DatasetLoader

class DatasetLoader

Bases: abc.ABC

A generic dataset.

Attributes Summary

context_channels	Get the number of features for each context.
drug_channels	Get the number of features for each drug.
num_contexts	Get the number of contexts.
num_drugs	Get the number of drugs.
num_labeled_triples	Get the number of labeled triples.

Methods Summary

get_context_features()	Get the context feature set.
get_drug_features()	Get the drug feature set.
get_generator(batch_size, context_features, …)	Initialize a batch generator.
get_generators(batch_size, context_features, …)	Generate a pre-stratified pair of batch generators.
get_labeled_triples()	Get the labeled triples file from the storage.
summarize()	Summarize the dataset.

Attributes Documentation

context_channels

Get the number of features for each context.

Return type

int

drug_channels

Get the number of features for each drug.

Return type

int

num_contexts

Get the number of contexts.

Return type

int

num_drugs

Get the number of drugs.

Return type

int

num_labeled_triples

Get the number of labeled triples.

Return type

int

Methods Documentation

abstract get_context_features()

Get the context feature set.

Return type

ContextFeatureSet

abstract get_drug_features()

Get the drug feature set.

get_generator(batch_size, context_features, drug_features, drug_molecules, labeled_triples=None)

Initialize a batch generator.

Parameters

• batch_size (int) – Number of drug pairs per batch.

• context_features (bool) – Indicator whether the batch should include biological context features.

• drug_features (bool) – Indicator whether the batch should include drug features.

• drug_molecules (bool) – Indicator whether the batch should include drug molecules

• labeled_triples (Optional[LabeledTriples]) – A labeled triples object used to generate batches. If none is given, will use all triples from the dataset.

Return type

BatchGenerator

Returns

A batch generator

get_generators(batch_size, context_features, drug_features, drug_molecules, train_size=None, random_state=None)

Generate a pre-stratified pair of batch generators.

Return type

Tuple[BatchGenerator, BatchGenerator]

abstract get_labeled_triples()

Get the labeled triples file from the storage.

Return type

LabeledTriples

summarize()

Summarize the dataset.

Return type

None