bayesball

#----------------------------------------------
# R code for Bayesian Computation Webinar
# Jim Albert - June 12, 2014
# albert@bgsu.edu
#----------------------------------------------

#----------------------------------------------
# PART II:  Posterior-Predictive Model Checking
# Require packages pscl, arm, MASS
#----------------------------------------------

bayesball

#----------------------------------------------
# R code for Bayesian Computation Webinar
# Jim Albert - June 12, 2014
# albert@bgsu.edu
#----------------------------------------------
 
#---------------------------------------------------------------------
# PART III:  INTRODUCTION TO JAGS
# Negative binomial regression
# Example from Jackman, 2009

bayesball

#----------------------------------------------
# R code for Bayesian Computation Webinar
# Jim Albert - June 12, 2014
# albert@bgsu.edu
#----------------------------------------------

##################################################
# PART IV:  JAGS for Multilevel Modeling
# Require R packages Lahman, rjags, ggplot2
##################################################

bayesball

# read in variable names for game log dataset

Headers <- c("Date",                       "DoubleHeader",              
"DayOfWeek",                  "VisitingTeam",              
"VisitingTeamLeague",         "VisitingTeamGameNumber",    
"HomeTeam",                   "HomeTeamLeague"         ,   
"HomeTeamGameNumber",         "VisitorRunsScored"       ,  
"HomeRunsScore",              "LengthInOuts",              
"DayNight",                   "CompletionInfo",            
"ForfeitInfo",                "ProtestInfo"    ,           

bayesball

library(Lahman)
library(dplyr)

fielding.2b <- filter(Fielding, POS=="2B", yearID >= 1960)

rf.season.2b <- summarize(group_by(fielding.2b, yearID),
              RF.9 = 9 * (sum(PO, na.rm=TRUE) + 
                          sum(A, na.rm=TRUE)) / 
                    (sum(InnOuts / 3, na.rm=TRUE)))

bayesball

datamatrix <- matrix(c(
1,1,1,0,1,1,1,1,1,0,1,1,0,1,0,1,0,1,1,1,0,1,1,1,1,0,1,1,0,1,1,1,1,0,1,
1,0,1,1,1,1,0,1,0,1,1,0,1,1,0,0,0,1,1,0,0,0,1,1,1,0,1,0,0,1,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,0,0,1,1,1,1,0,0,1,1,1,0,1,1,1,1,1,1,0,1,1,0,0,0,0,
0,1,1,0,1,1,1,1,0,0,1,1,0,1,0,0,0,1,1,0,0,1,0,0,0,1,0,0,0,1,1,0,0,0,0,
1,0,0,0,1,1,1,0,0,0,0,1,0,0,0,0,1,0,0,1,1,1,1,0,0,0,1,1,0,1,0,0,0,0,0,
1,0,1,0,1,1,0,0,1,1,0,1,0,0,0,0,0,0,0,1,0,0,1,1,1,0,0,0,0,1,1,0,0,0,0,
0,1,1,1,1,1,1,1,1,1,1,1,0,1,1,0,1,0,1,0,1,1,1,1,1,1,1,1,0,0,1,0,0,0,1,
1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,0,1,1,1,1,1,1,1,1,0,1,1,1,0,1,1,0,0,0,
1,0,1,0,1,1,1,0,0,0,0,1,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,1,1,0,0,0,0,0,

bayesball

plot.batting.average <- function(name, season){
  require(Lahman)
  require(dplyr)
  Name <- unlist(strsplit(name, split=" "))
  id <- subset(Master, nameFirst==Name[1] & 
                       nameLast==Name[2])$playerID[1]
  data <- subset(Batting, playerID==id & yearID==season)
  data <- summarize(data, H=sum(H), AB=sum(AB),
                          SO=sum(SO), HR=sum(HR))
  so.rate <- with(data, SO / AB)

bayesball

graph.game <- function(d, game.id){
  require(ggplot2)
  d1 <- subset(d, substr(HALF.INNING, 1, 12) == game.id)
  d1$Play <- 1:dim(d1)[1]
  yr <- substr(d1[1, "HALF.INNING"], 4, 7)
  mo <- substr(d1[1, "HALF.INNING"], 8, 9)
  day <- substr(d1[1, "HALF.INNING"], 10, 11)
  print(ggplot(d1, aes(Play, P.NEW)) + geom_line() + 
    ylim(0, 1) + geom_hline(yintercept=0.5, color="red") +
    ylab("Probability Home Team Wins") +

bayesball

plot.trajectory <- function(player){
  d <- subset(sluggerdata, Player==player)
  p <- ggplot(d, aes(Age, HR/AB)) + 
    geom_point(size=4, color="red") +
    geom_smooth(size=2, color="blue") +
    labs(title = player)
  print(p)
}

bayesball

# Assuming that the retrosheet play-by-play files are available for a particulr
# season

# Function righthand computes the proportion of right-handed
# pitchers and right-handed batters for each inning for a 
# particular season
# inputs are the season and the retrosheet data for that season

righthand <- function(season, d){
  require(dplyr)