Matrix profiling is a popular baseline for finding anomalies in time series. It works by computing the nearest neighbor of segments to one another. If the nearest neighbor to a particular segment is far, then it is considered as a possible anomaly.
The library stumpy has a useful implementation of matrix profiling using the method stump.
In addition, we need to use find_anomalies to find the threshold over the array of distances.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4