Using the Machine Learning Toolkit and Showcase app

The Machine Learning Toolkit and Showcase app provides the following features:

• Search command extensions that have been added to the Splunk Search Processing Language (SPL) to perform machine learning analytics on data such as fitting and applying a model, along with commands to list, summarize, and delete learned models. For details, see Search commands for machine learning.
• Custom visualizations, which are reusable visualizations for viewing and analyzing data in a particular format. For details, see Custom visualizations.
• Assistants, which are dashboards that guide you through the machine learning workflow. Each assistant features a different algorithm to fit and apply a model, with custom visualizations to help you interpret the results.
• A Showcase of examples that display different sample datasets in the assistants for you to explore machine-learning concepts. Each example prepopulates an assistant to demonstrate how to perform different types of machine learning analysis and prediction using best practices.

Explore the Showcase examples

If you want to jump right in and explore, go to the Showcase page and open the examples, organized by type of analytic. Each example uses a sample dataset to demonstrate aspects of machine learning. By default all examples are displayed, but you can filter them by use case:

• IT
• Security
• Business
• Internet of things

When you click an example, the corresponding assistant is then populated with dataset options that correspond to the analytic.

For more about each example, see Showcase examples.

About the assistants

The assistants in the Machine Learning Toolkit and Showcase app are there for you to use with your own data. In each assistant, perform a lookup on a dataset, then follow the work flow to select fields to predict and fit the model.

Each assistant contains the following sections that vary depending on the type of machine learning analytic being performed:

• Create or Detect: Follow the work flow laid out in the assistant to create a new model or forecast or detect outliers. The work flow depends on the type of analyatic but usually includes performing a lookup on a dataset, selecting a field to predict or analyze, and selecting fields or values to use for performing different types of analysis.
• Load Existing Settings: The assistants keep a history of the settings you use each time you use an assistant, so you can view and compare the results of each attempt to use the settings from more successful configurations.
• Raw Data Preview: This section is displayed for predictions and forecasts to show you the data that is being used.
• Validate: Use the tables and visualizations to determine how well the model was fitted, how well outliers were detected, or how well a forecast performed.
• Deploy: Click these customized search queries to open the Search page to see different ways to use the analysis. You can also use some of these queries to create alerts.
• Show Source Code: Inspect the dashboard panels and view the XML and JavaScript source code in each assistant to see how it all works and then create custom dashboards to suit your needs.

For details about the assistants, see:

• Predict Numeric Fields
• Predict Categorical Fields
• Detect Numeric Outliers
• Detect Categorical Outliers
• Forecast Time Series

To view the source code for the entire app, see $SPLUNK_HOME/etc/apps/Splunk_ML_Toolkit:

Subdirectory	Description
/appserver/static and /bin	Contains the underlying code files (Python, JavaScript, CSS, and images).
/default	Contains configuration and dashboard files.
/lookup	Contains the sample datasets used in the Showcase examples, along with more information about the datasets and their licenses.
/models	Contains the learned models.