Data Engineers are the backbone of data..

Data Science Nugget 🧽

When was the last time you had cake? 

Pretty recent, right?

We all enjoy cake occasionally but often overlook one important aspect: the ingredients. 

To bake a cake, you need wheat, sugar, eggs, etc., all farmers produce.

So, the cake you eat is a product of the farmers' hard work. They grow it, water it, fight off plant diseases, and endure sleepless nights to provide bakers with the ingredients needed to bake a cake.

Yet, we often focus on the cake itself, ignoring the hard work behind it.

You might be wondering what cake has to do with data.

Bear with me.

Just as we often overlook the cake's ingredients, businesses sometimes neglect the vital role of data engineers and only appreciate data scientists.

Do you see where I’m going with this?

Data engineers handle the hard work behind the scenes. They ensure data scientists have access to clean, organized databases to analyze data and inform business decisions.

But they don’t get enough recognition for all the work that they do.

I posted this picture a couple of days ago and this sums it up best.

So what exactly do Data Engineers do?

They have these 3 key tasks:

1. Build Data Infrastructure: Create and maintain systems for collecting, storing, and processing data, ensuring data flows smoothly and is accessible.

2. Ensure Data Quality: Implement processes to clean and validate data, ensuring it is accurate and reliable for analysis.

3. Support Data-Driven Decisions: Provide the foundation for data analysis by making sure data is well-organized and available, enabling data scientists and analysts to generate insights that inform business decisions.

They ensure data is efficiently collected, stored, processed, and made accessible for analysis and decision-making.

In summary, data engineers lay the groundwork for data-driven businesses to operate effectively.

Interesting Dataset for Practice 📊

Video Game Sales Dataset

This dataset contains a list of video games with sales greater than 100,000 copies.

Project Ideas:

1) Correlation Analysis: Calculate the correlation between Global_Sales and sales in each region. Create a heatmap to visualize these correlations.

2) Market Share Analysis: Calculate the market share (percentage of total sales) for the top 5 publishers. Create a stacked area chart to show how market share has changed over time.

3) Sales trend analysis: Analyze how global sales trends have changed over the years. Identify which genres have grown or declined in popularity. Examine the relationship between release year and sales in different regions.

Q&A Section 🙋

A member of the Data Science Master Mind Group recently asked me:

"Today, I reviewed job descriptions from top product companies and noticed a preference for Tableau over PowerBI. I have some knowledge of PowerBI. Should I switch to Tableau, or can I stick with PowerBI?"

In my opinion, both are great tools.

Power BI has good integration with the Microsoft ecosystem (Like PowerApps)

Whereas Tableau is a very intuitive platform with great drag-and-drop features.

Rather than switching, I would suggest practicing the basics of both tools and mastering one of the tools.

Dashboard designing aspects are the same, only the calculation parts are different when it comes to Power BI and Tableau.

The pain point would be doing advanced calculations in the new tool. And this needs you to dedicate some time to figuring things out.

Whenever you're ready, there are 3 ways I can help you:

1. Data Science Study Plan: My well-researched and thought-out collection of study plans for Excel, SQL, Python, Power BI, and Tableau to help you learn the essential tools for Data Science.

2. Power BI Design Mastery: Helps you learn and improve the UI and UX of Power BI Dashboards and Reports.

3. Data Analysis for ChatGPT: Helps you explore the integration of ChatGPT into the world of data analysis.

-Sasi