Introduction

This guide describes how to use the ML-SPL API to import an algorithm for use in the Splunk Machine Learning Toolkit. The ML-SPL API has been refactored as of the 2.2.0 release to make it easier for developers to import algorithms. This API documentation applies to the Splunk Machine Learning Toolkit version 2.2.0 or later. Verify your Splunk Machine Learning Toolkit version before using this API.

The Splunk Machine Learning Toolkit contains 30 algorithms natively. (See the Algorithms section in the Splunk Machine Learning Toolkit User Guide for information about the algorithms packaged with the Splunk Machine Learning Toolkit.) You can extend the Splunk Machine Learning Toolkit with over 300 open source Python algorithms from scikit-learn, pandas, statsmodel, numpy, and scipy libraries. These open source algorithms are available to the Splunk Machine Learning Toolkit through the Python for Scientific Computing add-on.

You may also package your custom algorithm as a separate app to share on Splunkbase so that other Splunk Machine Learning Toolkit users can use it.

Coding is required to import an algorithm into the Splunk Machine Learning Toolkit, therefore development experience is necessary.