = np.concatenate((atoms1, atoms2), axis=0)
new_atoms2 = np.concatenate((atoms2, atoms1), axis=0)
new_adjs1 = np.concatenate((adjs1, adjs2), axis=0)
new_adjs2 = np.concatenate((adjs2, adjs1), axis=0)
new_labels = np.concatenate((labels, labels), axis=0)
new_dataset = NumpyTupleDataset(new_atoms1, new_adjs1, new_atoms2, new_adjs2, new_labels)
return new_dataset
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 test_get_item_list_index(self, long_data, index):
dataset = NumpyTupleDataset(*long_data)
actual = dataset[index]
batches = [d[index] for d in long_data]
length = len(batches[0])
expect = [tuple([batch[i] for batch in batches])
for i in six.moves.range(length)]
assert len(actual) == len(expect)
for tuple_a, tuple_e in six.moves.zip(actual, expect):
assert len(tuple_a) == len(tuple_e)
for a, e in six.moves.zip(tuple_a, tuple_e):
numpy.testing.assert_array_equal(a, e)
def add_super_nodes(dataset, smiles_pairs):
dataset_tuple = dataset.get_datasets()
atoms1, adjs1, atoms2, adjs2, labels = dataset_tuple
smiles1 = smiles_pairs[:, 0]
smiles2 = smiles_pairs[:, 1]
pickle_filename = 'smiles2mol_vec.pkl'
pickle_filepath = os.path.join(SUPER_NODE_PATH, pickle_filename)
with open(pickle_filepath, 'r') as reader:
smiles2atom_feat = pickle.load(reader)
atom_feat1 = [smiles2atom_feat[smiles] for smiles in smiles1]
atom_feat1 = np.array(atom_feat1, dtype=np.float32)
atom_feat2 = [smiles2atom_feat[smiles] for smiles in smiles2]
atom_feat2 = np.array(atom_feat2, dtype=np.float32)
new_dataset = NumpyTupleDataset(atoms1, adjs1, atom_feat1, atoms2, adjs2,
atom_feat2, labels)
return new_dataset
def to_multi_hot_labels(dataset, enc=None):
dataset_tuple = dataset.get_datasets()
atoms1, adjs1, atoms2, adjs2, labels = dataset_tuple
label_list = list()
for label in labels:
try:
label = [int(label)]
except ValueError:
label_in_str = str(label[0])
assert isinstance(label_in_str, str)
label = map(int, label_in_str.split('||'))
label_list.append(label)
if enc is None:
enc = MultiLabelBinarizer()
transformed_labels = enc.fit_transform(label_list)
else:
transformed_labels = enc.transform(label_list)
# enc_filename = 'multi_hot_enc.pkl'
# enc_filepath = os.path.join(KAIST_PATH, enc_filename)
#
# if not os.path.exists(enc_filepath):
# if not is_training:
# raise ValueError('The multi-hot encoder file does not exist.')
# else:
# enc.fit(label_list)
# joblib.dump(enc, enc_filepath)
# transformed_labels = enc.transform(label_list)
#
# else:
# enc = joblib.load(enc_filepath)
# transformed_labels = enc.transform(label_list)
new_dataset = NumpyTupleDataset(
atoms1, adjs1, atoms2, adjs2, transformed_labels
)
return new_dataset, enc
def to_one_hot_labels(dataset, is_training=True):
dataset_tuple = dataset.get_datasets()
atoms1, adjs1, atoms2, adjs2, labels = dataset_tuple
onehot_enc = OneHotEncoder(handle_unknown='ignore')
onehot_filename = 'onehot_enc.pkl'
onehot_filepath = os.path.join(KAIST_PATH, onehot_filename)
if not os.path.exists(onehot_filepath):
if not is_training:
raise ValueError('The one-hot encoder file does not exist.')
else:
onehot_enc.fit(labels)
joblib.dump(onehot_enc, onehot_filepath)
transformed_labels = onehot_enc.transform(labels).toarray().astype(np.int32)
else:
onehot_enc = joblib.load(onehot_filepath)
transformed_labels = onehot_enc.transform(labels).toarray().astype(np.int32)
new_dataset = NumpyTupleDataset(
atoms1, adjs1, atoms2, adjs2, transformed_labels
)
return new_dataset
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)
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()
labels = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] + (labels,)))
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)
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
# Set up the regressor.
metrics_fun = {'mean_abs_error': MeanAbsError(scaler=scaler),
'root_mean_sqr_error': RootMeanSqrError(scaler=scaler)}
regressor = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# Set up the updater.
updater = training.StandardUpdater(train_iter, optimizer, device=args.gpu,
converter=concat_mols)
# Set up the trainer.
print('Training...')
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.PrintReport(['epoch', 'main/loss', 'main/mean_abs_error',
'main/root_mean_sqr_error', '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)
# Save the standard scaler's parameters.
if scaler is not None:
with open(os.path.join(args.out, 'scaler.pkl'), mode='wb') as f:
pickle.dump(scaler, f, protocol=args.protocol)
def test_len(self, data):
dataset = NumpyTupleDataset(*data)
assert len(dataset) == 2
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(input_args=None):
# Parse the arguments.
args = parse_arguments(input_args)
device = args.gpu
method = args.method
if args.data_name == 'suzuki':
datafile = 'data/suzuki_type_test_v2.csv'
class_num = 119
class_dict = {'M': 28, 'L': 23, 'B': 35, 'S': 10, 'A': 17}
dataset_filename = 'test_data.npz'
labels = ['Yield', 'M', 'L', 'B', 'S', 'A', 'id']
elif args.data_name == 'CN':
datafile = 'data/CN_coupling_test.csv'
class_num = 206
class_dict = {'M': 44, 'L': 47, 'B': 13, 'S': 22, 'A': 74}
dataset_filename = 'test_CN_data.npz'
labels = ['Yield', 'M', 'L', 'B', 'S', 'A', 'id']
elif args.data_name == 'Negishi':
datafile = 'data/Negishi_test.csv'
class_num = 106
class_dict = {'M': 32, 'L': 20, 'T': 8, 'S': 10, 'A': 30}
dataset_filename = 'test_Negishi_data.npz'
labels = ['Yield', 'M', 'L', 'T', 'S', 'A', 'id']
elif args.data_name == 'PKR':
datafile = 'data/PKR_test.csv'
class_num = 83
class_dict = {
'M': 18,
'L': 6,
'T': 7,
'S': 15,
'A': 11,
'G': 1,
'O': 13,
'P': 4,
'other': 1
}
dataset_filename = 'test_PKR_data.npz'
labels = [
'Yield', 'M', 'L', 'T', 'S', 'A', 'G', 'O', 'P', 'other', 'id'
]
else:
raise ValueError('Unexpected dataset name')
cache_dir = os.path.join('input', '{}_all'.format(method))
# Dataset preparation.
def postprocess_label(label_list):
return numpy.asarray(label_list, dtype=numpy.float32)
print('Preprocessing dataset...')
# 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:
if args.method == 'mpnn':
preprocessor = preprocess_method_dict['ggnn']()
else:
preprocessor = preprocess_method_dict[args.method]()
parser = CSVFileParser(
preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_col=['Reactant1', 'Reactant2', 'Product'],
label_dicts=class_dict)
dataset = parser.parse(datafile)['dataset']
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
labels = dataset.get_datasets()[-2]
ids = dataset.get_datasets()[-1][:, 1].reshape(-1, 1)
yields = dataset.get_datasets()[-1][:, 0].reshape(-1, 1).astype(
'float32') # [:,0] added
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-2] + (
yields,
labels,
)))
# Load the standard scaler parameters, if necessary.
scaler = None
test = dataset
print('Predicting...')
# Set up the regressor.
model_path = os.path.join(args.in_dir, args.model_filename)
if os.path.exists(model_path):
classifier = Classifier.load_pickle(model_path, device=args.gpu)
else:
predictor = set_up_predictor(args.method, args.unit_num,
args.conv_layers, class_num)
classifier = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=args.gpu)
if args.load_modelname:
serializers.load_npz(args.load_modelname, classifier)
scaled_predictor = ScaledGraphConvPredictor(
graph_conv=classifier.predictor.graph_conv,
mlp=classifier.predictor.mlp)
classifier.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.
# Prediction function rewrite!!!
y_pred = classifier.predict(test, converter=extract_inputs)
y_pred_max = numpy.argmax(y_pred, axis=1)
y_pred_max = y_pred_max.reshape(-1, 1)
# y_pred_idx = y_pred.argsort(axis=1) # ascending
# Extract the ground-truth labels.
t = concat_mols(test, device=-1)[-1] # device 11/14 memory issue
original_t = cuda.to_cpu(t)
t_idx = original_t.squeeze(1)
t_idx = t_idx.argsort(axis=1)
# gt_indx = numpy.where(original_t == 1)
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels[:1]):
df_dict.update({
'y_pred_{}'.format(l): y_pred_max[:, -1].tolist(), # [:,-1]
't_{}'.format(l): t_idx[:, -1].tolist(),
})
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_max.shape[1]):
label_name = labels[:1][0][target_label]
print('label_name = {}, y_pred = {}, t = {}'.format(
label_name, y_pred_max[:n_eval, target_label], t_idx[:n_eval, -1]))
# Perform the prediction.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
classifier,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
with open(os.path.join(args.in_dir, 'eval_result.json'), 'w') as f:
json.dump(eval_result, f)
res_dic = {}
for i in range(len(y_pred)):
res_dic[i] = str(ids[i])
json.dump(res_dic, open(os.path.join(args.in_dir, "test_ids.json"), "w"))
pickle.dump(y_pred, open(os.path.join(args.in_dir, "pred.pkl"), "wb"))
pickle.dump(original_t, open(os.path.join(args.in_dir, "gt.pkl"), "wb"))
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 train():
parser = argparser.get_parser()
args = parser.parse_args()
device = -1
if args.gpu >= 0:
device = args.gpu
debug = args.debug
print('input args:\n',
json.dumps(vars(args), indent=4,
separators=(',', ':'))) # pretty print args
if args.data_name == 'qm9':
from data import transform_qm9
transform_fn = transform_qm9.transform_fn
atomic_num_list = [6, 7, 8, 9, 0]
mlp_channels = [256, 256]
gnn_channels = {'gcn': [8, 64], 'hidden': [128, 64]}
valid_idx = transform_qm9.get_val_ids()
elif args.data_name == 'zinc250k':
transform_fn = transform_fn_zinc250k
atomic_num_list = zinc250_atomic_num_list
mlp_channels = [1024, 512]
gnn_channels = {'gcn': [16, 128], 'hidden': [256, 64]}
valid_idx = transform_zinc250k.get_val_ids()
dataset = NumpyTupleDataset.load(
os.path.join(args.data_dir, args.data_file))
dataset = TransformDataset(dataset, transform_fn)
if len(valid_idx) > 0:
train_idx = [t for t in range(len(dataset)) if t not in valid_idx]
n_train = len(train_idx)
train_idx.extend(valid_idx)
train, test = chainer.datasets.split_dataset(dataset, n_train,
train_idx)
else:
train, test = chainer.datasets.split_dataset_random(
dataset, int(len(dataset) * 0.8), seed=args.seed)
train_iter = chainer.iterators.SerialIterator(train, args.batch_size)
num_masks = {
'node': args.num_node_masks,
'channel': args.num_channel_masks
}
mask_size = {
'node': args.node_mask_size,
'channel': args.channel_mask_size
}
num_coupling = {
'node': args.num_node_coupling,
'channel': args.num_channel_coupling
}
model_params = Hyperparameters(
args.num_atoms,
args.num_rels,
len(atomic_num_list),
num_masks=num_masks,
mask_size=mask_size,
num_coupling=num_coupling,
batch_norm=args.apply_batch_norm,
additive_transformations=args.additive_transformations,
learn_dist=args.learn_dist,
mlp_channels=mlp_channels,
gnn_channels=gnn_channels)
model = GraphNvpModel(model_params)
if device >= 0:
chainer.cuda.get_device(device).use()
model.to_gpu(device)
print('==========================================')
if device >= 0:
print('Using GPUs')
print('Num Minibatch-size: {}'.format(args.batch_size))
print('Num epoch: {}'.format(args.max_epochs))
print('==========================================')
os.makedirs(args.save_dir, exist_ok=True)
model.save_hyperparams(os.path.join(args.save_dir, 'graphnvp-params.json'))
opt = chainer.optimizers.Adam()
opt.setup(model)
updater = MolNvpUpdater(train_iter, opt, device=device, loss_func=None)
trainer = training.Trainer(updater, (args.max_epochs, 'epoch'),
out=args.save_dir)
# trainer.extend(extensions.dump_graph('log_likelihood'))
def print_validity(t):
adj, x = generate_mols(model, batch_size=100, gpu=device)
valid_mols = check_validity(adj, x, atomic_num_list,
device)['valid_mols']
mol_dir = os.path.join(args.save_dir,
'generated_{}'.format(t.updater.epoch))
# mol_dir = os.path.join(args.save_dir, 'generated_{}'.format(t.updater.iteration))
os.makedirs(mol_dir, exist_ok=True)
for ind, mol in enumerate(valid_mols):
save_mol_png(mol, os.path.join(mol_dir, '{}.png'.format(ind)))
if debug:
# trainer.extend(print_validity, trigger=(1, 'epoch'))
trainer.extend(print_validity, trigger=(100, 'iteration'))
save_epochs = args.save_epochs
if save_epochs == -1:
save_epochs = args.max_epochs
trainer.extend(extensions.snapshot(), trigger=(save_epochs, 'epoch'))
# trainer.extend(extensions.PlotReport(['log_likelihood'], 'epoch', file_name='qm9.png'),
# trigger=(100, 'iteration'))
trainer.extend(
extensions.PrintReport(
['epoch', 'log_likelihood', 'nll_x', 'nll_adj', 'elapsed_time']))
trainer.extend(extensions.LogReport())
trainer.extend(extensions.ProgressBar())
if args.load_params == 1:
chainer.serializers.load_npz(args.load_snapshot, trainer)
trainer.run()
chainer.serializers.save_npz(
os.path.join(args.save_dir, 'graph-nvp-final.npz'), model)
def test_invalid_datasets(self):
a = numpy.array([1, 2])
b = numpy.array([1, 2, 3])
with pytest.raises(ValueError):
NumpyTupleDataset(a, b)
def modify_dataset_for_hinge(dataset):
atoms1, adjs1, atoms2, adjs2, labels = dataset.get_datasets()
labels_squeezed = np.squeeze(labels, axis=1)
new_dataset = NumpyTupleDataset(atoms1, adjs1, atoms2, adjs2, labels_squeezed)
return new_dataset
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()
# 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():
# 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)
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 dataset():
a = numpy.random.random((10, 10))
b = numpy.random.random((10, 8))
c = numpy.random.random((10, 1))
return NumpyTupleDataset(a, b, c)
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():
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():
# 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()
labels = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] +
(labels, )))
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)
# Set up the iterator.
train_iter = SerialIterator(train, args.batchsize)
# Set up the regressor.
metrics_fun = {
'mean_abs_error': MeanAbsError(scaler=scaler),
'root_mean_sqr_error': RootMeanSqrError(scaler=scaler)
}
regressor = Regressor(predictor,
lossfun=F.mean_squared_error,
metrics_fun=metrics_fun,
device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# Set up the updater.
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
# Set up the trainer.
print('Training...')
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/mean_abs_error',
'main/root_mean_sqr_error', '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)
# Save the standard scaler's parameters.
if scaler is not None:
with open(os.path.join(args.out, 'scaler.pkl'), mode='wb') as f:
pickle.dump(scaler, f, protocol=args.protocol)
def main():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(
description='Regression with own dataset.')
parser.add_argument('--datafile', type=str, default='dataset.csv')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
nargs='+',
default=['value1', 'value2'],
help='target label for regression')
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)
args = parser.parse_args()
seed = args.seed
train_data_ratio = args.train_data_ratio
method = args.method
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
sys.exit("Error: No target label is specified.")
# Dataset preparation
# Postprocess is required for regression task
def postprocess_label(label_list):
return numpy.asarray(label_list, dtype=numpy.float32)
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
parser = CSVFileParser(preprocessor,
postprocess_label=postprocess_label,
labels=labels,
smiles_col='SMILES')
dataset = parser.parse(args.datafile)["dataset"]
if args.scale == 'standardize':
# Standard Scaler for labels
scaler = StandardScaler()
labels = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] +
(labels, )))
else:
# Not use scaler
scaler = None
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 = iterators.SerialIterator(train, args.batchsize)
val_iter = iterators.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
regressor = Regressor(
model,
lossfun=F.mean_squared_error,
metrics_fun={'abs_error': ScaledAbsError(scaler=scaler)},
device=args.gpu)
optimizer = optimizers.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())
# Note that original scale absolute errors are reported in
# (validation/)main/abs_error
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's parameters ---
protocol = args.protocol
model_path = os.path.join(args.out, 'model.npz')
print('saving trained model to {}'.format(model_path))
serializers.save_npz(model_path, regressor)
if scaler is not None:
with open(os.path.join(args.out, 'scaler.pkl'), mode='wb') as f:
pickle.dump(scaler, f, protocol=protocol)
# Example of prediction using trained model
smiles = 'c1ccccc1'
mol = Chem.MolFromSmiles(smiles)
preprocessor = preprocess_method_dict[method]()
standardized_smiles, mol = preprocessor.prepare_smiles_and_mol(mol)
input_features = preprocessor.get_input_features(mol)
atoms, adjs = concat_mols([input_features], device=args.gpu)
prediction = model(atoms, adjs).data[0]
if scaler is not None:
prediction = scaler.inverse_transform(prediction)
print('Prediction for {}:'.format(smiles))
for i, label in enumerate(args.label):
print('{}: {}'.format(label, prediction[i]))
def main(method, labels, unit_num, conv_layers, class_num, n_layers,
dropout_ratio, model_path, save_path):
# Dataset preparation
train, val, test, train_smiles, val_smiles, test_smiles = data.load_dataset(method, labels)
# --- model preparation ---
model = predictor.build_predictor(
method, unit_num, conv_layers, class_num, dropout_ratio, n_layers)
classifier = L.Classifier(model,
lossfun=F.sigmoid_cross_entropy,
accfun=F.binary_accuracy)
print('Loading model parameter from ', model_path)
serializers.load_npz(model_path, model)
target_dataset = val
target_smiles = val_smiles
val_mols = [Chem.MolFromSmiles(smi) for smi in tqdm(val_smiles)]
pyridine_mol = Chem.MolFromSmarts(PYRIDINE_SMILES)
pyridine_index = np.where(np.array([mol.HasSubstructMatch(pyridine_mol) for mol in val_mols]) == True)
val_pyridine_mols = np.array(val_mols)[pyridine_index]
# It only extracts one substructure, not expected behavior
# val_pyridine_pos = [set(mol.GetSubstructMatch(pi)) for mol in val_pyridine_mols]
def flatten_tuple(x):
return [element for tupl in x for element in tupl]
val_pyridine_pos = [flatten_tuple(mol.GetSubstructMatches(pyridine_mol)) for mol in val_pyridine_mols]
# print('pyridine_index', pyridine_index)
# print('val_pyridine_mols', val_pyridine_mols.shape)
# print('val_pyridine_pos', val_pyridine_pos)
# print('val_pyridine_pos length', [len(k) for k in val_pyridine_pos])
pyrigine_dataset = NumpyTupleDataset(*target_dataset.features[pyridine_index, :])
pyrigine_smiles = target_smiles[pyridine_index]
print('pyrigine_dataset', len(pyrigine_dataset), len(pyrigine_smiles))
atoms = pyrigine_dataset.features[:, 0]
num_atoms = [len(a) for a in atoms]
def clip_original_size(saliency, num_atoms):
"""`saliency` array is 0 padded, this method align to have original
molecule's length
"""
assert len(saliency) == len(num_atoms)
saliency_list = []
for i in range(len(saliency)):
saliency_list.append(saliency[i, :num_atoms[i]])
return saliency_list
def preprocess_fun(*inputs):
atom, adj, t = inputs
# HACKING for now...
atom_embed = classifier.predictor.graph_conv.embed(atom)
return atom_embed, adj, t
def eval_fun(*inputs):
atom_embed, adj, t = inputs
prob = classifier.predictor(atom_embed, adj)
out = F.sum(prob)
return out
calculator_method = args.calculator
print('calculator method', calculator_method)
if calculator_method == 'gradient':
# option1: Gradient
calculator = GradientCalculator(
classifier, eval_fun=eval_fun,
# target_key='embed', eval_key='out',
target_key=0,
# multiply_target=True # this will calculate grad * input
)
elif calculator_method == 'integrated_gradients':
# option2: IntegratedGradients
calculator = IntegratedGradientsCalculator(
classifier, eval_fun=eval_fun,
# target_key='embed', eval_key='out',
target_key=0, steps=10
)
elif calculator_method == 'occlusion':
# option3: Occlusion
def eval_fun_occlusion(*inputs):
atom_embed, adj, t = inputs
prob = classifier.predictor(atom_embed, adj)
# Do not take sum, instead return batch-wise score
out = F.sigmoid(prob)
return out
calculator = OcclusionCalculator(
classifier, eval_fun=eval_fun_occlusion,
# target_key='embed', eval_key='out',
target_key=0, slide_axis=1
)
else:
raise ValueError("[ERROR] Unexpected value calculator_method={}".format(calculator_method))
M = 100
num = 20
rates = np.linspace(0.1, 1, num=num)
print('M', M)
# --- VanillaGrad ---
saliency_arrays = calculator.compute_vanilla(
pyrigine_dataset, converter=concat_mols, preprocess_fn=preprocess_fun)
saliency = calculator.transform(
saliency_arrays, ch_axis=3, method='square')
# saliency_arrays -> M, batch_size, max_atom, ch_dim
# print('saliency_arrays', saliency_arrays.shape)
# saliency -> batch_size, max_atom
# print('saliency', saliency.shape)
saliency_vanilla = clip_original_size(saliency, num_atoms)
# recall & precision
vanilla_recall, vanilla_precision = calc_recall_precision(saliency_vanilla, rates, val_pyridine_pos)
print('vanilla_recall', vanilla_recall)
print('vanilla_precision', vanilla_precision)
# --- SmoothGrad ---
saliency_arrays = calculator.compute_smooth(
pyrigine_dataset, converter=concat_mols, preprocess_fn=preprocess_fun,
M=M,
mode='absolute', scale=0.15 # previous implementation
# mode='relative', scale=0.05
)
saliency = calculator.transform(
saliency_arrays, ch_axis=3, method='square')
saliency_smooth = clip_original_size(saliency, num_atoms)
# recall & precision
smooth_recall, smooth_precision = calc_recall_precision(saliency_smooth, rates, val_pyridine_pos)
print('smooth_recall', smooth_recall)
print('smooth_precision', smooth_precision)
# --- BayesGrad ---
# bayes grad is calculated by compute_vanilla with train=True
saliency_arrays = calculator.compute_vanilla(
pyrigine_dataset, converter=concat_mols, preprocess_fn=preprocess_fun,
M=M, train=True)
saliency = calculator.transform(
saliency_arrays, ch_axis=3, method='square', lam=0)
saliency_bayes = clip_original_size(saliency, num_atoms)
bayes_recall, bayes_precision = calc_recall_precision(saliency_bayes, rates, val_pyridine_pos)
print('bayes_recall', bayes_recall)
print('bayes_precision', bayes_precision)
plt.figure(figsize=(7, 5), dpi=200)
plt.plot(vanilla_recall, vanilla_precision, 'k-', color='blue', label='VanillaGrad')
plt.plot(smooth_recall, smooth_precision, 'k-', color='green', label='SmoothGrad')
plt.plot(bayes_recall, bayes_precision, 'k-', color='red', label='BayesGrad(Ours)')
plt.axhline(y=vanilla_precision[-1], color='gray', linestyle='--')
plt.legend()
plt.xlabel("recall")
plt.ylabel("precision")
if save_path:
print('saved to ', save_path)
plt.savefig(save_path)
# plt.savefig('artificial_pr.eps')
else:
plt.show()
def test_get_datasets(self, data):
dataset = NumpyTupleDataset(*data)
datasets = dataset.get_datasets()
assert len(datasets) == len(data)
for i in range(len(datasets)):
numpy.testing.assert_array_equal(datasets[i], data[i])
def main():
args = parse_arguments()
# Set up some useful variables that will be used later on.
dataset_name = args.dataset
method = args.method
num_data = args.num_data
n_unit = args.unit_num
conv_layers = args.conv_layers
task_type = molnet_default_config[dataset_name]['task_type']
model_filename = {'classification': 'classifier.pkl',
'regression': 'regressor.pkl'}
print('Using dataset: {}...'.format(dataset_name))
# Set up some useful variables that will be used later on.
if args.label:
labels = args.label
cache_dir = os.path.join('input', '{}_{}_{}'.format(dataset_name,
method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_{}_all'.format(dataset_name,
method))
class_num = len(molnet_default_config[args.dataset]['tasks'])
# Load the train and validation parts of the dataset.
filenames = [dataset_part_filename(p, num_data)
for p in ['train', 'valid']]
paths = [os.path.join(cache_dir, f) for f in filenames]
if all([os.path.exists(path) for path in paths]):
dataset_parts = []
for path in paths:
print('Loading cached dataset from {}.'.format(path))
dataset_parts.append(NumpyTupleDataset.load(path))
else:
dataset_parts = download_entire_dataset(dataset_name, num_data, labels,
method, cache_dir)
train, valid = dataset_parts[0], dataset_parts[1]
# # Scale the label values, if necessary.
# if args.scale == 'standardize':
# if task_type == 'regression':
# print('Applying standard scaling to the labels.')
# datasets, scaler = standardize_dataset_labels(datasets)
# else:
# print('Label scaling is not available for classification tasks.')
# else:
# print('No label scaling was selected.')
# scaler = None
# Set up the predictor.
predictor = set_up_predictor(method, n_unit, conv_layers, class_num)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid, args.batchsize, repeat=False,
shuffle=False)
# Load metrics for the current dataset.
metrics = molnet_default_config[dataset_name]['metrics']
metrics_fun = {k: v for k, v in metrics.items()
if isinstance(v, types.FunctionType)}
loss_fun = molnet_default_config[dataset_name]['loss']
if task_type == 'regression':
model = Regressor(predictor, lossfun=loss_fun,
metrics_fun=metrics_fun, device=args.gpu)
# TODO: Use standard scaler for regression task
elif task_type == 'classification':
model = Classifier(predictor, lossfun=loss_fun,
metrics_fun=metrics_fun, device=args.gpu)
else:
raise ValueError('Invalid task type ({}) encountered when processing '
'dataset ({}).'.format(task_type, dataset_name))
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(model)
# Save model-related output to this directory.
model_dir = os.path.join(args.out, os.path.basename(cache_dir))
if not os.path.exists(model_dir):
os.makedirs(model_dir)
# Set up the updater.
updater = training.StandardUpdater(train_iter, optimizer, device=args.gpu,
converter=concat_mols)
# Set up the trainer.
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=model_dir)
trainer.extend(E.Evaluator(valid_iter, model, device=args.gpu,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
# Report various metrics.
print_report_targets = ['epoch', 'main/loss', 'validation/main/loss']
for metric_name, metric_fun in metrics.items():
if isinstance(metric_fun, types.FunctionType):
print_report_targets.append('main/' + metric_name)
print_report_targets.append('validation/main/' + metric_name)
elif issubclass(metric_fun, BatchEvaluator):
trainer.extend(metric_fun(valid_iter, model, device=args.gpu,
eval_func=predictor,
converter=concat_mols, name='val',
raise_value_error=False))
print_report_targets.append('val/main/' + metric_name)
else:
raise TypeError('{} is not a supported metrics function.'
.format(type(metrics_fun)))
print_report_targets.append('elapsed_time')
# Augmented by Ishiguro
# ToDo: consider go/no-go of the following block
# (i) more reporting for val/evalutaion
# (ii) best validation score snapshot
if task_type == 'regression':
if 'RMSE' in metric_name:
trainer.extend(E.snapshot_object(model, "best_val_" + model_filename[task_type]), trigger=training.triggers.MinValueTrigger('validation/main/RMSE'))
elif 'MAE' in metric_name:
trainer.extend(E.snapshot_object(model, "best_val_" + model_filename[task_type]), trigger=training.triggers.MinValueTrigger('validation/main/MAE'))
else:
print("No validation metric defined?")
assert(False)
elif task_type == 'classification':
train_eval_iter = iterators.SerialIterator(train, args.batchsize,repeat=False, shuffle=False)
trainer.extend(ROCAUCEvaluator(
train_eval_iter, predictor, eval_func=predictor,
device=args.gpu, converter=concat_mols, name='train',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
# extension name='validation' is already used by `Evaluator`,
# instead extension name `val` is used.
trainer.extend(ROCAUCEvaluator(
valid_iter, predictor, eval_func=predictor,
device=args.gpu, converter=concat_mols, name='val',
pos_labels=1, ignore_labels=-1))
print_report_targets.append('train/main/roc_auc')
print_report_targets.append('validation/main/loss')
print_report_targets.append('val/main/roc_auc')
trainer.extend(E.snapshot_object(model, "best_val_" + model_filename[task_type]), trigger=training.triggers.MaxValueTrigger('val/main/roc_auc'))
else:
raise NotImplementedError(
'Not implemented task_type = {}'.format(task_type))
trainer.extend(E.PrintReport(print_report_targets))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the model's parameters.
model_path = os.path.join(model_dir, model_filename[task_type])
print('Saving the trained model to {}...'.format(model_path))
model.save_pickle(model_path, protocol=args.protocol)
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)
