Before we begin
If you’ve found yourself here, we probably have something in common.
Perhaps you’ve realised that there is more to data science than writing code or chasing the latest fashionable tools.
Perhaps you’ve also grown a little tired of the constant buzz around AI.
What I often miss when I read about data science are the decisions behind the analysis. Where were the data found? How were they curated? Why were they transformed this way?
Why is that? The process of solving problems can be messy -and certainly not linear- but it’s also the most exciting part. So why are the most interesting parts of the journey so rarely discussed?
I don’t know the answer. But I suspect I’m not the only person who would rather read about how data scientists actually get their hands dirty than about the latest AI model.
I hope you do too.
Why these notebooks
I believe most complex problems can be solved through a succession of simple steps. Complexity often disappears once you clearly define where you want to go and have the discipline to keep moving in that direction.
That’s how I’ve always worked, whether I was researching past climate change, freelancing on diverse data science projects, or preparing data science workshops.
Different activities, one process: clarify the question, gather and curate the data, then break the path between what I know and what I want to know into simple, manageable steps.
What you can expect
These notebooks are where I allow myself to think out loud. Some investigations will lead somewhere interesting. Others less so.
And that’s perfectly fine, as the final insights are never what I want to share.
What I really want to document is this: Good data science is not about avoiding complexity. It’s about refusing to create unnecessary complexity.
The subjects are simply the excuse. My goal is to document a way of thinking that you can reuse in your own work.
Thank you for stopping by. I hope you’ll enjoy following a few of these investigations, and perhaps even start one of your own.
Cheers,
Manuel Chevalier
Teaching
Many of the ideas explored in this notebook eventually become workshops, teaching material and practical resources through DataSharp Academy.