Deployment

Once you have a fully built model container, deploying it as a REST service so you can serve predictions on the web is as simple as calling model$predict on your incoming stream of single row data points representing customers, leads, emails, or whatever else you were modeling for.

The current release of the modeling engine does not include deployment tools out-of-the-box, but it should be straightforward for any engineering teams to build some using HTTP server packages like microserver or Rserve.

See the Syberia roadmap to learn when deployment tools will be released into the modeling engine (or beat us to the punch!).

Next Steps

• Summary and review

• Introduction
• An example
• Additional resources
• Download and Setup
  • Troubleshooting
• Basic Usage
• Modeling 101
  • The Basic Modeling Cycle
  • The Four Stages
• Mungebits
  • The Basic Mungebit
  • Testing Mungebits
  • Advanced Mungebits
• Stagerunner
  • The Execution Cycle
  • A Simple Stagerunner
  • More Complicated Runners
  • The Modeling Engine
  • Re-running Stages
  • The Modeling Cycle
• Model Objects
  • The Tundra Container
  • Serialization of Model Objects
  • Constructing Model Objects
  • Help From Modeling Engine
  • Appendix: Model Deflation
  • Appendix: Custom Serializers
• Managing Large Projects
  • Modeling Engine Conventions
  • The Base Engine
  • Basic Director Object
  • Preprocessors and Parsers
  • Additional Functionality
• Testing
  • Defining Tests
  • Testing Models
  • Appendix: Test Configuration
  • Appendix: Continuous Integration
• Deployment
• Summary and Review
  • The Modeling Engine
  • The Base Engine
  • The Modeling Grammar
  • Mungebits
• Roadmap