Open dwr-psandhu opened 8 months ago
An anomaly detector is a just a function that takes named args and returns a boolean series or dataframe with True indicating anomaly. You don't need to append columns or anything like that. Eventually I may re-add things like "and" and "or" as in ADTK, although complex rules haven't proven useful so far. I would look at the inputs and outputs of something simple in vtools error_detect.py and also look at the yaml config file.
This is available in sklearn and I am adding it with a test and function. Could you review it and see if this is a right way to add a outlier detection function.