conference speakers by frequency

speaker_frequency.rb

require "csv"

headers = ["year", "date", "time", "speakers", "title", "abstract", "type", "tags", "slides", "video", "audio"]
# create new csv for the final output with the final header:w
CSV.open("all.csv", "wb", write_headers: true, headers: headers) do |csv|
  Dir["csv/*.csv"].each do |path|  # for each of your csv files
    CSV.foreach(path, headers: true, return_headers: false) do |row| # don't output the headers in the rows
      csv << row # append to the final file
    end
  end
end

table = CSV.parse(File.read("all.csv"), headers: true)
speakers = table.by_col["speakers"]
speakers = speakers.reject {|x| x.nil? }
speakers = speakers.map {|x| x.split "|" }.flatten
speakers = speakers.map {|x| x.gsub(/\(.*?\)/, '') }.flatten
speakers = speakers.map {|x| x.strip }.flatten

def frequency(a)
  a.group_by do |e|
    e
  end.map do |key, values|
    [key, values.size]
  end
end

p frequency(speakers).sort_by(&:last)