Welcome to the Operationalizing Solutions with Azure Data Factory (ADF), delivered by your Microsoft Data Science team. In this workshop, you'll cover how ADF can be used to incorporate machine learning into your data workflows. This allows your data to be used for predictive purposes and not just historical reporting.
Lab and Course materials are available at: LearnAnalytics-ADF-ML-student.zip
This video series and accompanying lab is designed to take approximately 2-3 hours. All materials are provided for follow-on self-study.
Prerequisites
There are a few things you will need in order to properly follow the course materials:
- There are a few things you need prior to coming to class:
- Experience and an understanding of ADF (similar to what would be covered in the Cortana Intelligence Suite Workshop)
- Experience using Azure ML (similar to what would be covered in the Cortana Intelligence Suite Workshop)
- A subscription to Microsoft Azure (this may be provided through your company or as part of your invitation – you must have this enabled prior to class – you will be using Azure throughout the course, for all labs, work, and exercises).
- You can sign up for a free account here (but don't use it until the class starts, and don't sign up more than a week in advance of the class) – https://azure.microsoft.com/en-us/pricing/freetrial/
- Or you can use your MSDN subscription – https://azure.microsoft.com/en-us/pricing/memberoffers/msdn-benefits/
- Your employer may provide Azure resources to you, but make sure you check to see if you can deploy assets and that they know you'll be using their subscription in the class.
- If you would also like to work with some of the tools locally (you still need an Azure subscription for this class), you can optionally obtain:
- A laptop that you can install software on
- Visual Studio installed – the Community Edition (free) is acceptable – Version 2015 preferable ( https://www.visualstudio.com/en-us/products/visual-studio-community-vs.aspx ) - RStudio is also allowed, but not covered.
- It's also a good idea to have a general level of predictive and classification Statistics, and a basic understanding of Machine Learning. A brief overview of these technologies is covered for the concepts presented.
Concepts Covered
- What is ADF?
- The ADF Process
- How can a traditional data workflow become predictive?
Technologies Covered
- Azure Storage
- Azure ML
- Azure Data Factory
Skills Taught
At the end of the course you will have acquired the following skills:
- Sourcing Data from Azure Storage and other locations
- Converting an Azure ML experiment into a production-level API
- Call machine learning models as part of the ADF pipeline
- Storing results to Azure Storage and other locations
