NaNs in ISC analysis using brainiak package

, ,
1

Hi all,

I’m trying to run a spatial ISC analysis using the isc function from the brainiak package in Python. I’m running into an issue where I have NaNs for some of the voxels for some of my subjects. The function has a tolerate_nans option, where it handles NaNs when averaging over all subjects to do a leave one out analysis, but the correlation doesn’t work because there are still NaNs in the single subject being correlated to the average. Is there a way to get around this issue, or am I missing something about how the function should be used?

Thanks so much!

2

Hi,
You can try this line to Convert the nans od your data into zeros
your_dataname[np.isnan(your_dataname)] = 0