# The frequency of names starting with vowels vs. consonants over time

The frequency of names starting with vowels vs. consonants over time

The data set babynames provides all names for US babies from 1880-2017. Using this resources, I want to determine the frequency of names starting with vowels vs. consonants over time

I believe the amount of names starting with constants will exceedingly surpass individuals names starting with vowels.

The first step is to load all of my packages

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.8     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.1
## ✔ readr   2.1.2     ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(babynames)
library(ggthemes)

The first step is to determine first letters in all the names.

baby_first_letter <- babynames %>%
  mutate(first_letter = substr(name, 1,1)) 

I then filtered the first letter into vowels and directed a,e,i,o,u to be refferd to as vowels

baby_first_letter %>% 
  filter(first_letter %in% c("A", "E", "I", "O", "U")) -> vowels


vowels %>% 
  group_by(year, first_letter) %>% 
  summarize(total = sum(n)) %>% 
  ggplot(aes(year, total, color = first_letter)) + geom_line()

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

The data arranges the baby’s first letter by one of the five vowels and plots it

baby_first_letter %>% 
  filter(first_letter %in% c("B","C","D", "F", "G", "H", "J","K", "L", "M", "N","P", "Q", "R", "S", "T", "V", "W", "X", "Y", "Z")) -> constants

I then filtered to 21 constants and directed them to be titled as constants

constants %>% 
  group_by(year, first_letter) %>% 
  summarize(total = sum(n)) %>% 
  ggplot(aes(year, total, color = first_letter)) + geom_line()

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

The data arranges the baby’s first letter by one of the 21 consonants and plots the seperate individual letters

Next I will plot the vowels and consonants together

vowels %>% 
  mutate(type = "vowel") -> vowels

constants %>% 
  mutate(type = "constants") -> constants

vowels %>% 
  full_join(constants) -> grouped

## Joining, by = c("year", "sex", "name", "n", "prop", "first_letter", "type")

I then added a new column to group the 21 consonants and titled the group constants so the 21 separate letters would group together. Next, I added a new column to the 5 vowels and labeled the group vowels. After, I joined the constants group and vowels andplotted them together.

vowels %>% 
  group_by(year, type) %>% 
  summarize(total = sum(n)) -> vowels_per_year

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

grouped %>% 
  group_by(year, type) %>% 
  summarize(total = sum(n)) -> per_year

## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.

I then plotted the points together and separated the values into the same proportion so the data would be accurately depicted.

per_year <- per_year %>% 
  mutate(normal= case_when(type %in% "vowel" ~ total/5,
                           type%in% "constants" ~ total/21))

ggplot(per_year, aes(year, normal, color = type)) + geom_line()

The number of individuals with names starting with constants is significantly higher than those starting with a vowel. When the values are placed into the same proportion the constants in the mid to late 1900’s are significantly higher than names beginning with vowels. Recently, there has been a jump in individuals names starting with vowels.