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 main():
"""Launcher."""
preprocessor = preprocess_method_dict["nfp"]()
dataset = datasets.get_qm9(preprocessor, labels="h**o")
cache_dir = "data/"
if not (os.path.exists(cache_dir)):
os.makedirs(cache_dir)
NumpyTupleDataset.save(cache_dir + "data.npz", dataset)
dataset = NumpyTupleDataset.load(cache_dir + 'data.npz')
train_data_ratio = 0.7
train_data_size = int(len(dataset) * train_data_ratio)
train, validation = split_dataset_random(dataset, train_data_size, 777)
print('train dataset size:', len(train))
print('validation dataset size:', len(validation))
n_unit = 16
conv_layers = 4
model = GraphConvPredictor(NFP(n_unit, n_unit, conv_layers),
MLP(n_unit, 1))
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
label = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, label))
labels = [label]
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached data from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the newly preprocessed dataset.
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Use a predictor with scaled output labels.
model_path = os.path.join(args.in_dir, args.model_filename)
regressor = Regressor.load_pickle(model_path, device=args.gpu)
scaler = regressor.predictor.scaler
if scaler is not None:
scaled_t = scaler.transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] +
(scaled_t, )))
# Split the dataset into training and testing.
train_data_size = int(len(dataset) * args.train_data_ratio)
_, test = split_dataset_random(dataset, train_data_size, args.seed)
# This callback function extracts only the inputs and discards the labels.
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
def postprocess_fn(x):
if scaler is not None:
scaled_x = scaler.inverse_transform(x)
return scaled_x
else:
return x
# Predict the output labels.
print('Predicting...')
y_pred = regressor.predict(test,
converter=extract_inputs,
postprocess_fn=postprocess_fn)
# Extract the ground-truth labels.
t = concat_mols(test, device=-1)[-1]
original_t = scaler.inverse_transform(t)
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({
'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): original_t[:, i],
})
df = pandas.DataFrame(df_dict)
# Show a prediction/ground truth table with 5 random examples.
print(df.sample(5))
n_eval = 10
for target_label in range(y_pred.shape[1]):
label_name = labels[target_label]
diff = y_pred[:n_eval, target_label] - original_t[:n_eval,
target_label]
print('label_name = {}, y_pred = {}, t = {}, diff = {}'.format(
label_name, y_pred[:n_eval, target_label],
original_t[:n_eval, target_label], diff))
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
regressor,
converter=concat_mols,
device=args.gpu)()
print('Evaluation result: ', eval_result)
# Save the evaluation results.
save_json(os.path.join(args.in_dir, 'eval_result.json'), eval_result)
# Calculate mean abs error for each label
mae = numpy.mean(numpy.abs(y_pred - original_t), axis=0)
eval_result = {}
for i, l in enumerate(labels):
eval_result.update({l: mae[i]})
save_json(os.path.join(args.in_dir, 'eval_result_mae.json'), eval_result)
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label:
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
else:
labels = D.get_qm9_label_names()
cache_dir = os.path.join('input', '{}_all'.format(method))
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached data from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the newly preprocessed dataset.
if not os.path.exists(cache_dir):
os.mkdir(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Load the standard scaler parameters, if necessary.
if args.scale == 'standardize':
scaler_path = os.path.join(args.in_dir, 'scaler.pkl')
print('Loading scaler parameters from {}.'.format(scaler_path))
with open(scaler_path, mode='rb') as f:
scaler = pickle.load(f)
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and testing.
train_data_size = int(len(dataset) * args.train_data_ratio)
_, test = split_dataset_random(dataset, train_data_size, args.seed)
# Use a predictor with scaled output labels.
model_path = os.path.join(args.in_dir, args.model_filename)
regressor = Regressor.load_pickle(model_path, device=args.gpu)
# Replace the default predictor with one that scales the output labels.
scaled_predictor = ScaledGraphConvPredictor(regressor.predictor)
scaled_predictor.scaler = scaler
regressor.predictor = scaled_predictor
# This callback function extracts only the inputs and discards the labels.
def extract_inputs(batch, device=None):
return concat_mols(batch, device=device)[:-1]
# Predict the output labels.
print('Predicting...')
y_pred = regressor.predict(test, converter=extract_inputs)
# Extract the ground-truth labels.
t = concat_mols(test, device=-1)[-1]
n_eval = 10
# Construct dataframe.
df_dict = {}
for i, l in enumerate(labels):
df_dict.update({
'y_pred_{}'.format(l): y_pred[:, i],
't_{}'.format(l): t[:, i],
})
df = pandas.DataFrame(df_dict)
# Show a prediction/ground truth table with 5 random examples.
print(df.sample(5))
for target_label in range(y_pred.shape[1]):
diff = y_pred[:n_eval, target_label] - t[:n_eval, target_label]
print('target_label = {}, y_pred = {}, t = {}, diff = {}'.format(
target_label, y_pred[:n_eval, target_label],
t[:n_eval, target_label], diff))
# Run an evaluator on the test dataset.
print('Evaluating...')
test_iterator = SerialIterator(test, 16, repeat=False, shuffle=False)
eval_result = Evaluator(test_iterator,
regressor,
converter=concat_mols,
device=args.gpu)()
# Prevents the loss function from becoming a cupy.core.core.ndarray object
# when using the GPU. This hack will be removed as soon as the cause of
# the issue is found and properly fixed.
loss = numpy.asscalar(cuda.to_cpu(eval_result['main/loss']))
eval_result['main/loss'] = loss
print('Evaluation result: ', eval_result)
# Save the evaluation results.
with open(os.path.join(args.in_dir, 'eval_result.json'), 'w') as f:
json.dump(eval_result, f)
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached dataset from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor,
labels=labels,
target_index=target_index)
else:
# Load the entire dataset.
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Scale the label values, if necessary.
if args.scale == 'standardize':
print('Fit StandardScaler to the labels.')
scaler = StandardScaler()
scaler.fit(dataset.get_datasets()[-1])
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, valid = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num, scaler)
# Set up the regressor.
device = chainer.get_device(args.device)
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
regressor = Regressor(predictor,
lossfun=F.mean_squared_error,
metrics_fun=metrics_fun,
device=device)
print('Training...')
run_train(regressor,
train,
valid=valid,
batch_size=args.batchsize,
epoch=args.epoch,
out=args.out,
extensions_list=None,
device=device,
converter=concat_mols,
resume_path=None)
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.save_pickle(model_path, protocol=args.protocol)
def main():
# Parse the arguments.
args = parse_arguments()
# Set up some useful variables that will be used later on.
method = args.method
if args.label != 'all':
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Get the filename corresponding to the cached dataset, based on the amount
# of data samples that need to be parsed from the original dataset.
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
# Load the cached dataset.
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
dataset = None
if os.path.exists(dataset_cache_path):
print('Loading cached dataset from {}.'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('Preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Select the first `num_data` samples from the dataset.
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor, labels=labels,
target_index=target_index)
else:
# Load the entire dataset.
dataset = D.get_qm9(preprocessor, labels=labels)
# Cache the laded dataset.
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
# Scale the label values, if necessary.
if args.scale == 'standardize':
print('Applying standard scaling to the labels.')
scaler = StandardScaler()
scaled_t = scaler.fit_transform(dataset.get_datasets()[-1])
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1]
+ (scaled_t,)))
else:
print('No standard scaling was selected.')
scaler = None
# Split the dataset into training and validation.
train_data_size = int(len(dataset) * args.train_data_ratio)
train, valid = split_dataset_random(dataset, train_data_size, args.seed)
# Set up the predictor.
predictor = set_up_predictor(method, args.unit_num, args.conv_layers,
class_num, scaler)
# Set up the iterators.
train_iter = iterators.SerialIterator(train, args.batchsize)
valid_iter = iterators.SerialIterator(valid, args.batchsize, repeat=False,
shuffle=False)
# Set up the regressor.
device = args.gpu
metrics_fun = {'mae': MeanAbsError(scaler=scaler),
'rmse': RootMeanSqrError(scaler=scaler)}
regressor = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(regressor)
# Set up the updater.
updater = training.StandardUpdater(train_iter, optimizer, device=device,
converter=concat_mols)
# Set up the trainer.
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(E.Evaluator(valid_iter, regressor, device=device,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(E.PrintReport([
'epoch', 'main/loss', 'main/mae', 'main/rmse', 'validation/main/loss',
'validation/main/mae', 'validation/main/rmse', 'elapsed_time']))
trainer.extend(E.ProgressBar())
trainer.run()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
regressor.save_pickle(model_path, protocol=args.protocol)
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)
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():
# Supported preprocessing/network list
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
label_names = [
'A', 'B', 'C', 'mu', 'alpha', 'h**o', 'lumo', 'gap', 'r2', 'zpve',
'U0', 'U', 'H', 'G', 'Cv'
]
scale_list = ['standardize', 'none']
parser = argparse.ArgumentParser(description='Regression with QM9.')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
choices=label_names,
default='',
help='target label for regression, '
'empty string means to predict all '
'property at once')
parser.add_argument('--scale',
type=str,
choices=scale_list,
default='standardize',
help='Label scaling method')
parser.add_argument('--conv-layers', '-c', type=int, default=4)
parser.add_argument('--batchsize', '-b', type=int, default=32)
parser.add_argument('--gpu', '-g', type=int, default=-1)
parser.add_argument('--out', '-o', type=str, default='result')
parser.add_argument('--epoch', '-e', type=int, default=20)
parser.add_argument('--unit-num', '-u', type=int, default=16)
parser.add_argument('--seed', '-s', type=int, default=777)
parser.add_argument('--train-data-ratio', '-t', type=float, default=0.7)
parser.add_argument('--protocol', type=int, default=2)
parser.add_argument('--model-filename', type=str, default='regressor.pkl')
parser.add_argument('--num-data',
type=int,
default=-1,
help='Number of data to be parsed from parser.'
'-1 indicates to parse all data.')
args = parser.parse_args()
seed = args.seed
train_data_ratio = args.train_data_ratio
method = args.method
if args.label:
labels = args.label
cache_dir = os.path.join('input', '{}_{}'.format(method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input', '{}_all'.format(method))
class_num = len(D.get_qm9_label_names())
# Dataset preparation
dataset = None
num_data = args.num_data
if num_data >= 0:
dataset_filename = 'data_{}.npz'.format(num_data)
else:
dataset_filename = 'data.npz'
dataset_cache_path = os.path.join(cache_dir, dataset_filename)
if os.path.exists(dataset_cache_path):
print('load from cache {}'.format(dataset_cache_path))
dataset = NumpyTupleDataset.load(dataset_cache_path)
if dataset is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# only use first 100 for debug
target_index = numpy.arange(num_data)
dataset = D.get_qm9(preprocessor,
labels=labels,
target_index=target_index)
else:
dataset = D.get_qm9(preprocessor, labels=labels)
os.makedirs(cache_dir)
NumpyTupleDataset.save(dataset_cache_path, dataset)
if args.scale == 'standardize':
# Standard Scaler for labels
ss = StandardScaler()
labels = ss.fit_transform(dataset.get_datasets()[-1])
else:
ss = None
dataset = NumpyTupleDataset(*(dataset.get_datasets()[:-1] + (labels, )))
train_data_size = int(len(dataset) * train_data_ratio)
train, val = split_dataset_random(dataset, train_data_size, seed)
# Network
n_unit = args.unit_num
conv_layers = args.conv_layers
if method == 'nfp':
print('Train NFP model...')
model = GraphConvPredictor(
NFP(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'ggnn':
print('Train GGNN model...')
model = GraphConvPredictor(
GGNN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'schnet':
print('Train SchNet model...')
model = GraphConvPredictor(
SchNet(out_dim=class_num, hidden_dim=n_unit, n_layers=conv_layers),
None)
elif method == 'weavenet':
print('Train WeaveNet model...')
n_atom = 20
n_sub_layer = 1
weave_channels = [50] * conv_layers
model = GraphConvPredictor(
WeaveNet(weave_channels=weave_channels,
hidden_dim=n_unit,
n_sub_layer=n_sub_layer,
n_atom=n_atom), MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'rsgcn':
print('Train RSGCN model...')
model = GraphConvPredictor(
RSGCN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
else:
raise ValueError('[ERROR] Invalid method {}'.format(method))
train_iter = I.SerialIterator(train, args.batchsize)
val_iter = I.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
regressor = Regressor(
model,
lossfun=F.mean_squared_error,
metrics_fun={'abs_error': ScaledAbsError(scale=args.scale, ss=ss)},
device=args.gpu)
optimizer = O.Adam()
optimizer.setup(regressor)
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
E.Evaluator(val_iter,
regressor,
device=args.gpu,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
trainer.extend(
E.PrintReport([
'epoch', 'main/loss', 'main/abs_error', 'validation/main/loss',
'validation/main/abs_error', 'elapsed_time'
]))
trainer.extend(E.ProgressBar())
trainer.run()
# --- save regressor & standardscaler ---
protocol = args.protocol
regressor.save_pickle(os.path.join(args.out, args.model_filename),
protocol=protocol)
if args.scale == 'standardize':
with open(os.path.join(args.out, 'ss.pkl'), mode='wb') as f:
pickle.dump(ss, f, protocol=protocol)
def main():
# 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():
method_list = ['nfp', 'ggnn', 'schnet', 'weavenet', 'rsgcn']
dataset_names = list(molnet_default_config.keys())
parser = argparse.ArgumentParser(description='molnet example')
parser.add_argument('--method',
'-m',
type=str,
choices=method_list,
default='nfp')
parser.add_argument('--label',
'-l',
type=str,
default='',
help='target label for regression, empty string means '
'to predict all property at once')
parser.add_argument('--conv-layers', '-c', type=int, default=4)
parser.add_argument('--batchsize', '-b', type=int, default=32)
parser.add_argument('--gpu', '-g', type=int, default=-1)
parser.add_argument('--out', '-o', type=str, default='result')
parser.add_argument('--epoch', '-e', type=int, default=20)
parser.add_argument('--unit-num', '-u', type=int, default=16)
parser.add_argument('--dataset',
'-d',
type=str,
choices=dataset_names,
default='bbbp')
parser.add_argument('--protocol', type=int, default=2)
parser.add_argument('--model-filename', type=str, default='regressor.pkl')
parser.add_argument('--num-data',
type=int,
default=-1,
help='Number of data to be parsed from parser.'
'-1 indicates to parse all data.')
args = parser.parse_args()
dataset_name = args.dataset
method = args.method
num_data = args.num_data
n_unit = args.unit_num
conv_layers = args.conv_layers
print('Use {} dataset'.format(dataset_name))
if args.label:
labels = args.label
cache_dir = os.path.join(
'input', '{}_{}_{}'.format(dataset_name, method, labels))
class_num = len(labels) if isinstance(labels, list) else 1
else:
labels = None
cache_dir = os.path.join('input',
'{}_{}_all'.format(dataset_name, method))
class_num = len(molnet_default_config[args.dataset]['tasks'])
# Dataset preparation
def get_dataset_paths(cache_dir, num_data):
filepaths = []
for filetype in ['train', 'valid', 'test']:
filename = filetype + '_data'
if num_data >= 0:
filename += '_' + str(num_data)
filename += '.npz'
filepath = os.path.join(cache_dir, filename)
filepaths.append(filepath)
return filepaths
filepaths = get_dataset_paths(cache_dir, num_data)
if all([os.path.exists(fpath) for fpath in filepaths]):
datasets = []
for fpath in filepaths:
print('load from cache {}'.format(fpath))
datasets.append(NumpyTupleDataset.load(fpath))
else:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
# only use first 100 for debug if num_data >= 0
target_index = numpy.arange(num_data) if num_data >= 0 else None
datasets = D.molnet.get_molnet_dataset(dataset_name,
preprocessor,
labels=labels,
target_index=target_index)
if not os.path.exists(cache_dir):
os.makedirs(cache_dir)
datasets = datasets['dataset']
for i, fpath in enumerate(filepaths):
NumpyTupleDataset.save(fpath, datasets[i])
train, val, _ = datasets
# Network
if method == 'nfp':
print('Train NFP model...')
predictor = GraphConvPredictor(
NFP(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'ggnn':
print('Train GGNN model...')
predictor = GraphConvPredictor(
GGNN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'schnet':
print('Train SchNet model...')
predictor = GraphConvPredictor(
SchNet(out_dim=class_num, hidden_dim=n_unit, n_layers=conv_layers),
None)
elif method == 'weavenet':
print('Train WeaveNet model...')
n_atom = 20
n_sub_layer = 1
weave_channels = [50] * conv_layers
predictor = GraphConvPredictor(
WeaveNet(weave_channels=weave_channels,
hidden_dim=n_unit,
n_sub_layer=n_sub_layer,
n_atom=n_atom), MLP(out_dim=class_num, hidden_dim=n_unit))
elif method == 'rsgcn':
print('Train RSGCN model...')
predictor = GraphConvPredictor(
RSGCN(out_dim=n_unit, hidden_dim=n_unit, n_layers=conv_layers),
MLP(out_dim=class_num, hidden_dim=n_unit))
else:
raise ValueError('[ERROR] Invalid method {}'.format(method))
train_iter = iterators.SerialIterator(train, args.batchsize)
val_iter = iterators.SerialIterator(val,
args.batchsize,
repeat=False,
shuffle=False)
metrics_fun = molnet_default_config[dataset_name]['metrics']
loss_fun = molnet_default_config[dataset_name]['loss']
task_type = molnet_default_config[dataset_name]['task_type']
if task_type == 'regression':
model = Regressor(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=args.gpu)
# TODO(nakago): Use standard scaler for regression task
elif task_type == 'classification':
model = Classifier(predictor,
lossfun=loss_fun,
metrics_fun=metrics_fun,
device=args.gpu)
else:
raise NotImplementedError(
'Not implemented task_type = {}'.format(task_type))
optimizer = optimizers.Adam()
optimizer.setup(model)
updater = training.StandardUpdater(train_iter,
optimizer,
device=args.gpu,
converter=concat_mols)
trainer = training.Trainer(updater, (args.epoch, 'epoch'), out=args.out)
trainer.extend(
E.Evaluator(val_iter, model, device=args.gpu, converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(E.LogReport())
print_report_targets = ['epoch', 'main/loss', 'validation/main/loss']
if metrics_fun is not None and type(metrics_fun) == dict:
for m_k in metrics_fun.keys():
print_report_targets.append('main/' + m_k)
print_report_targets.append('validation/main/' + m_k)
if task_type == 'classification':
# Evaluation for train data takes time, skip for now.
# trainer.extend(ROCAUCEvaluator(
# train_iter, model, device=args.gpu, eval_func=predictor,
# converter=concat_mols, name='train', raise_value_error=False))
# print_report_targets.append('train/main/roc_auc')
trainer.extend(
ROCAUCEvaluator(val_iter,
model,
device=args.gpu,
eval_func=predictor,
converter=concat_mols,
name='val',
raise_value_error=False))
print_report_targets.append('val/main/roc_auc')
print_report_targets.append('elapsed_time')
trainer.extend(E.PrintReport(print_report_targets))
trainer.extend(E.ProgressBar())
trainer.run()
# --- save model ---
protocol = args.protocol
model.save_pickle(os.path.join(args.out, args.model_filename),
protocol=protocol)
def main():
# Parse the arguments.
args = parse_arguments()
method = args.method
if args.data_name == 'suzuki':
datafile = 'data/suzuki_type_train_v2.csv'
class_num = 119
class_dict = {'M': 28, 'L': 23, 'B': 35, 'S': 10, 'A': 17}
dataset_filename = 'data.npz'
labels = ['Yield', 'M', 'L', 'B', 'S', 'A', 'id']
elif args.data_name == 'CN':
datafile = 'data/CN_coupling_train.csv'
class_num = 206
class_dict = {'M': 44, 'L': 47, 'B': 13, 'S': 22, 'A': 74}
dataset_filename = 'CN_data.npz'
labels = ['Yield', 'M', 'L', 'B', 'S', 'A', 'id']
elif args.data_name == 'Negishi':
datafile = 'data/Negishi_train.csv'
class_num = 106
class_dict = {'M': 32, 'L': 20, 'T': 8, 'S': 10, 'A': 30}
dataset_filename = 'Negishi_data.npz'
labels = ['Yield', 'M', 'L', 'T', 'S', 'A', 'id']
elif args.data_name == 'PKR':
datafile = 'data/PKR_train.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 = '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. Postprocessing is required for the regression task.
def postprocess_label(label_list):
return numpy.asarray(label_list, dtype=numpy.float32)
# 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...')
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)
# Load the entire dataset.
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)
# Scale the label values, if necessary.
if args.scale == 'standardize':
scaler = StandardScaler()
labels = dataset.get_datasets()[-2]
# yields = dataset.get_datasets()[-1]
yields = dataset.get_datasets()[-1][:, 0].reshape(-1,
1).astype('float32')
# Filter index here
# range_exp = (0.0 <= yields) & (yields <= 1.0)
range_exp = numpy.argsort(yields[:, 0]) # ascending
start_len = 0
end_len = len(yields) #int(len(yields) / 4)
range_exp = range_exp[start_len:end_len]
range_dataset = (dataset.get_datasets()[0][range_exp],
dataset.get_datasets()[1][range_exp],
dataset.get_datasets()[2][range_exp],
dataset.get_datasets()[3][range_exp],
dataset.get_datasets()[4][range_exp],
dataset.get_datasets()[5][range_exp])
yields = yields[range_exp]
labels = labels[range_exp]
dataset = NumpyTupleDataset(*(range_dataset + (
yields,
labels,
)))
else:
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(args.method, args.unit_num, args.conv_layers,
class_num)
# Set up the iterator.
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
classifier = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=args.gpu)
# Set up the optimizer.
optimizer = optimizers.Adam()
optimizer.setup(classifier)
# 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.Evaluator(valid_iter,
classifier,
device=device,
converter=concat_mols))
trainer.extend(E.snapshot(), trigger=(args.epoch, 'epoch'))
trainer.extend(
E.snapshot_object(
classifier,
filename='model_epoch-{.updater.epoch}')) # save every 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()
# Save the regressor's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
classifier.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(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"))
if data_name == 'qm9':
max_atoms = 9
elif data_name == 'zinc250k':
max_atoms = 38
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
if data_type == 'gcn':
preprocessor = RSGCNPreprocessor(out_size=max_atoms)
elif data_type == 'relgcn':
# preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True, return_is_real_node=False)
preprocessor = GGNNPreprocessor(out_size=max_atoms, kekulize=True)
else:
raise ValueError("[ERROR] Unexpected value data_type={}".format(data_type))
data_dir = "."
os.makedirs(data_dir, exist_ok=True)
if data_name == 'qm9':
dataset = datasets.get_qm9(preprocessor)
elif data_name == 'zinc250k':
dataset = datasets.get_zinc250k(preprocessor)
else:
raise ValueError("[ERROR] Unexpected value data_name={}".format(data_name))
NumpyTupleDataset.save(
os.path.join(data_dir,
'{}_{}_kekulized_ggnp.npz'.format(data_name, data_type)),
dataset)
def main():
# Parse the arguments.
args = parse_arguments()
args.out = os.path.join(args.out, args.method)
save_args(args, args.out)
if args.label:
labels = args.label
class_num = len(labels) if isinstance(labels, list) else 1
else:
raise ValueError('No target label was specified.')
# Dataset preparation. Postprocessing is required for the regression task.
def postprocess_label_float(label_list):
return numpy.asarray(label_list, dtype=numpy.float32)
def postprocess_label_int(label_list):
return numpy.asarray(label_list, dtype=numpy.int64)
# Apply a preprocessor to the dataset.
if args.train:
## training data
fn,ext = os.path.splitext(args.train)
if ext==".npz":
print('Loading training dataset...')
train = NumpyTupleDataset.load(args.train)
else:
print('Preprocessing training dataset...')
preprocessor = preprocess_method_dict[args.method]()
if args.classification:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_int,labels=labels, smiles_col='SMILES')
else:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_float,labels=labels, smiles_col='SMILES')
train = parser.parse(args.train)['dataset']
NumpyTupleDataset.save(os.path.join(args.out,os.path.split(fn)[1]), train)
# Scale the label values, if necessary.
if args.scale == 'standardize':
scaler = StandardScaler()
scaler.fit(train.get_datasets()[-1])
else:
scaler = None
## test data
fn,ext = os.path.splitext(args.val)
if ext==".npz":
print('Loading test dataset...')
test = NumpyTupleDataset.load(args.val)
else:
print('Preprocessing test dataset...')
preprocessor = preprocess_method_dict[args.method]()
if args.classification:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_int,labels=labels, smiles_col='SMILES')
else:
parser = CSVFileParser(preprocessor, postprocess_label=postprocess_label_float,labels=labels, smiles_col='SMILES')
test = parser.parse(args.val)['dataset']
NumpyTupleDataset.save(os.path.join(args.out,os.path.split(fn)[1]), test)
# Set up the model.
device = chainer.get_device(args.device)
converter = converter_method_dict[args.method]
metrics_fun = {'mae': F.mean_absolute_error, 'rmse': rmse}
if args.classification:
if args.load_model:
model = Classifier.load_pickle(args.load_model, device=device)
print("model file loaded: ",args.load_model)
else:
predictor = set_up_predictor(args.method, args.unit_num, args.conv_layers, class_num)
model = Classifier(predictor,
lossfun=F.sigmoid_cross_entropy,
metrics_fun=F.binary_accuracy,
device=device)
else:
if args.load_model:
model = Regressor.load_pickle(args.load_model, device=device)
print("model file loaded: ",args.load_model)
else:
predictor = set_up_predictor(
args.method+args.method_suffix, args.unit_num,
args.conv_layers, class_num, label_scaler=scaler)
model = Regressor(predictor, lossfun=F.mean_squared_error,
metrics_fun=metrics_fun, device=device)
if args.train:
if args.balanced_iter:
train = BalancedSerialIterator(train, args.batchsize, train.features[:, -1], ignore_labels=-1)
train.show_label_stats()
print('Training...')
log_keys = ['main/mae','main/rmse','validation/main/mae','validation/main/rmse','validation/main/roc_auc']
extensions_list = [extensions.PlotReport(log_keys, 'iteration', trigger=(100, 'iteration'), file_name='loss.png')]
if args.eval_roc and args.classification:
extensions_list.append(ROCAUCEvaluator(
test, model, eval_func=predictor,
device=device, converter=converter, name='validation',
pos_labels=1, ignore_labels=-1, raise_value_error=False))
save_json(os.path.join(args.out, 'args.json'), vars(args))
run_train(model, train, valid=test,
batch_size=args.batchsize, epoch=args.epoch,
out=args.out, extensions_list=extensions_list,
device=device, converter=converter) #, resume_path=args.resume)
# Save the model's parameters.
model_path = os.path.join(args.out, args.model_filename)
print('Saving the trained model to {}...'.format(model_path))
if hasattr(model.predictor.graph_conv, 'reset_state'):
model.predictor.graph_conv.reset_state()
model.save_pickle(model_path, protocol=args.protocol)
## prediction
it = SerialIterator(test, args.batchsize, repeat=False, shuffle=False)
result = []
for batch in it:
in_arrays = convert._call_converter(converter, batch, device)
with chainer.using_config('train', False), chainer.function.no_backprop_mode():
if isinstance(in_arrays, tuple):
res = model(*in_arrays)
elif isinstance(in_arrays, dict):
res = model(**in_arrays)
else:
res = model(in_arrays)
result.extend(model.y.array.get())
numpy.savetxt(os.path.join(args.out,"result.csv"), numpy.array(result))
eval_result = Evaluator(it, model, converter=converter,device=device)()
print('Evaluation result: ', eval_result)