"ValueError: window must be non-negative" raised during Extract and Embed features part

[frr665]

Hi,

I'm new on B-SOID and I ran across the following error message while trying to extract and embed features :

ValueError: window must be non-negative
Traceback:
File "c:\users\x\anaconda3\envs\bsoid_v2\lib\site-packages\streamlit\script_runner.py", line 332, in _run_script
    exec(code, module.__dict__)
File "C:\Users\x\B-SOID\bsoid_app.py", line 46, in <module>
    extractor.main()
File "C:\Users\x\B-SOID\bsoid_app\extract_features.py", line 192, in main
    self.compute()
File "C:\Users\x\B-SOID\bsoid_app\extract_features.py", line 84, in compute
    disp_boxcar.append(boxcar_center(disp_r[:, l], window))
File "C:\Users\x\B-SOID\bsoid_app\bsoid_utilities\likelihoodprocessing.py", line 16, in boxcar_center
    moving_avg = np.array(a1.rolling(window=n, min_periods=1, center=True).mean())
File "c:\users\x\anaconda3\envs\bsoid_v2\lib\site-packages\pandas\core\generic.py", line 10551, in rolling
    closed=closed,
File "c:\users\x\anaconda3\envs\bsoid_v2\lib\site-packages\pandas\core\window\rolling.py", line 169, in __init__
    self.validate()
File "c:\users\x\anaconda3\envs\bsoid_v2\lib\site-packages\pandas\core\window\rolling.py", line 1965, in validate
    raise ValueError("window must be non-negative")

I had no issue during the preprocessing part. I used tracking data in .h5 format from SLEAP 1.3.0. pose estimation software. I tried with data from 10fps and 25fps videos and had the same error message. Does anyone have an idea on what went wrong and how to fix it ?

Thanks a lot, Hugo

I have attached a package list of the anaconda environment I used if you want to check it : package-list.txt