pnpl.datasets.gwilliams2022.dataset.Gwilliams2022

pnpl.datasets.gwilliams2022.dataset.Gwilliams2022#

class pnpl.datasets.gwilliams2022.dataset.Gwilliams2022(data_path, task, preprocessing='notch+bp+ds', preprocessing_config=None, include_subjects=None, exclude_subjects=None, include_sessions=None, exclude_sessions=None, include_tasks=None, exclude_tasks=None, include_run_keys=None, exclude_run_keys=None, standardize=True, clipping_boundary=10.0, channel_means=None, channel_stds=None, include_info=False, create_h5_if_missing=True, download=True, preload_h5=False)[source]#

MEG-MASC continuous MEG dataset.

Parameters:

  • data_path (str) – Local data directory. Files are arranged in BIDS layout here (matching what OSF provides). Created if missing.

  • task – Object implementing pnpl.tasks.base.TaskProtocol. See pnpl.tasks.gwilliams2022 for ready-made tasks.

  • preprocessing (Optional[str]) – Preprocessing string used in derivative filenames (e.g. "notch+bp+ds"). When None, the raw KIT recording is materialized to H5 unchanged.

  • preprocessing_config (Optional[Dict[str, Dict[str, Any]]]) – Optional preprocessing-step overrides forwarded to pnpl.preprocessing.Pipeline.

  • exclude_subjects (Optional[Sequence[str]]) – BIDS subject ids without the sub- prefix (e.g. "01").

  • exclude_sessions (Optional[Sequence[str]]) – "0" or "1".

  • exclude_tasks (Optional[Sequence[str]]) – Task ids in MEG-MASC’s BIDS layout ("0"..``”3”`` — one per story).

  • exclude_run_keys (Optional[Sequence[tuple]]) – Tuples of (subject, session, task, run) to include/exclude. MEG-MASC uses a single run per task, so run is always "01".

  • channel_stds (ndarray | None) – See pnpl.datasets.mixins.StandardizationMixin.

  • include_info (bool) – If True, __getitem__ returns (x, y, info).

  • create_h5_if_missing (bool) – If True (default), materialize the cached H5 from a local preprocessed FIF or — failing that — by running the preprocessing pipeline against the raw KIT recording.

  • download (bool) – If True, fetch missing files from OSF on demand.

  • include_subjects (Optional[Sequence[str]])

  • exclude_subjects

  • include_sessions (Optional[Sequence[str]])

  • exclude_sessions

  • include_tasks (Optional[Sequence[str]])

  • exclude_tasks

  • include_run_keys (Optional[Sequence[tuple]])

  • exclude_run_keys

  • standardize (bool)

  • clipping_boundary (Optional[float])

  • channel_means (ndarray | None)

  • channel_stds

  • preload_h5 (bool)

__init__(data_path, task, preprocessing='notch+bp+ds', preprocessing_config=None, include_subjects=None, exclude_subjects=None, include_sessions=None, exclude_sessions=None, include_tasks=None, exclude_tasks=None, include_run_keys=None, exclude_run_keys=None, standardize=True, clipping_boundary=10.0, channel_means=None, channel_stds=None, include_info=False, create_h5_if_missing=True, download=True, preload_h5=False)[source]#
Parameters:

  • data_path (str)

  • preprocessing (str | None)

  • preprocessing_config (Dict[str, Dict[str, Any]] | None)

  • include_subjects (Sequence[str] | None)

  • exclude_subjects (Sequence[str] | None)

  • include_sessions (Sequence[str] | None)

  • exclude_sessions (Sequence[str] | None)

  • include_tasks (Sequence[str] | None)

  • exclude_tasks (Sequence[str] | None)

  • include_run_keys (Sequence[tuple] | None)

  • exclude_run_keys (Sequence[tuple] | None)

  • standardize (bool)

  • clipping_boundary (float | None)

  • channel_means (ndarray | None)

  • channel_stds (ndarray | None)

  • include_info (bool)

  • create_h5_if_missing (bool)

  • download (bool)

  • preload_h5 (bool)

Methods

__init__(data_path, task[, preprocessing, ...])

calculate_standardization_params(h5_data_loader)

Calculate channel means and stds across all runs.

clip_sample(sample, boundary)

Clip sample values to [-boundary, boundary].

close_h5_files()

Close all open H5 file handles and drop preloaded arrays.

ensure_file(fpath)

Ensure a file exists locally, downloading from OSF if needed.

get_bids_raw_path(subject, session, task, run)

Construct path to raw BIDS MEG file.

get_calibration_files()

Get paths to Maxwell filter calibration files.

get_dataset_manifest([refresh])

Build a manifest of every file on OSF storage for the configured node(s).

get_derivatives_path(subject, session[, ...])

Construct path to derivatives directory.

get_elp_path(subject, session)

get_events_path(subject, session, task, run)

Construct path to events TSV file.

get_h5_dataset(run_key)

Get (cached) H5 dataset for a run.

get_h5_path(subject, session, task, run[, ...])

Construct path to H5 file.

get_headpos_path(subject, session, task, run)

Construct path to cached head position file.

get_hsp_path(subject, session)

get_markers_path(subject, session, task)

get_meg_dir(subject, session)

get_preprocessed_path(subject, session, ...)

Construct path to preprocessed file in derivatives.

get_sfreq_from_h5(h5_path)

Get sampling frequency from H5 file.

init_continuous_h5([preload_h5])

Initialize the H5 data cache.

list_remote_files([refresh])

Return dataset-relative file paths advertised by the OSF manifest.

load_continuous_window(subject, session, ...)

Load a time window from continuous H5 data.

load_continuous_window_from_sample(sample)

Load time window from a sample tuple.

load_head_positions(subject, session, task, run)

Load cached head positions from CSV file.

load_preprocessed_bids(subject, session, ...)

Load a preprocessed FIF file from the derivatives directory.

load_raw_bids(subject, session, task, run[, ...])

Load the raw KIT recording, fetching it (and the marker / head-shape sidecars KIT requires) from OSF if necessary.

prefetch_files(file_paths)

Prefetch multiple files in parallel (skips already-present).

raw_bids_exists(subject, session, task, run)

Check if raw BIDS data exists for given identifiers.

resolve_remote_file(rel_path)

Resolve a single file's OSF location by walking only the folders on its path (~3-4 API calls per new folder, served from cache thereafter).

setup_standardization([standardize, ...])

Set up standardization parameters.

standardize(data)

Apply z-score normalization and optional clipping to data.

Attributes

OSF_API_BASE

OSF_FILES_BASE

OSF_PROJECT_FALLBACKS

OSF_PROJECT_ID

OSF_TOKEN_ENV

broadcasted_means

broadcasted_stds

channel_means

channel_stds

label_info

n_channels

n_times