Skip to content
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
bin luminosity tweaks Apr 16, 2018
docs v1.2.11 Jan 17, 2019
etc v1.2.1-luminosity Jun 22, 2018
examples/data Merged the crucible branch and Panorama to master Jul 17, 2016
skyline Fix #86 Jan 17, 2019
tests nosec bandit Sep 13, 2017
updates/sql anomalous_datapoint greater than DECIMAL (2638) Oct 25, 2018
utils
.gitignore
.travis.yml
CHANGES.md
LICENSE Create proper formatted LICENSE Oct 10, 2018
LICENSE.md
dev-requirements.txt
docs-requirements.txt nosec bandit Sep 13, 2017
readme.md
readthedocs.yml
requirements.txt
setup.cfg tests setup Ionosphere v1.1.0-alpha Dec 11, 2016
setup.py
skyline.png Merged the crucible branch and Panorama to master Jul 17, 2016

readme.md

Skyline

Skyline is a near real time anomaly detection system, built to enable passive monitoring of hundreds of thousands of metrics, without the need to configure a model/thresholds for each one, as you might do with Nagios. It is designed to be used wherever there are a large quantity of high-resolution time series which need constant monitoring. Once a metrics stream is set up from Graphite, additional metrics are automatically added to Skyline for analysis. Skyline's easily extended algorithms attempt to automatically detect what it means for each metric to be anomalous. Once set up and running, Skyline allows the user to train it what is not anomalous on a per metric basis.

Improvements to the original Etsy Skyline

  • Improving the anomaly detection methodologies used in the 3-sigma context to vastly increase performance.
  • Extending Skyline's 3-sigma methodology to enable the operator and Skyline to handle seasonality in metrics.
  • The addition of an anomalies database for learning and root cause analysis.
  • Adding the ability for the operator to train Skyline and have Skyline learn things that are NOT anomalous using a time series similarities comparison method based on features extraction and comparison using the tsfresh package.
  • Adding the ability to Skyline to determine what other metrics are related to an anomaly event using cross correlation analysis of all the metrics using Linkedin's luminol library when an anomaly event is triggered and recording these in the database to assist in root cause analysis.

Documentation

Skyline documentation is available online at http://earthgecko-skyline.readthedocs.io/en/latest/

The documentation for your version is also viewable in a clone locally in your browser at file://<PATH_TO_YOUR_CLONE>/docs/_build/html/index.html and via the the Skyline Webapp frontend via the docs tab.

Other

https://gitter.im/earthgecko-skyline/Lobby

You can’t perform that action at this time.