Disclaimer

This article was created based on my personal notes with support from Microsoft Copilot. While Copilot assisted in structuring and refining the content, all technical details have been carefully reviewed and developed by me. Yep, the title image has a typo…thanks to the creativity of Copilot…life is sometimes imperfection 😜.

Thanks for the photo to Jason Leung on Unsplash .

After six months of steady learning—roughly 30 minutes a day, almost every workday—I’m proud to say I’ve officially earned my Data Analyst certification from DataCamp. 🎉 It’s been a ride full of stats, Python, and a few unexpected hiccups, but I made it through. And I want to share the story—not just to celebrate, but to reflect on why I did it, what I learned, and what’s next.

Why Data Analyst, Why Now?

As a BI Engineer with solid experience in SQL and Power BI, I’ve always been curious about expanding my analytical toolkit. A while back, I dipped my toes into a Data Scientist course, but quickly realized I was missing some foundational knowledge—especially in statistics. That attempt fizzled out, but the itch to learn remained.

Meanwhile, the data world kept buzzing about cloud tech. But here’s the thing: my current role is deeply rooted in on-premise infrastructure. Learning about cloud platforms like AWS or Azure felt more like chasing hype than building practical skills I could actually use. Plus, within the Experian group (where I worked until recently), SQL Server was more of a sidekick than a hero. Most data folks were working with Python, Spark, and Snowflake.

That’s when the Starship Programme caught my eye—a company-sponsored exchange where you get to work abroad for a few weeks on a real use case. Python and Data Analyst skills were a perfect match for the program’s requirements. Back in 2024, I didn’t apply. I was swamped with projects and honestly felt underqualified. But this year, I was ready… only to find out the program won’t run in 2025. And since August, my employer 3C is no longer part of Experian, so priorities have shifted anyway.

Still, I’m glad I stuck with the certification. I’d come so far—why stop now? And even within my current company (3C), Python has its place. For example, we’re planning to use Great Expectations Core for data quality monitoring. So yes, the skills are relevant.

Learning Curve: Stats vs. Code

Let’s be real: Python isn’t that hard if you’ve worked with languages like Java or PowerShell. My real challenge was the statistical theory—sampling, hypothesis testing, and the like. DataCamp did a great job breaking it down. The platform mixes theory with hands-on practice, daily quizzes, and real-world examples. In the timed exams for theory you get multiple-choice questions to test your understanding, and there’s enough time to think through your answers. If you’re stronger in one area, you can balance out weaker spots. That flexibility helped a lot.

The Certification Experience

The practical exam was based on a marketing campaign analysis for an office supply company. You had to clean and analyze the data, summarize your approach for the Head of Analytics, and record a video presentation with actionable recommendations. I loved that last part—recommendations are something I want to integrate more into my day-to-day work.

The exam was supposed to take 4–6 hours. I spent at least 12. But I learned a ton in the process.

Now, here’s the fun part: I failed the practical section on my first try. Every. Single. Time. 😅

For the Data Analyst Associate, I didn’t fully complete the task, and the auto-grading module ran twice by accident—instant fail. For the full Data Analyst cert, I took the exam while on vacation in Vietnam. A surprise power outage hit just as I was wrapping up, and I submitted in a rush.

The instructions said “no code please,” so I only wrote a summary in the Data Lab notebook. I couldn’t upload images due to company restrictions, so I linked them from OneDrive. Turns out, that wasn’t accepted. Fail again.

On the second attempt, after a few emails with DataCamp support, I discovered the dataset was embedded in the notebook, meaning I could run the Python code directly there. Also, pro tip: use the “Hide all Code” feature before publishing. It keeps your notebook clean and focused on the visuals, not the code cells.

If you fail, you have to wait 14 days to retake the exam—and redo the theory section too. Not ideal, but it gave me time to regroup.

Final Thoughts

If you’re in a similar spot—wondering whether to go for a certification, doubting your skills, or facing setbacks—don’t overthink it. Just start. Push through the challenges. Failing once doesn’t mean you’re not cut out for it. Technical glitches, confusing instructions, or even a power outage in Southeast Asia… it’s all part of the journey.

I’m proud of this milestone. Not just for the badge, but for the persistence it represents. And now, with Python and a stronger grasp of statistics in my toolkit, I’m excited to see where it takes me next.