CSVFolderDataset

class torcheeg.datasets.CSVFolderDataset(csv_path: str = './data.csv', read_fn: None | ~typing.Callable = <function default_read_fn>, online_transform: None | ~typing.Callable = None, offline_transform: None | ~typing.Callable = None, label_transform: None | ~typing.Callable = None, io_path: str = './io/folder', io_size: int = 10485760, io_mode: str = 'lmdb', num_worker: int = 0, verbose: bool = True, in_memory: bool = False, **kwargs)

Read meta information from CSV file and read EEG data from folder according to the meta information. The CSV file should contain the following columns:

• subject_id (Optional): The subject id of the EEG data. Commonly used in training and testing dataset split.

• label (Optional): The label of the EEG data. Commonly used in training and testing dataset split.

• file_path (Required): The path to the EEG data file.

# data.csv
# | subject_id | trial_id | label | file_path                 |
# | ---------- | -------  | ----- | ------------------------- |
# | sub1       | 0        | 0     | './data/label1/sub1.fif' |
# | sub1       | 1        | 1     | './data/label2/sub1.fif' |
# | sub1       | 2        | 2     | './data/label3/sub1.fif' |
# | sub2       | 0        | 0     | './data/label1/sub2.fif' |
# | sub2       | 1        | 1     | './data/label2/sub2.fif' |
# | sub2       | 2        | 2     | './data/label3/sub2.fif' |

def default_read_fn(file_path, **kwargs):
    # Load EEG file
    raw = mne.io.read_raw(file_path)
    # Convert raw to epochs
    epochs = mne.make_fixed_length_epochs(raw, duration=1)
    # Return EEG data
    return epochs

dataset = CSVFolderDataset(csv_path='./data.csv',
                           read_fn=default_read_fn,
                           online_transform=transforms.ToTensor(),
                           label_transform=transforms.Select('label'),
                           num_worker=4)

Parameters:

• csv_path (str) – The path to the CSV file.

• read_fn (Callable) – Method for reading files in a folder. By default, this class provides methods for reading files using mne.io.read_raw. At the same time, we allow users to pass in custom file reading methods. The first input parameter of whose is file_path, and other parameters are additional parameters passed in when the class is initialized. For example, you can pass chunk_size=32 to FolderDataset, then chunk_size will be received here.

• online_transform (Callable, optional) – The transformation of the EEG signals and baseline EEG signals. The input is a np.ndarray, and the ouput is used as the first and second value of each element in the dataset. (default: None)

• offline_transform (Callable, optional) – The usage is the same as online_transform, but executed before generating IO intermediate results. (default: None)

• label_transform (Callable, optional) – The transformation of the label. The input is an information dictionary, and the ouput is used as the third value of each element in the dataset. (default: None)

• io_path (str) – The path to generated unified data IO, cached as an intermediate result. (default: /io/deap)

• io_size (int) – Maximum size database may grow to; used to size the memory mapping. If database grows larger than map_size, an exception will be raised and the user must close and reopen. (default: 10485760)

• io_mode (str) – Storage mode of EEG signal. When io_mode is set to lmdb, TorchEEG provides an efficient database (LMDB) for storing EEG signals. LMDB may not perform well on limited operating systems, where a file system based EEG signal storage is also provided. When io_mode is set to pickle, pickle-based persistence files are used. (default: lmdb)

• num_worker (int) – Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process. (default: 0)

• verbose (bool) – Whether to display logs during processing, such as progress bars, etc. (default: True)

• in_memory (bool) – Whether to load the entire dataset into memory. If in_memory is set to True, then the first time an EEG sample is read, the entire dataset is loaded into memory for subsequent retrieval. Otherwise, the dataset is stored on disk to avoid the out-of-memory problem. (default: False)