Have you been importing and building your own custom algorithms into the Splunk Machine Learning Toolkit, but didn’t know how to share them with the rest of the community? Are you short on time for adding that extra algorithm you need for your use case and interested to know what other Splunkers are doing with the Splunk MLTK for the same scenario? Then check out our open source community on Github that lets you share your algorithms with other Splunk MLTK users or import one of the algorithms that have been shared by the community: mltk-algo-contrib.
What is Splunk MLTK Algorithms on GitHub?
- Splunk MLTK Algorithms on GitHub is an open source community around sharing and reusing machine learning algorithms built by customers and partners.
- Custom algorithms can be added to the community by following the ML-SPL API guidelines. These APIs are basically thin wrappers around machine learning estimators provided by libraries such as scikit-learn, statsmodels and scipy.
- The Splunk open source community is a helpful place where new and existing users of the Splunk Machine Learning Toolkit can see and share examples, raise issues or questions, and learn about new algorithms.
- Customers looking for solutions that are outside the Machine Learning Toolkit’s 80 odd algorithms can use the Github community to open the gates to more use cases and customization.
Customers looking for solutions that are outside the Splunk Machine Learning Toolkit’s 80-odd algorithms can use the Github community to open the gates to more use cases and customization.
How Do We Use It?
The GitHub repo has a readme file which gives you detailed instructions on dependencies, basic example and explains the process of adding new algorithms.
Splunk Enterprise and Splunk Cloud customers can leverage a new app, Splunk MLTK Algorithms on GitHub, which provides community-based algorithms that can be installed on a cloud environment (Splunk Cloud customers should create a support ticket to have this app installed by their Cloud Admin). Check out our "Splunk Community for MLTK Algorithms on GitHub" video for more details, and please refer to the .conf18 session video and slides to learn more about how to extend MLTK with GitHub.
And for an in-depth look at how to use the Splunk Machine Learning Toolkit, check out these webinars:
- Getting Started with Machine Learning
- Splunk's Machine Learning Toolkit: Technical Deep Dive and Demo Part 1
- Splunk's Machine Learning Toolkit: Technical Deep Dive and Demo Part 2
- Machine Learning in Action: Stop IT Events Before They Become Outages
Interested in trying out the Splunk Machine Learning Toolkit at your organization? Splunk offers FREE data science resources to help you get it up and running. Learn more about the Machine Learning Customer Advisory Program.