Created
May 5, 2014 16:36
-
-
Save malev/f2e5a2d37f0fea5d4a74 to your computer and use it in GitHub Desktop.
Gender detection testing app
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
require 'csv' | |
require 'net/http' | |
require 'json' | |
require 'beauvoir' | |
require 'sexmachine' | |
names_with_gender = [] | |
CSV.foreach('input.csv') do |row| | |
names_with_gender << row | |
end | |
class Genderize | |
attr_reader :names_with_gender, :names | |
def initialize(names=[]) | |
@names = names | |
@names_with_gender = [] | |
if File.exists?('cache.json') | |
call_cache | |
else | |
call | |
end | |
end | |
def guess(name) | |
names_with_gender[@names.index(name)][1] | |
end | |
def call | |
parse(Net::HTTP.get(uri)) | |
end | |
def call_cache | |
parse(File.open('cache.json').readlines().first) | |
end | |
def parse(res) | |
JSON.parse(res).each do |genderize| | |
names << genderize['name'] | |
names_with_gender << [genderize['name'], clean_gender(genderize['gender'])] | |
end | |
end | |
def clean_gender(gender) | |
if gender | |
gender | |
else | |
"unknown" | |
end | |
end | |
def uri | |
pre_query_string = [] | |
names.each_with_index do |name, index| | |
pre_query_string << "name[#{index}]=#{name}" | |
end | |
URI("http://api.genderize.io?" + pre_query_string.join("&")) | |
end | |
end | |
class SexMachinizer | |
def initialize | |
@detector = SexMachine::Detector.new(unknown_value: 'unknown') | |
end | |
def guess(name) | |
clean(@detector.get_gender(name).to_s) | |
end | |
def clean(gender) | |
if /\_/ =~ gender | |
gender.split('_')[1] | |
else | |
gender | |
end | |
end | |
end | |
beauvoir = Beauvoir::Categorizer.new | |
sex_machinizer = SexMachinizer.new | |
genderize = Genderize.new | |
CSV.open('output.csv', 'w') do |csv| | |
names_with_gender.sort_by { |name_with_gender| name_with_gender[0] }.each do |row| | |
row << beauvoir.guess(row[0]) | |
row << sex_machinizer.guess(row[0]) | |
row << genderize.guess(row[0]) | |
csv << row | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment