Jean-Baptiste SCHIRATTI
Jean-Baptiste SCHIRATTI
+1 I would also be interested in having an optional `fit_intercept` parameter in `SAGAClassifier`.
@morganmcg1 I would also be interested in a W&B logger for this repo.
I ran the following code with and without adding a `@memory.cache` decorator (with `memory = Memory(cachedir=mkdtemp())`) on top of `power_spectrum`: ``` import numpy as np import timeit from mne_features.feature_extraction import...
Addressed in #42.
Thank you @GuillaumeCorda for opening this issue. From what I understand, the number of IMF (intrinsic mode functions) obtained using the EMD algorithm is data-dependent, meaning that two consecutive epochs...
Yes! AFAIK, the multivariate EMD takes as input as multivariate signal and outputs a certain number of signals called *intrinsic mode functions* (IMF), which have the same dimension as the...
Since the EMD should be applied before epoching, shouldn't it be considered for MNE rather than MNE-features? By design, MNE-features assumes that the data is already epoched.
I agree! @GuillaumeCorda Using existing implementations (or clean versions of these implementations) ([Univariate/Bivariate EMD](https://github.com/laszukdawid/PyEMD) ; [Multivariate EMD](https://github.com/mariogrune/MEMD-Python-)), you could write an example (to be put under `mne_features/examples`) showing how EMD...
Thank you @BarryLiu97 for your interest in mne-features. This would be a good feature function for mne-features! Feel free to start a PR and implement a `compute_epileptogenicity_index` function.
Yes, I do `make clean`each time I build the doc.