Machine Learning Toolkit version dependencies

The Machine Learning Toolkit (MLTK) releases updates on a regular schedule. Keep your instance of the MLTK and affiliated add-ons up-to-date to access the latest features.

• For a list view of features included by release version, see What's new in the Machine Learning Toolkit.
• For installation information including links to Splunkbase for required add-ons, see Upgrade the Machine Learning Toolkit.

Upgrading to version 5.3.0 of the MLTK requires the retraining of any old models.

About the PSC add-on

MLTK requires installation of the Python for Scientific Computing (PSC) add-on. Version 3.0.0 of the PSC add-on brings updates to several libraries in the package. In particular, Numpy, Scipy, scikit-learn, Statsmodels, and Networkx are upgraded to their latest available versions.

On November 16, 2021 version 3.0.1 of the Python for Scientific Computing (PSC) add-on was released. This version is limited to configuration updates for deployment on Splunk Cloud Platform.

If you have any custom algorithms that rely on the PSC libraries, upgrading the PSC add-on will impact those algorithms. You must re-train any models (re-run the search that used the fit command) using those algorithms after you upgrade the PSC add-on.

Versions 2.0.2 and 2.0.1 of the PSC add-on are limited to minor library upgrades from version 2.0.0. There are no differences in functionality to version 2.0.0 of the PSC add-on.

Version matrix

You can use the following table to ensure you are using the correct combination of MLTK, the PSC add-on, Python, and Splunk Enterprise:

MLTK version	PSC add-on version	Python version	Splunk Enterprise version	Notes
5.3.0	3.0.0 or 3.0.1 required	3	8.0.x, 8.1.x, or 8.2.0	This version of the MLTK requires version 3.0.0 or 3.0.1 of the PSC add-on. Users upgrading to this version must retrain models created in earlier versions of the MLTK.
5.2.2	2.0.0, 2.0.1, or 2.0.2	3	8.0.x, 8.1.x, or 8.2.0	This version of the MLTK is limited to a minor enhancement.
5.2.1	2.0.0, 2.0.1, or 2.0.2	3	8.0.x, 8.1.x, or 8.2.0	This version of the MLTK is limited to a minor enhancement.
5.2.0	2.0.0, 2.0.1, or 2.0.2	3	8.0.x, 8.1.x, or 8.2.0	This version of the MLTK is available with Splunk Enterprise version 8.0.x, 8.1.x, or 8.2.0.
5.1.0	2.0.0, 2.0.1, or 2.0.2	3	8.0.x or 8.1.x	This version of the MLTK is available with Splunk Enterprise version 8.0.x or 8.1.x.
5.0.0	2.0.0, 2.0.1, or 2.0.2	3	8.0.x or 8.1.x	This version of the MLTK is only available with Splunk Enterprise version 8.0.x or 8.1.x. Users upgrading to this version must retrain models created in earlier versions of the MLTK. The file extension for models has changed from .csv to .mlmodel.
4.5.0	1.4	2.x	7.x	This version includes all the features of version 5.0.0 barring the support of the random_state parameter of the DensityFunction anomaly detection algorithm. Models created in earlier versions of the MLTK maintain compatibility and do not require retraining.
4.4.2	1.4 or 1.3	2.x	7.x	No new features from version 4.4.1. PSC version 1.4 recommended.
4.4.1	1.4 or 1.3	2.x	7.x	PSC version 1.4 recommended.
4.4.0	1.4 or 1.3	2.x	7.x	PSC version 1.4 recommended.