public void TestRatioSplit()
{
var ratings = new TimedRatings();
ratings.Add(0, 0, 5.0f, new DateTime(2011, 10, 31));
ratings.Add(0, 1, 4.5f, new DateTime(2011, 11, 1));
ratings.Add(0, 2, 5.0f, new DateTime(2011, 11, 3));
ratings.Add(0, 3, 4.5f, new DateTime(2011, 11, 4));
ratings.Add(1, 0, 1.0f, new DateTime(2011, 10, 31));
ratings.Add(1, 1, 2.5f, new DateTime(2011, 11, 2));
ratings.Add(1, 2, 1.0f, new DateTime(2011, 12, 1));
ratings.Add(1, 3, 2.5f, new DateTime(2011, 12, 4));
var split1 = new RatingsPerUserChronologicalSplit(ratings, 0.25);
Assert.AreEqual(6, split1.Train[0].Count);
Assert.AreEqual(2, split1.Test[0].Count);
Assert.AreEqual(3, split1.Train[0].ByUser[0].Count);
Assert.AreEqual(3, split1.Train[0].ByUser[1].Count);
Assert.AreEqual(1, split1.Test[0].ByUser[0].Count);
Assert.AreEqual(1, split1.Test[0].ByUser[1].Count);
var split2 = new RatingsPerUserChronologicalSplit(ratings, 0.5);
Assert.AreEqual(4, split2.Train[0].Count);
Assert.AreEqual(4, split2.Test[0].Count);
Assert.AreEqual(2, split2.Train[0].ByUser[0].Count);
Assert.AreEqual(2, split2.Train[0].ByUser[1].Count);
Assert.AreEqual(2, split2.Test[0].ByUser[0].Count);
Assert.AreEqual(2, split2.Test[0].ByUser[1].Count);
}
/// <summary>Read in rating data from a TextReader</summary>
/// <param name="reader">the <see cref="TextReader"/> to read from</param>
/// <param name="user_mapping">mapping object for user IDs</param>
/// <param name="item_mapping">mapping object for item IDs</param>
/// <returns>the rating data</returns>
public static ITimedRatings Read(TextReader reader, IEntityMapping user_mapping = null, IEntityMapping item_mapping = null)
{
if (user_mapping == null)
user_mapping = new IdentityMapping();
if (item_mapping == null)
item_mapping = new IdentityMapping();
var ratings = new TimedRatings();
string[] separators = { "::" };
string line;
while ((line = reader.ReadLine()) != null)
{
string[] tokens = line.Split(separators, StringSplitOptions.None);
if (tokens.Length < 4)
throw new FormatException(string.Format("Expected at least 4 columns: {0}", line));
int user_id = user_mapping.ToInternalID(tokens[0]);
int item_id = item_mapping.ToInternalID(tokens[1]);
float rating = float.Parse(tokens[2], CultureInfo.InvariantCulture);
long seconds = uint.Parse(tokens[3]);
var time = new DateTime(seconds * 10000000L).AddYears(1969);
var offset = TimeZone.CurrentTimeZone.GetUtcOffset(time);
time -= offset;
ratings.Add(user_id, item_id, rating, time);
}
return ratings;
}
public void TestTimeSplit()
{
var ratings = new TimedRatings();
ratings.Add(0, 0, 5.0f, new DateTime(2011, 10, 31));
ratings.Add(0, 1, 4.5f, new DateTime(2011, 11, 1));
ratings.Add(1, 0, 1.0f, new DateTime(2011, 10, 31));
ratings.Add(1, 1, 2.5f, new DateTime(2011, 11, 2));
var split1 = new RatingsChronologicalSplit(ratings, new DateTime(2011, 11, 2));
Assert.AreEqual(3, split1.Train[0].Count);
Assert.AreEqual(1, split1.Test[0].Count);
Assert.AreEqual(2, split1.Train[0].ByUser[0].Count);
Assert.AreEqual(1, split1.Train[0].ByUser[1].Count);
Assert.AreEqual(0, split1.Test[0].ByUser[0].Count);
Assert.AreEqual(1, split1.Test[0].ByUser[1].Count);
Assert.AreEqual(new DateTime(2011, 10, 31), split1.Train[0].EarliestTime);
Assert.AreEqual(new DateTime(2011, 11, 1), split1.Train[0].LatestTime);
Assert.AreEqual(new DateTime(2011, 11, 2), split1.Test[0].EarliestTime);
Assert.AreEqual(new DateTime(2011, 11, 2), split1.Test[0].LatestTime);
var split2 = new RatingsChronologicalSplit(ratings, new DateTime(2011, 11, 1));
Assert.AreEqual(2, split2.Train[0].Count);
Assert.AreEqual(2, split2.Test[0].Count);
Assert.AreEqual(1, split2.Train[0].ByUser[0].Count);
Assert.AreEqual(1, split2.Train[0].ByUser[1].Count);
Assert.AreEqual(1, split2.Test[0].ByUser[0].Count);
Assert.AreEqual(1, split2.Test[0].ByUser[1].Count);
Assert.AreEqual(new DateTime(2011, 10, 31), split2.Train[0].EarliestTime);
Assert.AreEqual(new DateTime(2011, 10, 31), split2.Train[0].LatestTime);
Assert.AreEqual(new DateTime(2011, 11, 1), split2.Test[0].EarliestTime);
Assert.AreEqual(new DateTime(2011, 11, 2), split2.Test[0].LatestTime);
}
public static IRatings CreateRandomTimedRatings(int num_users, int num_items, int num_ratings)
{
var random = MyMediaLite.Random.GetInstance();
var ratings = new TimedRatings();
for (int i = 0; i < num_ratings; i++)
{
int user_id = random.Next(num_users);
int item_id = random.Next(num_items);
int rating_value = 1 + random.Next(5);
ratings.Add(user_id, item_id, rating_value, DateTime.Now);
}
return ratings;
}
/// <summary>Read in rating data from a TextReader</summary>
/// <param name="reader">the <see cref="TextReader"/> to read from</param>
/// <param name="user_mapping">mapping object for user IDs</param>
/// <param name="item_mapping">mapping object for item IDs</param>
/// <param name="test_rating_format">whether there is a rating column in each line or not</param>
/// <returns>the rating data</returns>
static public ITimedRatings Read(
TextReader reader,
IMapping user_mapping = null, IMapping item_mapping = null,
TestRatingFileFormat test_rating_format = TestRatingFileFormat.WITH_RATINGS)
{
if (user_mapping == null)
user_mapping = new IdentityMapping();
if (item_mapping == null)
item_mapping = new IdentityMapping();
var ratings = new TimedRatings();
string[] separators = { "::" };
string line;
int seconds_pos = test_rating_format == TestRatingFileFormat.WITH_RATINGS ? 3 : 2;
while ((line = reader.ReadLine()) != null)
{
string[] tokens = line.Split(separators, StringSplitOptions.None);
if (test_rating_format == TestRatingFileFormat.WITH_RATINGS && tokens.Length < 4)
throw new FormatException("Expected at least 4 columns: " + line);
if (test_rating_format == TestRatingFileFormat.WITHOUT_RATINGS && tokens.Length < 3)
throw new FormatException("Expected at least 3 columns: " + line);
int user_id = user_mapping.ToInternalID(tokens[0]);
int item_id = item_mapping.ToInternalID(tokens[1]);
float rating = test_rating_format == TestRatingFileFormat.WITH_RATINGS ? float.Parse(tokens[2], CultureInfo.InvariantCulture) : 0;
long seconds = uint.Parse(tokens[seconds_pos]);
var time = new DateTime(seconds * 10000000L).AddYears(1969);
var offset = TimeZone.CurrentTimeZone.GetUtcOffset(time);
time -= offset;
ratings.Add(user_id, item_id, rating, time);
}
return ratings;
}
/// <summary>Read in rating data from a TextReader</summary>
/// <param name="reader">the <see cref="TextReader"/> to read from</param>
/// <param name="user_mapping">mapping object for user IDs</param>
/// <param name="item_mapping">mapping object for item IDs</param>
/// <param name="ignore_first_line">if true, ignore the first line</param>
/// <returns>the rating data</returns>
static public ITimedRatings Read(TextReader reader, IMapping user_mapping = null, IMapping item_mapping = null, bool ignore_first_line = false)
{
if (user_mapping == null)
{
user_mapping = new IdentityMapping();
}
if (item_mapping == null)
{
item_mapping = new IdentityMapping();
}
if (ignore_first_line)
{
reader.ReadLine();
}
var ratings = new MyMediaLite.Data.TimedRatings();
var time_split_chars = new char[] { ' ', '-', ':' };
string line;
while ((line = reader.ReadLine()) != null)
{
if (line.Length == 0)
{
continue;
}
string[] tokens = line.Split(Constants.SPLIT_CHARS);
if (tokens.Length < 4)
{
throw new FormatException("Expected at least 4 columns: " + line);
}
int user_id = user_mapping.ToInternalID(tokens[0]);
int item_id = item_mapping.ToInternalID(tokens[1]);
float rating = float.Parse(tokens[2], CultureInfo.InvariantCulture);
string date_string = tokens[3];
if (tokens[3].StartsWith("\"") && tokens.Length > 4 && tokens[4].EndsWith("\""))
{
date_string = tokens[3] + " " + tokens[4];
date_string = date_string.Substring(1, date_string.Length - 2);
}
uint seconds;
if (date_string.Length == 19) // format "yyyy-mm-dd hh:mm:ss"
{
var date_time_tokens = date_string.Split(time_split_chars);
ratings.Add(
user_id, item_id, rating,
new DateTime(
int.Parse(date_time_tokens[0]),
int.Parse(date_time_tokens[1]),
int.Parse(date_time_tokens[2]),
int.Parse(date_time_tokens[3]),
int.Parse(date_time_tokens[4]),
int.Parse(date_time_tokens[5])));
}
else if (date_string.Length == 10 && date_string[4] == '-') // format "yyyy-mm-dd"
{
var date_time_tokens = date_string.Split(time_split_chars);
ratings.Add(
user_id, item_id, rating,
new DateTime(
int.Parse(date_time_tokens[0]),
int.Parse(date_time_tokens[1]),
int.Parse(date_time_tokens[2])));
}
else if (uint.TryParse(date_string, out seconds)) // unsigned integer value, interpreted as seconds since Unix epoch
{
var time = new DateTime(seconds * 10000000L).AddYears(1969);
var offset = TimeZone.CurrentTimeZone.GetUtcOffset(time);
ratings.Add(user_id, item_id, rating, time - offset);
}
else
{
ratings.Add(user_id, item_id, rating, DateTime.Parse(date_string, CultureInfo.InvariantCulture));
}
if (ratings.Count % 200000 == 199999)
{
Console.Error.Write(".");
}
if (ratings.Count % 12000000 == 11999999)
{
Console.Error.WriteLine();
}
}
ratings.InitScale();
return(ratings);
}
/// <summary>Read in rating data from a TextReader</summary>
/// <param name="reader">the <see cref="TextReader"/> to read from</param>
/// <param name="user_mapping">mapping object for user IDs</param>
/// <param name="item_mapping">mapping object for item IDs</param>
/// <param name="ignore_first_line">if true, ignore the first line</param>
/// <returns>the rating data</returns>
public static ITimedRatings Read(TextReader reader, IEntityMapping user_mapping = null, IEntityMapping item_mapping = null, bool ignore_first_line = false)
{
if (user_mapping == null)
user_mapping = new IdentityMapping();
if (item_mapping == null)
item_mapping = new IdentityMapping();
if (ignore_first_line)
reader.ReadLine();
var ratings = new MyMediaLite.Data.TimedRatings();
var time_split_chars = new char[] { ' ', '-', ':' };
string line;
while ((line = reader.ReadLine()) != null)
{
if (line.Length == 0)
continue;
string[] tokens = line.Split(Constants.SPLIT_CHARS);
if (tokens.Length < 4)
throw new FormatException("Expected at least 4 columns: " + line);
int user_id = user_mapping.ToInternalID(tokens[0]);
int item_id = item_mapping.ToInternalID(tokens[1]);
float rating = float.Parse(tokens[2], CultureInfo.InvariantCulture);
string date_string = tokens[3];
if (tokens[3].StartsWith("\"") && tokens.Length > 4 && tokens[4].EndsWith("\""))
{
date_string = tokens[3] + " " + tokens[4];
date_string = date_string.Substring(1, date_string.Length - 2);
}
uint seconds;
if (date_string.Length == 19) // format "yyyy-mm-dd hh:mm:ss"
{
var date_time_tokens = date_string.Split(time_split_chars);
ratings.Add(
user_id, item_id, rating,
new DateTime(
int.Parse(date_time_tokens[0]),
int.Parse(date_time_tokens[1]),
int.Parse(date_time_tokens[2]),
int.Parse(date_time_tokens[3]),
int.Parse(date_time_tokens[4]),
int.Parse(date_time_tokens[5])));
}
else if (date_string.Length == 10 && date_string[4] == '-') // format "yyyy-mm-dd"
{
var date_time_tokens = date_string.Split(time_split_chars);
ratings.Add(
user_id, item_id, rating,
new DateTime(
int.Parse(date_time_tokens[0]),
int.Parse(date_time_tokens[1]),
int.Parse(date_time_tokens[2])));
}
else if (uint.TryParse(date_string, out seconds)) // unsigned integer value, interpreted as seconds since Unix epoch
{
var time = new DateTime(seconds * 10000000L).AddYears(1969);
var offset = TimeZone.CurrentTimeZone.GetUtcOffset(time);
ratings.Add(user_id, item_id, rating, time - offset);
}
else
ratings.Add(user_id, item_id, rating, DateTime.Parse(date_string, CultureInfo.InvariantCulture));
if (ratings.Count % 200000 == 199999)
Console.Error.Write(".");
if (ratings.Count % 12000000 == 11999999)
Console.Error.WriteLine();
}
ratings.InitScale();
return ratings;
}