Fundamentals of Data Visualization
summary
Covers concrete rules and tools: use OpenRefine for sanitizing messy categorical inputs, Recharts or D3 for plotting, ColorBrewer/ColorHexa for accessible palettes, and prefer bar/line/scatter/heatmap rules (bar for discrete, line for continuous, max four series). Demonstrates a machine‑learning housing demo with 89.7% test accuracy and runs a live experiment (piechartssuck.com/experiments/7) that uses a dependent t‑test to compare pie vs bar estimates but fails during demo; promises to publish cleaned results. Key tips: start y‑axis at zero, use area not diameter for bubbles.
AI-written summary · about
chapters (18)
- 0:00Introduction to data visualization
- 1:50Why terrible visualizations matter
- 5:04Responsibility with big data
- 7:11Avoiding misleading stories
- 9:45Example of great visualization
- 11:57Best practices for chart types
- 13:27Common pitfalls in scaling
- 15:33Bar and column charts guide
- 16:17Line charts explained
- 17:00Area charts and scatter plots
- 18:06Histograms and heat maps
- 18:50Pie charts and their flaws
- 25:18Live experiment debacle
- 25:39Tools for charting in React
- 26:43D3 for advanced visualizations
- 27:25Colorblind-friendly designs
- 28:53Tools for color selection
- 30:21Key takeaways and conclusion
related talks
01h 38mEffective Data Visualization
01h 01mEffective Data Visualization
48mData Visualization in Practice
10mThe Future of Data Visualization
32mData Viz for Engineers: Optimizing Insight & Decision Making Through Visualization
11mData Visualization & Storytelling
02h 23mEffective Data Visualization
31mData Storytelling through Visualization