Azure Machine Learning Hands-on Labs

Last update: Oct 17, 2017

In this post I will provide information on Azure Machine Learning (ML) Hands-on Labs training for developers, which we will be delivering in New York and other technology centers. After this training you will know how to create Azure Machine Learning experiment, select best ML model, convert the training experiment to a predictive experiment, and create application which will use the model.

The training consists of following labs.

  1. Predict Individual’s Income >50K (Estimated: 1 hour).
  2. Convert a training experiment into a predictive experiment in Azure ML by Mostafa Elzoghbi (Estimated: 30 minutes).
  3. Consume an Azure ML web service using Visual Studio 2015 by Mostafa Elzoghbi (Estimated: 30 minutes).
  4. Flight delay prediction by Todd Kitta. (Estimated: 3 hours) Start from Task 2. This model can be reused later in a separate Cortana Intelligence Suite End-to-End Training.

If you need more detailed instructions for self-placed training, you may also use Hands-on Labs from edX courses (videos with theory and quizzes are included).

  1. DAT203.1x Data Science Essentials
  2. DAT203.2x Principles of Machine Learning
  3. DAT203.3x Applied Machine Learning

Prerequisites

Please install the below software:

  • Activate your Azure account and bring your Microsoft account credentials. Don’t have a Microsoft account? Sign up now.
  • If you do not have Microsoft Azure account, activate a free 30-day trial Microsoft Azure account, or if you subscribe to MSDN, activate your free Azure MSDN subscriber benefits.
  • Preferred OS is Windows 10.
  • Make sure that Visual Studio 2015 Community, Pro, or Enterprise is installed. Make sure that Office 2013 or later is installed. (Optional; alternatively, you may use Windows Data Science virtual machine in Azure).
  • Create Azure ML workspace for free by signing up here.

Additional resources:

  1. Azure Machine Learning (ML)
  2. Cortana Intelligence Suite: Big Data and Advanced Analytics
  3. Big Data Presentation Deck
  4. Azure ML Data Camp Deck
  5. Detailed Azure ML Hands-on-Labs

Next Steps:

  1. Cortana Intelligence Suite End-to-End Training (Using the Flight Delay Prediction model in Azure-based solution).
  2. Data Science with Microsoft R Hands-on Labs (Different ways of using R language).

Data Science with Microsoft R Hands-on Labs

In this post I will provide list of most important publically available Data Science with Microsoft R Hands-on Labs which we use in MTC New York for Microsoft R workshops.

To start doing labs provided below it’s a good idea to have a general level of predictive and classification Statistics, and a basic understanding of Machine Learning and Open R language. (For this you may use DAT204x Introduction to R for Data Science, DAT209x Programming in R for Data Science and other courses from Microsoft Data Science specialization).

Microsoft R Hands-on Labs

  1. Exploring SQL Server 2016 R Services and Microsoft R Client with R Tools for Visual Studio. (3 hours; manual is available, all necessary tools and files are included; uses New York Taxi dataset; when you see “Times Squire” in the code, change it to “New York” and save)
  2. MTC Microsoft R training by Jarek Kazmierczak. (1-2 hours; contains source file and R scripts)
  3. edX: DAT213x Analyzing Big Data with Microsoft R Server by Seth Mottaghinejad. (16 hours; contains videos, scripts; you may also earn Microsoft certificate; uses New York Taxi dataset; please let me know if you experience any issues with ggplot2 and ggrepel).
  4. Flight delay prediction with Azure ML (90 minutes; exercise 1 from Cortana Intelligence Suite End-to-End Training by Todd Kitta)
  5. Text Mining with R with Azure ML by Seayoung Rhee. (1 hour)
  6. edX. DAT203.1x Data Science Essentials
  7. edX. DAT203.2x Principles of Machine Learning
  8. edX. DAT203.3x Applied Machine Learning
  9. HDInsight Spark MLib (placeholder)
  10. Cognitive Toolkit (CNTK) Deep Dive and Hands-on (tutorial; video).

Here is one of screenshots from the first (highly recommended) training based on New York Taxi dataset.

sqlrserviceslabnyc

Prerequisites to use Data Science Virtual Machine

The Data Science Virtual Machine has all of the tools you will need to work with the materials. You will need Microsoft Azure subscription for this.

  1. To use subscription to Microsoft Azure you can sign up for a free account here or you can use your MSDN subscription.
  2. To create the Data Science Virtual Machine in Azure please login to Azure Portal and create the virtual machine. (New -> Search for “data science” -> select “Data Science Virtual Machine” -> Create).
  3. Optionally you may test your Microsoft R code on top of HDInsight Spark cluster created in Azure Portal.

Prerequisites to use your local machine

If you would like to work with some of the tools locally, please install following components.

  1. Visual Studio – the Community Edition (free) is acceptable – Version 2015 preferable.
  2. Install R Tools for Visual Studio.
  3. Optionally you may use RStudio.
  4. Optionally you may install SQL Server Developer Edition for SQL Server related content.

Additional materials