MPP On-Demand: Implementing Predictive Solutions with Spark in HDInsight (DAT202.3x) Course Outline
*** Note: This is an On-Demand Self Study Class ***
You can take this class at any time; there are no set dates. It features hands-on labs so you can practice new skills at your workstation. Other parts of the course include video lectures that you can view on-the-go from your phone or tablet. In all cases, customers must call us directly to register this class at 800-288-8221.
MPP On-Demand Series
This course is part of the Microsoft Professional Program Series, MPP: Data Science Track and MPP: Big Data Track. It can be taken individually or as part of either 9-course series, plus a capstone project. You will need to purchase a validated certificate to get credit for this class as part of the MPP. Request the certificate at time of registration.
On-Demand Learner Profiles
MPP On-Demand is a self-study training solution that was designed for two types of learners. First, MPP On-Demand is a great fit for experienced IT professionals who don't need traditional 5-day classes to upgrade their existing skills. They can pick and choose topics to make the most effective use of their time. Second, MPP On-Demand is perfect for highly-motivated individuals who are new to a technology and need to space their learning over a period of weeks or months. These learners can take their time and repeat sections as needed until they master the new concepts.
Verified Certificate Included!
If you plan to use your course for job applications, promotions, or school applications, an MPP certificate will help you get recognized. The certificate is verifiable and is included in all MPP purchases. Its also a great way to give yourself an incentive to complete the course and celebrate your success. For more information regarding Verified Certificates, go to
MPP Verified Certificates
This course is part of the Microsoft Professional Program Certificate in Big Data.
The open-source programming language R has for a long time been popular (particularly in academia) for data processing and statistical analysis. Among R's strengths are that it's a succinct programming language and has an extensive repository of third party libraries for performing all kinds of analyses. Together, these two features make it possible for a data scientist to very quickly go from raw data to summaries, charts, and even full-blown reports. However, one deficiency with R is that traditionally it uses a lot of memory, both because it needs to load a copy of the data in its entirety as a data.frame object, and also because processing the data often involves making further copies (sometimes referred to as copy-on-modify). This is one of the reasons R has been more reluctantly received by industry compared to academia.
The main component of Microsoft R Server (MRS) is the RevoScaleR package, which is an R library that offers a set of functionalities for processing large datasets without having to load them all at once in the memory. RevoScaleR offers a rich set of distributed statistical and machine learning algorithms, which get added to over time. Finally, RevoScaleR also offers a mechanism by which we can take code that we developed on our laptop and deploy it on a remote server such as SQL Server or Spark (where the infrastructure is very different under the hood), with minimal effort.
In this course, we will show you how to use MRS to run an analysis on a large dataset and provide some examples of how to deploy it on a Spark cluster or a SQL Server database. Upon completion, you will know how to use R for big-data problems.
Since RevoScaleR is an R package, we assume that the course participants are familiar with R. A solid understanding of R data structures (vectors, matrices, lists, data frames, environments) is required. For example, students should be able to confidently tell the difference between a list and a data frame, or what each object is generally a good representation for and how to subset it. Students should be familiar with basic programming concepts such as control flows, loops, functions and scope. Students should have a good understanding of how to write and debug R functions. Finally, students are expected to have a good understanding of data manipulation and data processing in R (e.g. functions such as merge, transform, subset, cbind, rbind, lapply, apply). Familiarity with 3rd party packages such as dplyr is also helpful.
Approximately 4 weeks assuming 2 to 4 hours of effort per week.
What you'll learn
You will learn how to use MRS to read, process, and analyze large datasets including:
Read data from flat files into Rs data frame object, investigate the structure of the dataset and make corrections, and store prepared datasets for later use
Prepare and transform the data
Calculate essential summary statistics, do crosstabulation, write your own summary functions, and visualize data with the ggplot2 package
Build predictive models, evaluate and compare models, and generate predictions on new data
View outline in Word