Building complex data visualisations using ChatGPT
summary
Uses ChatGPT plus Vega-Lite inside Power BI via Deneb to generate JSON specs iteratively, turning raw daily temperature and rainfall tables into a layered visualization with day-by-day min/max columns, an all-time min/max background band, an all-time average line and a cumulative rainfall subplot. Workflow relies on many small iterative prompts rather than one huge prompt, deals with context forgetting, and produces the finished custom visual in about 3 hours of back-and-forth.
AI-written summary · about
chapters (7)
- 0:00Introduction to session
- 3:32Tools for visualization
- 10:11Iterative prompting strategy
- 16:34Starting with simple visuals
- 27:47Iterating to final result
- 31:56Tips and best practices
- 34:23Q&A and closing
related talks
25mCan ChatGPT build a Data Platform faster than a developer?
50mMastering Rapid Power BI Development with ChatGPT: A Deep Dive
20mRapid Power BI Development with ChatGPT, Tips & Tricks
20mHow to improve Q&A in Power BI
27mBuild a ChatGPT RAG Data Pipeline
25mReal-Time and Historical NLP Market Dashboard with RisingWave and Chat-GPT
48mPower BI for Developers
36mAI for Government Efficiency with ChatGPT: From Hype to Reality
