Data set is missing

[xiatian815]

Define input time-series feather files for the two datasets

UCLA_CNP_input_time_series_data = pd.read_feather('data/input_data/UCLA_CNP_AROMA_2P_GMR_fMRI_TS.feather')
ABIDE_input_time_series_data = pd.read_feather('data/input_data/ABIDE_FC1000_fMRI_TS.feather')
These two files do not exist after the data you provided is downloaded.

[anniegbryant]

Hi @xiatian815, thanks for the interest in our repo and for taking the time to raise this issue! You are correct that those two files were not included in this GitHub repository as they are both >100MB in size. Instead, we have included these files (as well as any/all others needed to replicate our analyses) in a corresponding Zenodo repository: https://zenodo.org/records/10431855

I bolded this part of the readme now so that hopefully it is clearer to readers going forward. Hope this helps -- let us know if you run into any other issues!

[xiatian815]

Hello, these two data files are still not included in the downloaded compressed package. Are they generated by preprocessing?

[anniegbryant]

Ah, thank you for the screenshot @xiatian815 -- that helped me realize that I forgot to update the file names in the extract_time_series_features.ipynb notebook. I've fixed these in the latest commit . Sorry for the oversight and thank you for bringing this to our attention!