New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
method = "gesd" from the function anomalize() seems to not support very low variance data #12
Comments
Ah good catch. Maybe there should be some sort of small value ( |
Ditto. Here is a
|
For anyone facing this issue while doing feature engineering, until it gets fixed you can use |
Preconditions:
I am currently exploring for anomalies a grouped tibble with 3932 groups.
The following data may be used to reproduce the group within which I get an issue.
Code for reproducibility:
Expected result:
A time tibble classifying each observation as either an anomaly or not.
Actual result:
I believe the error is the result of almost all remainders' being equal to 0. Consequently, the mean absolute deviation is equal to 0 and the following line of the
gesd
function yields either Inf or NaN (dividing by 0).A way of handling this event should be included where outliers are being identified.
The text was updated successfully, but these errors were encountered: