Created
May 8, 2012 11:18
-
-
Save miguelff/2634316 to your computer and use it in GitHub Desktop.
An script to grab some quick dirty stats of the aol query log
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 | |
files = %w{aol015 aol026}.map{|f| f+".sessionized"} | |
sessions = {} | |
#load sessions hash | |
files.each do |f| | |
lines = File.open(f).each do |line| | |
if line.length > 10 | |
sid, uid, q, *rest = line.split("\t") | |
if sessions.has_key? sid | |
sessions[sid] << q | |
else | |
sessions[sid] = [q] | |
end | |
end | |
end | |
end | |
#remove query duplicates | |
session_queries = sessions.values.map(&:uniq) | |
#number of sessions | |
number_of_sessions = session_queries.size.to_f | |
#average query length | |
avg_length = session_queries.reduce(0) {|sum, value| sum + value.size} / number_of_sessions | |
#frequencies | |
freqs = [] | |
session_queries.map(&:size).reduce(freqs) do |freqs, size| | |
freqs[size] = freqs[size].nil? ? 1 : freqs[size] + 1 | |
freqs | |
end | |
freqs.map!{|freq| freq ? freq : 0} | |
#relative frequencies | |
freqs_rel = freqs.map { |x| x / number_of_sessions} | |
one = freqs_rel.reduce(0) {|sum, value| sum + value} | |
output=<<END | |
TOTAL sessions: | |
#{number_of_sessions} | |
AVG length: | |
#{avg_length} | |
Freqs: | |
#{freqs.inspect} | |
Rel freqs: | |
#{freqs_rel.inspect} | |
one: #{one} | |
END | |
puts output |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment