An implementation of 'Find-S' Algorithm in Ruby

find-s.rb

#!/usr/bin/env ruby

#  find-s.rb
#  
#  Copyright 2012 AbdulKarim Memon <[email protected]>
#  
#  This program is free software; you can redistribute it and/or modify
#  it under the terms of the GNU General Public License as published by
#  the Free Software Foundation; either version 2 of the License, or
#  (at your option) any later version.
#  
#  This program is distributed in the hope that it will be useful,
#  but WITHOUT ANY WARRANTY; without even the implied warranty of
#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#  GNU General Public License for more details.
#  
#  You should have received a copy of the GNU General Public License
#  along with this program; if not, write to the Free Software
#  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
#  MA 02110-1301, USA.
#  
#  Implementation of 'Find-S Algorithm in Ruby.' 
#  
#  Sample Input file ("find-s.input")
#     sunny,warm,1
#     sunny,cold,0
#     rainy,warm,1
#  
#  "H" is the final Output Hash with the most generalized hypothesis.
#  

require 'csv'

H={"sky"=>[],"temp"=>[]}
h=[]

#reading from the CSV formatted input
CSV.read('find-s.input').each do |item|
  #entry is an Array
  h.push ({"sky"=>item[0], "temp"=>item[1]}) if item[2] != "0"
end

# puts h
# => {"sky"=>"sunny", "temp"=>"warm"}
# => {"sky"=>"rainy", "temp"=>"warm"}

# push each 'value' of the positive input set to the 
# generalized hypothesis
h.each do |entry|
  H["sky"] << entry["sky"]
  H["temp"] << entry ["temp"]
end

# remove the duplicate entries from each "value" array.

# H.each do
#   H["sky"].uniq!
#   H["temp"].uniq!
# end
H.each_value(&:uniq!) # is the same as .each_value{|o| o.uniq}

puts H