databio / bedboss

Python pipeline for processing BED files for BEDbase
https://docs.bedbase.org
BSD 2-Clause "Simplified" License
1 stars 0 forks source link

Dev bedclassifier script #67

Closed donaldcampbelljr closed 3 months ago

donaldcampbelljr commented 3 months ago
donaldcampbelljr commented 3 months ago

More work towards #60

The major modification to the pipeline:

The script I added for testing runs separately from the main pipeline and should not impact performance.

Most recent testing added to PEP: https://pephub.databio.org/donaldcampbelljr/bedclassifier_tuning_geo?tag=default ~95% accuracy on classification for bed files for n=1567 bedfiles

donaldcampbelljr commented 3 months ago

We chatted about the above and agreed to merge the changes since only exceptions were added to main pipeline and everything else (such as the BedClassifier Class) are self contained