Updates the metric's state using the passed batch output. This is called once for each batch. Args: output: the i

Fit the embedding network based on provided instances. Parameters ---------- graphs: graph.KnowledgeGraph The gra

Returns the smiles strings associated with the molecules. :return: A list of smiles strings.

Returns the features associated with each molecule (if they exist). :return: A list of 1D numpy arrays containing the features for e

Shuffles the dataset. :param seed: Optional random seed.

Returns the targets associated with each molecule. :return: A list of lists of floats containing the targets.

Extract random walks of depth - 1 hops rooted in root.

Gets smiles string and target values (and optionally compound names if provided) from a CSV file. :param path: Path to a CSV file. :para

Creates a one-hot encoding. :param value: The value for which the encoding should be one. :param choices: A list of possible values.

Add a uni-directional edge.

Add a vertex to the Knowledge Graph.

Evaluates predictions using a metric function and filtering out invalid targets. :param preds: A list of lists of shape (data_size, num_task

First apply fit to create a Word2Vec model and then generate embeddings for the provided instances. Parameters ----------

Get all the neighbors of vertex (vertex -> neighbor).

Selects the message features from source corresponding to the atom or bond indices in index. :param source: A tensor of shape (num_bonds, hi

Creates a directory given a path to either a directory or file. If a directory is provided, creates that directory. If a file is provided (i

Returns the number of prediction tasks. :return: The number of tasks.

Updates the learning rate by taking a step. :param current_step: Optionally specify what step to set the learning rate to. I

Builds a MoleculeModel, which is a message passing neural network + feed-forward layers. :param args: Arguments. :return: A MoleculeMode

Learns means and standard deviations across the 0th axis. :param X: A list of lists of floats. :return: The fitted StandardS

Normalizes the features of the dataset using a StandardScaler (subtract mean, divide by standard deviation). If a scaler is provided

Makes predictions on a dataset using an ensemble of models. :param model: A model. :param data: A MoleculeDataset. :param batch_size

Sorts the dataset using the provided key. :param key: A function on a MoleculeDatapoint to determine the sorting order.

Splits data into training, validation, and test splits. :param data: A MoleculeDataset. :param split_type: Split type. :param sizes:

Initializes the MoleculeModel. :param classification: Whether the model is a classification model.

Builds a MoleculeModel, which is a message passing neural network + feed-forward layers. :param args: Arguments. :return: A MoleculeMode

Gets an activation function module given the name of the activation. :param activation: The name of the activation function. :return: Th

Gets the dimensionality of atom features. :param: Arguments.

Gets the dimensionality of bond features. :param: Arguments.

Returns the header of a data CSV file. :param path: Path to a CSV file. :return: A list of strings containing the strings in the comma-s

Gets the task names from a data CSV file. :param path: Path to a CSV file. :param use_compound_names: Whether file has compound names in

Initialize the experiment: - dump parameters - create a logger

Loads a model checkpoint. :param path: Path where checkpoint is saved. :param current_args: The current arguments. Replaces the argument

Modifies and validates training arguments in place. :param args: Arguments.

Determines number of trainable parameters. :param model: An nn.Module. :return: The number of trainable parameters.

Parses arguments for training (includes modifying/validating arguments). :return: A Namespace containing the parsed, modified, and validated

Parse a URI: remove the prefix, parse the name part (Camel cases are plit)

Builds a feature vector for an atom. :param atom: An RDKit atom. :param functional_groups: A k-hot vector indicating the functional grou

Builds a feature vector for a bond. :param bond: A RDKit bond. :return: A list containing the bond features.

Returns the compound names associated with the molecule (if they exist). :return: A list of compound names or None if the dataset do

Creates the message passing encoder for the model. :param args: Arguments.

Creates the feed-forward network for the model. :param args: Arguments.

Filters out invalid SMILES. :param data: A MoleculeDataset. :return: A MoleculeDataset with only valid molecules.

Returns the names of available features generators.

Returns the components of the BatchMolGraph. :return: A tuple containing PyTorch tensors with the atom features, bond features, and

Converts SMILES to a MoleculeDataset. :param smiles: A list of SMILES strings. :param skip_invalid_smiles: Whether to skip and filter ou

Makes predictions on a dataset using an ensemble of models. :param model: A model. :param data: A MoleculeDataset. :param batch_size

Gets a registered FeaturesGenerator by name. :param features_generator_name: The name of the FeaturesGenerator. :return: The desired Fea

Gets the metric function corresponding to a given metric name. :param metric: Metric name. :return: A metric function which takes as arg

Initializes the weights of a model in place. :param model: An nn.Module.

Performs the inverse transformation by multiplying by the standard deviations and adding the means. :param X: A list of lists of flo

Loads the arguments a model was trained with. :param path: Path where model checkpoint is saved. :return: The arguments Namespace that t

Logs and returns statistics about counts and average target values in molecular scaffolds. :param data: A MoleculeDataset. :param index_