API Reference

Classifiers

rCCA(stimulus, fs[, event, onset_event, ...])	Reconvolution CCA classifier.
eCCA(lags, fs[, cycle_size, ...])	ERP CCA classifier.
Ensemble(estimator, gate)	Ensemble classifier.

EEG

generate_impulse_response(fs[, components, ...])	Generate a temporal response function (i.e., a VEP / impulse response kernel) as the sum of one or more Ricker wavelets (a biphasic bump, similar to a single-component visual evoked potential).
generate_c_vep_source(stimulus, y, n_samples, fs)	Generate a single-source c-VEP signal per trial.
generate_mixing_matrix(n_channels[, ...])	Generate a mixing matrix that projects one or more sources to channel space, simulating volume conduction.
apply_mixing_matrix(source, mixing_matrix)	Project one or more source signals to channel space using a mixing matrix.
generate_white_noise(n_trials, n_channels, ...)	Generate white sensor / measurement noise, i.e., independent and identically distributed Gaussian noise per channel and sample.
generate_pink_noise(n_trials, n_channels, ...)	Generate 1/f (pink) noise per channel, approximating the aperiodic background spectrum of EEG.
generate_line_noise(n_trials, n_channels, ...)	Generate electrical line noise (e.g., 50 Hz mains interference and its harmonics), shared (with only small gain variations) across channels, with a random phase per trial.
generate_noise(n_trials, n_channels, ...[, ...])	Generate multi-channel EEG background noise as the sum of white sensor noise, 1/f pink noise, and electrical line noise.
generate_c_vep(n_trials, n_channels, ...[, ...])	Generate a synthetic multi-channel c-VEP EEG dataset.

Envelope

aud_space_bw(fmin, fmax[, bw, scale])	Auditory scale points specified by bandwidth.
aud_to_freq(aud[, scale])	Convert auditory units at the auditory scale to frequency (Hz).
gammatone(audio, fs[, fs_inter, fs_target, ...])	Compute the envelope of audio using a gammatone filterbank.
rms(audio, fs[, fs_inter, fs_target])	Compute the envelope of the audio as the root mean square (RMS) of the signal.
erb_space_bw(fmin, fmax[, bw])	Auditory scale points specified by bandwidth.
freq_to_aud(freq[, scale])	Convert frequencies (Hz) to auditory units at the auditory scale.

Gates

AggregateGate([aggregate])	Gate described by an aggregate function.
DifferenceGate(estimator)	Gate described by classification of difference scores.

Plotting

eventplot(S, E, fs[, ax, upsample, plotfs, ...])	Plot the event time-series.
stimplot(S, fs[, ax, upsample, plotfs, labels])	Plot the stimulus time-series.
topoplot(z, locfile[, cbar, ax, iso, chan, ...])	Plot a topoplot.

Stimulus

make_apa_sequence()	Make an almost perfect auto-correlation (APA) sequence.
make_de_bruijn_sequence([k, n, seed])	Make a de Bruijn sequence.
make_golay_sequence()	Make complementary Golay sequences.
make_gold_codes([poly1, poly2, seed1, seed2])	Make a set of Gold codes.
make_m_sequence([poly, base, seed])	Make a maximum length sequence.
is_de_bruijn_sequence(stimulus[, k, n])	Check whether a stimulus is a de Bruijn sequence.
is_gold_code(stimulus)	Check whether a stimulus is a Gold code.
is_m_sequence(stimulus)	Check whether a stimulus is an m-sequence.
modulate(stimulus)	Modulate a stimulus.
shift(stimulus, stride)	Shift a code to create multiple circularly shifted versions of it.
optimize_subset_clustering(X, n_subset)	Optimize the subset by first clustering similar codes and subsequently selecting the best candidates from each cluster.
optimize_layout_incremental(X, neighbours[, ...])	Optimize the allocation of codes to a layout by considering the correlation between neighboring codes.

Stopping

BayesStopping(estimator, segment_time, fs[, ...])	Bayesian dynamic stopping.
CriterionStopping(estimator, segment_time, fs)	Criterion static stopping.
DistributionStopping(estimator, segment_time, fs)	Distribution dynamic stopping.
MarginStopping(estimator, segment_time, fs)	Margin dynamic stopping.
ValueStopping(estimator, segment_time, fs[, ...])	Value dynamic stopping.

Transformers

CCA(n_components[, gamma_x, gamma_y, ...])	Canonical correlation analysis (CCA).
Vectorizer([channel_prime])	Vectorizer.

Utilities

correct_latency(X, y, latency, fs[, axis])	Correct for a latency in data.
correlation(A, B[, n_old, avg_old, cov_old, ...])	Compute the correlation coefficient.
covariance(data[, n_old, avg_old, cov_old, ...])	Compute the covariance matrix.
decoding_matrix(data, length[, stride])	Make a Hankel-like decoding matrix.
encoding_matrix(stimulus, length[, stride, ...])	Make a Toeplitz-like encoding matrix.
euclidean(A, B[, sum_aa_old, sum_bb_old, ...])	Compute the Euclidean distance.
event_matrix(stimulus, event[, onset_event])	Make an event matrix.
filterbank(X, passbands, fs[, tmin, ftype, ...])	Apply a filterbank.
find_neighbours(layout[, border_value])	Find the neighbour pairs (horizontal, vertical, diagonal) in a rectangular layout.
find_worst_neighbour(score, neighbours, layout)	Find the neighbouring pair with maximum score.
pinv(A[, alpha])	Compute the (Moore-Penrose) pseudo-inverse of a matrix.
itr(n, p, t)	Compute the information-transfer rate (ITR).
trials_to_epochs(X, y, codes, epoch_size, ...)	Slice trials to epochs.