book

Analyzing Baseball Data with R

by Max Marchi, Jim Albert

January 2018

Beginner to intermediate

334 pages

8h 44m

English

Chapman and Hall/CRC

Read now

Unlock full access

1.1 Introduction1.2 The Lahman Database: Season-by-Season Data1.2.1 Bonds, Aaron, and Ruth home run trajectories1.2.2 Obtaining the database1.2.3 The Master table1.2.4 The Batting table1.2.5 The Pitching table1.2.6 The Fielding table1.2.7 The Teams table1.2.8 Baseball questions1.3 Retrosheet Game-by-Game Data1.3.1 The 1998 McGwire and Sosa home run race1.3.2 Retrosheet1.3.3 Game logs1.3.4 Obtaining the game logs from Retrosheet1.3.5 Game log example1.3.6 Baseball questions1.4 Retrosheet Play-by-Play Data1.4.1 Event files1.4.2 Event example1.4.3 Baseball questions1.5 Pitch-by-Pitch Data1.5.1 MLBAM Gameday and PITCHf/x1.5.2 PITCHf/x Example1.5.3 Baseball questions1.6 Summary1.7 Further Reading1.8 Exercises
2.1 Introduction2.2 Installing R and RStudio2.3 Vectors2.3.1 Career of Warren Spahn2.3.2 Vectors: defining and calculations2.3.3 Vector functions2.3.4 Vector index and logical variables2.4 Objects and Containers in R2.4.1 Character data and matrices2.4.2 Factors2.4.3 Lists2.5 Collection of R Commands2.5.1 R scripts2.5.2 R functions2.6 Reading and Writing Data in R2.6.1 Importing data from a file2.6.2 Saving datasets2.7 Data Frames2.7.1 Introduction2.7.2 Manipulations with data frames2.7.3 Merging and selecting from data frames2.8 Packages2.9 Splitting, Applying, and Combining Data2.9.1 Using sapply2.9.2 Using ddply in the plyr package2.10 Getting Help2.11 Further Reading2.12 Exercises
3.1 Introduction3.2 Factor Variable3.2.1 A bar graph3.2.2 Add axes labels and a title3.2.3 Other graphs of a factor3.3 Saving Graphs3.4 Dot plots3.5 Numeric Variable: Stripchart and Histogram3.6 Two Numeric Variables3.6.1 Scatterplot3.6.2 Building a graph, step-by-step3.7 A Numeric Variable and a Factor Variable3.7.1 Parallel stripcharts3.7.2 Parallel boxplots3.8 Comparing Ruth, Aaron, Bonds, and A-Rod3.8.1 Getting the data3.8.2 Creating the player data frames3.8.3 Constructing the graph3.9 The 1998 Home Run Race3.9.1 Getting the data3.9.2 Extracting the variables3.9.3 Constructing the graph3.10 Further Reading3.11 Exercises
4.1 Introduction4.2 The Teams Table in Lahman's Database4.3 Linear Regression4.4 The Pythagorean Formula for Winning Percentage4.5 The Exponent in the Pythagorean Formula4.6 Good and Bad Predictions by the Pythagorean Formula4.7 How Many Runs for a Win?4.8 Further Reading4.9 Exercises

5.1 The Run Expectancy Matrix5.2 Runs Scored in the Remainder of the Inning5.3 Creating the Matrix5.4 Measuring Success of a Batting Play5.5 Albert Pujols5.6 Opportunity and Success for All Hitters5.7 Position in the Batting Lineup5.8 Run Values of Different Base Hits5.8.1 Value of a home run5.8.2 Value of a single5.9 Value of Base Stealing5.10 Further Reading and Software5.11 Exercises
6.1 Introduction6.2 The lattice Package6.2.1 Introduction6.2.2 The verlander dataset6.2.3 Basic plotting with lattice6.2.4 Multipanel conditioning6.2.5 Superposing group elements6.2.6 Scatterplots and dot plots6.2.7 The panel function6.2.8 Building a graph, step-by-step6.3 The ggplot2 Package6.3.1 Introduction6.3.2 The cabrera dataset6.3.3 The first layer6.3.4 Grouping factors6.3.5 Multipanel conditioning (faceting)6.3.6 Adding elements6.3.7 Combining information6.3.8 Adding a smooth line with error bands6.3.9 Dealing with cluttered charts6.3.10 Adding a background image6.4 Further Reading6.5 Exercises
7.1 Introduction7.2 Hitter's Counts and Pitcher's Counts7.2.1 Introduction7.2.2 An example for a single pitcher7.2.3 Pitch sequences on Retrosheet7.2.3.1 Functions for string manipulation7.2.3.2 Finding plate appearances going through a given count7.2.4 Expected run value by count7.2.5 The importance of the previous count7.3 Behaviors by Count7.3.1 Swinging tendencies by count7.3.1.1 Propensity to swing by location7.3.1.2 Effect of the ball/strike count7.3.2 Pitch selection by count7.3.3 Umpires' behavior by count7.4 Further Reading7.5 Exercises
8.1 Introduction8.2 Mickey Mantle's Batting Trajectory8.3 Comparing Trajectories8.3.1 Some preliminary work8.3.2 Computing career statistics8.3.3 Computing similarity scores8.3.4 Defining age, OBP, SLG, and OPS variables8.3.5 Fitting and plotting trajectories8.4 General Patterns of Peak Ages8.4.1 Computing all fitted trajectories8.4.2 Patterns of peak age over time8.4.3 Peak age and career at-bats8.5 Trajectories and Fielding Position8.6 Further Reading8.7 Exercises
9.1 Introduction9.2 Simulating a Half Inning9.2.1 Markov chains9.2.2 Review of work in runs expectancy9.2.3 Computing the transition probabilities9.2.4 Simulating the Markov chain9.2.5 Beyond runs expectancy9.2.6 Transition probabilities for individual teams9.3 Simulating a Baseball Season9.3.1 The Bradley-Terry model9.3.2 Making up a schedule9.3.3 Simulating talents and computing win probabilities9.3.4 Simulating the regular season9.3.5 Simulating the post-season9.3.6 Function to simulate one season9.3.7 Simulating many seasons9.4 Further Reading9.5 Exercises
10.1 Introduction10.2 The Great Streak10.2.1 Finding game hitting streaks10.2.2 Moving batting averages10.3 Streaks in Individual At-Bats10.3.1 Streaks of hits and outs10.3.2 Moving batting averages10.3.3 Finding hitting slumps for all players10.3.4 Were Suzuki and Ibanez unusually streaky?10.4 Local Patterns of Weighted On-Base Average10.5 Further Reading10.6 Exercises
11.1 Introduction11.2 Installing MySQL and Creating a Database11.3 Connecting R to MySQL11.3.1 Connecting using package RMySQL11.3.2 Connecting using Package RODBC11.4 Filling a MySQL Game Log Database from R11.4.1 From Retrosheet to R11.4.2 From R to MySQL11.5 Querying Data from R11.5.1 Introduction11.5.2 Coors Field and run scoring11.6 Baseball Data as MySQL Dumps11.6.1 Lahman's database11.6.2 Retrosheet database11.6.3 PITCHf/x database11.7 Calculating Basic Park Factors11.7.1 Loading the data in R11.7.2 Home run park factor11.7.3 Assumptions of the proposed approach11.7.4 Applying park factors11.8 Further Reading11.9 Exercises
12.1 Introduction12.2 A Motivating Example: Comparing Fielding Metrics12.2.1 Introduction12.2.2 The fielding metrics12.2.3 Reading an Excel spreadsheet (XLConnect)12.2.4 Summarizing multiple columns (doBy)12.2.5 Finding the most similar string (stringdist)12.2.6 Applying a function on multiple columns (plyr)12.2.7 Weighted correlations (weights)12.2.8 Displaying correlation matrices (ellipse)12.2.9 Evaluating the fielding metrics (psych)12.3 Comparing Two Shortstops12.3.1 Reshaping the data (reshape2)12.3.2 Plotting the data (ggplot2 and directlabels)12.4 Further Reading12.5 Exercises
A.1 Downloading Play-by-Play FilesA.1.1 IntroductionA.1.2 SetupA.1.3 Using a special function for a particular seasonA.1.4 Reading the files into RA.1.5 The function parse.retrosheet.pbpA.2 Retrosheet Event Files: a Short ReferenceA.2.1 Game and event identifiersA.2.2 The state of the gameA.3 Parsing Retrosheet Pitch SequencesA.3.1 IntroductionA.3.2 SetupA.3.3 Evaluating every count
B.1 IntroductionB.2 Where are the Data Stored?B.3 Suitable Formats for PITCHf/x DataB.3.1 Obtaining data from on-line resourcesB.3.2 Parsing in RB.3.2.1 A wrapper functionB.4 Details on the DataB.4.1 atbat attributesB.4.2 pitch attributesB.4.3 hip attributes (hit locations data)B.5 Special Notes About the Gameday and PITCHf/x DataB.6 MiscellaneaB.6.1 Calculating the pitch trajectoryB.6.2 An R package for getting and visualizing PITCHf/x data: pitchRxB.6.3 Cross-referencing with other data sourcesB.6.4 Online resources

Content preview from Analyzing Baseball Data with R

Preface

Baseball has always had a fascination with statistics. Schwarz (2005) documents: the quantitative measurements of teams and players since the beginning of professional baseball history in the 19th century. Since the foundation of the Society of Baseball Research in 1971, an explosion of new measures have been developed for understanding offensive and defensive contributions of players. One can learn much about the current developments in sabermetrics by viewing articles at websites such as www.baseballprospectus.com, www.hardballtimes.com, and www.fangraphs.com.

The quantity and detail of baseball data has exhibited remarkable growth since the birth of the Internet. The first data were collected for players, and teams for individual seasons ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Start your free trial

Introducing Charticulator for Power BI: Design Vibrant and Customized Visual Representations of Data

Publisher Resources

ISBN: 9781315360591

Analyzing Baseball Data with R

by Max Marchi, Jim Albert

Preface

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

You might also like

Introducing Charticulator for Power BI: Design Vibrant and Customized Visual Representations of Data

Textile Fiber Microscopy

Panel Data Econometrics with R

Julia Quick Syntax Reference: A Pocket Guide for Data Science Programming

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,and much more.

You might also like

Introducing Charticulator for Power BI: Design Vibrant and Customized Visual Representations of Data

Textile Fiber Microscopy

Panel Data Econometrics with R

Julia Quick Syntax Reference: A Pocket Guide for Data Science Programming

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.