Azure Data Scientist Associate Certification Guide

Develop the skills you need to run machine learning workloads in Azure and take the DP-100 exam with confidence

Key Features

• Create end-to-end machine learning training pipelines, with or without code
• Track experiment progress using the cloud-based, MLflow compatible process of Azure ML services
• Operationalize your machine learning models by creating batch and real-time endpoints

Book Description

An Azure data scientist is someone who applies their machine learning and data science knowledge to run ML workloads on Azure. This book helps you to acquire practical knowledge for your data science projects and covers everything you need to pass the DP-100 exam and become a certified Azure data scientist.

The book begins with a short introduction to data science, teaching you how to deploy an Azure ML workspace and showing you the overall components that are available in the workspace. You'll then find out how to run data science experiments by using web designers and wizards provided in Azure ML Studio. As you progress, you'll explore the Azure ML software development kit (SDK) for Python and learn how to create experiments and publish models using code. You will also discover how to embed the application performance monitoring (APM) tool into the deployed inference service endpoints and leverage the labeling project capabilities of Azure ML services to label images for computer-vision-based algorithm.

By the end of this Azure book, you'll be able to plan for and create a suitable working environment for data science workloads on Azure, run data experiments and train predictive models, manage and optimize models, and deploy machine learning models to production.

What you will learn

• Provision a working environment for data science workloads in Azure
• Run data experiments and train models using Azure ML services
• Use hyperparameter tuning to optimize trained models
• Deploy and test consuming models in production
• Monitor and interpret productionized models
• Perform classification, regression, and time series forecasting with the AutoML wizard

Who This Book Is For

This book is for developers or data scientists looking for ways to scale their machine learning experiments in Azure cloud. Basic knowledge of Python is needed to follow the code samples present in the book. Some experience in training machine learning models in Python with common frameworks like scikit-learn will help you understand the content more easily.

Table of Contents

1. An Overview of Modern Data Science
2. Deploying Azure Machine Learning Workspace Resources
3. Azure Machine Learning Studio Components
4. Configuring the Workspace
5. Letting the Machines Do the Model Training
6. Visual Model Training and Publishing
7. The AzureML Python SDK
8. Experimenting with Python Code
9. Optimizing the ML Model
10. Interpreting Model Results
11. Working with Pipelines
12. Operationalizing Models with Code