Created
December 1, 2013 22:46
-
-
Save charlieegan3/7741849 to your computer and use it in GitHub Desktop.
A simple script to process a list of films to find the most common cast members.
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 'badfruit' | |
require 'guess' | |
require 'sexmachine' | |
d = SexMachine::Detector.new | |
bf = BadFruit.new("YOUR_RT_API_KEY") | |
movies = ["Hunger Games: Catching Fire","Gravity", "..." ] | |
total = movies.size.to_s | |
puts "Starting fetch for #{total} movies...\n" | |
cast = [] | |
count = 0 | |
movies.each do |movie| | |
count += 1 | |
print count | |
result = bf.movies.search_by_name(movie)[0] | |
if result.nil? | |
print ("\b"* count.to_s.length) + " * No matches for: " + movie + "\n" | |
else | |
result.full_cast.each do |member| | |
cast.push([member.name, movie]) | |
end | |
end | |
print ("\b"* count.to_s.length) | |
end | |
puts "Calculating Results..." | |
results_hash = Hash.new() | |
cast.each do |member| | |
begin | |
results_hash[member[0]] = results_hash[member[0]].push(member[1]) | |
rescue | |
results_hash[member[0]] = [member[1]] | |
end | |
end | |
results = [] | |
results_hash.each do |member| | |
gender = Guess.gender(member[0])[:gender] | |
if gender == "unknown" | |
gender = d.get_gender(member[0], :usa).to_s #most likly to be an american context | |
if gender.include? "male" #can be mostly_male in some cases... | |
gender = "male" | |
elsif gender.include? "female" | |
gender = "female" | |
else | |
gender = "unknown" | |
end | |
end | |
#classification ajustments | |
male_names = ["Morgan Freeman", "Viggo", "Stellan", "Mads", "Woody", "Angus", "Giancarlo", "Afemo", "Jesper", "Ludger", "Mykelti"] | |
female_names = ["Cate", "Sigourney", "Liv"] | |
unknown_names = ["Jamie"] | |
male = /#{male_names.join("|")}/ | |
female = /#{female_names.join("|")}/ | |
unknown = /#{unknown_names.join("|")}/ | |
if male === member[0] | |
gender = "male" | |
end | |
if female === member[0] | |
gender = "female" | |
end | |
if unknown === member[0] | |
gender = "unknown" | |
end | |
results.push([member[0], gender, member[1].size, member[1]]) | |
end | |
results = results.sort_by{|member|member[2]}.reverse | |
puts "\nQuery Results:" | |
results.each do |r| | |
#uncomment to get *all* your results | |
#puts t.to_s | |
end | |
puts "Top Ten" | |
results[0..9].each do |r| puts " * #{r[0].to_s}, #{r[2].to_s}" end | |
count = 0 | |
puts "\nTop Actors" | |
results.each do |r| | |
if r[1] == "male" | |
puts " * #{r[0].to_s}, #{r[2].to_s}" | |
count += 1 | |
end | |
if count == 10 | |
break | |
end | |
end | |
count = 0 | |
puts "Top Actresses" | |
results.each do |r| | |
if r[1] == "female" | |
puts " * #{r[0].to_s}, #{r[2].to_s}" | |
count += 1 | |
end | |
if count == 10 | |
break | |
end | |
end | |
count = 0 | |
puts "Top Unclassified" | |
results.each do |r| | |
if r[1] == "unknown" | |
puts " * #{r[0].to_s}, #{r[2].to_s}" | |
count += 1 | |
end | |
if count == 10 | |
break | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment