private void RunRatingPrediction()
{
// step 1: dataset
Dataset <ItemRating> dataset;
if (Parameters.GetValueOrDefault("data-format", "") == "crowdrec")
{
string efile = Parameters.GetValueOrDefault("entitiesfile", "");
string rfile = Parameters.GetValueOrDefault("relationsfile", "");
if (efile == "" || rfile == "")
{
throw new WrapRecException("The parameters 'entitesfile' and 'relationsfile' should be specified.");
}
var reader = new CrowdRecDataReader(efile, rfile);
var container = new CrowdRecDataContainer();
reader.LoadData(container);
if (Parameters.GetValueOrDefault("testportion", "") == "")
{
throw new WrapRecException("The parameter 'testportion' should be specified.");
}
dataset = new ItemRatingDataset(container, float.Parse(Parameters["testportion"]));
}
else if (Parameters.GetValueOrDefault("dataset", "") != "")
{
dataset = GetDataset <ItemRating>(Parameters["dataset"], "", new ItemRatingMap());
}
else if (Parameters.GetValueOrDefault("trainfile", "") != "" && Parameters.GetValueOrDefault("testfile", "") != "")
{
dataset = GetDataset <ItemRating>(Parameters["trainfile"], Parameters["testfile"], new ItemRatingMap());
}
else
{
throw new WrapRecException("Not enough information about dataset. Check help!");
}
// step 2: recommender
IModel recommender = GetRecommender();
Console.WriteLine("\nRecommender: {0}\n", recommender.GetType().Name);
// step3: evaluation
var ep = new EvaluationPipeline <ItemRating>(new EvalutationContext <ItemRating>(recommender, dataset));
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
}
static void Run(string trainingSet, string testSet)
{
// step 1: dataset
var container = new MovieTweetingsDataContainer();
var reader = new MovieTweetingsReader(trainingSet, testSet);
reader.LoadData(container);
Console.WriteLine("Data container statistics:\n {0}", container.ToString());
var dataset = new ItemRatingDataset(container);
var featureBuilder = new MovieTweetingLibSvmFeatureBuilder(container);
// svm parameters
var svmParameters = new SvmParameter
{
SvmType = SvmType.C_SVC,
KernelType = KernelType.Linear,
CacheSize = 128,
C = 1,
Eps = 1e-3,
Shrinking = true,
Probability = false
};
// step 2: recommender
var labelSelector = new Func <ItemRating, double>(ir =>
{
var t = container.Tweets[ir];
return(((t.RetweetCount + t.FavoriteCount) > 0) ? 1.0 : 0.0);
});
var recommender = new LibSvmClassifier(svmParameters, featureBuilder, labelSelector);
// step3: evaluation
var ep = new EvaluationPipeline <ItemRating>(new EvalutationContext <ItemRating>(recommender, dataset));
ep.Evaluators.Add(new WriteChallengeOutput(container, "test_output.dat"));
ep.Run();
}
public void RunDemo()
{
// step 1: load dataset
var container = new CrowdRecDataContainer();
var reader = new CrowdRecDataReader(_entitesFile, _relationsFile);
reader.LoadData(container);
var dataset = new ItemRatingDataset(container, 0.3f);
// step 2: recommender
var recommender = new MediaLiteRatingPredictor(new BiasedMatrixFactorization());
// step 3: evaluations
var pipline = new EvaluationPipeline<ItemRating>(new EvalutationContext<ItemRating>(recommender, dataset));
pipline.Evaluators.Add(new RMSE());
pipline.Evaluators.Add(new MAE());
pipline.Run();
}
static void Run(string trainingSet, string testSet)
{
// step 1: dataset
var container = new MovieTweetingsDataContainer();
var reader = new MovieTweetingsReader(trainingSet, testSet);
reader.LoadData(container);
Console.WriteLine("Data container statistics:\n {0}", container.ToString());
var dataset = new ItemRatingDataset(container);
var featureBuilder = new MovieTweetingLibSvmFeatureBuilder(container);
// svm parameters
var svmParameters = new SvmParameter
{
SvmType = SvmType.C_SVC,
KernelType = KernelType.Linear,
CacheSize = 128,
C = 1,
Eps = 1e-3,
Shrinking = true,
Probability = false
};
// step 2: recommender
var labelSelector = new Func<ItemRating, double>(ir =>
{
var t = container.Tweets[ir];
return ((t.RetweetCount + t.FavoriteCount) > 0) ? 1.0 : 0.0;
});
var recommender = new LibSvmClassifier(svmParameters, featureBuilder, labelSelector);
// step3: evaluation
var ep = new EvaluationPipeline<ItemRating>(new EvalutationContext<ItemRating>(recommender, dataset));
ep.Evaluators.Add(new WriteChallengeOutput(container, "test_output.dat"));
ep.Run();
}
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 RunDemo()
{
// step 1: load dataset
var container = new CrowdRecDataContainer();
var reader = new CrowdRecDataReader(_entitesFile, _relationsFile);
reader.LoadData(container);
var dataset = new ItemRatingDataset(container, 0.3f);
// step 2: recommender
var recommender = new MediaLiteRatingPredictor(new BiasedMatrixFactorization());
// step 3: evaluations
var pipline = new EvaluationPipeline <ItemRating>(new EvalutationContext <ItemRating>(recommender, dataset));
pipline.Evaluators.Add(new RMSE());
pipline.Evaluators.Add(new MAE());
pipline.Run();
}
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 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 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();
}
