little_women_names.R

library(babynames)
library(tidyverse)

bab <- babynames %>% filter(sex=="F" & year >= 1945)

bab$rgx_match <- as.character(NA)
for(i in c('Amy', 'Beth', 'Meg', 'Jo')) {
  rgx <- paste0('^', i, '.*$')
  bab$rgx_match <- coalesce(
    ifelse(grepl(rgx, bab$name), rgx, NA),
    bab$rgx_match)
}
    
bab %>%
  filter(!is.na(rgx_match)) %>% 
  group_by(year, name=rgx_match) %>%
  summarise(n=sum(n)) %>%
  ggplot(aes(year, n, color=name, group=name)) +
  geom_line() +
  geom_vline(xintercept = 1968) +
  annotate(geom='text', x=1968, y=20000, 
           label="1968", angle=90, vjust=-1) +
  theme_light() +
  labs(title = 'Count of name matches for US female babies',
       subtitle = 'Source: SSA',
       color='name regex')