Lecture 10 – Visualization, Part 2
Presented by Fernando Perez
Content by Fernando Perez, Suraj Rampure, Ani Adhikari, Sam Lau, Yifan Wu, Deborah Nolan
Extra reading on colormaps:
- matplotlib colormaps (BIDS)
- How the Rainbow Color Map Misleads
- When to use Sequential and Diverging Palettes
- Color Use Guidelines
A random one of the following Google Forms will give you an alphanumeric code once you submit; you should take this code and enter it into the “Lecture 10” question in the “Quick Check Codes” assignment on Gradescope to get credit for submitting this Quick Check. You must submit this by Monday, October 5th at 11:59PM to get credit for it.
Ensuring that the axes in our visualizations aren't misleading.
Designing visualizations that are well-suited for making comparisons.
How to use color to create effective visualizations. How to choose color schemes that are clear and accessible.
How to choose markings that the human eye can easily interpret. Issues to avoid, such as jiggling baselines and overplotting.
Discussing the supplemental text that publication-ready plots need.
When to use smoothing. How kernel density estimates are created. Looking at various kernels. Understanding the impact of the bandwidth hyperparameter.
Discussing why we prefer linear relationships. Understanding how to "reverse-engineer" a linearized relationship to determine the true relationship. Identifying which transformations to use in order to linearize a relationship.