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.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=""))

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

---
title: "WPA work"
author: "Jim Albert"
date: "January 23, 2015"
output: html_document
---

First source three functions:

* prob.win.game2 computes the win probabilities after each inning

bayesball

# loading in Retrosheet data for the seasons 1960 through 2013 from my website 
load(url("http://bayes.bgsu.edu/baseball/pbp.1960.1979.Rdata"))
load(url("http://bayes.bgsu.edu/baseball/pbp.1980.1999.Rdata"))
load(url("http://bayes.bgsu.edu/baseball/pbp.2000.2013.Rdata"))

batter.matchup.ggplot <- function(Name, graph=TRUE, retroid=FALSE){
  # this function assumes the data frames pbp.60.79, pbp.80.99, and pbp.00.13 are
  # in the workspace
  fit.model <- function(y, n){
    require(LearnBayes)

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)

bayesball

# code for estimating platoon effects for 2014 season
# one needs Retrosheet play-by-play for this season
# also uses the Master file in the Lahman database to get the player batting sides
# last, one needs a file from fangraphs to compute the weights in the wOBA formula

library(dplyr)

# retrieved wOBA weights from http://www.fangraphs.com/guts.aspx?type=cn
# stored in file fangraphs.csv
fangraphs <- read.csv("~/Dropbox/2014 WORK/situational/fangraphs.csv")

bayesball

# load relevant packages

library(dplyr)
library(ggplot2)

# function will download retrosheet game log data for a particular
# season

load.gamelog <- function(season, headers){
  download.file(