Average Penis and Breast Size by Country

Daily Graph Series

Average Penis and Breast Size

R Code for Plot

# Load some R packages: 
library(rvest)
library(tidyverse)
library(hrbrthemes)
my_font <- "Roboto Condensed"
bkgrnd <- "#1e1e1e"

# Collect data: 

"https://www.worlddata.info/average-breastsize.php" %>% 
  read_html() %>% 
  html_table() %>% 
  .[[1]] -> breast_size



"https://www.worlddata.info/average-penissize.php" %>% 
  read_html() %>% 
  html_table() %>% 
  .[[1]] -> penis_size



# Rename for all columns: 

names(breast_size) <- c("rank", "country", "cup", "volume", "min_vol_quan", "max_vol_quan", "bmi")
names(penis_size) <- c("rank", "country", "penis_length", "body_heifht", "percent_height")

n1 <- nrow(breast_size)
n2 <- nrow(penis_size)

r1 <- floor(n1 / 3)
r2 <- floor(n2 / 3)


breast_size %>% 
  mutate(group = case_when(rank <= r1 ~ "Biggest", 
                           rank > r1 & rank <= 2*r1 ~ "Middle", 
                           TRUE ~ "Smallest")) %>% 
  arrange(volume) %>% 
  mutate(country = factor(country, levels = country)) -> breast_size

colors1 <- c("firebrick", "yellow", "cyan")
colors2 <- c("firebrick", "#cc4125", "#073763")

breast_size %>% 
  ggplot(aes(country, volume, fill = group, color = group)) + 
  geom_col(width = 0.8) + 
  theme_modern_rc() + 
  facet_wrap(~ group, scales = "free_y") + 
  coord_flip() + 
  scale_fill_manual(values = colors2, name = "") + 
  scale_color_manual(values = colors2, name = "") + 
  geom_text(data =  breast_size %>% filter(volume >= 370), aes(label = volume), 
            color = "white", hjust = 1.1, family = my_font, size = 3.5) + 
  geom_text(data =  breast_size %>% filter(volume < 370), aes(label = volume),
            color = "white", hjust = -0.2, family = my_font, size = 3.5) + 
  theme(legend.text = element_text(color = "white")) + 
  theme(legend.position = "top") + 
  theme(axis.text.x = element_blank()) + 
  theme(panel.grid = element_blank()) + 
  theme(legend.text = element_text(size = 11, face = "bold", family = my_font)) + 
  theme(plot.caption = element_text(size = 11, face = "italic")) + 
  theme(plot.subtitle = element_text(size = 13, color = "white")) + 
  theme(plot.title = element_text(size = 22)) + 
  labs(x = NULL, y = NULL, 
       title = "Figure 1: Average Breast Size by Country, 2019", 
       subtitle = "In the evaluations there are no self-assessments, but only results of medical professionals. All subjects were between 28 and\n30 years old and were divided according to their country of birth. All women were in normal health, not pregnant, not lactating,\nhormonally treated and had no breast surgery. The breast size measurement is in cubic centimeter.", 
       caption = "Data Source: https://www.worlddata.info") + 
  theme(axis.text.y = element_text(color = "white", size = 10)) + 
  theme(axis.text.x = element_blank())
  
  

penis_size %>% 
  mutate(penis_length = str_replace_all(penis_length, " cm", "") %>% as.numeric()) %>% 
  mutate(group = case_when(rank <= r2 ~ "Biggest", 
                           rank > r2 & rank <= 2*r2 ~ "Middle", 
                           TRUE ~ "Smallest")) %>% 
  arrange(penis_length) %>% 
  mutate(country = case_when(str_detect(country, "the Congo") ~ "Congo", 
                             str_detect(country, "Central African") ~ "Central African", 
                             TRUE ~ country)) %>% 
  mutate(country = factor(country, levels = country)) -> penis_size 

penis_size %>% 
  mutate(label = as.character(penis_length %>% round(1))) %>% 
  mutate(label = case_when(str_detect(country, "Korea") ~ label, 
                           str_count(label) != 4 ~ paste0(label, ".0"),
                           TRUE ~ label)) -> penis_size



penis_size %>% 
  ggplot(aes(country, penis_length, fill = group, color = group)) + 
  geom_col(width = 0.8) + 
  theme_modern_rc() + 
  facet_wrap(~ group, scales = "free_y") + 
  coord_flip() + 
  scale_fill_manual(values = colors2, name = "") + 
  scale_color_manual(values = colors2, name = "") + 
  geom_text(aes(label = label), color = "white", hjust = 1.1) + 
  theme(legend.text = element_text(color = "white")) + 
  theme(legend.position = "top") + 
  theme(axis.text.x = element_blank()) + 
  theme(panel.grid = element_blank()) + 
  theme(legend.text = element_text(size = 11, face = "bold", family = my_font)) + 
  theme(plot.subtitle = element_text(size = 13, color = "white")) + 
  theme(plot.caption = element_text(size = 11, face = "italic")) + 
  theme(plot.title = element_text(size = 22)) + 
  labs(x = NULL, y = NULL, 
       title = "Figure 2: Average Penis Size by Country, 2019", 
       subtitle = "Basically, the length is always measured on the top of the stem root to the top of the glans. Over all countries the average size of a penis\nis about 14.03 cm. The longest one is 17.93 cm long and carried by men in Congo. Men in South Korea have to get along with only 9.66 cm.", 
       caption = "Data Source: https://www.worlddata.info") + 
  theme(axis.text.y = element_text(color = "white", size = 10)) + 
  theme(axis.text.x = element_blank())