if(!require(tidyverse)){install.packages("tidyverse"); library(tidyverse)}
if(!require(survival)){install.packages("survival"); library(survival)}
if(!require(survminer)){install.packages("survminer"); library(survminer)}
if(!require(ggfortify)){install.packages("ggfortify"); library(ggfortify)}
if(!require(patchwork)){install.packages("patchwork"); library(patchwork)}
if(!require(tidyverse)){install.packages("tidyverse"); library(tidyverse)}
if(!require(sysfonts)){install.packages("sysfonts"); library(sysfonts)}
if(!require(showtext)){install.packages("showtext"); library(showtext)}
if(!require(RColorBrewer)){install.packages("RColorBrewer");library(RColorBrewer)}
font_add_google("Roboto Mono", "roboto_mono")
font <- "roboto_mono"
showtext_auto()
# Color palette
color <- palette.colors(palette = "Okabe-Ito")
color <- append(color, "#40B0A6")
color[1] <- "#D41159"
Custom_Style <- function() {
ggplot2::theme(
plot.title = ggplot2::element_text(family=font,
size=28,
face="bold",
color="#222222"),
plot.subtitle = ggplot2::element_text(family=font,
size=20,
color="#222222"),
plot.caption = ggplot2::element_text(family=font,
size=12,
color="#222222"),
legend.position = "bottom",
legend.title = ggplot2::element_text(family=font,
size=12,
face="bold",
color="#222222"),
# legend.text.align = 0,
legend.key = ggplot2::element_blank(),
legend.text = ggplot2::element_text(family=font,
size=9,
color="#222222"),
# Axis format
axis.text = ggplot2::element_text(family = font,
size=10,
color="#222222"),
axis.text.x = ggplot2::element_text(margin=ggplot2::margin(5, b = 10)),
axis.line = ggplot2::element_line(colour = alpha('#222222', 0.5), size =0.5),
axis.title = ggplot2::element_text(family=font,
size=12,
face="bold",
color="#222222"),
# Grid lines
panel.grid.minor = ggplot2::element_blank(),
panel.grid.major.y = ggplot2::element_blank(),
panel.grid.major.x = ggplot2::element_blank(),
# Very pale cream/yellow background
panel.background = element_rect(fill = "#FFFBF0",
color = "#FFFBF0",
linewidth = 0.5,
linetype = "solid"),
plot.background = element_rect(fill = "#FFFBF0",
color = "#FFFBF0",
linewidth = 0.5,
linetype = "solid"),
legend.background = element_rect(fill = "#FFFBF0",
color = "#FFFBF0",
linewidth = 0.5,
linetype = "solid"),
)
}
cdc_datasets <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-02-11/cdc_datasets.csv')
fpi_codes <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-02-11/fpi_codes.csv')
omb_codes <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-02-11/omb_codes.csv')
Agency <- omb_codes %>%
group_by(agency_name) %>%
summarise(n = n()) %>%
arrange(desc(n)) %>%
slice(1: 10)
p1 <- Agency %>%
ggplot(aes(x = fct_reorder(agency_name, n, .desc = TRUE), y = n)) + # Explicitly set y to n
geom_col(aes(fill = as.factor(agency_name))) + # Use geom_col() instead of geom_bar()
labs(subtitle = str_wrap("CDC Database Archiving: Top 10 Agencies that have archived databases since 2016", 40), x = "Agency Name", y = "Count (n)", fill = "Agency Name") +
geom_text(aes(label = paste0("n = ", n)),
vjust = -0.5, # Position above the bar
size = 4, # Adjusted size for better readability
family = font) +
Custom_Style() +
scale_fill_manual(values = color) +
scale_x_discrete(labels = function(x) str_wrap(x, width =10)) +
theme(legend.position = "none",
legend.title = element_blank(),
axis.text.x = element_text(size = 6))
timeline_data <- cdc_datasets %>%
mutate(
level_of_access = case_when(
public_access_level %in% c("public", "public domain") ~ "Public Access",
public_access_level == "restricted public" ~ "Restricted Access",
public_access_level == "non-public" ~ "No Public Access",
TRUE ~ "Unspecified"
),
issued = as.Date(issued)
) %>%
filter(!is.na(issued)) |>
arrange(issued) %>%
mutate(
Time_to_Archiv = as.numeric(issued - min(issued)),
Evt = 1,
archival_date = min(issued) + Time_to_Archiv
)
min <- min(timeline_data$issued)
km_fit <- survfit(Surv(Time_to_Archiv, Evt) ~ 1, data = timeline_data)
km_df <- data.frame(
time = km_fit$time,
survival = km_fit$surv,
cumulative_events = 1 - km_fit$surv,
archival_date = min(timeline_data$issued) + km_fit$time
)
p2 <- ggplot(km_df, aes(x = archival_date, y = cumulative_events)) +
geom_step(color = "#40B0A6") +
scale_x_date(date_breaks = "1 year", date_labels = "%Y") + # Format x-axis as years
labs(x = "Year", y = "Archival Events", subtitle = str_wrap("Kaplan-Meier Curve of Archiving of CDC Databases", 40), caption = "Each step signifies an increase in database archiving \n TidyTuesday: Week 6, 2025") +
Custom_Style() +
theme(axis.text.y = element_blank())
p1
