Chapter 4: Further Reading

Annotated Bibliography

This curated reading list provides resources for deepening your understanding of exploratory data analysis, visualization, and their application to basketball analytics.

Foundational Texts

Exploratory Data Analysis

Exploratory Data Analysis John W. Tukey | Addison-Wesley, 1977

The foundational text that established EDA as a discipline. Tukey's philosophy of "letting the data speak" remains relevant. His emphasis on visual methods and resistance to premature conclusions is essential reading for any analyst.

The Visual Display of Quantitative Information (2nd Edition) Edward R. Tufte | Graphics Press, 2001

The definitive work on data visualization principles. Tufte's concepts of "chartjunk" and data-ink ratio guide the creation of clear, effective visualizations. The principles apply directly to creating publication-quality basketball graphics.

Python Visualization

Python Data Science Handbook Jake VanderPlas | O'Reilly Media, 2016

Comprehensive coverage of matplotlib, seaborn, and pandas visualization. Chapter 4 on Visualization with Matplotlib is particularly relevant. Available free online at jakevdp.github.io/PythonDataScienceHandbook/.

Fundamentals of Data Visualization Claus O. Wilke | O'Reilly Media, 2019

A guide to making informative and compelling figures. While using R examples, the principles are language-agnostic. Excellent for understanding when to use different chart types.

Storytelling with Data Cole Nussbaumer Knaflic | Wiley, 2015

Focuses on the communication aspect of data visualization. Particularly useful for analysts who need to present findings to non-technical stakeholders like coaches or front office executives.

Basketball Analytics Visualization

Sprawlball: A Visual Tour of the New Era of the NBA Kirk Goldsberry | Houghton Mifflin Harcourt, 2019

The best example of basketball data visualization for a general audience. Goldsberry's shot charts and spatial analysis set the standard for visual basketball analytics. Essential inspiration for shot chart design.

Basketball on Paper Dean Oliver | Potomac Books, 2004

While focused on statistics, Oliver's work demonstrates effective presentation of basketball data. His "Four Factors" analysis shows how to distill complex data into actionable insights.

Academic Resources

EDA Methodology

Statistical Rethinking Richard McElreath | CRC Press, 2020

While primarily about Bayesian statistics, McElreath's approach to understanding data before modeling is exemplary. His workflow of simulation and visualization before inference is valuable.

Exploratory Data Analysis with MATLAB (2nd Edition) Wendy L. Martinez, Angel Martinez, Jeffrey Solka | CRC Press, 2010

Comprehensive coverage of EDA techniques including dimensionality reduction and clustering. While in MATLAB, concepts translate to Python.

Sports Analytics Papers

A Visual Exploration of NBA Shot Charts Various Authors | MIT Sloan Sports Analytics Conference

Search for shot chart papers at the Sloan conference proceedings. Multiple papers have advanced shot chart visualization techniques.

Characterizing the Spatial Structure of Defensive Skill in Professional Basketball Alexander Franks et al. | Annals of Applied Statistics, 2015

Demonstrates sophisticated spatial analysis of basketball data. Advanced but shows what's possible with thorough exploratory analysis.

Online Resources

Tutorials and Guides

Pandas User Guide: Visualization https://pandas.pydata.org/docs/user_guide/visualization.html

Official documentation for pandas plotting capabilities. Essential reference for quick exploratory plots.

Seaborn Tutorial https://seaborn.pydata.org/tutorial.html

Official seaborn documentation with excellent examples. The distribution and categorical plotting tutorials are particularly relevant to basketball analysis.

Matplotlib Tutorials https://matplotlib.org/stable/tutorials/

Comprehensive matplotlib tutorials covering everything from basic plots to advanced customization.

Basketball Data Visualization Examples

Kirk Goldsberry's Twitter/X @kirkgoldsberry

Regular posting of innovative basketball visualizations. Good source for current visualization trends in basketball analytics.

FiveThirtyEight NBA Coverage https://fivethirtyeight.com/tag/nba/

Data journalism that combines statistical rigor with accessible visualization. Good examples of presenting complex analysis to general audiences.

Cleaning the Glass https://cleaningtheglass.com

Subscription service with excellent visualization of player and team statistics. Good model for context-adjusted statistical presentation.

Python Libraries Documentation

Plotly for Python https://plotly.com/python/

Interactive visualization library. Useful for creating dashboards and exploratory tools that allow dynamic filtering and drill-down.

Altair https://altair-viz.github.io/

Declarative visualization library based on Vega-Lite. Offers a different approach to visualization that some find more intuitive than matplotlib.

Bokeh https://bokeh.org/

Interactive visualization library for web deployment. Useful for creating shareable, interactive shot charts and performance dashboards.

Video Resources

Visualization Courses

Data Visualization with Python (Coursera) IBM | Multiple instructors

Covers matplotlib, seaborn, and folium. Good for reinforcing fundamentals with hands-on exercises.

Information Visualization (Coursera) University of California, Davis | Isabel Meirelles

Broader coverage of visualization theory and practice. Useful for understanding when and why to use different visualization types.

Conference Talks

Effective Data Visualization (PyCon talks) Various presenters

Search YouTube for PyCon talks on data visualization. Many excellent presentations on matplotlib, seaborn, and visualization best practices.

MIT Sloan Sports Analytics Conference https://www.sloansportsconference.com/

Annual conference with many presentations involving data visualization. Videos often available after the conference.

Books on Specific Topics

Statistical Graphics

Visualizing Data William S. Cleveland | Hobart Press, 1993

Classic text on statistical graphics principles. Cleveland's work on perception in data visualization remains highly relevant.

Grammar of Graphics (2nd Edition) Leland Wilkinson | Springer, 2005

The theoretical foundation for ggplot2, plotnine, and similar libraries. Understanding this framework helps when working with any plotting library.

Interactive Visualization

Interactive Data Visualization for the Web (2nd Edition) Scott Murray | O'Reilly Media, 2017

D3.js focused but covers principles applicable to any interactive visualization. Useful if building web-based basketball dashboards.

For those new to data visualization:

  1. Start with: Tufte's "Visual Display of Quantitative Information"
  2. Then read: Knaflic's "Storytelling with Data"
  3. Practice with: Python Data Science Handbook (visualization chapter)
  4. Study: Seaborn tutorial documentation
  5. For inspiration: Goldsberry's "Sprawlball"

For experienced analysts focusing on basketball:

  1. Start with: Goldsberry's work and FiveThirtyEight examples
  2. Then study: Academic papers on spatial basketball analysis
  3. Explore: Interactive libraries (Plotly, Bokeh) for dashboards
  4. Follow: Active basketball data visualization practitioners

Tools Beyond Python

Other Languages

R and ggplot2 https://ggplot2.tidyverse.org/

R's primary visualization library. Many excellent basketball visualizations are created in R; understanding ggplot2 concepts translates well.

Tableau Public https://public.tableau.com/

Desktop application for creating interactive visualizations without coding. Useful for rapid prototyping and sharing.

Design Tools

Figma / Adobe Illustrator Professional design tools

For publication-quality graphics, exported matplotlib figures are often refined in design tools. Worth learning basics for final polish.

Staying Current

Data visualization is an evolving field. To stay current:

  1. Follow visualization practitioners on Twitter/X
  2. Attend or watch recordings from Sloan Sports Analytics Conference
  3. Explore Observable (observablehq.com) for interactive visualization examples
  4. Monitor library release notes for new features
  5. Practice by recreating visualizations you find compelling

A Note on Style

Every organization develops its own visualization style guide. When creating basketball visualizations:

  • Consider your audience (coaches vs. executives vs. media)
  • Match complexity to context (exploratory vs. presentation)
  • Maintain consistency within projects
  • Prioritize clarity over novelty
  • Test visualizations with intended users

The best visualization is one that effectively communicates the intended message to its audience.

Last updated: Chapter 4 publication date. Check for updated resources at the textbook companion website.