yzhao062 / pyod

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
http://pyod.readthedocs.io
BSD 2-Clause "Simplified" License
8.27k stars 1.35k forks source link

TOS selection methods and parameter #543

Open Jak253 opened 5 months ago

Jak253 commented 5 months ago

In the XGBOD Paper and the dedicated XGBOD Github Repo there was a parameter "p" for the selection of the TOS. I cant find it in the PyOD implementation, neither the selection methods as described in the paper (random, accurate, balanced). Does the current implementation append every TOS to the original feature space?