Analysis of Retrosheet’s Major League Baseball Game Log Data on ejections.
Questions:
Which years and teams have the highest and lowest ejection rates?
Are there certain umpires who eject more frequently?
Are there patterns in the number of ejections based on the “Eras” of baseball?
What factors have the strongest correlation with ejections?
Why do umpires eject players, coaches, and managers from baseball games?
Abusive language
Throwing at another player
Brawling
Violating rules such as doctoring pitches
When did ejectionsbecome a norm in MLB?
Prior to 1889, umpires did not impose ejections but rather fines.
Increase of “inappropriate behavior” persisted and thus ejection were voted in.
Source: (Imber, 2024)
Retrosheet Ejections Data https://www.retrosheet.org/eject.htm
Retrosheet has detailed information on more than 18,000 ejections from 1889-2023
For data clean up, I had to join tables of data with the names of players, coaches, umpires, etc. with the ejections table based on Retrosheet IDs.
I also had to clean up columns with shortened words like “C” for “Coach” etc.
ejections <- read.csv("C:/CS 134/Final Project 1/alldata/ejections.csv")
View(ejections)
ballparks <- read.csv("C:/CS 134/Final Project 1/alldata/ballparks.csv")
View(ballparks)
teams <- read.csv("C:/CS 134/Final Project 1/alldata/teams.csv")
View(teams)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
ejections_teams <- left_join(ejections, teams, by = "TEAM") %>%
select(TEAM, NICKNAME, DATE, GAMEID, EJECTEENAME, JOB, UMPIRENAME, INNING, REASON)
library(dplyr)
ejections_years <- ejections_teams %>%
mutate(DATE = as.Date(DATE, format = "%m/%d/%Y")) %>%
group_by(Year = format(DATE, "%Y")) %>%
summarize(TOTAL = n())
colnames(ejections_years)[colnames(ejections_years) == "NICKNAME"] <- "TEAM"
colnames(ejections_years)[colnames(ejections_years) == "Year"] <- "YEAR"
library(ggplot2)
ejections_years$YEAR <- as.numeric(ejections_years$YEAR)
ggplot(data = ejections_years,
aes(x = YEAR, y = TOTAL, color = YEAR)) +
geom_point(size = 3) +
labs(title = "Ejections By Year",
subtitle = "1914 had the most ejections (339). 1892 had the least ejections (8). By comparison, 2023 had 247 ejections.") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_x_continuous(breaks = seq(1880, 2030, by = 10), labels = scales::number_format())
ejections_totals <- ejections_teams %>%
group_by(NICKNAME) %>%
summarize(TOTAL = n()) %>%
mutate(PROPORTION = TOTAL / sum(TOTAL))
colnames(ejections_totals)[colnames(ejections_totals) == "NICKNAME"] <- "TEAM"
library(ggplot2)
ggplot(data = ejections_totals,
mapping = aes(x = TEAM, y = TOTAL, color = TEAM)) +
geom_point(size = 3) +
labs(title = "Ejections By Team",
subtitle = "Of current MLB teams, the Dodgers have the most ejections (1097) and the Nationals have the least ejections (128).") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
# Create Data Set for Ejections By Umpire
library(dplyr)
library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
ejections_umpires <- ejections_teams %>%
group_by(UMPIRENAME) %>%
summarize(TOTAL = n(),
`DATE_START` = min(year(as.Date(DATE, format = "%m/%d/%Y"))),
`DATE_END` = max(year(as.Date(DATE, format = "%m/%d/%Y"))),
.groups = "drop")
colnames(ejections_umpires)[colnames(ejections_umpires) == "UMPIRENAME"] <- "UMPIRE"
ggplot(ejections_umpires, aes(x = UMPIRE, y = TOTAL)) +
geom_col(fill = "004d71") +
labs(title = "Total Ejections By Umpire Name", subtitle = "Bill Klem made the most ejections (364 from 1905-1940)", x = "Umpire", y = "Total") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
library(dplyr)
eras <- c("Dead Ball Era", "Live Ball Era", "Integration Era", "Expansion Era", "Free Agency Era", "Steroid Era", "Modern Era")
era_ranges <- c(1901, 1920, 1942, 1961, 1977, 1994, 2005, Inf)
ejections_years_eras <- ejections_teams %>%
mutate(DATE = as.Date(DATE, format = "%m/%d/%Y")) %>%
group_by(Year = format(DATE, "%Y")) %>%
summarize(TOTAL = n())
colnames(ejections_years_eras)[colnames(ejections_years_eras) == "NICKNAME"] <- "TEAM"
colnames(ejections_years_eras)[colnames(ejections_years_eras) == "Year"] <- "YEAR"
ejections_years_eras <- ejections_years_eras %>%
mutate(ERA = case_when(
YEAR >= era_ranges[1] & YEAR < era_ranges[2] ~ eras[1],
YEAR >= era_ranges[2] & YEAR < era_ranges[3] ~ eras[2],
YEAR >= era_ranges[3] & YEAR < era_ranges[4] ~ eras[3],
YEAR >= era_ranges[4] & YEAR < era_ranges[5] ~ eras[4],
YEAR >= era_ranges[5] & YEAR < era_ranges[6] ~ eras[5],
YEAR >= era_ranges[6] & YEAR < era_ranges[7] ~ eras[6],
YEAR >= era_ranges[7] & YEAR < era_ranges[8] ~ eras[7],
YEAR >= era_ranges[4] ~ eras[4],
TRUE ~ "Unknown"
)) %>%
group_by(YEAR, ERA) %>%
summarize(TOTAL = sum(TOTAL))
## `summarise()` has grouped output by 'YEAR'. You can override using the
## `.groups` argument.
library(dplyr)
eras <- c("Dead Ball Era", "Live Ball Era", "Integration Era", "Expansion Era", "Free Agency Era", "Steroid Era", "Modern Era")
era_ranges <- c(1901, 1920, 1942, 1961, 1977, 1994, 2005, Inf)
ejections_eras <- ejections_years %>%
mutate(ERA = case_when(
YEAR >= era_ranges[1] & YEAR < era_ranges[2] ~ eras[1],
YEAR >= era_ranges[2] & YEAR < era_ranges[3] ~ eras[2],
YEAR >= era_ranges[3] & YEAR < era_ranges[4] ~ eras[3],
YEAR >= era_ranges[4] & YEAR < era_ranges[5] ~ eras[4],
YEAR >= era_ranges[5] & YEAR < era_ranges[6] ~ eras[5],
YEAR >= era_ranges[6] & YEAR < era_ranges[7] ~ eras[6],
YEAR >= era_ranges[7] & YEAR < era_ranges[8] ~ eras[7],
YEAR >= era_ranges[4] ~ eras[4],
TRUE ~ "Unknown"
)) %>%
group_by(ERA) %>%
summarize(TOTAL = sum(TOTAL))
library(ggplot2)
ejections_years_eras$YEAR <- as.numeric(as.character(ejections_years_eras$YEAR))
ggplot(ejections_years_eras, aes(x = YEAR, y = TOTAL, fill = ERA)) +
geom_col() +
scale_x_continuous(breaks = seq(1889, 2023, by = 25))
# Observations
What factors have the strongest correlation with ejections? - By looking at the eras of baseball and seeing the spread of ejections amongst those years, I have made the following observations: - Umpires were influenced by the new ejection rule (see Dead Ball Era) and frequently gave ejections. - Increased ejections were influenced by the Steroid Era, assuming increased scoring lead to increased rules broken.
# Making interactive plots for Ejections by Eras
options(repos = c(CRAN = "https://cran.rstudio.com/"))
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ purrr 1.0.2 ✔ tibble 3.2.1
## ✔ readr 2.1.4 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(plotly)
##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout
library(scales)
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
static_plot <- ggplot(ejections_years_eras, aes(x = YEAR, y = TOTAL, fill = ERA)) +
geom_col() +
scale_x_continuous(breaks = seq(1889, 2023, by = 25))
ggplotly(static_plot)
install.packages("flexdashboard")
## Installing package into 'C:/Users/cngil/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)
## package 'flexdashboard' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\cngil\AppData\Local\Temp\RtmpOYrcWF\downloaded_packages