Implementing the Data Science Workflow in Microsoft Azure

Paths

Implementing the Data Science Workflow in Microsoft Azure

Authors: Jared Rhodes, Neeraj Kumar, Xavier Morera, Saravanan Dhandapani, Tim Warner

Microsoft Azure contains a massive offering of services that can be used together to implement the data science workflow. This path walks you through this workflow, as it is... Read more

What you will learn

  • Source, clean, and prepare data using Microsoft Azure
  • Implement feature selection using Microsoft Azure
  • Build models and evaluate their effectiveness in Microsoft Azure
  • Use Microsoft Azure services to deploy and manage your model
  • Communicate results to the business using the Microsoft Azure platform

Pre-requisites

This path is intended for experienced data scientists interested in understanding how their everyday workflows are enabled by Microsoft Azure. It is expected that the learner understand basic data science principles, such as data munging and cleaning, model selection and implementation, and data communication.

Beginner

In this section of the path, learners will work through data sourcing and preparation. In addition, the features of Microsoft Azure that help with data exploration are highlighted.

Building Your First Data Science Project in Microsoft Azure

by Jared Rhodes

Jun 19, 2020 / 1h 25m

1h 25m

Start Course
Description

The past five years have shown a boom in the data science field with advancements in hardware and cloud computing. In this course, Building Your First Data Science Project in Microsoft Azure, you will learn about data science and how to get started utilizing it in Microsoft Azure. First, you will learn the data science and the tools surrounding it. Next, you will discover how to create a development environment in Microsoft Azure. Finally, you will explore how to maintain and utilize that development environment. When you are finished with this course, you will have the skills and knowledge of data science to build your first data science project in Microsoft Azure. Software required: Microsoft Azure

Table of contents
  1. Course Overview
  2. Determining Which Tools to Use
  3. Setting up a Development Environment
  4. Using the New Development Environment

Sourcing Data in Microsoft Azure

by Jared Rhodes

Dec 11, 2019 / 1h 12m

1h 12m

Start Course
Description

The cloud has nearly infinite compute power for processing. In this course, Sourcing Data in Microsoft Azure, you'll learn foundational knowledge of data types, data policy, and finding data. First, you'll learn how to register data sources with Azure Data Catalog. Next, you'll discover how to extract, transform, and load data with Azure Data Factory. Finally, you'll explore how to set up data processing with Azure HD Insight. When you're finished with this course, you'll have the skills and knowledge of the tools and processes needed to source data in Microsoft Azure. Software required: Microsoft Azure portal.

Table of contents
  1. Course Overview
  2. Identifying Potential Data Sources
  3. Extracting and Loading Data into an Azure Workflow

Cleaning and Preparing Data in Microsoft Azure

by Jared Rhodes

Dec 16, 2019 / 1h 7m

1h 7m

Start Course
Description

No data science project of merit has ever started with great data ready to plug into an algorithm. In this course, Cleaning and Preparing Data in Microsoft Azure, you'll learn foundational knowledge of the steps required to utilize data in a machine learning project. First, you'll discover different types of data and languages. Next, you'll learn about managing large data sets and handling bad data. Finally, you'll explore how to utilize Azure Notebooks. When you're finished with this course, you'll have the skills and knowledge of preparing data needed for use in Microsoft Azure. Software required: Microsoft Azure.

Table of contents
  1. Course Overview
  2. Transforming Data into Usable Datasets
  3. Wrangling Data

Exploring Data in Microsoft Azure Using Kusto Query Language and Azure Data Explorer

by Neeraj Kumar

Sep 12, 2019 / 2h 45m

2h 45m

Start Course
Description

Businesses around the world are making huge investments in data analytics to be able to make critical decisions for steering growth and remain competitive. Data science is the ability to capture and process raw data, and then analyze, visualize, and communicate the processed information as insights to the stakeholders that brings in the value by enabling businesses in making critical decisions. In this course, Exploring Data in Microsoft Azure Using Kusto Query Language and Azure Data Explorer, you will use Azure Data Explorer to perform data exploration services. First, you will familiarize yourself with data exploration service in Azure. Next, you will learn how to build the Azure Data Explorer environment from Azure Portal as well as using PowerShell and CLI. Then, you will discover how to use the Kusto Query Language to perform time series analysis, followed by how data ingestion is performed using EventHubs and EventGrids. Finally, you will explore how to manage Data Explorer cluster performance and database permissions. When you’re finished with this course, you will have all the necessary skills and confidence to take your organization to the next level as a data scientist.

Table of contents
  1. Course Overview
  2. Azure Data Explorer (ADX) Overview
  3. Building the ADX Environment
  4. Using the Kusto Query Language (KQL)
  5. Data Ingestion for ADX
  6. Managing Azure Data Explorer

Intermediate

These courses will inform learners on selecting and extracting features using Microsoft Azure services, then building models that consume those features and evaluating their validity.

Feature Selection and Extraction in Microsoft Azure

by Xavier Morera

Dec 12, 2019 / 1h 27m

1h 27m

Start Course
Description

It is no secret that Data Scientists spend a very large proportion of their time preparing data. In this course, Feature Selection and Extraction in Microsoft Azure, you'll gain the ability to prepare your data for use in your machine learning models. First, you'll learn how to extract features from raw data, including non-text formats. Next, you'll discover how to normalize features, converting your data to a common scale without distorting your data. Finally, you'll explore how to select those features that are more relevant to your model. When you're finished with this course, you'll have the skills and knowledge of feature extraction, normalization, and selection needed to prepare your data. Software required: Azure ML Studio classic.

Table of contents
  1. Course Overview
  2. Exploring Your Dataset for Feature Selection and Extraction
  3. Performing Feature Extraction
  4. Performing Feature Normalization
  5. Performing Feature Selection
  6. Final Takeaway

Developing Models in Microsoft Azure

by Saravanan Dhandapani

Dec 16, 2019 / 1h 55m

1h 55m

Start Course
Description

Many developers struggle with the time and effort it takes in designing and developing a highly optimal machine learning model. In this course, Developing Models in Microsoft Azure, you will learn the foundational knowledge of machine learning solutions offered by Microsoft Azure. First, you will understand the basics of setting up workspaces, creating blobstore, and making and registering datasets. Next, you will explore how to create an experiment and submit the run on a compute target provided by Microsoft Azure. Finally, you will explore how to tune hyperparameters and use automated machine learning models, allowing for the development of models without writing a single line of code. When you are finished with this course, you will have the skills and knowledge on the various cutting edge features offered by Microsoft Azure Machine Learning service that are necessary in developing a machine learning model.

Table of contents
  1. Course Overview
  2. Understanding Azure Machine Learning service
  3. Import and Prepare Data for Modeling
  4. Training, Tracking, and Monitoring a Model
  5. Tuning Hyperparameters and AutoML

Evaluating Model Effectiveness in Microsoft Azure

by Tim Warner

Dec 19, 2019 / 50m

50m

Start Course
Description

Data science and machine learning professionals work tirelessly to improve the quality of their ML models. In this course, Evaluating Model Effectiveness in Microsoft Azure, you will learn how to use Azure Machine Learning Studio to improve your models. First, you will learn how to evaluate model effectiveness in Azure. Next, you will discover how to improve model performance by eliminating overfitting and implementing ensembling. Finally, you will explore how to assess ML model interpretability. When you are finished with this course, you will have the skills and knowledge of Azure Machine Learning needed to ensure your ML models are consistent, accurate, and explainable.

Table of contents
  1. Course Overview
  2. Evaluating Model Effectiveness
  3. Improving Model Performance
  4. Assessing Model Explainability

Advanced

In this final segment of the path, learners will deploy and manage their models in the Microsoft Azure platform, and learn how to use features of the platform to communicate data insights with others.

Deploying and Managing Models in Microsoft Azure

by Jared Rhodes

Dec 4, 2019 / 59m

59m

Start Course
Description

One of the most overlooked processes in data science is managing the life cycle of models. In this course, Deploying and Managing Models in Microsoft Azure, you'll gain foundational knowledge of Azure Machine Learning. First, you'll discover how to create and utilize Azure Machine Learning. Next, you'll find out how to integrate with Azure DevOps. Finally, you'll explore how to utilize them together to automate the deployment and management of models. When you're finished with this course, you'll have the skills and knowledge of model life cycle management needed to manage a machine learning project. Software required: Microsoft Azure.

Table of contents
  1. Course Overview
  2. Deploying a Machine Learning Model
  3. Using Continuous Integration and Continuous Deployment
  4. Managing a Model's Lifecycle

Communicating Insights from Microsoft Azure to the Business

by Neeraj Kumar

Dec 12, 2019 / 2h 18m

2h 18m

Start Course
Description

There is currently a paradigm shift happening in the way organizations are doing business. They need tools to help them get expository insights from the plethora of sources, including their own historical data. This helps them make crucial business decisions at the right moment in order to grow their business or to meet the current and future business requirements. In this course, Communicating Insights from Microsoft Azure to the Business, you will gain the ability to utilize machine learning and artificial intelligence to uncover meaningful insights from data that can be used by business owners to make critical decisions. First, you will learn about data science and how to use the Azure Data Science services to perform data analysis on a large volume of data. Then, you will explore Azure Databricks and how to utilize features like Event Hubs, Data Lake Storage, and what you can glean from an exploratory analysis using these tools. Finally, you will discover how to communicate critical insights to the business from Microsoft Azure using tools like Power BI and MatPlotLib. By the end of this course, you will be confident in taking up Azure Data Science projects for your organization as a skilled data scientist and help your organization grow by providing knowledge business insights to the stakeholders and enable them to take critical decisions.

Table of contents
  1. Course Overview
  2. Setting the Stage
  3. Working with Azure Databricks
  4. Model Evaluation and Summarizing Results
  5. Reviewing Results with Stakeholders