def test_concat_mols_2d_gpu(data_2d, data_2d_expect):
result = concat_mols(data_2d, device=0)
assert chainer.cuda.get_device_from_array(result[0]).id == 0
assert chainer.cuda.get_device_from_array(result[1]).id == 0
assert numpy.array_equal(chainer.cuda.to_cpu(result[0]),
data_2d_expect[0])
assert numpy.array_equal(chainer.cuda.to_cpu(result[1]),
data_2d_expect[1])
def eval_func(atoms_1, adj_1, atoms_2, adj_2):
sample = [
(atoms_1, adj_1),
(atoms_2, adj_2),
]
sample = concat_mols(sample)
atoms_1, adj_1 = sample[0]
atoms_2, adj_2 = sample[1]
print(atoms_1, adj_1)
print('shape 1:', atoms_1.shape, adj_1.shape)
print('shape 2:', atoms_2.shape, adj_2.shape)
pred, _ = model.predictor.predict(atoms_1, adj_1, atoms_2, adj_2)
return pred
def predict(self, *args, batchsize=32, device=-1):
if device >= 0:
chainer.cuda.get_device_from_id(device).use()
self.to_gpu() # Copy the model to the GPU
# TODO: Not test yet, check behavior
data = args[0]
y_list = []
for i in range(0, len(data), batchsize):
atoms, adjs = concat_mols(data[i:i + batchsize], device=device)[:2]
y = self._predict(atoms, adjs)
y_list.append(cuda.to_cpu(y.data))
y_array = numpy.concatenate(y_list, axis=0)
return y_array
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)
gwm=args.gwm)
chainer.serializers.load_npz(args.g_action, g_action)
# chainer.cuda.get_device_from_id(0).use()
# g_stop.to_gpu()
valid_raw = uspto_dataset.read_data(args.test_path)
valid_dataset = uspto_dataset.USPTO_dataset(valid_raw)
valid_iter = SerialIterator(valid_dataset, 20, repeat=False, shuffle=False)
one_part_acc = []
for batch in valid_iter:
# get one batch of test data
f_atoms, f_bonds, super_node_x, \
atom_label, mask_reagents, mask_reactants_reagents, pair_label, mask_pair_select, \
action, step_num, \
stop_idx, \
sample_index = concat_mols(batch, device=-1)
atom_label -= 1
mask_reagents -= 2
mask_reactants_reagents -= 2
action -= 1
with chainer.using_config('train', False):
inference(g_stop, g_atom, g_pair, g_action, f_atoms, f_bonds,
super_node_x, atom_label, mask_reagents,
mask_reactants_reagents, pair_label, mask_pair_select,
action, step_num, stop_idx, sample_index, valid_raw,
args.out)
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():
# 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']
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(
description='Regression with own dataset.')
parser.add_argument('datafile', type=str)
parser.add_argument('--method', '-m', type=str, choices=method_list,
default='nfp')
parser.add_argument('--label', '-l', nargs='+',
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)
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
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())
# Note that scaled errors are reported as (validation/)main/accuracy
trainer.extend(E.PrintReport(['epoch', 'main/loss', 'main/accuracy',
'validation/main/loss',
'validation/main/accuracy',
'elapsed_time']))
trainer.extend(E.ProgressBar())
trainer.run()
# 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]
print('Prediction for {}:'.format(smiles))
for i, label in enumerate(args.label):
print('{}: {}'.format(label, prediction[i]))
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 extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def test_concat_mols_2d_cpu(data_2d, data_2d_expect):
result = concat_mols(data_2d, device=-1)
assert numpy.array_equal(result[0], data_2d_expect[0])
assert numpy.array_equal(result[1], data_2d_expect[1])
h_s = self.embed_super(super_node)
for step in range(self.n_update_layers):
h_new = self.update_layers[step](h=h, adj=adj)
h_new, h_s = self.gwm(h, h_new, h_s, step)
h = h_new
return h
def reset_state(self):
if hasattr(self.update_layers[0], 'reset_state'):
[update_layer.reset_state() for update_layer in self.update_layers]
self.gwm.reset_state()
if __name__ == '__main__':
import uspto_pre
from chainer.iterators import SerialIterator
from chainer_chemistry.dataset.converters import concat_mols
train_raw = uspto_pre.read_data('../train.txt.proc')
train_dataset = uspto_pre.USPTO_pre(train_raw[:100], 'softmax')
train_iter = SerialIterator(train_dataset, 3)
model = ggnn_gwm()
for b in train_iter:
atom_feature, adjs, supernode_feature, label, ind = concat_mols(b, padding=-1)
print(model(atom_feature, adjs, supernode_feature))
def converter(batch, device):
return concat_mols(batch, device)[:-1]
def train(gpu, method, epoch, batchsize, n_unit, conv_layers, dataset, smiles,
M, n_split, split_idx, order):
n = len(dataset)
assert len(order) == n
left_idx = (n // n_split) * split_idx
is_right_most_split = (n_split == split_idx + 1)
if is_right_most_split:
test_order = order[left_idx:]
train_order = order[:left_idx]
else:
right_idx = (n // n_split) * (split_idx + 1)
test_order = order[left_idx:right_idx]
train_order = np.concatenate([order[:left_idx], order[right_idx:]])
new_order = np.concatenate([train_order, test_order])
n_train = len(train_order)
# Standard Scaler for labels
ss = StandardScaler()
labels = dataset.get_datasets()[-1]
train_label = labels[new_order[:n_train]]
ss = ss.fit(train_label) # fit only by train
labels = ss.transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] + (labels, )))
dataset_train = SubDataset(dataset, 0, n_train, new_order)
dataset_test = SubDataset(dataset, n_train, n, new_order)
# Network
model = predictor.build_predictor(method,
n_unit,
conv_layers,
1,
dropout_ratio=0.25,
n_layers=1)
train_iter = I.SerialIterator(dataset_train, batchsize)
val_iter = I.SerialIterator(dataset_test,
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)
scaled_x0 = ss.inverse_transform(cuda.to_cpu(x0))
scaled_x1 = ss.inverse_transform(cuda.to_cpu(x1))
diff = scaled_x0 - scaled_x1
return np.mean(np.absolute(diff), axis=0)[0]
regressor = Regressor(model,
lossfun=F.mean_squared_error,
metrics_fun={'abs_error': scaled_abs_error},
device=gpu)
optimizer = O.Adam(alpha=0.0005)
optimizer.setup(regressor)
updater = training.StandardUpdater(train_iter,
optimizer,
device=gpu,
converter=concat_mols)
dir_path = get_dir_path(batchsize, n_unit, conv_layers, M, method)
dir_path = os.path.join(dir_path, str(split_idx) + "-" + str(n_split))
os.makedirs(dir_path, exist_ok=True)
print('creating ', dir_path)
np.save(os.path.join(dir_path, "test_idx"), np.array(test_order))
trainer = training.Trainer(updater, (epoch, 'epoch'), out=dir_path)
trainer.extend(
E.Evaluator(val_iter, regressor, device=gpu, converter=concat_mols))
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()
# --- Plot regression evaluation result ---
dataset_test = SubDataset(dataset, n_train, n, new_order)
batch_all = concat_mols(dataset_test, device=gpu)
serializers.save_npz(os.path.join(dir_path, "model.npz"), model)
result = model(batch_all[0], batch_all[1])
result = ss.inverse_transform(cuda.to_cpu(result.data))
answer = ss.inverse_transform(cuda.to_cpu(batch_all[2]))
plot_result(result,
answer,
save_filepath=os.path.join(dir_path, "result.png"))
# --- Plot regression evaluation result end ---
np.save(os.path.join(dir_path, "output.npy"), result)
np.save(os.path.join(dir_path, "answer.npy"), answer)
smiles_part = np.array(smiles)[test_order]
np.save(os.path.join(dir_path, "smiles.npy"), smiles_part)
# calculate saliency and save it.
save_result(dataset, model, dir_path, M)
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 extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def inference():
logging.basicConfig(level=logging.INFO)
parser = argparse.ArgumentParser(description='')
parser.add_argument('--batch_size', type=int, default=16)
# parser.add_argument('--epoch', type=int, default=10)
# parser.add_argument('--lr', type=float, default=1e-3)
parser.add_argument('--gpu', action='store_true')
parser.add_argument('--out', default='result_debug/')
# parser.add_argument('--frequency', type=int, default=-1)
# parser.add_argument('--decay_iter', type=int, default=40000)
parser.add_argument('--gnn_dim', type=int, default=300)
parser.add_argument('--n_layers', type=int, default=3)
parser.add_argument('--nn_dim', type=int, default=100)
# parser.add_argument('--train_path', default='../train.txt.proc')
parser.add_argument('--valid_path', default='../test.txt.proc')
parser.add_argument('--communicator', type=str, default='pure_nccl')
parser.add_argument('--type', default='debug')
parser.add_argument('--rich', type=strtobool, default='false')
parser.add_argument('--snapshot')
args = parser.parse_args()
assert args.type in ['debug', 'all']
if args.gpu:
comm = chainermn.create_communicator(args.communicator)
device = comm.intra_rank
else:
comm = chainermn.create_communicator('naive')
device = -1
if comm.rank == 0:
print(glob.glob(args.out + 'snapshot_*'))
model = pair_matrix_model(gnn_dim=args.gnn_dim,
n_layers=args.n_layers,
nn_dim=args.nn_dim)
chainer.serializers.load_npz(args.out + args.snapshot, model)
if device > 0:
chainer.cuda.get_device_from_id(device).use()
model.to_gpu()
valid_raw = uspto_pre.read_data(args.valid_path)
if comm.rank == 0:
if args.type == 'debug':
valid_dataset = uspto_pre.USPTO_pre(valid_raw[:40], args.rich)
elif args.type == 'all':
valid_dataset = uspto_pre.USPTO_pre(valid_raw, args.rich)
else:
valid_dataset = None, None
valid_dataset = chainermn.scatter_dataset(valid_dataset,
comm,
shuffle=False)
valid_iter = SerialIterator(valid_dataset,
args.batch_size,
repeat=False,
shuffle=False)
for batch in valid_iter:
in_arrays = concat_mols(batch=batch, device=device, padding=-1)
assert isinstance(in_arrays, tuple)
with chainer.using_config('train', False):
h = model.ggnn_gwm(in_arrays[0], in_arrays[1], in_arrays[2])
ind = in_arrays[4]
adj = in_arrays[1][:, :4, :, :]
batch_size = h.shape[0]
graph_size = h.shape[1]
hidden_size = h.shape[2]
h = h.reshape(batch_size, 1, -1, hidden_size) + h.reshape(
batch_size, -1, 1, hidden_size)
h = h.reshape(batch_size, -1, hidden_size)
h1 = model.nn1(h)
h1 = h1.reshape(batch_size, graph_size, graph_size, 5)
for x in range(batch_size):
index = ind[x]
action_pred = []
for i in range(graph_size):
for j in range(i + 1, graph_size):
if adj[x, 0, i, j] == -1:
break
else:
bt_pred = h1[x, i, j].data.argmax()
if bt_pred == 0:
if adj[x, :, i, j].sum() != 0:
action_pred.append(
str(i) + '-' + str(j) + '-' +
str(bt_pred))
else:
if adj[x, bt_pred - 1, i, j] == 0:
action_pred.append(
str(i) + '-' + str(j) + '-' +
str(bt_pred))
with open(args.out + 'inf_' + args.snapshot + '.txt',
'a') as file:
file.write(str(index))
for a_p in action_pred:
file.write('\t' + a_p)
file.write('\n')
