Estimate Age from First Name in R

estimate_age.R

library(stringr)
library(plyr)

# We're assuming you've downloaded the SSA files into your R project directory.

file_listing = list.files()[3:135]
for (f in file_listing) {
  year = str_extract(f, "[0-9]{4}")
  if (year == "1880") { # Initializing the very long dataframe
    name_data = read.csv(f, header=FALSE)
    names(name_data) = c("Name", "Sex", "Pop")
    name_data$Year = rep(year, dim(name_data)[1]) }
  else { # adding onto the very long dataframe
    name_data_new = read.csv(f, header=FALSE)
    names(name_data_new) = c("Name", "Sex", "Pop")
    name_data_new$Year = rep(year, dim(name_data_new)[1])
    name_data = rbind(name_data, name_data_new)
  }}

year_pop_totals = ddply(name_data, .(Year), function (x) sum(x$Pop))
name_data = merge(name_data, year_pop_totals, by.x="Year", by.y="Year", all.x=TRUE)
name_data$Rel_Pop = name_data$Pop/name_data$V1

estimate_age = function (input_name, sex = NA) {
  if (is.na(sex)) {
    name_subset = subset(name_data, Name == input_name & Year >= 1921)} #1921 is a year I chose arbitrarily.  Change how you like.
  else {
    name_subset = subset(name_data, Name == input_name & Year >= 1921 & Sex == sex)
  }
  year_and_rel_pop = name_subset[which(name_subset$Rel_Pop == max(name_subset$Rel_Pop)),c(1,6)]
  current_year = as.numeric(substr(Sys.time(),1,4))
  estimated_age = current_year - as.numeric(year_and_rel_pop[1])
  return(list(year_of_birth=as.numeric(year_and_rel_pop[1]), age=estimated_age, relative_pop=sprintf("%1.2f%%",year_and_rel_pop[2]*100)))
}