I can't find "./Data/RAS_LOGS" mentioned by Quick Start in project files. Where did it come from？

[Millet-Sea]

And when I try to run the code ，it comes to an error：

(venv) E:\LogClass\LogClass-master>python -m logclass --train --kfold 3 --logs_type "bgl" --raw_logs "data/open_source_logs" --report macro

Experiment ID: 3077882225
-------------------------------------params-------------------------------------
Beginning experiment using the following configuration:

           report: ['macro']
            train: True
            force: False
         base_dir: E:\LogClass\LogClass-master\output
        logs_type: bgl
    healthy_label: unlabeled
         features: ['tfilf']
    binary_classifier: pu_learning
    multi_classifier: svm
             swap: False
         raw_logs: data\open_source_logs
            kfold: 3
             logs: E:\LogClass\LogClass-master\output\preprocessed_logs\bgl.txt
               id: 3077882225
           id_dir: E:\LogClass\LogClass-master\output\logclass_bgl_3077882225
       models_dir: E:\LogClass\LogClass-master\output\logclass_bgl_3077882225\models
     features_dir: E:\LogClass\LogClass-master\output\logclass_bgl_3077882225\features
      results_dir: E:\LogClass\LogClass-master\output\logclass_bgl_3077882225\results

---

Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "E:\LogClass\LogClass-master\logclass.py", line 199, in
main()
File "E:\LogClass\LogClass-master\logclass.py", line 188, in main
preprocess = preprocess_registry.get_preprocessor(params['logs_type'])
File "E:\LogClass\LogClass-master\preprocess\registry.py", line 20, in get_preprocessor
return _PREPROCESSORS[data_src]
KeyError: 'bgl'

Is there anything missing？

[yurypal]

I've had the same error and (as the trace suggests) this is because the preprocessor key is missing from the dictionary. I tracked this down to the __init__.py file that does not automatically execute... I found a quick workaround by simply inserting to the logclass.py the scripts that register the preprocessors.

from preprocess import bgl_preprocessor
from preprocess import open_source_logs

However, the are more hurdles along the way.. pity that this work is so difficult to reproduce.

[yurypal]

Regarding the RAS_LOGS. I found them here (from the reference in the README file).
Using this data and after quite a bit of tinkering, I finally got to run the example successfully.