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 CreateDatasetsFromOriginalDataset()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var bookDomain = new Domain("book");
var musicDomain = new Domain("music");
var dvdDomain = new Domain("dvd");
var videoDomain = new Domain("video");
var bookReader = new CsvReader(Paths.AmazonAllBookRatings, config, bookDomain);
var musicReader = new CsvReader(Paths.AmazonAllMusicRatings, config, musicDomain);
var dvdReader = new CsvReader(Paths.AmazonAllDvdRatings, config, dvdDomain);
var videoReader = new CsvReader(Paths.AmazonAllVideoRatings, config, videoDomain);
bookReader.LoadData(container);
musicReader.LoadData(container);
dvdReader.LoadData(container);
videoReader.LoadData(container);
var output = container.Users.Values.Where(u =>
{
var counts = u.Ratings.GroupBy(r => r.Domain).Select(g => g.Count());
return counts.All(c => c >= 1 && c <= 20) && (counts.Count() > 3);
})
//.Select(u => new { UserId = u.Id, Counts = u.Ratings.GroupBy(r => r.Domain.Id).Select(g => g.Count().ToString()).Aggregate((a,b) => a + " " + b) })
//.Select(a => a.UserId + "," + a.Counts);
.SelectMany(u => u.Ratings.Where(r => r.Domain == musicDomain))
//.SelectMany(u => u.Ratings.GroupBy(r => r.Item.Id).Select(g => g.Take(1).Single()))
.Select(r => r.ToString());
Console.WriteLine("Writing...");
var header = new string[] { "UserId,ItemId,Rating" };
// selected1: only music between 5 to 20
// selected2: only music between 1 to 20
// selected3: only music between 2 to 20
// selected4: all domains with ratings between 1 to 20
File.WriteAllLines("music_selected4.csv", header.Concat(output));
//container.PrintStatistics();
}
public void ReportStatistics()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var bookDomain = new Domain("book", true);
var musicDomain = new Domain("music");
var dvdDomain = new Domain("dvd");
var videoDomain = new Domain("video");
var trainReader = new CsvReader(Paths.AmazonBooksTrain75, config, bookDomain);
var testReader = new CsvReader(Paths.AmazonBooksTest25, config, bookDomain, true);
var musicReader = new CsvReader(Paths.AmazonMusicRatings, config, musicDomain);
var dvdReader = new CsvReader(Paths.AmazonDvdRatings, config, dvdDomain);
var videoReader = new CsvReader(Paths.AmazonVideoRatings, config, videoDomain);
trainReader.LoadData(container);
testReader.LoadData(container);
musicReader.LoadData(container);
dvdReader.LoadData(container);
videoReader.LoadData(container);
container.WriteHistogram(Paths.AmazonProcessedPath);
}
public void TestNewDataset()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var bookDomain = new Domain("book", true);
var musicDomain = new Domain("music");
var dvdDomain = new Domain("dvd");
var videoDomain = new Domain("video");
var bookReader = new CsvReader("books_selected4.csv", config, bookDomain);
//var trainReader = new CsvReader("books_selected1_train.csv", config, bookDomain);
//var testReader = new CsvReader("books_selected1_test.csv", config, bookDomain, true);
var musicReader = new CsvReader(Paths.AmazonAllMusicRatings, config, musicDomain);
var dvdReader = new CsvReader(Paths.AmazonAllDvdRatings, config, dvdDomain);
var videoReader = new CsvReader(Paths.AmazonAllVideoRatings, config, videoDomain);
bookReader.LoadData(container);
//trainReader.LoadData(container);
//testReader.LoadData(container);
musicReader.LoadData(container);
//dvdReader.LoadData(container);
//videoReader.LoadData(container);
container.PrintStatistics();
//musicDomain.CacheUserData();
var splitter = new CrossDomainSimpleSplitter(container, 0.25f);
//splitter.SaveSplitsAsCsv("books_selected1_train.csv", "books_selected1_test.csv");
//return;
//var splitter = new RatingSimpleSplitter(container, 0.25f);
var numAuxRatings = new List<int> { 0, 1, 2, 3, 5, 7, 10 };
var rmse = new List<string>();
var mae = new List<string>();
var durations = new List<string>();
foreach (var num in numAuxRatings)
{
var startTime = DateTime.Now;
// step 2: recommender
LibFmTrainTester recommender;
CrossDomainLibFmFeatureBuilder featureBuilder = null;
if (num == 0)
{
recommender = new LibFmTrainTester(experimentId: num.ToString());
}
else
{
featureBuilder = new CrossDomainLibFmFeatureBuilder(bookDomain, num);
recommender = new LibFmTrainTester(experimentId: num.ToString(), featureBuilder: featureBuilder);
}
// 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();
//File.WriteAllLines("maps.txt", featureBuilder.Mapper.OriginalIDs.Zip(featureBuilder.Mapper.InternalIDs, (f, s) => f + "\t" + s));
rmse.Add(recommender.RMSE.ToString());
mae.Add(ctx["MAE"].ToString());
var duration = DateTime.Now.Subtract(startTime);
durations.Add(((int)duration.TotalMilliseconds).ToString());
}
Console.WriteLine("NumAuxRatings\tRMSE\tMAE\tDuration");
for (int i = 0; i < numAuxRatings.Count(); i++)
{
Console.WriteLine("{0}\t{1}\t{2}\t{3}", numAuxRatings[i], rmse[i], mae[i], durations[i]);
}
}
public void TestCrossDomain()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var domain1 = new Domain("domain1", true);
var domain2 = new Domain("domain2");
var trainReader = new CsvReader(Paths.TestDomain1Train, config, domain1);
var auxReader = new CsvReader(Paths.TestDomain2, config, domain2);
var testReader = new CsvReader(Paths.TestDomain1Test, config, domain1, true);
trainReader.LoadData(container);
auxReader.LoadData(container);
testReader.LoadData(container);
var dataset = new ItemRatingDataset(container);
var featureBuilder = new CrossDomainLibFmFeatureBuilder(domain1);
// step 2: recommender
var recommender = new LibFmTrainTester(featureBuilder: featureBuilder);
// step3: evaluation
var ep = new EvaluationPipeline<ItemRating>(new EvalutationContext<ItemRating>(recommender, dataset));
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
// featureBuilder.Mapper.OriginalIDs.ToList().ForEach(Console.WriteLine);
// featureBuilder.Mapper.InternalIDs.ToList().ForEach(Console.WriteLine);
}
public void TestAuxDataSize()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var bookDomain = new Domain("book", true);
var musicDomain = new Domain("music");
var dvdDomain = new Domain("dvd");
var videoDomain = new Domain("video");
var bookReader = new CsvReader("books_selected4.csv", config, bookDomain);
//var trainReader = new CsvReader("books_selected1_train.csv", config, bookDomain);
//var testReader = new CsvReader("books_selected1_test.csv", config, bookDomain, true);
var musicReader = new CsvReader(Paths.AmazonAllMusicRatings, config, musicDomain);
var dvdReader = new CsvReader(Paths.AmazonAllDvdRatings, config, dvdDomain);
var videoReader = new CsvReader(Paths.AmazonAllVideoRatings, config, videoDomain);
bookReader.LoadData(container);
//trainReader.LoadData(container);
//testReader.LoadData(container);
musicReader.LoadData(container);
//dvdReader.LoadData(container);
//videoReader.LoadData(container);
container.PrintStatistics();
var splitter = new CrossDomainSimpleSplitter(container, 0.25f);
//splitter.SaveSplitsAsCsv("books_selected1_train.csv", "books_selected1_test.csv");
var rmse = new List<string>();
var mae = new List<string>();
var durations = new List<string>();
for (int i = 0; i < 10; i++)
{
var startTime = DateTime.Now;
musicDomain.ActivateData(0.1f);
// step 2: recommender
LibFmTrainTester recommender;
CrossDomainLibFmFeatureBuilder featureBuilder = null;
featureBuilder = new CrossDomainLibFmFeatureBuilder(bookDomain, 10);
recommender = new LibFmTrainTester(experimentId: i.ToString(), featureBuilder: featureBuilder);
// 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();
rmse.Add(recommender.RMSE.ToString());
mae.Add(ctx["MAE"].ToString());
var duration = DateTime.Now.Subtract(startTime);
durations.Add(((int)duration.TotalMilliseconds).ToString());
}
Console.WriteLine("NumAuxRatings\tRMSE\tMAE\tDuration");
for (int i = 0; i < 10; i++)
{
Console.WriteLine("{0}\t{1}\t{2}\t{3}", i, rmse[i], mae[i], durations[i]);
}
}
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 TestAmazonDatasetSingle()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var trainReader = new CsvReader<ItemRating>(Paths.AmazonBooksTrain75, config, new ItemRatingMap());
var testReader = new CsvReader<ItemRating>(Paths.AmazonBooksTest25, config, new ItemRatingMap());
var dataset = new Dataset<ItemRating>(trainReader, testReader);
// step 2: recommender
var recommender = new MediaLiteRatingPredictor(new BiasedMatrixFactorization());
// 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 TestAmazonCrossDomainVideo()
{
// step 1: dataset
var config = new CsvConfiguration()
{
Delimiter = ",",
HasHeaderRecord = true
};
var container = new CrossDomainDataContainer();
var bookDomain = new Domain("book");
var musicDomain = new Domain("music");
var dvdDomain = new Domain("dvd");
var videoDomain = new Domain("video", true);
var trainReader = new CsvReader(Paths.AmazonVideoTrain75, config, videoDomain);
var testReader = new CsvReader(Paths.AmazonVideoTest25, config, videoDomain, true);
var musicReader = new CsvReader(Paths.AmazonMusicRatings, config, musicDomain);
var dvdReader = new CsvReader(Paths.AmazonDvdRatings, config, dvdDomain);
var bookReader = new CsvReader(Paths.AmazonBooksRatings, config, bookDomain);
//var tempReader = new LibFmReader(_ecirTrain, _ecirTest) { MainDomain = bookDomain, AuxDomain = musicDomain, UserDataPath = _musicUsersPath };
trainReader.LoadData(container);
testReader.LoadData(container);
musicReader.LoadData(container);
dvdReader.LoadData(container);
bookReader.LoadData(container);
//tempReader.LoadData(container);
//container.ShuffleDomains();
container.PrintStatistics();
//musicDomain.CacheUserData();
var splitter = new CrossDomainSimpleSplitter(container);
//var splitter = new RatingSimpleSplitter(container);
var numAuxRatings = new int[4] { 0, 1, 2, 3 };
var rmse = new List<string>();
var mae = new List<string>();
var durations = new List<string>();
foreach (var num in numAuxRatings)
{
var startTime = DateTime.Now;
// step 2: recommender
ITrainTester<ItemRating> recommender;
CrossDomainLibFmFeatureBuilder featureBuilder = null;
if (num == 0)
{
recommender = new LibFmTrainTester(experimentId: num.ToString());
}
else
{
featureBuilder = new CrossDomainLibFmFeatureBuilder(videoDomain, num);
//featureBuilder.LoadCachedUserData(_musicUsersPath);
recommender = new LibFmTrainTester(experimentId: num.ToString(), featureBuilder: featureBuilder);
}
// 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();
//File.WriteAllLines("maps.txt", featureBuilder.Mapper.OriginalIDs.Zip(featureBuilder.Mapper.InternalIDs, (f, s) => f + "\t" + s));
rmse.Add(ctx["RMSE"].ToString());
mae.Add(ctx["MAE"].ToString());
var duration = DateTime.Now.Subtract(startTime);
durations.Add(((int)duration.TotalMilliseconds).ToString());
}
Console.WriteLine("NumAuxRatings\tRMSE\tMAE\tDuration");
for (int i = 0; i < numAuxRatings.Count(); i++)
{
Console.WriteLine("{0}\t{1}\t{2}\t{3}", numAuxRatings[i], rmse[i], mae[i], durations[i]);
}
}
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);
}