Babynames

The Data

The data this week comes from babynames R package from Hadley Wickham. Note that other datasets exist, like the nzbabynames package from Emily Kothe.

babynames <- read_csv("babynames.csv") %>%
  janitor::clean_names()

nz_baby <- read_csv("nz_names.csv") %>%
  janitor::clean_names() %>%
  mutate(sex = case_when(
    sex == "Female" ~ "F",
    sex == "Male" ~ "M",
    TRUE ~ sex
  ))

maori_baby <- read_csv("maorinames.csv") %>%
  janitor::clean_names() %>%
  mutate(sex = case_when(
    sex == "Female" ~ "F",
    sex == "Male" ~ "M",
    TRUE ~ sex
  ))


all_names <- babynames %>% 
  inner_join(nz_baby, by = c("name" = "name", "sex" = "sex", "year" = "year")) %>%
  mutate(nz_count = count, us_count = n)

pop_nz_names_F <- nz_baby %>%
  filter(sex == "F") %>%
  group_by(name) %>%
  summarize(nz_count = sum(count)) %>%
  arrange(nz_count) %>%
  top_n(10) %>% 
  select(name) %>%
  pull()

pop_nz_names_M <- nz_baby %>%
  filter(sex == "M") %>%
  group_by(name) %>%
  summarize(nz_count = sum(count)) %>%
  arrange(nz_count) %>%
  top_n(10) %>% 
  select(name) %>%
  pull()

Wrangling

The most poisoned baby name in history, read this.

babynames %>%
  filter(name == "Hilary") %>%
  filter(sex == "F") %>%
  ggplot() + 
  geom_line(aes(x = year, y = n)) + 
  geom_vline(xintercept = 1992)

all_names %>%
  filter(name %in% pop_nz_names_F) %>%
  filter(sex == "F") %>%
  ggplot(aes(x = year)) + 
  geom_line(aes(y = nz_count*100, color = "NZ")) + 
  geom_line(aes(y = us_count, color = "US")) + 
  scale_y_continuous(sec.axis = sec_axis(~./100, name = "Name Count in NZ") ) +
  scale_color_manual(values = c("#52854C", "#CC79A7")) + 
  labs(y = "Name Count in US",
       x = "",
       color = "Country",
       title = "Comparison of female name popularity",
       subtitle = "top 10 most popular NZ female names over all years") + 
  facet_wrap(~name)

all_names %>%
  filter(name %in% pop_nz_names_M) %>%
  filter(sex == "M") %>%
  ggplot(aes(x = year)) + 
  geom_line(aes(y = nz_count*100, color = "NZ")) + 
  geom_line(aes(y = us_count, color = "US")) + 
  scale_y_continuous(sec.axis = sec_axis(~./100, name = "Name Count in NZ") ) +
  scale_color_manual(values = c("#52854C", "#CC79A7")) + 
  labs(y = "Name Count in US",
       x = "",
       color = "Country",
       title = "Comparison of male name popularity",
       subtitle = "top 10 most popular NZ male names over all years") + 
  facet_wrap(~name)

all_names %>%
  filter(year == 2017) %>%
  ggplot() + 
  geom_point(aes(x = us_count, y = nz_count, color = sex)) +
  coord_trans(x = "log10", y = "log10")