pnpl.datasets.mixins.StandardizationMixin

class pnpl.datasets.mixins.StandardizationMixin

Mixin providing standardization functionality for MEG data.

Classes using this mixin should have: - points_per_sample: int - Number of time points per sample - run_keys: list - List of run keys for computing stats - A method to load H5 data for computing statistics

__init__()

Methods

__init__()
calculate_standardization_params(h5_data_loader)	Calculate channel means and stds across all runs.
clip_sample(sample, boundary)	Clip sample values to [-boundary, boundary].
setup_standardization([standardize, ...])	Set up standardization parameters.
standardize(data)	Apply z-score normalization and optional clipping to data.

Attributes

broadcasted_means
broadcasted_stds
channel_means
channel_stds