Alexandre Gramfort

icon indicating a website link http://alexandre.gramfort.net icon indicating an email [email protected]

icon company Meta icon location Paris, France icon location Machine Learning researcher @ Meta Reality Labs, scikit-learn core dev, pythonista interested in neuroscience applications

Results 758 comments of Alexandre Gramfort

Error: read_source_spaces

it seems to be read: https://github.com/mne-tools/mne-matlab/blob/master/matlab/mne_read_source_spaces.m#L251 if you read it back from Python you recover the info?

Error: read_source_spaces

please provide a full code snippet using sample data so we can debug faster.

Error: read_source_spaces

@sivyobe I edited your code snippet. I can confirm the error. I don't have much time now. It's a bug in the matlab IO. maybe @SherazKhan knows what to do

Multiple calls to `power_spectrum`

either use memory or allow to pass precomputed PSDs

Multiple calls to `power_spectrum`

yes you need to test on a real size problem

ModuleNotFoundError: No module named 'mne_features'

I suspect you have 2 python versions installed on your system or that the install crashed somewhere

compute_samp_entropy argument of type 'builtin_function_or_method' is not iterable

you'll need to fix mne-features for the new sklearn version

FIX: deal with flat epochs in feature extraction

I would fix each feature function individually as depending on method 0 is a good default or not.

Set frequency bands value while extracting features

your data is of dtype int64 do: scores = cross_val_score(pipe, data.astype(float), y, cv=skf) and it works >

Set frequency bands value while extracting features

int64 and float64 are the same size. 64 bits per entry. It just needs to be fixed in mne-features. >