AnomalyDetection
AnomalyDetection copied to clipboard
twitter
Anomaly Detection with R
Hey, just wanted to let you know there are now versions of AnomalyDetection in [Rust](https://github.com/ankane/AnomalyDetection.rs) and [Ruby](https://github.com/ankane/AnomalyDetection.rb). Thanks for this library!
The date of the data I have is the monthly data from January 2010, February 2010 to December 2019. I want to use AnomalyDetectionVec to find anomaly for the data....
The parameters use_decomp and use_esd are not used in the implementation of function detect_anoms, I don't know why do you keep them. Can anyone explain for me?
I was assigned with project to do anomaly detection on for all our company KPIs. I googled and found AnomalyDetection by Twitter. There was an idea from my colleague to...
Error: Failed to install 'AnomalyDetection' from GitHub: (converted from warning) cannot remove prior installation of package ‘Rcpp’ Which version of R is supported?
This is a renewed pull request for the 'millisecond' precision fixes. I added a fix for the delta_sigma bug to the previous branch but it appears somebody else beat me...
There seems to be an unnecessary use of eval for timestamp aggregation. This patch uses the sum function directly. The other changes are just removal of unnecessary trailing whitespace.
> after granulation from sec to min, assign 'min' so the switch instruction can now work properly This fixes cases when we have time series with granulation in seconds, tested...
data_sigma might be NA which breaks the == check. Fixes issue #58 Fixes issue #57
