Splunk Machine Learning Toolkit

Overview

Details

Splunk Machine Learning Toolkit

The Splunk Machine Learning Toolkit App delivers new SPL commands, custom visualizations, assistants, and examples to explore a variety of ml concepts.

Each assistant includes end-to-end examples with datasets, plus the ability to apply the visualizations and SPL commands to your own data. You can inspect the assistant panels and underlying code to see how it all works.

Look for our ML Youtube Playlist for simple explanations of how to use MLTK and what it is for..

ML Cheat Sheet https://docs.splunk.com/images/3/3f/Splunk-MLTK-QuickRefGuide-2019-web.pdf

Assistants:
* Predict Numeric Fields (Linear Regression): e.g. predict median house values.
* Predict Categorical Fields (Logistic Regression): e.g. predict customer churn.
* Detect Numeric Outliers (distribution statistics): e.g. detect outliers in IT Ops data.
* Detect Categorical Outliers (probabilistic measures): e.g. detect outliers in diabetes patient records.
* Forecast Time Series: e.g. forecast data center growth and capacity planning.
* Cluster Numeric Events: e.g. Cluster Hard Drives by SMART Metrics

Smart Assistants (new assistants with revamped UI and better ml pipeline/experiment management):
*Smart Forecasting Assistant (provides enhanced time-series analysis for users with little to no SPL knowledge and leverages the StateSpaceForecasting algorithm): e.g. forecasting app logons with special days

Available on both on-premise and cloud.

Splunk App for Data Science and Deep Learning
The Splunk App for Data Science and Deep Learning (DSDL), formerly known as the Deep Learning Toolkit (DLTK), lets you integrate advanced custom machine learning and deep learning systems with the Splunk platform. The app extends the Splunk Machine Learning Toolkit (MLTK) with prebuilt Docker containers for TensorFlow, PyTorch, and a collection of data science, NLP, and classical machine learning libraries. When you use the predefined workflows of Jupyter Lab Notebooks, the app enables you to build, test, and operationalize customized models with the Splunk platform. You can leverage GPUs for compute-intense training tasks and deploy models on CPU or GPU enabled containers.

Splunk Community for MLTK Algorithms on GitHub
Check out our Open Source community on Github that lets you share your algorithms with the community of Splunk MLTK users or import one of the algorithms that have been shared by the community: https://github.com/splunk/mltk-algo-contrib

The GitHub repo algorithms are also available as an app which provides access to custom algorithms. Cloud customers can use GitHub algorithms via this app and need to create a support ticket to have this installed:https://splunkbase.splunk.com/app/4403/
Available on cloud and on-premise

For the Splunk Machine Learning Toolkit documention, see: http://docs.splunk.com/Documentation/MLApp/latest.

Datasets

This application may contain certain sample files and datasets, which are provided for your convenience only. Such files and datasets contain information and data compiled by third parties, and Splunk makes no representation or warranty that the data contained in such files and datasets are true, accurate, complete or sanitized.

Requirements

You must install the Python for Scientific Computing Add-on before installing the Machine Learning Toolkit. Please download and install the appropriate version here:

Mac: https://splunkbase.splunk.com/app/2881/
Linux 64-bit: https://splunkbase.splunk.com/app/2882/
Windows 64-bit: https://splunkbase.splunk.com/app/2883/

Installation

To install an app within Splunk Enterprise:

Log into Splunk Enterprise.
Next to the Apps menu, click the Manage Apps icon.
Click Install app from file.
In the Upload app dialog box, click Choose File.
Locate the .tar.gz or .tar file you just downloaded, then click Open or Choose.
Click Upload.

Release Notes

Version 5.4.0

Feb. 23, 2023

This new version of MLTK enables users to upload their pre-trained ONNX models in MLTK with a simple UI. Once the model is in Splunk, users can use the model with their Splunk data with no modification to their existing workflows.
This capability extends the usability of MLTK and ML-SPL beyond models trained using MLTK. Users can now take advantage of a wider range of libraries for training their models, such as TensorFlow, PyTorch, Keras, Matlab, among others.
This version also extends the anomaly detection capabilities of MLTK by adding multivariate outlier detection with the addition of a new algorithm: MultivariateOutlierDetection.
MLTK 5.4.0 requires PSC 4.1 to be installed. It is not backward compatible with PSC 4.0 or lower.
Minor bug fixes are included as well.

Version 5.3.3

Aug. 11, 2022

This MLTK version does not include any new features, and addresses bug fixes only.
The Classic tab of MLTK app is now removed from the MLTK app. The features of Classic tab are already available in the Experiments tab.
Version 4.0.0 of the PSC add-on is supported by MLTK 5.3.3 on Splunk 8.1.x, 8.2.x and Splunk 9.0.0.
Internet Explorer browser is no longer supported with MLTK 5.3.3 due to the browser’s retirement by Microsoft.

Version 5.3.1

Jan. 12, 2022

This release of Splunk Machine Learning Toolkit (MLTK) contains minor changes and bug fixes to bring compatibility with Python for Scientific Computing (PSC) version 3.0.2.
- A new parameter of exclude_dist is available for the Density Function algorithm. Use this parameter when dist=auto to exclude a minimum of 1 and a maximum of 3 of the available distribution types (norm, expon, gaussian_kde, beta). For more information, see Density Function.
- The streaming_apply feature has now been removed, after deprecation in version 5.0.
- Users upgrading to MLTK version 5.3.0 or higher must retrain models created in lower versions of MLTK.

Version 5.3.0

Sept. 14, 2021

This release of Splunk Machine Learning Toolkit (MLTK) contains changes to bring compatibility with Python for Scientific Computing (PSC) version 3.0.0 and above. Therefore, this version of MLTK is only compatible with PSC 3.0.0 and later.

Note that models created in MLTK version 5.2.2 and earlier are not compatible with this version of MLTK (version 5.3.0) and after. Therefore, if you are upgrading to this version of MLTK, you must also re-create your existing MLTK models.

Version 5.2.2

July 15, 2021

Version 5.2.2
Features and improvements:
There are no new features in MLTK version 5.2.2. A few bug fixes and improvements are included in this release.
This version of MLTK replaces jQuery2 with jQuery3 to address vulnerability issues of jQuery2.
To confirm you are using a compatible version of the MLTK, see the Machine Learning Toolkit version dependencies matrix.

196,091

Downloads

Share Subscribe

Version

Built by

Splunk Inc.

Support

Splunk Supported Questions on Splunk Answers File a case Flag as inappropriate

App Contents: Visualizations