Oracle Machine Learning with R

Module 01:

• Overview of Oracle Machine Learning for R
• Oracle Machine Learning Notebooks
• Oracle Machine Learning: Key Attributes
• Oracle R Distribution
• Oracle Machine Learning for R: Installation Steps
• Practice I-I: Understanding the Lab Environment
• Practice 1-2: Connect to the R console
• Practice 1-3: Connect to RStudio Server
• Practice 1-4: Run the Sample Scripts

Module 02:

• OML4R Transparency Layer: Introduction
• Using ore.connect Function
• In-Database Sampling
• Ordering Framework Creating Ordered and Unordered ore.frame Objects
• Practice 2-1: Using the ore.connect Function
• Practice 2-2: Working with OML4R Transparency Layer
• Practice 2-3: Additional Transparency Layer Functions
• Practice 2-4: Working with ore.Frame Database Table Proxy Object
• Practice 2-5: Using Scale() and Transform() Functions
• Practice 2-6: Sampling Data
• Practice 2-7: Using the core.disconnect Function

Module 03: OML4R Transparency Layer: Create and Manage R Objects in Oracle Database

• Introduction to OML4R Transparency Layer
• ore.save() Function
• Create R Objects for In-Database Data
• Move Data to and from the Database
• Practice 3-1: Get Objects with ore.get Function
• Practice 3-2: Using ore.Create, ore.Push, and ore.Drop
• Practice 3-3: Create and Manage R Object in Oracle Database using R Data Store

Module 04: OML4R Transparency Layer: Data Preparation and Data Manipulation

• Introduction to OML4R Transparency Layer
• Using row indexing
• Exploratory Data Analysis Functions
• Using Third-Party Packages on the R Client
• Practice 4-1: Basic data manipulation using OREdplyr
• Practice 4-2: Stacking and Grouping using OREdplyr
• Practice 4-3: Chaining Using OREdplyr
• Practice 4-4: Implementing Rank Function using OREdplyr
• Practice 4-5: Aggregate the Column values using the OREdplyr
• Practice 4-6: Joining data using OREdplyr

Module 05: OML4R Embedded R Execution — R Interface

• Introduction to OML4R Embedded R Execution — R Interface
• User-Defined R Functions for Embedded R Execution
• Functionality of Automatic Connection
• Using the ore.doEval Function
• OML4R-Defined Graphics Function
• Practice 5-1: Using ore.doEval() with R Script Repository
• Practice 5-2: Using ore.table.Apply()
• Practice 5-3: Using Embedded R Execution Functions: ore.groupApply, ore.indexApply
• Practice 5-4: Best Practice Workflow for Developing Deployable User-Defined Functions

Module 06: OML4R Embedded R Execution — SQL Interface

• OML4R Embedded R Execution — SQL Interface
• SQL API for Oracle Machine Learning for R
• Returning R Statistical Results as a Database Table
• Manage User-Defined R Functions using the SQL Interface
• PL/SQL Procedures for Managing R Scripts and Datastores
• Practice 6-1: Build an 1m Model by using rqTable Eval()
• Practice 6-2: Score Data in Batch Mode Using rqTable Eval()
• Practice 6-3: Passing Arguments to User-Defined Functions using SQL API
• Practice 6-4: Using the SQL Datastore API
• Practice 6-5: Additional Code Samples

Module 07: Modeling in OML4R: Part 1

• Modeling in OML4R: Part I
• OREdm Package
• Feature Extraction – Explicit Semantic Analysis (ESA)
• Generalized Linear Models
• Clustering – K-Means
• Classification – Naive Bayes
• Feature Extraction Non-negative Matrix Factorization (NMF)
• Partitioned Models
• Practice 7-1: using Ore.odmGLM
• Practice 7-2: Using Ore_odmSVM
• Practice 7-3: using Ore_odmKMeans
• Practice 7-4: using Ore.odmAssocRules
• Practice 7-5: Using ERE Framework algorithms
• Practice 7-6: Identifying Frequently-Purchased Groceries

Module 08: Modeling in OML4R: Part 2

• Introduction
• Neural Networks
• Singular Value Decomposition
• Practice 8-1: using ore.glm Function
• Practice 8-2: Using ore.neural Function
• Practice 8-3: using ore.randomForest Function
• Practice 8-4: Usecase-Estimating Wine Quality

Module 09: Working with ROracle

• Introduction
• Connect to an extproc for Use within OML4R Embedded R Execution
• Read/Write Table Methods
• Practice 9-1: using the ROracle Interface

Module 10: OML4R Statistics Engine

• OML4R Statistics Engine
• ore_summary
• ore.rank
• ore.sort
• ore.corr
• ore.crosstab
• ore.freq
• ore.esm
• ore.univariate
• Practice 10-1: Working with OML4R Statistical Functions
• Practice 10-2: Using ore.summary Function
• Practice 10-3: Using ore.rank Function
• Practice 10-4: using ore.sort Function

Module 11: OML4R Best Practices

• Introduction
• Open Source Packages
• Machine Learning Interface: Benefits
• Explicitly Specifying Oracle Database Parallelism
• Embedded R Execution Initial Memory Management Considerations
• Datastore: Benefits
• Object Migration

Oracle Machine Learning with R Course Prerequisites:

• Proficiency in basic computer programming
• Knowledge of basic statistics concepts
• Familiarity with Oracle Database concepts and SQL
• Basic understanding of machine learning algorithms and models
• Prior exposure to R programming language
• Background in data manipulation and cleaning techniques.