RSA toolbox searchlight crossnobis

JasminStein · June 22, 2023, 4:22pm

Hi everyone,

I am trying to run a searchlight analyses using the Python RSA toolbox. What I want is to compute searchlight RDMs across multiple runs using cross-validated square Mahalanobis distance. However, the get_searchlight_RDMSs function takes in a 2d data input. What does my input data need to look like for this function to compute the crossnobis in a searchlight? Is that even possible?

Thanks a lot!
Jasmin

foldes.andrei · June 28, 2023, 5:10pm

Hello,

Funnily enough somebody just posted about this exact issue on github two days ago
You might try contacting them for their solution to get crossnobis working for that specific functions:

github.com/rsagroup/rsatoolbox

Minimal changes to `get_searchlight_RDMs` to make it more convenient

opened 12:18PM - 26 Jun 23 UTC

mathias-sm

`get_searchlight_RDMs` is very convenient when working with fMRI datasets, but a… few small changes would make it easier for me to use, and might benefit others. As things stand, I basically wrote my own version of it, which is almost 100% identical to upstream. I am aware of the efforts in PR #253 whence this issue instead of a PR with my small changes. There are two things that I would happily add because I use/need them: * `calc_rdm` takes more arguments than `get_searchlight_RDMs` does, making the later less flexible than the former, e.g. I needed to pass a `cv_descriptor` when using `crossnobis` distance, but `get_searchlight_RDMs` cannot handle that. Same with `noise`, `prior_lambda` and `prior_weight`. Adding them to `get_searchlight_RDMs` could be useful, possibly with `**kwargs`? * Parallelizing over `chunks` seems easy and reasonable, esp. as the searchlight util functions already make use of joblib's parallel. I did it by turning `for chunks in tqdm(chunked_center, desc='Calculating RDMs...'):` into a function like `def chunk_to_rdm(chunk):`, then called with `RDM_corrs = Parallel(n_jobs=-1)(delayed(chunk_to_rdm)(chunk) for chunk in track(chunked_center))` followed by ```python for chunks, RDM_corr in zip(chunked_center, RDM_corrs): RDM[chunks, :] = RDM_corr.dissimilarities ``` I'd be happy to add these two changes (I have already added them locally to what I'm running, but this makes sharing my code with others harder), and would happily upstream them if it's considered useful.