Navigating your journey into Data Analytics

It’s been a while I made a post here, and as a comeback, I’ll try to answer a question I’ve been asked a lot in the past year: “How do I navigate my journey into data analytics?”

I shared in a previous post how I would approach this. First, understand the big picture. Then focus on a sub-discipline. And finally, build stuff.

The aim of this post—assuming you’ve decided on a sub-discipline to focus on—is to share some resources to get you started. These are not exhaustive. Just the minimum to get you started. You can always discover more resources as you get along on your learning journey.

Before going on to the resources, I’ll summarise the different sub-disciplines. To explain this, I have borrowed an image from Monica Rogati’s?The AI Hierarchy of Needs?and added my interpretation of where the sub-disciplines come in. Please note that, depending on who you ask, the responsibility of each sub-discipline would vary. If you were to look at two openings for a data engineer, chances are the roles will have different responsibilities. For simplicity, I’ve deliberately not used the term “data science” as a sub-discipline.

Common skill(s)

• Learn SQL: You’ll interact with SQL in whichever sub-discipline you choose. So it’s a must-have skill. There are many good SQL courses out there, but you can check out this free SQL tutorial from Code Academy.
• Learn Python: This is a nice-to-have if you’ve chosen the data visualisation sub-discipline, but a must-have for data engineering and machine learning. Check out this Python course by Jose Portilla.

Data visualisation/Business intelligence/Data analysis

• Learn a data visualisation tool. Tableau or Power BI would be okay. Again, you can take any of the many good courses out there. I always recommend this Tableau course by Kirill Eremenko because it is what I started with.
• Learn data visualisation design best practices. Building effective data visualisations often require a lot of attention to details such as knowing your audience, what message you intend to pass across, best chart types to use, colour palettes, etc. Here are four good books that cover effective techniques for visual best practices: The Visual Display of Quantitative Information (2nd Edition) by Edward Tufte, Data Visualization: A Successful Design Process by Andy Kirk, The Functional Art: An Introduction to Information Graphics and Visualization by Alberto Cairo, and Storytelling with Data: A Data Visualization Guide for Business Professionals by Cole Nussbaumer Knaflic

Data Engineering

• Learn data modeling. The go-to resource for data modelling is Kimball’s Data Warehouse Toolkit book. While the way we model data is changing, it’s still a good book to read. Here is a good guide on how to read the book.
• Learn how to build a data pipeline. This course covers some of the many tools you can use in building a pipeline.

Machine learning

My experience in this area is rudimentary, having never directly applied it in my previous roles. However, I can point you to some good resources. Check out this machine learning course by Stanford University to get started. Another good resource is the Fundamentals of Machine Learning for Predictive Data Analytics book.

Knowing what resources to consume is not enough. You should have a personal roadmap. I have shared in a previous post the importance of having a personal roadmap. A roadmap helps you stay consistent and focused. Without one, you may end up in a never-ending cycle of taking courses and not moving to the next step in your journey, which could be getting your next job or applying your knowledge gained to current or upcoming projects. Your Best Year Ever by Michael Hyaat is a good resource for designing a personal roadmap.

Feel free to drop a comment if you have a question.