FedLibSVMDataset

class fl_sim.data_processing.FedLibSVMDataset(dataset_name: str, num_clients: int, iid: bool = True, criterion_name: str = 'svm', seed: int = 0)

Bases: FedDataset

property candidate_models: Dict[str, Module]

A set of candidate models.

property criteria_mapping: Dict[str, Module]

Mapping from criterion name to criterion.

property doi: List[str]

DOI(s) related to the dataset.

download_if_needed() → None

Download data if needed.

evaluate(probs: Tensor, truths: Tensor) → Dict[str, float]

Evaluation using predictions and ground truth.

Parameters:

• probs (torch.Tensor) – Predicted probabilities.

• truths (torch.Tensor) – Ground truth labels.

Returns:

Evaluation results.

Return type:

Dict[str, float]

extra_repr_keys() → List[str]

Extra keys for __repr__() and __str__().

get_dataloader(train_bs: int | None = None, test_bs: int | None = None, client_idx: int | None = None) → Tuple[DataLoader, DataLoader]

Get local dataloader at client client_idx or get the global dataloader.

Parameters:

• train_bs (int, optional) – Batch size for training dataloader. If None, use default batch size.

• test_bs (int, optional) – Batch size for testing dataloader. If None, use default batch size.

• client_idx (int, optional) – Index of the client to get dataloader. If None, get the dataloader containing all data. Usually used for centralized training.

Returns:

• train_dl (torch.utils.data.DataLoader) – Training dataloader.

• test_dl (torch.utils.data.DataLoader) – Testing dataloader.

classmethod list_all_libsvm_datasets() → DataFrame

List all LibSVM datasets.

classmethod list_datasets() → List[str]

List all available LibSVM datasets.

load_partition_data(batch_size: int | None = None) → tuple

Partition data into all local clients.

Parameters:

batch_size (int, optional) – Batch size for dataloader. If None, use default batch size.

Returns:

• train_clients_num: int

  Number of training clients.

• train_data_num: int

  Number of training data.

• test_data_num: int

  Number of testing data.

• train_data_global: torch.utils.data.DataLoader

  Global training dataloader.

• test_data_global: torch.utils.data.DataLoader

  Global testing dataloader.

• data_local_num_dict: dict

  Number of local training data for each client.

• train_data_local_dict: dict

  Local training dataloader for each client.

• test_data_local_dict: dict

  Local testing dataloader for each client.

• n_class: int

  Number of classes.

Return type:

tuple

load_partition_data_distributed(process_id: int, batch_size: int | None = None) → tuple

Get local dataloader at client process_id or get global dataloader.

Parameters:

• process_id (int) – Index of the client to get dataloader. If None, get the dataloader containing all data, usually used for centralized training.

• batch_size (int, optional) – Batch size for dataloader. If None, use default batch size.

Returns:

• train_clients_num: int

  Number of training clients.

• train_data_num: int

  Number of training data.

• train_data_global: torch.utils.data.DataLoader or None

  Global training dataloader.

• test_data_global: torch.utils.data.DataLoader or None

  Global testing dataloader.

• local_data_num: int

  Number of local training data.

• train_data_local: torch.utils.data.DataLoader or None

  Local training dataloader.

• test_data_local: torch.utils.data.DataLoader or None

  Local testing dataloader.

• n_class: int

  Number of classes.

Return type:

tuple

property num_classes: int

Number of classes.

property num_features: int

Number of features.

reset_seed(seed: int) → None

Reset the seed and re-partition the data.

Parameters:

seed (int) – Random seed for data partitioning.

Return type:

None

property url: str

URL for downloading the dataset.