rr
1e85d5f3e2
Added a conda environment.yaml file for running the project on the cluster.
2025-09-01 12:18:04 +02:00
bs
316a7f0343
Added new evaluation method
2025-08-12 08:43:33 +02:00
bs
dbbdcd0078
Changed requirement for windows, added percentage splitting methods
2025-08-05 16:57:29 +02:00
rr
ffc010aaf6
Commented out the warning printout
2025-07-28 15:34:08 +02:00
rr
85022f9fcc
Added a main for the model training and evaluation. The code from the jupyter notebook has been split up into functions in pipeline.py. User input has been removed and instead replaced with function arguments, to change at the start of main.py.
2025-07-28 15:30:27 +02:00
rr
b5794122c1
Trasnfered the jupyter notebook code to a .py file, no changes made yet. Don't execute, will probably make one unhappy.
2025-07-24 11:17:23 +02:00
rr
bfb3f6fd9d
Added the original dataset files and preprocessing jupyter notebook i was provided
2025-07-24 11:04:58 +02:00
rr
dad9b33fe8
Created a requirements.txt, using python 3.11.13
2025-07-24 10:48:43 +02:00
rr
bf73e4b8b8
Created a file with the non jupyter version of the code.
...
Moved all imports to the top as well as all function definitions.
Changed the paths to work with relative paths within the repo.
Otherwise the code is unchanged.
2025-07-19 18:16:41 +02:00
rr
edcb0a0e2b
Test push + file to put all the code from the notebook in
2025-07-16 16:48:22 +02:00
rr
43867979ef
Added the dataset files as well as the original jupyter notebook and the provided instructions.
2025-07-16 16:38:03 +02:00
rr
150a36e9c2
Initial commit
2025-07-16 15:02:04 +02:00
rr
bs