def load_dataset(method, labels, prefix='input', num_data=-1):
policy = _CacheNamePolicy(method, labels, prefix, num_data=num_data)
train_path = policy.get_train_file_path()
val_path = policy.get_val_file_path()
test_path = policy.get_test_file_path()
train, val, test = None, None, None
if os.path.exists(policy.cache_dir):
print('load from cache {}'.format(policy.cache_dir))
train = NumpyTupleDataset.load(train_path)
val = NumpyTupleDataset.load(val_path)
test = NumpyTupleDataset.load(test_path)
if train is None or val is None or test is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Use `num_data` examples for train
target_index = numpy.arange(num_data)
train, val, test = D.get_tox21(preprocessor,
labels=labels,
train_target_index=target_index,
val_target_index=None,
test_target_index=None)
else:
train, val, test = D.get_tox21(preprocessor, labels=labels)
# Cache dataset
policy.create_cache_directory()
NumpyTupleDataset.save(train_path, train)
NumpyTupleDataset.save(val_path, val)
NumpyTupleDataset.save(test_path, test)
return train, val, test
def load_dataset(method, labels, prefix='input', num_data=-1):
policy = _CacheNamePolicy(method, labels, prefix, num_data=num_data)
train_path = policy.get_train_file_path()
val_path = policy.get_val_file_path()
test_path = policy.get_test_file_path()
train, val, test = None, None, None
print()
if os.path.exists(policy.cache_dir):
print('load from cache {}'.format(policy.cache_dir))
train = NumpyTupleDataset.load(train_path)
val = NumpyTupleDataset.load(val_path)
test = NumpyTupleDataset.load(test_path)
if train is None or val is None or test is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if num_data >= 0:
# Use `num_data` examples for train
target_index = numpy.arange(num_data)
train, val, test = D.get_tox21(
preprocessor, labels=labels,
train_target_index=target_index, val_target_index=None,
test_target_index=None
)
else:
train, val, test = D.get_tox21(preprocessor, labels=labels)
# Cache dataset
policy.create_cache_directory()
NumpyTupleDataset.save(train_path, train)
NumpyTupleDataset.save(val_path, val)
NumpyTupleDataset.save(test_path, test)
return train, val, test
def load_dataset(method, labels, prefix='input'):
method = 'nfp' if 'nfp' in method else method # to deal with nfpdrop
method = 'ggnn' if 'ggnn' in method else method # to deal with ggnndrop
policy = _CacheNamePolicy(method, labels, prefix)
train_path = policy.get_train_file_path()
val_path = policy.get_val_file_path()
test_path = policy.get_test_file_path()
smiles_path = policy.get_smiles_path()
train, val, test = None, None, None
train_smiles, val_smiles, test_smiles = None, None, None
print()
if os.path.exists(policy.cache_dir):
print('load from cache {}'.format(policy.cache_dir))
train = NumpyTupleDataset.load(train_path)
val = NumpyTupleDataset.load(val_path)
test = NumpyTupleDataset.load(test_path)
train_smiles, val_smiles, test_smiles = utils.load_npz(smiles_path)
if train is None or val is None or test is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
if labels == 'pyridine':
train, val, test, train_smiles, val_smiles, test_smiles = D.get_tox21(
preprocessor, labels=None, return_smiles=True)
print('converting label into pyridine...')
# --- Pyridine = 1 ---
train_pyridine_label = [
hassubst(Chem.MolFromSmiles(smi), smart=PYRIDINE_SMILES) for smi in tqdm(train_smiles)]
val_pyridine_label = [
hassubst(Chem.MolFromSmiles(smi), smart=PYRIDINE_SMILES) for smi in tqdm(val_smiles)]
test_pyridine_label = [
hassubst(Chem.MolFromSmiles(smi), smart=PYRIDINE_SMILES) for smi in tqdm(test_smiles)]
train_pyridine_label = numpy.array(train_pyridine_label)[:, None]
val_pyridine_label = numpy.array(val_pyridine_label)[:, None]
test_pyridine_label = numpy.array(test_pyridine_label)[:, None]
print('train positive/negative', numpy.sum(train_pyridine_label == 1), numpy.sum(train_pyridine_label == 0))
train = NumpyTupleDataset(*train.features[:, :-1], train_pyridine_label)
val = NumpyTupleDataset(*val.features[:, :-1], val_pyridine_label)
test = NumpyTupleDataset(*test.features[:, :-1], test_pyridine_label)
else:
train, val, test, train_smiles, val_smiles, test_smiles = D.get_tox21(
preprocessor, labels=labels, return_smiles=True)
# Cache dataset
policy.create_cache_directory()
NumpyTupleDataset.save(train_path, train)
NumpyTupleDataset.save(val_path, val)
NumpyTupleDataset.save(test_path, test)
train_smiles = numpy.array(train_smiles)
val_smiles = numpy.array(val_smiles)
test_smiles = numpy.array(test_smiles)
utils.save_npz(smiles_path, (train_smiles, val_smiles, test_smiles))
return train, val, test, train_smiles, val_smiles, test_smiles
def load_dataset(method, labels, prefix='input'):
policy = _CacheNamePolicy(method, labels, prefix)
train_path = policy.get_train_file_path()
val_path = policy.get_val_file_path()
test_path = policy.get_test_file_path()
train, val, test = None, None, None
print()
if os.path.exists(policy.cache_dir):
print('load from cache {}'.format(policy.cache_dir))
train = NumpyTupleDataset.load(train_path)
val = NumpyTupleDataset.load(val_path)
test = NumpyTupleDataset.load(test_path)
if train is None or val is None or test is None:
print('preprocessing dataset...')
preprocessor = preprocess_method_dict[method]()
train, val, test = D.get_tox21(preprocessor, labels=labels)
# Cache dataset
policy.create_cache_directory()
NumpyTupleDataset.save(train_path, train)
NumpyTupleDataset.save(val_path, val)
NumpyTupleDataset.save(test_path, test)
return train, val, test