def _initialize_dataloader(self, training_set):
dataset = md.Dataset(smiles_list=training_set,
vocabulary=self.model.vocabulary,
tokenizer=mv.SMILESTokenizer())
return tud.DataLoader(dataset,
batch_size=self.batch_size,
shuffle=True,
collate_fn=md.Dataset.collate_fn)
def _initialize_dataloader(self, path):
training_set = uc.read_smi_file(path)
dataset = md.Dataset(smiles_list=training_set,
vocabulary=self._model.vocabulary,
tokenizer=mv.SMILESTokenizer())
dataloader = torch.utils.data.DataLoader(
dataset,
batch_size=self._batch_size,
shuffle=self._shuffle_each_epoch,
collate_fn=md.Dataset.collate_fn)
return dataloader
def run(self, smiles_list):
"""
Calculates the NLL for a set of SMILES strings.
:param smiles_list: List with SMILES.
:return: An iterator with each NLLs in the same order as the SMILES list.
"""
dataset = md.Dataset(smiles_list, self.model.vocabulary, self.model.tokenizer)
dataloader = tud.DataLoader(dataset, batch_size=self.batch_size, collate_fn=md.Dataset.collate_fn,
shuffle=False)
for batch in dataloader:
for nll in self.model.likelihood(*batch).data.cpu().numpy():
yield nll
def run(self, scaffold_list):
"""
Samples the model for the given number of SMILES.
:params scaffold_list: A list of scaffold SMILES.
:return: An iterator with each of the batches sampled in (scaffold, decoration, nll) triplets.
"""
dataset = md.Dataset(scaffold_list, self.model.vocabulary.scaffold_vocabulary,
self.model.vocabulary.scaffold_tokenizer)
dataloader = tud.DataLoader(dataset, batch_size=self.batch_size,
shuffle=False, collate_fn=md.Dataset.collate_fn)
for batch in dataloader:
for scaff, dec, nll in self.model.sample_decorations(*batch):
yield scaff, dec, nll
def initialize_dataloader(self, data_path, batch_size, vocab, data_type):
# Read train or validation
data = pd.read_csv(os.path.join(data_path, data_type + '.csv'),
sep=",")
dataset = md.Dataset(data=data,
vocabulary=vocab,
tokenizer=mv.SMILESTokenizer(),
prediction_mode=False)
dataloader = torch.utils.data.DataLoader(
dataset,
batch_size,
shuffle=True,
collate_fn=md.Dataset.collate_fn)
return dataloader
def _initialize_dataloader(self, path):
training_set = chem_smiles.read_smiles_file(
path,
standardize=self._config.standardize,
randomize=self._config.randomize)
dataset = reinvent_dataset.Dataset(
smiles_list=training_set,
vocabulary=self._model.vocabulary,
tokenizer=reinvent_vocabulary.SMILESTokenizer())
dataloader = torch.utils.data.DataLoader(
dataset,
batch_size=self._config.batch_size,
shuffle=self._config.shuffle_each_epoch,
collate_fn=reinvent_dataset.Dataset.collate_fn)
return dataloader
def initialize_dataloader(self, opt, vocab, test_file):
"""
Initialize dataloader
:param opt:
:param vocab: vocabulary
:param test_file: test_file_name
:return:
"""
# Read test
data = pd.read_csv(os.path.join(opt.data_path, test_file + '.csv'), sep=",")
dataset = md.Dataset(data=data, vocabulary=vocab, tokenizer=self.tokenizer, prediction_mode=True)
dataloader = torch.utils.data.DataLoader(dataset, opt.batch_size,
shuffle=False, collate_fn=md.Dataset.collate_fn)
return dataloader