Infer Gender from a Census Name Matrix

Aggregates the male and female birth-certificate counts for the supplied name tokens and returns the majority gender together with its confidence.

Usage

determine_gender(x)

Arguments

x

A data.table of census data as returned by get_census_data(), containing the male_value and female_value columns.

Value

A character vector of length two: the inferred gender code ("M", "F", or "U" when no counts are available) and the confidence percentage for that call. When gender is unknown only "U" is returned.

Examples

x <- "livingston III,  Mr. MICHAEL JOHN9"
x <- prep_name(x)
x <- strsplit(x, " ")[[1]]
cd <- get_census_data(x)
determine_gender(cd)
#> [1] "M"    "99.6"