roiextract.pipeline.MeanAggregation#

class roiextract.pipeline.MeanAggregation(flip=False)#

Averaging-based aggregation of reconstructed source time courses within the ROI. Optionally, a sign flip can be applied before averaging to reduce potential cancellation of activity. This pipeline step corresponds to the mne.extract_label_time_course() function with mode="mean" or mode="mean_flip".

Parameters:

flipbool, default=False: Whether to apply a sign flip before averaging. Sign flip is determined based on the singular value decomposition of the leadfield, as performed in mne.label_sign_flip().

Methods

`fit`(data, src, labels)	Fit the aggregation step to the provided data, source space, and labels.
`fit_transform`(data, src, labels)	Fit the aggregation step to the provided data, source space, and labels, and apply the aggregation to extract the ROI time courses.
`get_names`()	Label names are used as names for rows of the weight matrix.
`get_params`()	Get the single `flip` parameter of the aggregation step as a dictionary.
`get_weights`()	Weight matrix corresponding to the resulting aggregation transformation.
`transform`(data)	Apply the fitted aggregation to the provided data.

fit(data, src, labels)#

Fit the aggregation step to the provided data, source space, and labels.

Parameters:

dataSourceEstimate: The source estimate containing the reconstructed source time courses.
srcSourceSpaces: The definition of the considered source space for inverse modeling.
labelsLabel | list of Label: The label or list of labels defining the ROIs for which time courses should be extracted.

Returns:

selfMeanAggregation: The fitted aggregation step.

fit_transform(data, src, labels)#: Fit the aggregation step to the provided data, source space, and labels, and apply the aggregation to extract the ROI time courses. See fit() and transform() for details on the parameters and return values, respectively.

get_names()#

Label names are used as names for rows of the weight matrix.

Returns:

row_nameslist of str: Names for rows of the weight matrix.

get_params()#

Get the single flip parameter of the aggregation step as a dictionary.

Returns:

paramsdict: The parameters of the aggregation step.

get_weights()#

Weight matrix corresponding to the resulting aggregation transformation.

Returns:

weightsarray: The weight matrix.

transform(data)#

Apply the fitted aggregation to the provided data. The applied transformation corresponds to the mne.extract_label_time_course() function with mode="mean" or mode="mean_flip" for flip=False and flip=True, respectively.

Parameters:

dataSourceEstimate: The source estimate containing the reconstructed source time courses.

Returns:

label_tcarray, shape (n_labels, n_times): The extracted time courses for each label.