immuneML.data_model.dataset package

Submodules

immuneML.data_model.dataset.Dataset module

class immuneML.data_model.dataset.Dataset.Dataset(encoded_data=None, name: Optional[str] = None, identifier: Optional[str] = None, labels: Optional[dict] = None)[source]

Bases: object

SUBSAMPLED = 'subsampled'
TEST = 'test'
TRAIN = 'train'
abstract clone()[source]
abstract get_batch(batch_size: int = 1)[source]
abstract get_data(batch_size: int = 1)[source]
abstract get_example_count()[source]
abstract get_example_ids()[source]
abstract get_label_names()[source]
abstract get_metadata(field_names: list, return_df: bool = False)[source]
abstract make_subset(example_indices, path, dataset_type: str)[source]

immuneML.data_model.dataset.ElementDataset module

class immuneML.data_model.dataset.ElementDataset.ElementDataset(labels: Optional[dict] = None, encoded_data: Optional[immuneML.data_model.encoded_data.EncodedData.EncodedData] = None, filenames: Optional[list] = None, identifier: Optional[str] = None, file_size: int = 50000, name: Optional[str] = None)[source]

Bases: immuneML.data_model.dataset.Dataset.Dataset

This is the base class for ReceptorDataset and SequenceDataset which implements all the functionality for both classes. The only difference between these two classes is whether paired or single chain data is stored.

clone()[source]
get_batch(batch_size: int = 10000)[source]
get_data(batch_size: int = 10000)[source]
get_example_count()[source]
get_example_ids()[source]
get_filenames()[source]
get_label_names()[source]

Returns the list of metadata fields which can be used as labels

make_subset(example_indices, path, dataset_type: str)[source]

Creates a new dataset object with only those examples (receptors or receptor sequences) available which were given by index in example_indices argument.

Parameters
  • example_indices (list) – a list of indices of examples (receptors or receptor sequences) to use in the new dataset

  • path (Path) – a path where to store the newly created dataset

  • dataset_type (str) – a type of the dataset used as a part of the name of the resulting dataset; the values are defined as constants in Dataset

Returns

a new dataset object (ReceptorDataset or SequenceDataset, as the original dataset) which includes only the examples specified under example_indices

set_filenames(filenames)[source]

immuneML.data_model.dataset.ReceptorDataset module

class immuneML.data_model.dataset.ReceptorDataset.ReceptorDataset(labels: Optional[dict] = None, encoded_data: Optional[immuneML.data_model.encoded_data.EncodedData.EncodedData] = None, filenames: Optional[list] = None, identifier: Optional[str] = None, file_size: int = 50000, name: Optional[str] = None)[source]

Bases: immuneML.data_model.dataset.ElementDataset.ElementDataset

A dataset class for receptor datasets (paired chain). All the functionality is implemented in ElementDataset class, except creating a new dataset and obtaining metadata.

classmethod build_from_objects(receptors: List[immuneML.data_model.receptor.Receptor.Receptor], file_size: int, path: pathlib.Path, name: Optional[str] = None)[source]
clone()[source]
get_metadata(field_names: list, return_df: bool = False)[source]

Returns a dict or an equivalent pandas DataFrame with metadata information from Receptor objects for provided field names

immuneML.data_model.dataset.RepertoireDataset module

class immuneML.data_model.dataset.RepertoireDataset.RepertoireDataset(labels: Optional[dict] = None, encoded_data: Optional[immuneML.data_model.encoded_data.EncodedData.EncodedData] = None, repertoires: Optional[list] = None, identifier: Optional[str] = None, metadata_file: Optional[pathlib.Path] = None, name: Optional[str] = None)[source]

Bases: immuneML.data_model.dataset.Dataset.Dataset

add_encoded_data(encoded_data: immuneML.data_model.encoded_data.EncodedData.EncodedData)[source]
clone()[source]
get_batch(batch_size: int = 1)[source]
get_data(batch_size: int = 1)[source]
get_example_count()[source]
get_example_ids()[source]

Returns a list of example identifiers

get_filenames()[source]

Returns the paths to files in which repertoire information is stored

get_label_names(refresh=False)[source]

Returns the list of metadata fields which can be used as labels; if refresh=True, it reloads the fields from disk

get_metadata(field_names: list, return_df: bool = False)[source]

A function to get the metadata of the repertoires. It can be useful in encodings or reports when the repertoire information needed is not present only in the label chosen for the ML model (e.g., disease), but also other information (e.g., age, HLA).

Parameters
  • field_names (list) – list of the metadata fields to return; the fields must be present in the metadata files. To find fields available, use get_label_names function.

  • return_df (bool) – determines if the results should be returned as a dataframe where each column corresponds to a field or as a dictionary

Returns

a dictionary where keys are fields names and values are lists of field values for each repertoire; alternatively returns the same information in dataframe format

get_metadata_fields(refresh=False)[source]

Returns the list of metadata fields, includes also the fields that will typically not be used as labels, like filename or identifier

get_repertoire(index: int = - 1, repertoire_identifier: str = '')immuneML.data_model.repertoire.Repertoire.Repertoire[source]
get_repertoire_ids() → list[source]

Returns a list of repertoire identifiers, same as get_example_ids()

make_subset(example_indices, path: pathlib.Path, dataset_type: str)[source]

Creates a new dataset object with only those examples (repertoires) available which were given by index in example_indices argument.

Parameters
  • example_indices (list) – a list of indices of examples (repertoires) to use in the new dataset

  • path (Path) – a path where to store the newly created dataset

  • dataset_type (str) – a type of the dataset used as a part of the name of the resulting dataset; the values are defined as constants in Dataset

Returns

a new RepertoireDataset object which includes only the repertoires specified under example_indices

immuneML.data_model.dataset.SequenceDataset module

class immuneML.data_model.dataset.SequenceDataset.SequenceDataset(labels: Optional[dict] = None, encoded_data: Optional[immuneML.data_model.encoded_data.EncodedData.EncodedData] = None, filenames: Optional[list] = None, identifier: Optional[str] = None, file_size: int = 50000, name: Optional[str] = None)[source]

Bases: immuneML.data_model.dataset.ElementDataset.ElementDataset

A dataset class for sequence datasets (single chain). All the functionality is implemented in ElementDataset class, except creating a new dataset and obtaining metadata.

classmethod build_from_objects(sequences: List[immuneML.data_model.receptor.receptor_sequence.ReceptorSequence.ReceptorSequence], file_size: int, path: pathlib.Path, name: Optional[str] = None)[source]
clone()[source]
get_metadata(field_names: list, return_df: bool = False)[source]

Returns a dict or an equivalent pandas DataFrame with metadata information under ‘custom_params’ attribute in SequenceMetadata object for every sequence for provided field names

Module contents