1 About Oracle Machine Learning for R

Oracle Machine Learning for R (OML4R), a component of Oracle Machine Learning on Oracle Database and Oracle Autonomous Database, makes the open-source R scripting language and environment ready for enterprise data. Oracle Machine Learning for R provides a database-centric environment for end-to-end analytical processes using R. OML4R contains functional areas, including the Transparency Layer, Embedded Execution, and In-Database Models.

Note:

OML4R in previous releases was named Oracle R Enterprise; this is why its API uses the "ore" prefix.

• Transparency Layer
  In the Transparency Layer, users run overloaded R functions within their R environment. These functions generate SQL query that run directly in the database. This is achieved through the use of data.frame proxy tables and views in the R environment, which map to tables and views in the database.
• In-Database Machine Learning Algorithms
  OML4R offers a natural R API for using in-database algorithms with the R Formula specification. These algorithms support classification, regression, clustering, attribute importance, anomaly detection, association rules, time series analysis, and feature extraction. Key features of in-database algorithms include automatic, algorithm-specific data preparation, partitioned model ensembles, and integrated text mining.
• Embedded R Execution
  Embedded R Execution enables users to run User-defined functions (UDFs) R functions using R engines spawned by the database environment. This feature provides functions that automate the process of loading database data into R functions and allows for the return of both structured and unstructured results, including images. Users can store and manage their R functions in the database script repository.