Created
April 19, 2017 23:02
-
-
Save baharefatemi/e4338625f00e4f623d236dbe0782b81e 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
base_file = File.read("u.data") | |
tag_file = File.read("u.user") | |
train_file = File.open("train.csv", "w") | |
test_file = File.open("test.csv", "w") | |
train_users = Array.new | |
test_users = Array.new | |
genders = Hash.new | |
items = Array.new | |
number_of_times_rated = Hash.new | |
ratings = Hash.new | |
splitted = Array.new | |
tag_file.each_line.with_index do |line, i| | |
splitted = line.split("|") | |
user = splitted[0].to_i | |
gender = splitted[2] | |
genders[user] = gender | |
end | |
base_file.each_line.with_index do |line, i| | |
splitted = line.split(" ") | |
user = splitted[0].to_i | |
item = splitted[1].to_i | |
rating = splitted[2].to_i | |
time_stamp = splitted[3].to_i | |
if(time_stamp <= 880845177) | |
if(not train_users.include? user) | |
train_users << user | |
ratings[user] = Hash.new | |
end | |
if(not items.include? item) | |
items << item | |
number_of_times_rated[item] = 0 | |
end | |
ratings[user][item] = [rating, time_stamp] | |
number_of_times_rated[item] = number_of_times_rated[item].to_i + 1 | |
elsif(time_stamp <= 884673930) | |
if(not test_users.include? user) | |
test_users << user | |
ratings[user] = Hash.new | |
end | |
if(not items.include? item) | |
items << item | |
# number_of_times_rated[item] = 0 | |
end | |
ratings[user][item] = [rating, time_stamp] | |
# number_of_times_rated[item] += 1 | |
end | |
end | |
test_users -= train_users | |
number_of_times_rated = number_of_times_rated.sort_by {|key, value| value} | |
output_file = File.open("log_new.txt", "w") | |
number_of_times_rated.each do |n| | |
new_line = "" | |
new_line << n[0].to_s | |
new_line << "^" | |
new_line << n[1].to_s | |
output_file.puts(new_line) | |
end |
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
base_file = File.read("u.data") | |
tag_file = File.read("u.user") | |
train_file = File.open("train.csv", "w") | |
test_file = File.open("test.csv", "w") | |
train_users = Array.new | |
test_users = Array.new | |
genders = Hash.new | |
items = Array.new | |
number_of_times_rated = Hash.new | |
ratings = Hash.new | |
splitted = Array.new | |
tag_file.each_line.with_index do |line, i| | |
splitted = line.split("|") | |
user = splitted[0].to_i | |
gender = splitted[2] | |
genders[user] = gender | |
end | |
base_file.each_line.with_index do |line, i| | |
splitted = line.split(" ") | |
user = splitted[0].to_i | |
item = splitted[1].to_i | |
rating = splitted[2].to_i | |
time_stamp = splitted[3].to_i | |
if(time_stamp <= 880845177) | |
if(not train_users.include? user) | |
train_users << user | |
ratings[user] = Hash.new | |
end | |
if(not items.include? item) | |
items << item | |
number_of_times_rated[item] = 0 | |
end | |
ratings[user][item] = [rating, time_stamp] | |
number_of_times_rated[item] = number_of_times_rated[item].to_i + 1 | |
elsif(time_stamp <= 884673930) | |
if(not test_users.include? user) | |
test_users << user | |
ratings[user] = Hash.new | |
end | |
if(not items.include? item) | |
items << item | |
# number_of_times_rated[item] = 0 | |
end | |
ratings[user][item] = [rating, time_stamp] | |
# number_of_times_rated[item] += 1 | |
end | |
end | |
test_users -= train_users | |
number_of_times_rated = number_of_times_rated.sort_by {|key, value| value} | |
output_file = File.open("log_new.txt", "w") | |
number_of_times_rated.each do |n| | |
new_line = "" | |
new_line << n[0].to_s | |
new_line << "^" | |
new_line << n[1].to_s | |
output_file.puts(new_line) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment