Very few judges have been women, historically speaking. Judgeships are lifetime appointments and the data indicates that most stay in their position 20+ years.
In a single chart, demonstrate the ratio of nominations that came from each party, the gender of nominees, and how long they served.
Goal: Make a Sankey diagram showing the flow of nominations through gender and length of service.
# Load packages
library(tidyverse)
library(tidytuesdayR)
library(here)
library(showtext)
library(ggtext)
library(ggalluvial)
library(scales)
# Load helper functions
source(here::here("R/utils/tidy_tuesday_helpers.R"))
# Set project title
title <- "US Judges"
tt_date <- "2025-06-10"# Load data from tidytuesdayR package
tuesdata <- tidytuesdayR::tt_load(tt_date)
# Extract elements from tuesdata
appointments <- tuesdata$judges_appointments
people <- tuesdata$judges_people
# Remove tuesdata file
rm(tuesdata)# View data
head(appointments)# A tibble: 6 × 15
judge_id court_name court_type president_name president_party nomination_date
<dbl> <chr> <chr> <chr> <chr> <chr>
1 3419 U. S. Dist… USDC Barack Obama Democratic 07/28/2011
2 1 U. S. Dist… USDC Franklin D. R… Democratic 02/03/1936
3 2 U. S. Dist… USDC Rutherford B.… Republican 01/06/1880
4 3 U. S. Dist… USDC Ronald Reagan Republican 07/22/1982
5 4 U. S. Dist… USDC Jimmy Carter Democratic 09/28/1979
6 5 U. S. Dist… USDC Gerald Ford Republican 06/18/1976
# ℹ 9 more variables: predecessor_last_name <chr>,
# predecessor_first_name <chr>, senate_confirmation_date <chr>,
# commission_date <chr>, chief_judge_begin <dbl>, chief_judge_end <dbl>,
# retirement_from_active_service <chr>, termination_date <chr>,
# termination_reason <chr>head(people)# A tibble: 6 × 13
judge_id name_first name_middle name_last name_suffix birth_date
<dbl> <chr> <chr> <chr> <chr> <dbl>
1 3419 Ronnie <NA> Abrams <NA> 1968
2 1 Matthew T. Abruzzo <NA> 1889
3 2 Marcus Wilson Acheson <NA> 1828
4 3 William Marsh Acker Jr. 1927
5 4 Harold Arnold Ackerman <NA> 1928
6 5 James Waldo Ackerman <NA> 1926
# ℹ 7 more variables: birthplace_city <chr>, birthplace_state <chr>,
# death_date <dbl>, death_city <chr>, death_state <chr>, gender <chr>,
# race <chr># Join tables and remove unneccesary columns
df <- appointments |>
left_join(people, by = "judge_id") |>
select(judge_id, name_first, name_middle, name_last, president_party, gender, commission_date, termination_date)
# Remove judges nominated by other parties (e.g., Whig, Federalist, etc.)
df <- df |>
mutate(president_party_grouped = case_when(
president_party == "Republican" ~ "Republican",
president_party == "Democratic" ~ "Democrat",
TRUE ~ "Other"
)) |>
filter(president_party_grouped != "Other") |>
select(-president_party)# Convert dates from character to Date type and calculate service length
df <- df |>
mutate(start_date = as.Date(commission_date, format = "%m/%d/%Y"),
end_date = as.Date(termination_date, format = "%m/%d/%Y"),
end_date = if_else(
is.na(end_date),
Sys.Date(),
end_date),
length_of_service = round(as.numeric(end_date - start_date) / 365.25, 1)
)# Create service length buckets
df <- df |>
mutate(length_of_service = case_when(
length_of_service < 5 ~ "0 - 5 years",
length_of_service < 10 ~ "5 - 10 years",
length_of_service < 15 ~ "10 - 15 years",
length_of_service < 20 ~ "15 - 20 years",
length_of_service >= 20 ~ "20+ years"
))# Group data for the Sankey
agg_df <- as.data.frame(table(df$president_party_grouped,
df$gender,
df$length_of_service))
# Add column names
colnames(agg_df) <- c("presidents_party", "judge_gender", "service_length", "freq")
# Re-order factor levels
agg_df$service_length <- fct_relevel(agg_df$service_length, c("0 - 5 years",
"5 - 10 years",
"10 - 15 years",
"15 - 20 years",
"20+ years"))# Load font
font_add_google("Merriweather", "merriweather")
showtext_auto()
showtext_opts(dpi = 300)
# Make plot
final_plot <- ggplot(agg_df) +
aes(
axis1 = presidents_party,
axis2 = judge_gender,
axis3 = service_length,
y = freq
) +
geom_alluvium(
aes(fill = presidents_party),
width = 1 / 12
) +
scale_fill_manual(values = c(
"Democrat" = "#3B77AF",
"Republican" = "#C43D35"
)) +
geom_stratum(
width = 0.4,
fill = "gray80"
) +
geom_text(
stat = "stratum",
aes(label = after_stat(stratum)),
family = "merriweather",
color = "#4A4A4A"
) +
scale_x_discrete(
limits = c("President's Party", "Gender", "Service Length"),
expand = c(0.1, 0.1)
) +
scale_y_continuous(labels = scales::comma) +
theme_minimal(base_family = "merriweather") +
labs(
title = "U.S. Judge Appointments Since 1789",
subtitle = "Federal appointments are a big deal because most judges end up serving more than 20 years. \nRepublican presidents have appointed 208 more judges than Democratic presidents. Historically, \nmost judges have been men, but women are increasingly holding these positions.",
y = "Appointments",
caption = "\nChart produced by Steven Villalon for Tidy Tuesday exercise on June 10, 2025."
) +
theme(
plot.background = element_rect(fill = "#EFDECD"),
panel.background = element_rect(fill = "#EFDECD"),
panel.grid = element_blank(),
legend.position = "none",
plot.margin = margin(t = 20, r = 20, b = 20, l = 20),
plot.title = element_text(
face = "bold",
size = 20,
color = "#8A3324"
),
plot.subtitle = element_text(
size = 10,
color = "gray30"
),
plot.caption = element_text(
hjust = 0,
color = "gray30"
),
axis.text.x = element_text(
size = 12,
color = "gray30"
),
axis.title.y = element_text(
size = 12,
color = "gray30",
margin = margin(r = 10)
)
)
final_plot
# Select file formats to export to
formats_to_export <- c("png", "svg")
# Save files to the output folder (uses custom R script)
save_tt_plots(
plot = final_plot,
title = title,
date = tt_date,
output_folder = "output",
formats = formats_to_export,
height = 6,
width = 8,
dpi = 300
)R version 4.4.1 (2024-06-14)
Platform: x86_64-apple-darwin20
Running under: macOS Ventura 13.7.6
Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/4.4-x86_64/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.4-x86_64/Resources/lib/libRlapack.dylib; LAPACK version 3.12.0
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
time zone: America/New_York
tzcode source: internal
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] scales_1.4.0 ggalluvial_0.12.5 ggtext_0.1.2 showtext_0.9-7
[5] showtextdb_3.0 sysfonts_0.8.9 here_1.0.1 tidytuesdayR_1.2.1
[9] lubridate_1.9.4 forcats_1.0.0 stringr_1.5.1 dplyr_1.1.4
[13] purrr_1.0.4 readr_2.1.5 tidyr_1.3.1 tibble_3.2.1
[17] ggplot2_3.5.2 tidyverse_2.0.0
loaded via a namespace (and not attached):
[1] utf8_1.2.5 rappdirs_0.3.3 generics_0.1.4 xml2_1.3.8
[5] stringi_1.8.7 hms_1.1.3 digest_0.6.37 magrittr_2.0.3
[9] evaluate_1.0.3 grid_4.4.1 timechange_0.3.0 RColorBrewer_1.1-3
[13] fastmap_1.2.0 rprojroot_2.0.4 jsonlite_2.0.0 textshaping_1.0.1
[17] httr2_1.1.2 cli_3.6.5 crayon_1.5.3 rlang_1.1.6
[21] gitcreds_0.1.2 bit64_4.6.0-1 withr_3.0.2 yaml_2.3.10
[25] parallel_4.4.1 tools_4.4.1 tzdb_0.5.0 curl_6.2.3
[29] vctrs_0.6.5 R6_2.6.1 lifecycle_1.0.4 bit_4.6.0
[33] htmlwidgets_1.6.4 vroom_1.6.5 ragg_1.4.0 pkgconfig_2.0.3
[37] pillar_1.10.2 gtable_0.3.6 glue_1.8.0 gh_1.5.0
[41] Rcpp_1.0.14 systemfonts_1.2.3 xfun_0.52 tidyselect_1.2.1
[45] knitr_1.50 farver_2.1.2 htmltools_0.5.8.1 svglite_2.2.1
[49] labeling_0.4.3 rmarkdown_2.29 compiler_4.4.1 gridtext_0.1.5