Ask any Data Scientist and they will tell you that the process of ‘wrangling’ (loading, understanding and preparing) data represents the lion’s share of their workload – often up to as much as 80%. However, that number is not as alarming as it may at first seem. To understand why, let me tell you about my living room.
A side-effect of all the time I spend breathing the rarified alpine air of the CDO community is that my SQL skills have become rather rusty. So I’ve been intrigued by the idea of using the code-generation capabilities of tools like ChatGPT and Bard to write SQL for me. But how good is the current crop of LLMs at creating SQL code that not only works, but generates the insight you’re actually looking for? I decided to find out.