Created
February 20, 2013 04:15
-
-
Save chadkouse/4992831 to your computer and use it in GitHub Desktop.
This file contains 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
File.open('foo_sorted_reduced.tab', 'w:UTF-8') { |f| | |
File.open('foo_sorted.tab', 'r:UTF-8').each_line do |line| | |
parts = line.strip.split("\t") | |
song_id = parts[0] | |
artist = parts[1] | |
title = parts[2] | |
date = parts[3] | |
country = parts[4] | |
if last_song_id == -1 | |
last_song_id = song_id | |
last_artist = artist | |
last_title = title | |
last_date = date | |
last_country = country | |
end | |
if last_song_id == song_id && | |
last_artist.casecmp(artist) == 0 && | |
last_title.casecmp(title) == 0 && | |
last_date.casecmp(date) == 0 && | |
last_country.casecmp(country) == 0 | |
song_id_country_count += 1 | |
next | |
end | |
#output the counts for the previous group | |
day = last_date[-2, 2] | |
f.printf("%s\t%s\t%s\t%s\t%d\t%s\n", last_song_id, | |
last_artist, | |
last_title, | |
day, | |
song_id_country_count, | |
last_country) | |
last_song_id = song_id | |
last_artist = artist | |
last_title = title | |
last_date = date | |
last_country = country | |
song_id_country_count = 1 | |
end | |
#output the counts for the last group | |
day = last_date[-2, 2] | |
f.printf("%s\t%s\t%s\t%s\t%d\t%s\n", last_song_id, | |
last_artist, | |
last_title, | |
day, | |
song_id_country_count, | |
last_country) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment