Lahman (version 4.0-1)

Managers: Managers table

Description

Managers table: information about individual team managers, teams they managed and some basic statistics for those teams in each year.

Usage

data(Managers)

Format

A data frame with 3370 observations on the following 10 variables.

playerID

Manager (player) ID code

yearID

Year

teamID

Team; a factor

lgID

League; a factor with levels AA AL FL NL PL UA

inseason

Managerial order. Zero if the individual managed the team the entire year. Otherwise denotes where the manager appeared in the managerial order (1 for first manager, 2 for second, etc.)

G

Games managed

W

Wins

L

Losses

rank

Team's final position in standings that year

plyrMgr

Player Manager (denoted by 'Y'); a factor with levels N Y

Source

Lahman, S. (2015) Lahman's Baseball Database, 1871-2014, 2015 version, http://baseball1.com/statistics/

Examples

####################################
# Basic career summaries by manager
####################################

library('plyr')
mgrsumm <- function(d) {
    df <- data.frame(with(d,
              nyear = length(unique(yearID)),
              yearBegin = min(yearID),
              yearEnd = max(yearID),
              nTeams = length(unique(teamID)),
              nfirst = sum(rank == 1L),
              W = sum(W),
              L = sum(L),
              WinPct = round(W/(W + L), 3)))
    df
}

mgrTotals <- ddply(Managers, .(playerID), summarise,
                  nyear = length(unique(yearID)),
                  yearBegin = min(yearID),
                  yearEnd = max(yearID),
                  nTeams = length(unique(teamID)),
                  nfirst = sum(rank == 1L),
                  games = sum(W + L),
                  W = sum(W),
                  L = sum(L),
                  WinPct = round(sum(W)/sum(W + L), 3))
mgrTotals <- merge(mgrTotals,
                   subset(Master, !is.na(playerID),
                          select = c('playerID', 'nameLast', 'nameFirst')),
                   by = 'playerID')

##########################
# Some basic queries
##########################

# Top 20 managers in terms of years of service:
head(arrange(mgrTotals, -nyear), 20)

# Top 20 winningest managers (500 games minimum)
head(arrange(subset(mgrTotals, games >= 500), -WinPct), 20)

# Hmm. Most of these are 19th century managers.
# How about the modern era?
head(arrange(subset(mgrTotals, yearBegin >= 1900 & games >= 500), -WinPct), 20)

# Top 10 managers in terms of percentage of titles (league or divisional) -
# should bias toward managers post-1970 since more first place finishes
# are available
head(arrange(subset(mgrTotals, yearBegin >= 1900 & games >= 500),
                -round(nfirst/nyear, 3)), 10)

# How about pre-1969?
head(arrange(subset(mgrTotals,
                    yearBegin >= 1900 & yearEnd <= 1969 & games >= 500),
                    -round(nfirst/nyear, 3)), 10)

##############################################
# Density plot of the number of games managed:
##############################################

library('ggplot2')
ggplot(mgrTotals, aes(x = games)) + geom_density(fill = 'red', alpha = 0.3) +
    labs(x = 'Number of games managed')

# Who managed more than 4000 games?
subset(mgrTotals, games >= 4000)
# Connie Mack had an advantage: he owned the Philadelphia A's :)

# Table of Tony LaRussa's team finishes:
with(subset(Managers, playerID == 'larusto01'), table(rank))

# To include zero frequencies, one alternative is the tabulate() function:
with(subset(Managers, playerID == 'larusto01'), tabulate(rank, 7))


##############################################
# Scatterplot of winning percentage vs. number of games managed (min 100)
##############################################

ggplot(subset(mgrTotals, yearBegin >= 1900 & games >= 100),
       aes(x = games, y = WinPct)) + geom_point() + geom_smooth() +
    labs(x = 'Number of games managed')

############################################
# Division titles
############################################

# Plot of number of first place finishes by managers with at least 8 years
# of experience in the divisional era (>= 1969):

divMgr <- subset(mgrTotals, yearBegin >= 1969 & nyear >= 8)

# Response is the number of titles
ggplot(divMgr, aes(x = nyear, y = nfirst)) +
    geom_point(position = position_jitter(w = 0.2)) +
    labs(x = 'Number of years', y = 'Number of divisional titles') +
    geom_smooth()

# Response is the proportion of titles
ggplot(divMgr, aes(x = nyear, y = round(nfirst/nyear, 3))) +
    geom_point(position = position_jitter(w = 0.2)) +
    labs(x = 'Number of years', y = 'Proportion of divisional titles') +
    geom_smooth()