serial_killers.R

library(rvest)
library(dplyr)
library(stringr)
library(ggplot2)

tbls <- read_html('https://en.wikipedia.org/wiki/List_of_serial_killers_by_number_of_victims') %>% html_table()


t1 <- tbls[[1]] %>% select(name = Name, country = Country, years = `Years active`, victims = `Proven victims`) %>% mutate(victims = as.character(victims))
t2 <- tbls[[2]] %>% select(name = Name, country = Country, years = `Years active`, victims = `Proven victims`)
t3 <- tbls[[3]] %>% select(name = Name, country = Country, years = `Years active`, victims = `Proven victims*`)
t4 <- tbls[[4]] %>% select(name = Name, country = Country, years = `Years active`, victims = `Proven victims*`) %>% mutate(victims = as.character(victims)) 


first.year <- Vectorize(function(s) {
  min(as.numeric(unlist(stringr::str_match_all(s, '[0-9]{4}'))))
})

last.year <- Vectorize(function(s) {
  max(as.numeric(unlist(stringr::str_match_all(s, '[0-9]{4}'))))
})

bind_rows(t1, t2, t3, t4) %>%
  mutate(first.year = first.year(years),
         last.year = last.year(years),
         victims = as.numeric(stringr::str_extract(victims, '[0-9]+'))) %>%
  group_by(last.year) %>%
  summarise(n = n(), victims = sum(victims)) %>%
  ggplot(aes(x = last.year, y = n)) +
  geom_line() +
  xlab('Last Year Active') +
  ylab('Number of Serial Killers') +
  theme_bw()