DP-100: Designing and Implementing a Data Science Solution on Azure
About this Course
Data Scientist is the central role in developing machine learning models. This role is responsible for solving the business problem that initiated the project. While the Data Engineer will prepare the data to be used for the models, the Data Scientist determines what data is needed for model training, creates model features from the data, determines what machine learning model to use, trains and evaluates the model, and often has involvement in model deployment. Often the data scientist needs to evaluate multiple models to determine which performs the best.
Gain the necessary knowledge about how to use Azure services to develop, train, and deploy, machine learning solutions. The course starts with an overview of Azure services that support data science. From there, it focuses on using Azure’s premier data science service, Azure Machine Learning service, to automate the data science pipeline. This course is focused on Azure and does not teach the student how to do data science. It is assumed students already know that.
Audience Profile
This course is aimed at data scientists and those with significant responsibilities in training and deploying machine learning models.
At Course Completion
Outline
Module 1: Doing Data Science on Azure
The student will learn about the data science process and the role of the data scientist. This is then applied to understand how Azure services can support and augment the data science process.
Lessons
- Introduce the Data Science Process
- Overview of Azure Data Science Options
- Introduce Azure Notebooks
Module 2: Doing Data Science with Azure Machine Learning service
The student will learn how to use Azure Machine Learning service to automate the data science process end to end.
Lessons
- Introduce Azure Machine Learning (AML) service
- Register and deploy ML models with AML service
Module 3: Automate Machine Learning with Azure Machine Learning service
In this module, the student will learn about the machine learning pipeline and how the Azure Machine Learning service's AutoML and HyperDrive can automate some of the laborious parts of it.
Lessons
- Automate Machine Learning Model Selection
- Automate Hyperparameter Tuning with HyperDrive
Module 4: Manage and Monitor Machine Learning Models with the Azure Machine Learning service
In this module, the student will learn how to automatically manage and monitor machine learning models in the Azure Machine Learning service.
Lessons
- Manage and Monitor Machine Learning Models
Prerequisites
- Azure Fundamentals
- Understanding of data science including how to prepare data, train models, and evaluate competing models to select the best one.
- How to program in the Python programming language and use the Python libraries: pandas, scikit-learn, matplotlib, and seaborn.