Part of my goal on this blog is to pit the different AI tools against each other. Being a data guy this will mostly come from python and SQL scripting, and perhaps data analysis if I can get it to do that. However I am also going to see how they compare with creativity. In the long term it would be cool to make some books using them and see how they turn out. Maybe a kids book and a super hero book. In making that Super Hero book, well in starting it, I thought of the idea of having a blog post to expand the world at the start of each chapter. From there I decided to create a blog for each of the Gen AI tools and to get them to create and blog about this fictional world and post these stories onto my YouTube channel. Will be interesting to see how the stories develop and if any of them get any view haha.
So recently parkrun removed all their stats and as a keen running who is trying to work their way up the top 100 of their local parkrun I wanted to get some of these stats back and have a bit of "fun" at the same time. So here is a little "ETL" process that I developed with the help of Gen AI. The steps of my ETL: Copy and paste data into Google Sheets template where an AI produced formula extracts URLS from the text and puts them into a new field. This effectively allows me to extract the parkrun athlete id, the primary key, and use it in my analysis. I also have a column to autofill the data I am processing. Use an Gen AI generated Google Apps script to process it into a processed sheet, this allows me to build up a backlog of events (I had over 500 to process). This is then queried using a Gen AI Google sheets query to extract key information and columns / format times etc. I then ingest the fully processed sheet into Keboola directly from Google Sheets. ...
Comments
Post a Comment