public void LoadData(DataContainer container)
{
if (!(container is MovieTweetingsDataContainer))
{
throw new Exception("The data container should have type MovieTweetingsDataContainer.");
}
var mtContainer = (MovieTweetingsDataContainer)container;
Console.WriteLine("Importing training set...");
foreach (string l in File.ReadAllLines(_trainSet).Skip(1))
{
var tokens = l.Split(',');
string tweetJson = tokens.Skip(4).Aggregate((a, b) => a + ',' + b);
mtContainer.AddMovieTweeting(tokens[0], tokens[1], float.Parse(tokens[2]), tweetJson, false);
}
Console.WriteLine("Importing test set...");
foreach (string l in File.ReadAllLines(_testSet).Skip(1))
{
var tokens = l.Split(',');
string tweetJson = tokens.Skip(4).Aggregate((a, b) => a + ',' + b);
mtContainer.AddMovieTweeting(tokens[0], tokens[1], float.Parse(tokens[2]), tweetJson, true);
}
}
public void LoadData(DataContainer container)
{
if (!(container is MusicDataContainer))
{
throw new Exception("The data container should have type MusicDataContainer.");
}
var mContainer = (MusicDataContainer)container;
foreach (string line in File.ReadAllLines(_path))
{
var tokens = line.Split(',');
var us = new UserSession() { User = mContainer.AddUser(tokens[0]) };
var tracks = tokens.Skip(2).Aggregate((a, b) => a + "," + b).Split('|');
foreach (string track in tracks.Take(tracks.Length - 1))
{
var parts = track.Split(',').Reverse().ToList();
//mContainer.AddPositiveFeedback(tokens[0], parts[0]);
mContainer.AddRating(tokens[0], parts[2], float.Parse(parts[1]) / 120);
var item = mContainer.AddItem(parts[2]);
us.Items.Add(item);
}
mContainer.Sessions.Add(us);
}
}
public void TestMovieLensSingle()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = "::",
HasHeaderRecord = true
};
// load data
var trainReader = new CsvReader(Paths.MovieLens1MTrain75, config);
var testReader = new CsvReader(Paths.MovieLens1MTest25, config, true);
var container = new DataContainer();
trainReader.LoadData(container);
testReader.LoadData(container);
var startTime = DateTime.Now;
var splitter = new RatingSimpleSplitter(container);
//var recommender = new MediaLiteRatingPredictor(new MatrixFactorization());
var recommender = new LibFmTrainTester(libFmPath: "LibFm.Net.64.exe");
// evaluation
var ctx = new EvalutationContext<ItemRating>(recommender, splitter);
var ep = new EvaluationPipeline<ItemRating>(ctx);
ep.Evaluators.Add(new RMSE());
ep.Run();
var duration = (int)DateTime.Now.Subtract(startTime).TotalMilliseconds;
Console.WriteLine("RMSE\tDuration\n{0}\t{1}", ctx["RMSE"], duration);
}
public void LoadData(DataContainer container)
{
if (!(container is MovieLensCrossDomainContainer))
throw new WrapRecException("The data container should have type MovieLensCrossDomainContainer.");
var mlContainer = (MovieLensCrossDomainContainer)container;
Console.WriteLine("Reading movies...");
foreach(string l in File.ReadAllLines(MoviesPath))
{
var parts = l.Split(new string[] { "::" }, StringSplitOptions.RemoveEmptyEntries);
var item = mlContainer.AddItem(parts[0]);
item.Properties["genres"] = parts[2];
}
Console.WriteLine("Creating domains...");
//mlContainer.CreateItemClusters(MoviesPath.GetDirectoryPath() + "\\GenreClusters.csv");
mlContainer.CreateDominantGenre(MoviesPath.GetDirectoryPath() + "\\DominantGenre.csv");
Console.WriteLine("Reading ratings...");
foreach (string l in File.ReadAllLines(RatingsPath).Skip(1))
{
var parts = l.Split(new string[] { "::" }, StringSplitOptions.RemoveEmptyEntries);
var ir = mlContainer.AddRating(parts[0], parts[1], float.Parse(parts[2]), false);
ir.Properties["timestamp"] = parts[3];
}
//mlContainer.CreateDomainsBasedOnDate();
//mlContainer.CreateDomainsWithEvenlyDistributedUsers();
}
public void LoadData(DataContainer container)
{
if (!(container is EpinionsCrossDomainDataContainer))
throw new WrapRecException("The data container should have type EpinionsCrossDomainDataContainer.");
var ecdContainer = (EpinionsCrossDomainDataContainer) container;
if (string.IsNullOrEmpty(FolderPath))
DomainsLoad(ecdContainer);
else
NormalRead(ecdContainer);
}
public void LoadData(DataContainer container)
{
if (!(container is CrowdRecDataContainer))
{
throw new Exception("The data container should have type CrowdRecDataContainer.");
}
var crContainer = (CrowdRecDataContainer)container;
LoadEntities(crContainer);
LoadRelations(crContainer);
}
public void LoadData(DataContainer container)
{
if (Domain != null)
{
((CrossDomainDataContainer)container).CurrentDomain = Domain;
}
while (_reader.Read())
{
// userId, itemId, rating
container.AddRating(_reader.GetField(0), _reader.GetField(1), float.Parse(_reader.GetField(2)), IsTestReader);
}
}
public void LoadData(DataContainer container)
{
var cdContainer = (CrossDomainDataContainer)container;
Dictionary<string, int> numAuxUserRatings = File.ReadAllLines(UserDataPath)
.Select(l =>
{
var parts = l.Split(' ');
return new { UserId = parts[0], Count = int.Parse(parts[1]) };
})
.ToDictionary(d => d.UserId, d => d.Count);
foreach (var l in File.ReadAllLines(TrainFile))
{
var parts = l.Split(' ');
float rating = float.Parse(parts[0]);
string userId = parts[1].Split(':')[0];
string itemId = parts[2].Split(':')[0];
cdContainer.CurrentDomain = MainDomain;
cdContainer.AddRating(userId, itemId, rating, false);
cdContainer.CurrentDomain = AuxDomain;
for (int i = 3; i < parts.Length; i++)
{
var itemRating = parts[i].Split(':');
cdContainer.AddRating(userId, itemRating[0], float.Parse(itemRating[1]) * 10, false);
}
}
foreach (var l in File.ReadAllLines(TestFile))
{
var parts = l.Split(' ');
float rating = float.Parse(parts[0]);
string userId = parts[1].Split(':')[0];
string itemId = parts[2].Split(':')[0];
cdContainer.CurrentDomain = MainDomain;
cdContainer.AddRating(userId, itemId, rating, true);
cdContainer.CurrentDomain = AuxDomain;
for (int i = 3; i < parts.Length; i++)
{
var itemRating = parts[i].Split(':');
cdContainer.AddRating(userId, itemRating[0], float.Parse(itemRating[1]), false);
}
}
}
public void LoadData(DataContainer container)
{
// load standard rating data into container
foreach (var reader in EpinionsReaders)
{
reader.LoadData(container);
}
// add relation specific data
foreach (var line in File.ReadAllLines(RelationsPath).Skip(1))
{
var parts = line.TrimStart(' ').Split('\t');
// make sure that the "u" suffix is also added when data is loaded into container
string userId = parts[0] + "u";
string connId = parts[1];
string strngth = parts[2];
if (container.Users.ContainsKey(userId))
container.Users[userId].AddProperty("Connections", connId + " " + parts[2]);
}
}
public TrustAwareLibFmFeatureBuilder(DataContainer container, int maxConnections, bool useConnectionStrength)
{
MaxConnections = maxConnections;
UseConnectionStrength = useConnectionStrength;
if (useConnectionStrength)
return;
_connectionsFreq = new Dictionary<string, int>();
foreach (var u in container.Users.Values)
{
string conns = u.GetProperty("Connections");
if (!string.IsNullOrEmpty(conns))
{
foreach (string connId in conns.Split(','))
{
AddConnectionCount(connId);
}
}
}
}
public void TestAmazonDatasetSingleNewModel()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var trainContainer = new DataContainer();
var testContainer = new DataContainer();
var trainReader = new CsvReader(Paths.AmazonBooksTrain75, config);
var testReader = new CsvReader(Paths.AmazonBooksTest25, config);
trainReader.LoadData(trainContainer);
testReader.LoadData(testContainer);
var dataset = new ItemRatingDataset(trainContainer, testContainer);
//var featureBuilder = new LibFmFeatureBuilder();
// step 2: recommender
var recommender = new LibFmTrainTester();
// step3: evaluation
var ep = new EvaluationPipeline<ItemRating>(new EvalutationContext<ItemRating>(recommender, dataset));
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
}
public void TestAmazonAllDomains2()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new DataContainer();
var bookReader = new CsvReader(Paths.AmazonBooksRatings, config);
var musicReader = new CsvReader(Paths.AmazonMusicRatings, config);
var dvdReader = new CsvReader(Paths.AmazonDvdRatings, config);
var videoReader = new CsvReader(Paths.AmazonVideoRatings, config);
bookReader.LoadData(container);
musicReader.LoadData(container);
dvdReader.LoadData(container);
videoReader.LoadData(container);
var splitter = new RatingSimpleSplitter(container, 0.25f);
var startTime = DateTime.Now;
var recommender = new LibFmTrainTester();
//var recommender = new MediaLiteRatingPredictor(new MatrixFactorization());
// step3: evaluation
var ctx = new EvalutationContext<ItemRating>(recommender, splitter);
var ep = new EvaluationPipeline<ItemRating>(ctx);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
var duration = DateTime.Now.Subtract(startTime);
Console.WriteLine("RMSE\t{0}\nDuration\t{1}", ctx["RMSE"], (int)duration.TotalMilliseconds);
}
public RatingSimpleSplitter(DataContainer container)
{
Train = container.Ratings.Where(r => r.IsTest == false);
Test = container.Ratings.Where(r => r.IsTest == true);
}
