Managing Big Data with R and Hadoop (FutureLearn)

Those with basic knowledge in statistical learning and R will better understand the methods behind and how to run them in parallel using map-reduce functions and Hadoop data storage. At the end of the course you will get access to RHadoop on a supercomputer at University of Ljubljana.

Syllabus

Week 1: Welcome to BIG DATA
Week 2: Working with Hadoop
Week 3: First steps in R and RHadoop
Week 4: Statistical learning with RHadoop: clustering
Week 5: Statistical learning with RHadoop: regression and classification

By the end of the course, you will:

• Explore basic functionality of Apache Hadoop and of RHadoop
• Experiment how to achieve performance of modern supercomputing
• Experiment regression, clustering and classification with RHadoop
• Investigate basic functionality of Bash terminal window
• Knowledge about statistical learning to instances of data provided by edcators
• How to do big data management with RHadoop on real supercomputer provided by Universiy of Ljubljana

Who is the course for?
This course is designed for people interested in data science, computational statistics and machine learning and have basic experiences with them. It will be also useful for advanced undergraduate students and first year PhD students in data analysis, statistics or bioinformatics, who wish to understand how to manage big data with Hadoop using R programming language.
We expect that the learners will also have basic experiences with linux and bash and working experiences with R and matrix operations. They should be also capable to download and run virtual machine.