093: Long Ball

Load data

library(cbbplotR)

# notes from downloading the files from stats.ncaa.org and then joining them
# files <- list.files(pattern="*.xlsx")

# obp_data <- data.frame()

# for (file in files) {
#  data <- readxl::read_xlsx(file)
#  obp_data <- rbind(obp_data, data)
# } 

# load in hr data
# files <- list.files(pattern="*.xlsx")

# hr_data <- data.frame()

# for (file in files) {
#  data <- readxl::read_xlsx(file)
#  hr_data <- rbind(hr_data, data)
# } 

# load in runs data 
# files <- list.files(pattern="*.xlsx")


# run_data <- data.frame()


# for (file in files) {
#  data <- readxl::read_xlsx(file)
#  run_data <- rbind(run_data, data)
# } 

# combine all the data by year 
# hr_data |> 
#  dplyr::group_by(Year) |> 
#  dplyr::summarise(
#    hr_g = sum(G),
#    total_hr = sum(HR),
#    max_team = Team[which.max(HR)],
#    max_hr = max(HR),
#    hrs_per_game = mean(HR/G),
#    list_hr = list(rev(HR/G))
#  ) |> 
#  dplyr::arrange(-hrs_per_game) -> hrpg 

# run_data |> 
#   dplyr::group_by(Year) |> 
#  dplyr::summarise(
#    run_g = sum(G),
#    total_runs = sum(R),
#    runs_per_game = mean(R/G)
#  ) |> 
#  dplyr::arrange(-runs_per_game) -> runpg

# obp_data |> 
#  dplyr::group_by(Year) |> 
#  dplyr::summarise(
#    obp_g = sum(G),
#    total_abs = sum(AB),
#    mean_obp = mean(PCT)
#  )  -> obp_pg


# hitdata <- runpg |> 
#  dplyr::left_join(hrpg, by = "Year") |> 
#  dplyr::left_join(obp_pg, by = "Year") |> 
#  dplyr::mutate(
#    ab_hr = total_abs/total_hr,
#  ) |> 
#  dplyr::select(-list_hr)

dingers <- readr::read_csv("dingers-24.csv")

xMR plot

dingers |> 
  ggplot2::ggplot(ggplot2::aes(x = Year, y = hrs_per_game,
                               label = round(hrs_per_game, 2))) +
  ggplot2::geom_point(color = "#333333", size = 3, shape = 21) + 
  ggplot2::geom_line(color = "#333333", linewidth = 1) + 
  ggplot2::geom_text(vjust = -2.25) +
  ggplot2::scale_x_continuous(breaks = seq(2014, 2024, 1)) +
  ggplot2::scale_y_continuous(breaks = seq(0, 1.5, .25), limits = c(0, 1.25)) +
  ggQC::stat_QC(method = "XmR",  color.qc_limits = "#b2182b", 
                color.qc_center = "#2b83ba") +
  ggthemes::theme_fivethirtyeight() +
  ggplot2::labs(
    title = "College Baseball: Home Runs per game by season",
    subtitle = "Teams are hitting more and more home runs per game over the past decade.<br>  \nChart shows variation using the <span style='color:#2b83ba'>average</span>, plus the 
    <span style='color:#b2182b'>upper control and lower control</span> over this span of time.",
    x = "",
    y = "HRs per game",
    caption = "<br>Viz by Chris @dadgumboxscores & Bless your chart<br>  \nData via stats.ncaa.org through May 12, 2024 games"
  ) +
  ggplot2::theme(legend.position = "none", 
                 plot.title = ggtext::element_markdown(), 
                 plot.subtitle = ggtext::element_textbox_simple(),
                 plot.caption = ggtext::element_markdown(),
                 text= ggplot2::element_text(family="Arial"), 
                 panel.grid = ggplot2::element_blank()
       ) +
  ggplot2::annotate(
    geom = "label",
    x = 2020,
    y = 0.25,
    color = "#333333",
    fill = "#ffffbf",
    label = "COVID cancelled 2020  \nseason in March",
    size = 3.25,
    fontface = 'bold',
    alpha = 0.3
  ) -> dinger_xmr_plot 

ggplot2::ggsave(
  "xmr_hrs.png",
  dinger_xmr_plot,
  w = 9.5,
  h = 8.5,
  dpi = 300,
  type = 'cairo'
)


dinger_xmr_plot