R code to generate a randomly selected combination of first/last names from 1990 data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# load required packages | |
library(dplyr) | |
library(babynames) | |
library(readr) | |
# first names from 1990 Social Security Adminstration baby names data | |
malenames <- babynames %>% | |
filter(year == 1990 & sex == "M") | |
malenames <- malenames %>% | |
mutate(rank = seq(1:nrow(malenames))) | |
femalenames <- babynames %>% | |
filter(year == 1990 & sex == "F") | |
femalenames <- femalenames %>% | |
mutate(rank = seq(1:nrow(femalenames))) | |
# sample names | |
male_sample <- tibble(rank=sample(c(1:nrow(malenames)), prob = malenames$prop, size = 10)) %>% | |
inner_join(malenames) | |
female_sample <- tibble(rank=sample(c(1:nrow(femalenames)), prob = femalenames$prop, size = 10)) %>% | |
inner_join(femalenames) | |
# surnames from 1990 US Census | |
surnames <- read.fwf("https://www2.census.gov/topics/genealogy/1990surnames/dist.all.last", widths =c(15,6,8,7)) | |
names(surnames) <- c("name","pc","cum_pc","rank") | |
# sample names | |
sample_m <- tibble(rank=sample(c(1:nrow(surnames)), prob = surnames$pc, size = 10)) %>% | |
inner_join(surnames) | |
sample_f <- tibble(rank=sample(c(1:nrow(surnames)), prob = surnames$pc, size = 10)) %>% | |
inner_join(surnames) | |
# final names | |
female_names_10 <- tibble(first=female_sample$name,last=sample_f$name) | |
male_names_10 <- tibble(first=male_sample$name,last=sample_m$name) | |
write_csv(female_names_10,"female_names.csv",na="") | |
write_csv(male_names_10,"male_names.csv",na="") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment