mne.decoding.TimeFrequency#

class mne.decoding.TimeFrequency(freqs, 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:
freqsarray_like of float, shape (n_freqs,)

The frequencies.

sfreqfloat | int, default 1.0

Sampling frequency of the data.

method‘multitaper’ | ‘morlet’, default ‘morlet’

The time-frequency method. ‘morlet’ convolves a Morlet wavelet. ‘multitaper’ uses Morlet wavelets windowed with multiple DPSS multitapers.

n_cyclesfloat | array of float, default 7.0

Number of cycles in the Morlet wavelet. Fixed number or one per frequency.

time_bandwidthfloat, default 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_fftbool, default True

Use the FFT for convolutions or not.

decimint | slice, default 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.

outputstr, default ‘complex’
  • ‘complex’ : single trial complex.

  • ‘power’ : single trial power.

  • ‘phase’ : single trial phase.

n_jobsint | None

The number of jobs to run in parallel. If -1, it is set to the number of CPU cores. Requires the joblib package. None (default) is a marker for ‘unset’ that will be interpreted as n_jobs=1 (sequential execution) unless the call is performed under a joblib.parallel_config context manager that sets another value for n_jobs. The number of epochs to process at the same time. The parallelization is implemented across channels.

verbosebool | str | int | None

Control verbosity of the logging output. If None, use the default verbosity level. See the logging documentation and mne.verbose() for details. Should only be passed as a keyword argument.

Methods

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.

fit(X, y=None)[source]#

Do nothing (for scikit-learn compatibility purposes).

Parameters:
Xarray, shape (n_samples, n_channels, n_times)

The training data.

yarray | None

The target values.

Returns:
selfobject

Return self.

fit_transform(X, y=None)[source]#

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

Parameters:
Xarray, shape (n_samples, n_channels, n_times)

The training data samples. The channel dimension can be zero- or 1-dimensional.

yNone

For scikit-learn compatibility purposes.

Returns:
Xtarray, shape (n_samples, n_channels, n_freqs, 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:
deepbool, optional

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:
paramsdict

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.

Parameters:
**paramsdict

Parameters.

Returns:
instinstance

The object.

transform(X)[source]#

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

Parameters:
Xarray, shape (n_samples, n_channels, n_times)

The training data samples. The channel dimension can be zero- or 1-dimensional.

Returns:
Xtarray, shape (n_samples, n_channels, n_freqs, n_times)

The time-frequency transform of the data, where n_channels can be zero- or 1-dimensional.