Fetching contributors…
Cannot retrieve contributors at this time
55 lines (50 sloc) 1.72 KB
\title{Yearly batting records for all major league baseball players}
\format{A 21699 x 22 data frame}
This data frame contains batting statistics for a subset
of players collected from
\url{}. There are a
total of 21,699 records, covering 1,228 players from 1871
to 2007. Only players with more 15 seasons of play are
Variables: \itemize{ \item id, unique player id \item
year, year of data \item stint \item team, team played
for \item lg, league \item g, number of games \item ab,
number of times at bat \item r, number of runs \item h,
hits, times reached base because of a batted, fair ball
without error by the defense \item X2b, hits on which the
batter reached second base safely \item X3b, hits on
which the batter reached third base safely \item hr,
number of home runs \item rbi, runs batted in \item sb,
stolen bases \item cs, caught stealing \item bb, base on
balls (walk) \item so, strike outs \item ibb, intentional
base on balls \item hbp, hits by pitch \item sh,
sacrifice hits \item sf, sacrifice flies \item gidp,
ground into double play }
baberuth <- subset(baseball, id == "ruthba01")
baberuth$cyear <- baberuth$year - min(baberuth$year) + 1
calculate_cyear <- function(df) {
cyear = year - min(year),
cpercent = cyear / (max(year) - min(year))
baseball <- ddply(baseball, .(id), calculate_cyear)
baseball <- subset(baseball, ab >= 25)
model <- function(df) {
lm(rbi / ab ~ cyear, data=df)
models <- dlply(baseball, .(id), model)