Be kind to yourself! Spend (less) time on Data Exploration
summary
Argues that careful exploration still pays back double and shows concrete results on the California housing dataset: house age and price are clipped at 50 revealing data truncation, a non‑linear interaction that a correlation matrix misses. Demonstrates five tools—pandas‑profiling, SweetViz, DABL, dTreeViz and dtale—notes a Graphviz dependency pain and dtale exposing a web UI on port 40000, warns these tools are memory‑bound, and cites Andrew Ng’s new label‑quality startup raising 56 million as further evidence to focus on the data.
AI-written summary · about
chapters (10)
- 0:00Welcome!
- 2:05What is Data Exploration?
- 2:26You have to get to know your data!
- 11:50Pandas Profiling
- 14:07SweetVIZ
- 15:59DABL
- 17:58dTreeViz
- 19:56dtale
- 22:35Conclusions
- 25:18Q&A
related talks
31mFundamentals of Data Visualization
42mInteractive Data Analysis: Visualization and Beyond
01h 38mEffective Data Visualization
32mData Viz for Engineers: Optimizing Insight & Decision Making Through Visualization
24mTalk Data to Me - the art of storytelling
20mDesigning for Big Data
10mThe Future of Data Visualization
01h 28mPython Visualization for Exploration of Data