nobel.R

gistfile1.txt

library(tidyverse)

df <- read_csv('nobel.csv')
dfyear <- read_csv('nobel-years.csv')

df %>% 
  left_join(dfyear) %>% 
  mutate(
    is_nobel_year = year == prize_year,
    label = sprintf("%d: %s", prize_year, name)
  ) %>% 
  ggplot(aes(x = year, y = reorder(label, desc(label)))) +
  geom_point(aes(size = editions, color=is_nobel_year), alpha=0.6) +
  theme_bw() +
  labs(
    title='Nobel prize winners (1990-2022) in German translations',
    subtitle = 'based on the North German K10plus union catalogue. For each name we checked all name variants, \nwe did not filter out duplicated records. Colour blue denotes the year of winning the prize.'
    ) +
  ylab('author') +
  xlab('publication year') +
  guides(color = "none")
  

nobel.csv contains 3 columns: name (the name of the author), year (the year), editions (the number of publications on that year)
nobel-years.csv contains 2 columns: name (the name of the author), prize_year (the name when the author received the prize)