Adventures in Machine Learning with Taylor Swift and Lady Gaga

gistfile1.rb

require 'nokogiri'
require 'classifier'
require 'open-uri'

@skynet = Classifier::Bayes.new 'lady_gaga', 'taylor_swift'

def train_skynet(url, trainer)
  # Grab the HTML from the url
  html = open(url)

  # Extract the lyrics from the #lyrics-body-text div
  lyrics = Nokogiri::HTML(html).css("#lyrics-body-text").text

  # Filter text to ensure only alphanumeric characters and
  # appropriate punctuation are used
  lyrics.gsub!(/[^A-Za-z0-9,.'\s]/, ' ')

  # Feed each line to skynet
  @skynet.send(trainer, lyrics)
end

# From http://www.metrolyrics.com/taylor-swift-lyrics.html
taylor_swift_urls = [
  "http://www.metrolyrics.com/i-knew-you-were-trouble-lyrics-taylor-swift.html",
  "http://www.metrolyrics.com/teardrops-on-my-guitar-lyrics-taylor-swift.html",
  "http://www.metrolyrics.com/we-are-never-ever-getting-back-together-lyrics-taylor-swift.html"
]
taylor_swift_urls.each do |url|
  train_skynet(url, :train_taylor_swift)
end 

# From http://www.metrolyrics.com/lady-gaga-lyrics.html
lady_gaga_urls = [
  "http://www.metrolyrics.com/bad-romance-lyrics-lady-gaga.html",
  "http://www.metrolyrics.com/telephone-lyrics-lady-gaga.html",
  "http://www.metrolyrics.com/pokerface-lyrics-lady-gaga.html"
]
lady_gaga_urls.each do |url|
  train_skynet(url, :train_lady_gaga)
end 

puts @skynet.classify "Shake it off, shake it off!"
puts @skynet.classify "At least that's what people say mmm, that's what people say mmm"
puts @skynet.classify "But I won't stop until that boy is mine"
puts @skynet.classify "Papa-paparazzi"
puts @skynet.classify "I'll follow you until you love me"