Microsoft offers an anomaly detection service on Azure, documentation here.
Create a primitive to use their API and return anomalies as (start, end) intervals.
Input: timeseries, subscription key, endpoint
Output: anomalies
Two options present themselves here:
client.last_detect to detect if the last point in a window is anomalous.client.entire_detect to detect all the points in a window.To specify subscription key and endpoint, edit the pipeline json file.
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