Tidy_Tuesday_CRAN

library(tidyverse)
library(ggthemes)

cran_code <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-11-12/loc_cran_packages.csv")

# Plot 1 ####
cran_code %>%
  group_by(language) %>%
  summarise(n = n()) %>%
  arrange(-n) %>%
  top_n(10, n) %>% 
  left_join(cran_code, by = "language") %>%
  mutate(prop_comments = (comment / (code + comment + blank)) * 100) %>%
  group_by(language) %>%
  summarise(mean_comments_percent = mean(prop_comments)) %>%
  ggplot(aes(x = fct_reorder(language, mean_comments_percent, median), 
             y = mean_comments_percent,
             fill = language)) +
  geom_col() +
  coord_flip() +
  guides(fill = FALSE) +
  labs(title = "Mean % of comments in package scripts",
       subtitle = "10 most commonly used languages in packages on CRAN",
       x = NULL,
       y = "Mean % of script lines which are comments") +
  scale_fill_viridis(option = "A", discrete = TRUE) +
  theme_economist() +
  theme(text = element_text(size = 12))
  
  # Plot 2 ####
  cran_code %>%
  group_by(language) %>%
  summarise(total = sum(code), med = median(code)) %>%
  arrange(-total) %>%
  top_n(10, total) %>%
  inner_join(cran_code, by = "language") %>%
  group_by(language) %>%
  ggplot(aes(x = fct_reorder(language, -med), y = code, colour = language)) +
  geom_jitter(width = .1, alpha = .01, size = 5) +
  stat_summary(fun.y = median, fun.ymin = min, fun.ymax = max, colour = "black", alpha = .3) +
  scale_y_log10() +
  theme_economist() +
  theme(axis.text.x = element_text(angle = 90, hjust = 0)) +
  theme(text = element_text(size = 12)) +
  labs(title = "Lines of code (log) by language in packages on CRAN",
       subtitle = "Top 10 languges determined by total lines of code in each language",
       x = NULL,
       y = "Number of lines of code (log)") +
  guides(colour = FALSE)