Analyzing mlb data with ggplot
9 likes5,181 views
The document discusses the use of ggplot for analyzing MLB data, highlighting its advantages such as ease of customization and reasonable assumptions for data visualization. It compares ggplot to alternatives like matplotlib and d3.js, focusing on its syntax and design for creating graphics. A case study involving pitch speed data illustrates how to implement ggplot and explore the effects of fatigue on pitching performance.
Analyzing mlb data with ggplot
- 1. analyzing MLB data with ggplot Greg Lamp
- 2. ggplot ● What is it? ● Alternatives ● How it works ● Why should I use it? ● Brief case study ● Questions
- 3. Here I am on the Internet. Founder/CTO @ Yhat Hi, I’m Greg!
- 10. a quick example
- 13. it’s not all bad!
- 15. matplotlib maturity, ipython, customization, community syntax, api, default themes, learning curve
- 17. d3.js
- 18. ggplot
- 19. ggplot d3.js
- 20. How it works
- 21. Format
- 22. ggplot
- 24. data frame
- 25. “aesthetics”
- 26. Aesthetics
- 30. color
- 31. shape
- 32. size
- 33. ...fill, alpha, slope, intercept, ymin, ymax, ...
- 35. geom_point
- 36. geom_area
- 38. stat_smooth
- 39. ...there are a few
- 43. Layers
- 44. ggplot()
- 46. + + ggplot() geom_point() stat_smooth()
- 47. + + ggplot() geom_point() stat_smooth()+ +
- 51. not real colors
- 53. still not real colors ...but i can guess what you mean
- 59. Looks pretty good (and is easy to customize)
- 62. Case Study
- 66. pitch speed
- 68. 103.4 mph
- 70. Load ggplot and pandas
- 71. Read in our pitch f/x data
- 72. define the x- axis pass in your data frame
- 73. add a histogram
- 74. How does fatigue impact velocity?
- 75. ...not helpful
- 78. What about at the individual level?
- 81. Justin Verlander
- 85. ggplot let’s you fail quicker
- 86. Finding Help
- 89. What’s next?