Last active
January 28, 2019 03:43
-
-
Save bayesball/70a166149f71622fed97 to your computer and use it in GitHub Desktop.
R function to compute and plot the probability a MLB home team wins a game at the end of each inning given a particular lead.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
plot.prob.home <- function(year, plot=TRUE){ | |
require(arm) | |
require(ggplot2) | |
load.gamelog <- function(season, headers){ | |
download.file( | |
url=paste("http://www.retrosheet.org/gamelogs/gl", season, ".zip" | |
, sep="") | |
, destfile=paste("gl", season, ".zip", sep="") | |
) | |
unzip(paste("gl", season, ".zip", sep="")) | |
gamelog <- read.table(paste("gl", season, ".txt", sep="") | |
, sep=",", stringsAsFactors=F) | |
names(gamelog) <- names(headers) | |
file.remove(paste("gl", season, ".zip", sep="")) | |
file.remove(paste("gl", season, ".txt", sep="")) | |
gamelog | |
} | |
headers <- read.csv("https://raw.githubusercontent.com/beanumber/baseball_R/master/data/game_log_header.csv") | |
d <- load.gamelog(year, headers) | |
# remove line scores for games when at least 10 runs are scored | |
d <- subset(d, !grepl("\\(", as.character(d$VisitorLineScore)) & | |
!grepl("\\(", as.character(d$HomeLineScore))) | |
# for a particular game, extract individual inning runs for | |
# visitor and home teams | |
get.visitor.innings <- function(j) | |
as.numeric(strsplit(as.character(d$VisitorLineScore[j]), | |
split="")[[1]])[1:8] | |
get.home.innings <- function(j) | |
as.numeric(strsplit(as.character(d$HomeLineScore[j]), | |
split="")[[1]])[1:8] | |
# apply these functions for all games | |
options(warn=-1) # turn off warnings | |
N <- dim(d)[1] | |
V <- t(sapply(1:N, get.visitor.innings)) | |
H <- t(sapply(1:N, get.home.innings)) | |
options(warn=0) # turn on warnings | |
# compute running scores of visitor and home teams | |
C.V <- t(apply(V, 1, cumsum)) | |
C.H <- t(apply(H, 1, cumsum)) | |
# compute running scores for each of 16 half-innings | |
mf <- function(y) rep(y, each=2) | |
CC.V <- t(apply(C.V, 1, mf)) | |
nf <- function(y) as.vector(matrix(c(0, y[1:(length(y) - 1)], y), | |
2, length(y), byrow=TRUE)) | |
CC.H <- t(apply(C.H, 1, nf)) | |
# compute game outcome (1 if home team wins, 0 otherwise) | |
O <- with(d, ifelse(HomeRunsScore > VisitorRunsScored, 1, 0)) | |
# run the logistic regression | |
logistic.fit <- function(half.inning){ | |
visitor.runs <- CC.V[, half.inning] | |
home.runs <- CC.H[, half.inning] | |
B <- data.frame(Run.diff = home.runs - visitor.runs, | |
Outcome = O) | |
coef(glm(Outcome ~ Run.diff, data=B, family=binomial)) | |
} | |
S <- t(sapply(1:16, logistic.fit)) | |
D <- data.frame(Inning=0, | |
Run.Lead=0, | |
Prob.Win=mean(O)) | |
for (r in -4:4){ | |
hi <- seq(2, 16, 2) | |
D <- rbind(D, data.frame(Inning=hi/2, | |
Run.Lead=r, | |
Prob.Win=invlogit(S[hi, 1] + r * S[hi, 2]))) | |
} | |
if(plot==TRUE){ | |
D$RUN.LEAD <- as.factor(D$Run.Lead) | |
print(ggplot(D, aes(Inning, Prob.Win, color=RUN.LEAD)) + | |
geom_point(size=4) + geom_line(size=1.5) + | |
labs(title=paste("Probability Home Team Wins At End of Each Inning:", | |
year, "Data")) + | |
ylab("Probability Home Team Wins") + | |
ylim(0, 1) + geom_hline(yintercept=0.5, size=1.5))} | |
D$Season <- year | |
D | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment