README.md

DP-100: Designing and Implementing a Data Science Solution on Azure

Course Labs

Welcome to the hands-on lab exercises for course DP-100 Designing and Implementing a Data Science Solution on Azure. The labs are designed to accompany the course and enable you to practice using the technologies described in the classroom materials.

You should complete the labs in order, following the instructions in each Markdown document carefully.

The labs require a Microsoft Azure subscription. If your instructor has not provided you with one, you can sign up for a free trial at https://azure.microsoft.com.

Tip: As you work through the labs, you may experience unexpected issues due to idiosyncratic browser settings, network configurations, and so on. We've documented a few common issues in the Tips document that may help. You can also view known issues for these labs.

Module 1: Introduction to Azure Machine Learning

• Lab 1A: Creating an Azure Machine Learning Workspace
• Lab 1B: Working with Azure Machine Learning Tools

Module 2: "No-code" Machine Learning with Designer

• Lab 2A: Creating a Training Pipeline with the Azure ML Designer
• Lab 2B: Deploying a Service with the Azure ML Designer

Module 3: Running Experiments and Training Models

• Lab 3A: Running Experiments
• Lab 3B: Training and Registering Models

Module 4: Working with Data

• Lab 4A: Working with Datastores
• Lab 4B: Working with Datasets

Module 5: Compute Contexts

• Lab 5A: Working with Environments
• Lab 5B: Working with Compute Targets

Module 6: Orchestrating Operations with Pipelines

• Lab 6A: Creating a Pipeline
• Lab 6B: Publishing a Pipeline

Module 7: Deploying and Consuming Models

• Lab 7A: Creating a Real-time Inferencing Service
• Lab 7B: Creating a Batch Inferencing Service

Module 8: Training Optimal Models

• Lab 8A: Tuning Hyperparameters
• Lab 8B: Using Automated Machine Learning

Module 9: Interpreting Models

• Lab 9A: Reviewing Automated Machine Learning Explanations
• Lab 9B: Interpreting Models

Module 10: Monitoring Models

• Lab 10A: Monitoring a Model with Application Insights
• Lab 10B: Monitoring Data Drift

Important: Remember to stop any virtual machines used in these labs when you no longer need them - this will minimize the Azure credit incurred for these services. When you have completed all of the labs, consider deleting the resource group you created if you don't plan to experiment with it any further.

Contributions

At this time, we are not accepting external contributions to this repo. If you have suggestions or spot any errors, please report them as issues.