Created
June 11, 2015 17:22
-
-
Save parrish/862d6a3e2d887d5a144e to your computer and use it in GitHub Desktop.
Combines chimp discussion data with chimp classification data
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
#!/usr/bin/env ruby | |
date = ARGV[0] | |
unless date | |
puts "usage: ruby #{ __FILE__ } <date>" | |
puts " eg: ruby #{ __FILE__ } 2015-06-07" | |
exit | |
end | |
classifications_filename = "#{ date }_chimp_classifications.csv" | |
discussions_filename = "#{ date }_chimp_discussions.csv" | |
combined_filename = "#{ date }_chimp_combined.csv" | |
discussion_data = { } | |
IO.foreach(discussions_filename).with_index do |line, index| | |
next if index == 0 | |
subject_id, tags, mentioned_in = line.chomp.split ',' | |
discussion_data[subject_id] = { 'tags' => tags, 'mentioned_in' => mentioned_in } | |
end | |
File.open(combined_filename, 'w') do |out| | |
IO.foreach(classifications_filename).with_index do |line, index| | |
line.chomp! | |
if index == 0 | |
out.puts "#{ line },tags,mentioned_in" | |
next | |
end | |
subject_id = line.split(',')[2].gsub '"', '' | |
talk_data = discussion_data[subject_id] | |
out.puts "#{ line },#{ talk_data['tags'] },#{ talk_data['mentioned_in'] }" | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment