batting_and_aging.R

library(Lahman)
library(plyr)
library(dplyr)
library(ggplot2)


master = Lahman::Master %>%
  select(playerID,birthYear)
bstats <- battingStats() %>%
  select(playerID, yearID,BA)

batting=left_join(bstats,master) %>%
  mutate(age=yearID-birthYear) %>%
  arrange(playerID,age) %>%
  filter(!is.na(BA) & !is.na(age)) %>%
  group_by(playerID) %>%
  filter(length(playerID)>=2) %>%
  mutate(yearsLeft=min_rank(desc(age))-1) %>%
  filter(!(yearsLeft==0 & yearID==2013))

###Split by people in their last year of play or not
plot_dataA = batting %>%
  group_by(age,LastYear=!(yearsLeft>0)) %>%
  summarise(
  mu=mean(BA),
  se=sqrt(var(BA)/length(BA)),
  obs=length(BA)
  ) %>% 
  filter(age>=20 & age <=42)

plot_dataA$se=with(plot_dataA,ifelse(LastYear,0,se))
plot_dataA$CareerYear=with(plot_dataA,ifelse(LastYear,"Last","Not Last"))


###Compute regardless of last year or not
plot_dataB = batting %>%
  group_by(age) %>%
  summarise(
    LastYear=NA,
    mu=mean(BA),
    se=sqrt(var(BA)/length(BA)),
    obs=length(BA)
  ) %>% 
  filter(age>=20 & age <=42)

plot_dataB$CareerYear="Combined"

plot_data=rbind(plot_dataA,plot_dataB)
plot_data$CareerYear=factor(plot_data$CareerYear,levels=c("Not Last","Combined","Last"))

#Hi Michael Schulte-Mecklenbeck!
p=ggplot(plot_data,aes(x=age,y=mu,ymin=mu-se,ymax=mu+se,group=CareerYear,color=CareerYear)) +
  geom_line() +
  geom_pointrange() +
  geom_point(aes(size=obs)) +
  scale_size_area() +
  labs(x="Age",y="Mean Batting Average")+
  theme(legend.position="bottom")
p
ggsave(plot=p,file="BA_by_Age.png",width=4,height=6)

p=ggplot(plot_data,aes(x=age,y=mu,ymin=mu-se,ymax=mu+se,group=CareerYear,color=CareerYear)) +
  stat_smooth(span=10,level=.9,method="loess") +
  geom_point(aes(size=obs)) +
  scale_size_area() +
  labs(x="Age",y="Mean Batting Average")+
  theme(legend.position="bottom")
p
ggsave(plot=p,file="BA_by_Age_smooth.png",width=4,height=6)