Created
March 31, 2014 21:08
-
-
Save malev/9902323 to your computer and use it in GitHub Desktop.
Generalize
This file contains hidden or 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 'json' | |
require 'uri' | |
require 'ostruct' | |
require 'httparty' | |
require 'progressbar' | |
require 'people' | |
class OutputCSV | |
attr_reader :filename | |
def initialize(filename) | |
@filename = filename | |
end | |
def store(rows) | |
CSV.open(filename, 'wb') do |csv| | |
rows.each { |row| csv << row } | |
end | |
end | |
end | |
class NameHandler | |
def initialize(filename) | |
@csv = CSV.read(filename, headers: true) | |
@np = People::NameParser.new | |
end | |
def names_list | |
@csv.map do |row| | |
first_and_middle_initial = row['EMPLOYEE FIRST NAME AND MIDDLE INITIAL'] | |
last_name = row['EMPLOYEE LAST NAME'] | |
if first_and_middle_initial && last_name | |
person = OpenStruct.new | |
person.first_and_middle_initial = first_and_middle_initial | |
person.last_name = last_name | |
person.parsed_name = @np.parse(first_and_middle_initial + " " + last_name) | |
person.checkeable_name = checkeable_name(person.parsed_name) | |
person | |
end | |
end.compact | |
end | |
def checkeable_name(parsed_name) | |
if parsed_name[:first].length > 1 | |
parsed_name[:first] | |
else | |
parsed_name[:middle] | |
end | |
end | |
end | |
def build_query(names) | |
URI.escape(names[0..15].each_with_index.map {|name, i| "name[#{i}]=#{name}"}.join("&")) | |
end | |
thread_list = [] | |
output_csv = OutputCSV.new('output.csv') | |
name_handler = NameHandler.new('guess-gender.csv') | |
puts "Starting talking with api" | |
name_handler.names_list.each_slice(10) do |group_names| | |
thread_list << Thread.new do | |
checkeable_names = group_names.map { |name| name.checkeable_name } | |
query_uri = "http://api.genderize.io?#{build_query(checkeable_names)}" | |
begin | |
response = HTTParty.get(query_uri) | |
rescue Timeout::Error | |
puts "FAILED FOR: #{checkeable_names}" | |
end | |
puts query_uri | |
if response.status == 200 | |
parsed_response = JSON.parse(response.body) | |
output_csv.store(parsed_name.values) | |
else | |
puts "FAILED FOR: #{checkeable_names}" | |
end | |
end | |
end | |
thread_list.each { |x| x.join } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
genderize.io sucks!