backend.data.FeatureData

class backend.data.FeatureData

__init__()

Initialize self. See help(type(self)) for accurate signature.

get_settings_params()

Returns only the settings-related params; not the data

update_from_params(params: dict)

Update this object’s attributes using the params dict. Any attributes in the excluded_params list will not be updated

clear_settings()

num_features_without_histories(n_chan)

Calculates the number of features currently being generated, without feature and state histories

num_features(n_chan, n_dof)

Calculates the number of features currently being generated, with feature and state histories

clear_data()

Clear the data while leaving settings unchanged

static concatenate(*data_objects)

Simply returns the first feature object

slice(start=None, end=None, bools=None)

Simply returns a copy of self

update_histories(output_data: backend.data.output_data.OutputData, n_chan: int)

Recomputes State and Feature History of output_data.z_f

update_current_state_history(output_data: backend.data.output_data.OutputData, idx: int, n_chan=None, n_feat=None)

Updates the state history of output_data.z_f at the current index: idx Either n_chan or n_feat (without histories) is required

update_current_feature_history(output_data: backend.data.output_data.OutputData, idx: int, n_chan=None, n_feat=None)

Updates the feature history of output_data.z_f at the current index: idx Either n_chan or n_feat (without histories) is required

calc_new_features(filtered_buffer: numpy.ndarray, output_data: backend.data.output_data.OutputData, output_idx: int, decoder=None, feature_timing_history=None, decoder_timing_history=None)

Calculate the features using filtered_buffer, and insert the features and their histories at the output_idx of output_data.

If decoder is provided, it will be used to compute the state history.

train_features(raw_data, output_data)

Train any trainable features on the raw data and their labels