Looks up indices of text tokens according to the vocabulary. If `unknown_token` of the vocabulary is None, looking up unknown tokens r

Initializes the learning rate scheduler. :param optimizer: A PyTorch optimizer. :param warmup_epochs: The number of epochs d

Initializes a MoleculeDatapoint, which contains a single molecule. :param line: A list of strings generated by separating a line in

Initializes a MoleculeDataset, which contains a list of MoleculeDatapoints (i.e. a list of molecules). :param data: A list of Molecu

Initialize StandardScaler, optionally with means and standard deviations precomputed. :param means: An optional 1D numpy array of pr

Computes the graph structure and featurization of a molecule. :param smiles: A smiles string. :param args: Arguments.

:param args: A :class:`~chemprop.args.TrainArgs` object containing model arguments. :param atom_fdim: Atom feature vector dimension.

precision = tp / tp + fp recall = tp / tp + fn

no dropout support batch_first support deprecated, the input and output tensors are provided as (batch, seq_len, feature).

Constructor

Constructor

Constructor

Returns the length of the dataset (i.e. the number of molecules). :return: The length of the dataset.

Computes the accuracy of a binary prediction task using a given threshold for generating hard predictions. Alternatively, compute accuracy fo

Clears featurization cache.

Computes the molecule vectors output from the last layer of a MoleculeModel. :param model: A MoleculeModel. :param data: A MoleculeDatas

Creates a logger with a stream handler and two file handlers. The stream handler prints to the screen depending on the value of `quiet`.

k-fold cross validation

Generate KnowledgeGraph using SPARQL Endpoint.

Encodes a batch of molecular graphs. :param mol_graph: A :class:`~chemprop.features.featurization.BatchMolGraph` representing

Runs the MoleculeModel on input. :param input: Input. :return: The output of the MoleculeModel.