Extract Galaxy Zoo Subject location data

extract_gz_subject_location_data.rb

def _iterate_cursor(collection: nil, query: { }, opts: { }, message: '')
  opts.reverse_merge! timeout: false
  index = 0
  total = collection.find(query).count
  message = "#{ message } Galaxy Zoo Subjects"

  collection.find(query, opts) do |cursor|
    while cursor.has_next?
      index += 1

      if index % 100 == 0
        progress = '%0.3f' % ((index / total.to_f) * 100)
        puts "#{ message }: [#{ progress }%]"
      end

      doc = cursor.next_document
      yield doc
    end
  end
end


require 'csv'

loc_headers = %w(standard thumbnail inverted)
csv_headers = ["id"] | loc_headers

CSV.open("log/gz_subject_locations.csv", "w") do |csv|
  csv << csv_headers

  _iterate_cursor(collection: GalaxyZooSubject.collection, message: 'Processing') do |doc|
    subject_locs = loc_headers.map do |attr_name|
      doc["location"][attr_name]
    end
    row = [ doc["_id"].to_s ] | subject_locs
    csv << row

    # puts [ doc["_id"].to_s ] | subject_locs
    # break #testing
  end
end