zach_alt_spelling.R

library(tidyverse)

# zachary / zachery by year
z_dat <- babynames::babynames %>%
  filter(grepl('^zach(a|e)ry$', tolower(name)) & year >= 1950) %>%
  group_by(name, year) %>%
  summarise(n=sum(n))

# when was peak zachary? 1993
z_dat %>%
  group_by(name) %>%
  summarise(year[which.max(n)])

# percent Zachery among (Zachary + Zachery) in a given year (5% in 86)
z_dat %>%
  filter(year == 1986) %>%
  with(., n[2] / sum(n))

# plot
z_dat %>%
  ggplot(aes(x=year, y=n, color=name)) +
  geom_line() +
  facet_wrap(~name, scales='free_y') +
  theme_light() +
  theme(legend.position = 'none') +
  scale_y_continuous(labels = scales::comma) +
  labs(title='USA baby name frequency by year',
       subtitle = "source: Social Security Administration",
       y='occurrences', x='year')

# incidence of the less common spelling is pretty well correlated w the name's popularity
merge(
  z_dat %>% 
  ungroup %>%
  filter(name=='Zachary') %>% 
  mutate('Zachary'=n) %>%
  select(-name, -n),
  
  z_dat %>% 
    ungroup %>%
    filter(name=='Zachery') %>% 
    mutate('Zachery'=n) %>%
    select(-name, -n),
  by='year', all=T) %>%
  mutate(all_zach = Zachary + Zachery,
         pct_zachery = Zachery / all_zach) %>%
  data.table::melt(id.var='year') %>%
  filter(variable %in% c('all_zach', 'pct_zachery'),
         year %>% between(1980, 2015)) %>%
  ggplot(aes(x=year, y=value, color=variable)) +
  geom_line() +
  facet_wrap(~variable, ncol=1, scales='free_y') +
  labs(y=NULL) +
  theme_light() + theme(legend.position='none') +
  scale_color_brewer(palette = 1, type='qual')