Model Management and Execution - Developer Documentation
Skip to content

Model Management and Execution

This section describes what models are in Predictive Learning and the steps required to develop a model.

Also included in this section are descriptions and step-by-step instructions for:

  • Developing a New Model
  • Importing a Model
  • Actions You can Take with Models
  • Executing a Model
  • Advanced Docker Model Settings
  • Executing Models on a Schedule

About Models and Model Types

Model is a analytical script written in form of Jupyter notebook, Zeppelin Notebook or bundled into a docker image.

Model Types

The types of models you can create in PrL are:

  • JSON
  • XML
  • Text
  • Jupyter Notebook
  • Docker Image

Viewing Models

Click a Browse Models link on the Models landing page. The Models list page displays a table that lists information about the models you have access to. Each model's details are shown, as well as icons that allow you to perform various actions with models.

Note

Maximum file size for the model uploads are limited to 50 MB.

Actions You can take with Models

Action icons appear on the right side of the Models table. Some icons display only when you click the series of ellipses. Here are the actions you can take with models:

Opening a model—click the launch icon to open a model.

Ellipses—click the ellipses to view actions you can take, that include:

  • Deleting a model—displays an "Are you sure?" dialog to prevent unintended deletions.
  • Editing a model—displays a dialog in which you can change the name and description in a pop-up dialog, but you cannot change the model type.
  • Creating a version—select whether to create a minor or major version (major = 2.0; minor=1.1), set an expiration date and model type, and browse for a model to upload, up to 50MB.
  • Downloading a model—opens File Manager for saving the model to the location you specify.

Importing a Model

When importing an existing model, the process begins with the "Import a Model/Develop a New Model" pop-up Window:

ImportaModel

Follow these steps to import a model:

  1. Click "Add/Develop Model" on the Landing or Models list page. The Import/Develop a Model pop-up window displays.
  2. Make sure you are on the "Import a Model" tab.
  3. Enter a name and description (optional).
  4. Select an expiration date from the Calendar pop-up window.
  5. Select a model type from the Type drop-down list, or select "Browse" to locate and select a model file.
  6. Click "Save". Your imported model displays in the Models table.

Developing a New Model

When developing a model, the process begins with the "Import a Model/Develop a New Model" pop-up Window:

DevelopNewModel

Follow these steps to develop a new model:

  1. Click "Add/Develop Model" on the Landing or Models page. The Import/Develop a Model pop-up window displays.
  2. Make sure you are on the "Develop a New Model" tab.
  3. Select an environment from the drop-down list and click "Start".
  4. When the environment configuration displays a "Running' status, click the arrow icon. Your environment configuration opens in Jupyter Notebook.

Executing a Model

Executing a model involves running an analytical model against source data in a specific environment. Sometimes this is called "running a job" in Predictive Learning.

To run a basic PrL job you need to configure:

  • Input—source (location) from which PrL reads the data for the job
  • Output—location to which PrL writes the job results data
  • Model—the mathematical model that runs against the input data
  • Environment—start and stop environments for running jobs

How to Execute a PrL Model

Follow these steps to execute your model:

  1. Click "Add Job" in Quick Actions.
  2. Enter a name and an optional description.
  3. Select a model from the drop-down list.
  4. Select an Environment Configuration from the drop-down list.
  5. Select a data source for Input and Output.
  6. If you want to schedule the job to run, see "How to Add a Schedule to a Job" below, before you click the "Add Job" button.
  7. Click "Add Job".

Executing Models on a Schedule

PrL jobs can be run ad-hoc or you can schedule them to run for a specific amount of time. If you want to run your job on a schedule, you have to set it up while you are creating the job.

How to Add a Schedule to a Model Job

The "Enable Scheduling" toggle is located at the bottom of the "Add a Job" page.

Follow these steps to add a schedule to a job that you create:

  1. Slide the Enable Scheduling toggle to the right.
  2. Enter a number in the Days to run field.
  3. Select a time increment from the drop-down list.
  4. Click "Add Schedule".

Advanced Docker Model Settings

When using Docker models, you can also customize the model using these additional settings:

  • External reference IDs
  • Start Command
  • Maximum Run Hours
  • Environment Variables (key/value pairs)
  • Entry Point
  • Scheduling

How to Add Advanced Settings to a Docker Job

With the exception of the Maximum Run Hours field, all of the advanced option fields are optional. Follow these steps to add advanced options to a job:

  1. Click "Advanced Details".
  2. Enter an optional external reference ID.
  3. Click the icon in the Environment Variables field to add Key / Value pairs in the pop-up window.
  4. Click "OK".
  5. Enter a Start Command and Entry point.
  6. Enter a number in the Maximum Run Hours field.
  7. Click "Add Job".

Except where otherwise noted, content on this site is licensed under the Development License Agreement.

Last update: May 22, 2023