Book Image

Data Analytics Made Easy

By : Andrea De Mauro
4 (1)
Book Image

Data Analytics Made Easy

4 (1)
By: Andrea De Mauro

Overview of this book

Data Analytics Made Easy is an accessible beginner’s guide for anyone working with data. The book interweaves four key elements: Data visualizations and storytelling – Tired of people not listening to you and ignoring your results? Don’t worry; chapters 7 and 8 show you how to enhance your presentations and engage with your managers and co-workers. Learn to create focused content with a well-structured story behind it to captivate your audience. Automating your data workflows – Improve your productivity by automating your data analysis. This book introduces you to the open-source platform, KNIME Analytics Platform. You’ll see how to use this no-code and free-to-use software to create a KNIME workflow of your data processes just by clicking and dragging components. Machine learning – Data Analytics Made Easy describes popular machine learning approaches in a simplified and visual way before implementing these machine learning models using KNIME. You’ll not only be able to understand data scientists’ machine learning models; you’ll be able to challenge them and build your own. Creating interactive dashboards – Follow the book’s simple methodology to create professional-looking dashboards using Microsoft Power BI, giving users the capability to slice and dice data and drill down into the results.
Table of Contents (14 chapters)
And now?
Other Books You May Enjoy

What this book covers

The path I have prepared for you alternates two types of content. Some chapters equip you with the unmissable foundations of data analytics—things like the basics of statistical learning, model validation, and data visualization principles. Other chapters provide practical guides on how to get things done on your computer—like step-by-step tutorials on building a dashboard in Power BI or automating data crunching with KNIME. The two types of content are complementary and organized according to the following structure:

Chapter 1,What is Data Analytics?, paves the way for our journey together. This chapter equips you with the proper terminology and provides a few frameworks (such as the three types of analytics, the data technology stack, the matrix of data job roles and skills, and the data-to-value paths), offering you some broader perspective on the true business potential of data and algorithms.

Chapter 2, Getting Started with KNIME, initiates you to KNIME and shows you how visual programming works by going through a few hands-on examples. The chapter includes the first tutorial of the book, in which you will create a routine for automating the clean-up of some consumer-generated data.

Chapter 3, Transforming Data, introduces the concept of the data model and shows you how to apply systematic transformations to datasets and make them fully usable for analytics. You will learn how to combine tables, aggregate values, apply loops, and use variables. In the tutorial, you will build a workflow for creating some simple automated financial reports starting from raw transactional data.

Chapter 4, What is Machine Learning?, separates the myth from the reality of intelligent machines able to autonomously learn from data. This chapter gives you the foundations of machine learning (like the taxonomy of available algorithms, how to validate models, and how to assess their accuracy) and lets you start identifying ways for AI to impact your actual work.

Chapter 5, Applying Machine Learning at Work, puts in practice what you will have learned in the former chapter. Its three practical tutorials will let you experience what real-world machine learning is all about. You will feel the excitement of predicting real estate rental prices in Rome, anticipating the reaction of consumers in front of a bank marketing campaign, and segment customers of an online retailer. By following the tutorials, you will build your own "templates" of predictive machines that you can then adapt as needed to your specific business needs.

Chapter 6, Getting Started with Power BI, prepares you to face an ever-present, primary need: building effective dashboards that "democratize" access to data and insights. In the tutorial, you will build a fully operating management dashboard in Power BI, including preparing the underlying data model and creating links across charts to drive interactivity.

Chapter 7, Visualizing Data Effectively, explains how to build professional-looking data visualizations that transfer business insights. The chapter will give you a framework for selecting the correct type of chart according to your business need and a set of visual design guidelines ensuring that your business messages come across crisp, loud, and clear.

Chapter 8, Telling Stories with Data, trains you to systematically prepare and deliver data stories that drive business action. Starting from the basic principles of persuasion, this chapter will teach you several techniques for making your data-based points as compelling as possible. The chapter will leave you with a structured template (the Data Storytelling Canvas) that you can keep on your desk and use when needed.

Chapter 9, Extending Your Toolbox, lets you catch a glimpse of what's beyond the tools and techniques included in the previous chapters so that you can plan ahead for your next development steps. The chapter contains hands-on, guided demonstrations of Tableau, Python (including its integration with KNIME), and for automated machine learning. Reading this concluding chapter will prove the general value of the broad set of skills you will have acquired by completing this journey.