Log Anomaly Detection - Machine learning to detect abnormal events logs
.. image:: https://api.travis-ci.org/aicoe/log-anomaly-detector.png?branch=master :target: http://travis-ci.org/aicoe/log-anomaly-detector .. image:: https://img.shields.io/pypi/v/log-anomaly-detector.svg :target: https://pypi.python.org/pypi/log-anomaly-detector/ .. image:: https://img.shields.io/pypi/dm/log-anomaly-detector.svg :target: https://pypi.python.org/pypi/log-anomaly-detector/ .. image:: https://img.shields.io/pypi/wheel/log-anomaly-detector.svg :target: https://pypi.python.org/pypi/log-anomaly-detector/ :alt: Wheel Status .. image:: https://readthedocs.org/projects/log-anomaly-detector/badge/?version=latest :target: https://log-anomaly-detector.readthedocs.io/en/latest/
Log anomaly detector is an open source project code named "Project Scorpio". LAD is also used for short. It can connect to streaming sources and produce predictions of abnormal log lines. Internally it uses unsupervised machine learning. We incorporate a number of machine learning models to achieve this result. In addition it includes a human in the loop feedback system.
.. image:: imgs/full-app.gif
The original goal for this project was to develop an automated means of notifying users when problems occur with their applications based on the information contained in their application logs. Unfortunately logs are full of messages that contain warnings or even errors that are safe to ignore, so simple “find-keyword” methods are insufficient . In addition, the number of logs are increasing constantly and no human will, or can, monitor them all. In short, our original aim was to employ natural language processing tools for text encoding and machine learning methods for automated anomaly detection, in an effort to construct a tool that could help developers perform root cause analysis more quickly on failing applications by highlighting the logs most likely to provide insight into the problem or to generate an alert if an application starts to produce a high frequency of anomalous logs.
It currently contains the following components:
.. image:: imgs/components.png
$ pip install log-anomaly-detector
...Or simply add it to your requirements.
LAD requires python 3.6
Official documentation for LAD can be found at https://log-anomaly-detector.readthedocs.io/en/latest
For help or questions about Log Anomaly Detector usage (e.g. "how do I do X?") then you can open an issue and mark it as question. One of our engineers would be glad to answer.
To report a bug, file a documentation issue, or submit a feature request, please open a GitHub issue.
For release announcements and other discussions, please subscribe to our mailing list (
Major updates will be presented at our AiOps special interest group meeting which is a part of openshift commons
OpenShift Commons AiOps Sig Calendar:
We happily welcome contributions to LAD. Please see our contribution guide for details.