Skip to main content

Sam Starosciak has completed

Case Study: Exploring Baseball Pitching Data in R

Start course For Free
4 hr
5,750 XP
Statement of Accomplishment Badge

Loved by learners at thousands of companies

Course Description

This course is a case study in baseball analytics, exploratory data analysis, and the R language. It introduces a rich baseball dataset from Major League Baseball's (MLB) Statcast system to develop skills in baseball analytics using the R language.

Throughout the course, you will use data on every pitch thrown by Zack Greinke during the 2015 MLB season. These data include information about pitch velocity, pitch type, pitch location, exit speed when the batter makes contact, the game situation (e.g. outs or ball-strike count), and the outcome of each pitch (e.g. strike, foul, home run, or walk).

By the end of the course, you will have a thorough understanding of the data and be able to create publication quality visuals to communicate what you have found.

For Business

Training 2 or more people?

Get your team access to the full DataCamp platform, including all the features.
DataCamp for BusinessFor a bespoke solution book a demo.
  1. 1

    Exploring pitch velocities

    Free

    Velocity is a key component in the arsenal of many pitchers. In this chapter, you will examine whether there was an uptick in Zack Greinke's velocity during his impressive July in 2015. The chapter will introduce how to deal with dates, plotting distributions with histograms, and using the very handy tapply() function.

    Play Chapter Now
    Did Zack Greinke pitch differently in July?
    50 xp
    Clean the data
    100 xp
    Check dates
    100 xp
    Delimit dates
    100 xp
    Subsets and histograms
    50 xp
    Velocity distribution
    100 xp
    Fastball velocity distribution
    100 xp
    Distribution comparisons with color
    100 xp
    Describe the histogram
    50 xp
    Using tapply() for comparisons
    50 xp
    tapply() for velocity changes
    100 xp
    Game-by-game velocity changes
    100 xp
    Tidying the data frame
    100 xp
    A game-by-game line plot
    100 xp
    Adding jittered points
    100 xp
    Wrap-up
    50 xp
  2. 2

    Exploring pitch types

    Pitchers throw various types of pitches with different velocities and trajectories in order to make it more difficult for the batter to hit the ball. This chapter will introduce pitch types and make heavy use of tables to examine changes to pitch type choices by Greinke in July, as well as in other important situations.

    Play Chapter Now
    Pitch mix
    50 xp
    Pitch mix tables
    100 xp
    Pitch mix table using prop.table()
    100 xp
    Pitch mix tables - July vs. other
    100 xp
    Describe fastball usage
    50 xp
    Pitch mix tables - changes in pitch type rates
    100 xp
    Describe pitch usage
    50 xp
    Ball-strike count and pitch usage
    50 xp
    Ball-strike count frequency
    100 xp
    Make a new variable
    100 xp
    Ball-strike count in July vs. other months
    100 xp
    Visualizing ball-strike count in July vs. other months
    100 xp
    Cross-tabulate pitch use in ball-strike counts
    100 xp
    Describe pitch count usage
    50 xp
    Pitch mix late in games
    100 xp
    Late game pitch mix - grouped barplots
    100 xp
    Describe late game pitching
    50 xp
    Wrap-up
    50 xp
  3. 3

    Exploring pitch locations

    As with velocity and pitch type, pitch location can play a key role in pitching success. This chapter leverages the rich information about location provided in the MLB Statcast data to visualize changes in Greinke's pitch location choice in July and in different ball-strike counts. You will also make use of the very important for loop in the context of plotting data.

    Play Chapter Now
    Pitch location and Greinke's July
    50 xp
    Locational changes - summary
    100 xp
    Describe the locations
    50 xp
    Locational changes - visualization
    100 xp
    Locational changes - plotting a grid
    100 xp
    Binning locational data
    100 xp
    Grid percentage question
    50 xp
    For loops for plots
    50 xp
    For loops and plotting locational grid proportions
    100 xp
    Binned locational differences
    100 xp
    Plotting zone proportion differences
    100 xp
    Describe the figure
    50 xp
    Location and ball-strike count
    100 xp
    0-2 vs. 3-0 locational changes
    100 xp
    Plotting count-based locational differences
    100 xp
    Wrap-up
    50 xp
  4. 4

    Exploring batted ball outcomes

    In this chapter, you'll bring it all together. Minimizing damage on each pitch is the key to run prevention by the pitcher. Therefore, you will look closely at outcomes from pitches thrown by Greinke in different months. We'll also introduce the ggplot2 package to create high quality visualizations of hitter exit speed when Greinke throws to different locations.

    Play Chapter Now
    Batted ball outcomes - contact rate
    50 xp
    Velocity impact on contact rate
    100 xp
    Pitch type impact on contact rate
    100 xp
    Velocity impact on contact by pitch type
    100 xp
    Greinke's out pitch?
    100 xp
    Describe 2-strike pitch usage
    50 xp
    Impact of pitch location on contact rate
    100 xp
    Using ggplot2
    50 xp
    Rethinking the use of for loops
    100 xp
    Contact rate with ggplot2
    100 xp
    Adding titles and axes to ggplot2 figure
    100 xp
    Making a heat map - visualizing hot and cold zones
    100 xp
    Adding text for contact rate values
    100 xp
    Batted ball outcomes - exit velocity
    50 xp
    Contact and exit speed
    100 xp
    Location and exit speed
    100 xp
    Plotting exit speed as a heat map
    100 xp
    Using tidy data and facets in ggplot2
    100 xp
    Wrap-up
    50 xp
For Business

Training 2 or more people?

Get your team access to the full DataCamp platform, including all the features.

datasets

greinke2015

collaborators

Collaborator's avatar
Nick Carchedi
Collaborator's avatar
Tom Jeon

prerequisites

Intermediate R
Brian M. Mills HeadshotBrian M. Mills

Assistant Professor at the University of Florida

Brian Mills is an Assistant Professor at the University of Florida, with research interests encompassing quantitative and economic analysis in sport. He earned a PhD and MA in Sport Management, an MA in Statistics, and an MA in Applied Economics from the University of Michigan. Brian has been an active contributor to the Sabermetric community through blogging about analytics and teaching how to use R to analyze baseball data.
See More

Join over 17 million learners and start Case Study: Exploring Baseball Pitching Data in R today!

Create Your Free Account

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.