Generate a Random Data Frame of Names and Genders

randomRespondents.R

# dependencies
library(dplyr)          # data wrangling
library(gender)         # assess gender
library(randomNames)    # generate names
library(stringr)        # work with strings

# create data frame of random names
names <- randomNames(30, which.names = "both", name.order = "first.last", name.sep = " ")
names <- as.data.frame(names, stringsAsFactors = FALSE)

# parse full name into first and last name variables
names %>%
  rename(fullName = names) %>%
  mutate(firstName = word(fullName,1)) %>%
  mutate(lastName = word(fullName,-1)) -> names

# evaluate names for typical gender
gender <- gender(names$firstName)

# trim gender data frame
gender %>%
  rename(firstName = name) %>%
  select(firstName, gender) -> gender

# combine name and gender data
sampleData <- left_join(names, gender, by = "firstName")

# make sure all names have a gender and there are no duplicates
sampleData <- filter(sampleData, is.na(gender) == FALSE)
sampleData <- distinct(sampleData, fullName, .keep_all = TRUE)

# take random sample of names
index <- sample(1:nrow(sampleData), 20)

# filter based on random sample
sampleData %>%
  mutate(row = row_number()) %>%
  filter(row %in% index == TRUE) %>%
  select(-row) -> sampleData

# save as tibble
sampleData <- as_tibble(sampleData)