mne.decoding.TimeFrequency¶

class mne.decoding.TimeFrequency(frequencies, sfreq=1.0, method=’morlet’, n_cycles=7.0, time_bandwidth=None, use_fft=True, decim=1, output=’complex’, n_jobs=1, verbose=None)[source]¶

Time frequency transformer.

Time-frequency transform of times series along the last axis.

Parameters:

frequencies : array-like of floats, shape (n_freqs,) The frequencies. sfreq : float | int, defaults to 1.0 Sampling frequency of the data. method : ‘multitaper’ | ‘morlet’, defaults to ‘morlet’ The time-frequency method. ‘morlet’ convolves a Morlet wavelet. ‘multitaper’ uses Morlet wavelets windowed with multiple DPSS multitapers. n_cycles : float | array of float, defaults to 7.0 Number of cycles in the Morlet wavelet. Fixed number or one per frequency. time_bandwidth : float, defaults to None If None and method=multitaper, will be set to 4.0 (3 tapers). Time x (Full) Bandwidth product. Only applies if method == ‘multitaper’. The number of good tapers (low-bias) is chosen automatically based on this to equal floor(time_bandwidth - 1). use_fft : bool, defaults to True Use the FFT for convolutions or not. decim : int | slice, defaults to 1 To reduce memory usage, decimation factor after time-frequency decomposition. If int, returns tfr[…, ::decim]. If slice, returns tfr[…, decim]. Note Decimation may create aliasing artifacts, yet decimation is done after the convolutions. output : str, defaults to ‘complex’ ‘complex’ : single trial complex. ‘power’ : single trial power. ‘phase’ : single trial phase. n_jobs : int, defaults to 1 The number of epochs to process at the same time. The parallelization is implemented across channels. verbose : bool, str, int, or None, defaults to None If not None, override default verbose level (see mne.verbose() and Logging documentation for more).

See also

mne.time_frequency.tfr_morlet, mne.time_frequency.tfr_multitaper

Methods

__hash__() <==> hash(x)
fit(X[, y])	Do nothing (for scikit-learn compatibility purposes).
fit_transform(X[, y])	Time-frequency transform of times series along the last axis.
get_params([deep])	Get parameters for this estimator.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Time-frequency transform of times series along the last axis.

__hash__() <==> hash(x)¶

fit(X, y=None)[source]¶

Do nothing (for scikit-learn compatibility purposes).

Parameters:	X : array, shape (n_samples, n_channels, n_times) The training data. y : array | None The target values.
Returns:	self : object Return self.

fit_transform(X, y=None)[source]¶

Time-frequency transform of times series along the last axis.

Parameters:	X : array, shape (n_samples, n_channels, n_times) The training data samples. The channel dimension can be zero- or 1-dimensional. y : None For scikit-learn compatibility purposes.
Returns:	Xt : array, shape (n_samples, n_channels, n_frequencies, n_times) The time-frequency transform of the data, where n_channels can be zero- or 1-dimensional.

get_params(deep=True)[source]¶

Get parameters for this estimator.

Parameters:	deep : boolean, optional If True, will return the parameters for this estimator and contained subobjects that are estimators.
Returns:	params : mapping of string to any Parameter names mapped to their values.

set_params(**params)[source]¶

Set the parameters of this estimator. The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object. Returns ——- self

transform(X)[source]¶

Time-frequency transform of times series along the last axis.

Parameters:	X : array, shape (n_samples, n_channels, n_times) The training data samples. The channel dimension can be zero- or 1-dimensional.
Returns:	Xt : array, shape (n_samples, n_channels, n_frequencies, n_times) The time-frequency transform of the data, where n_channels can be zero- or 1-dimensional.