public void TestDefaultBehaviorIsNoDecay()
{
var mf = new SocialMF()
{
LearnRate = 1.1f, NumIter = 10, Ratings = TestUtils.CreateRatings(), UserRelation = new SparseBooleanMatrix()
};
mf.Train();
Assert.AreEqual(1.1f, mf.current_learnrate);
}
public void TestCurrentLearnRate()
{
var mf = new SocialMF()
{
LearnRate = 1.1f, Ratings = TestUtils.CreateRatings(), UserRelation = new SparseBooleanMatrix()
};
mf.InitModel();
Assert.AreEqual(1.1f, mf.LearnRate);
Assert.AreEqual(1.1f, mf.current_learnrate);
}
public void TestImplicitTrust()
{
var socialReguls = new float[] { 1F };
var numFactors = new uint[] { 5, 10 };
var trustScores = new string[] { "trust_values_LATHIA.dat", "trust_values_HWANGCHEN.dat",
"trust_values_ODONOVAN.dat", "trust_values_PEARSON.dat", "trust_values_SHAMBOURLU.dat" };
// step 1: dataset
var config = new CsvConfiguration();
config.Delimiter = " ";
var trainReader = new CsvReader <ItemRating>(Paths.EpinionTrain80, config, new ItemRatingMap());
var testReader = new CsvReader <ItemRating>(Paths.EpinionTest20, config, new ItemRatingMap());
var dataset = new Dataset <ItemRating>(trainReader, testReader);
foreach (string scoreFile in trustScores)
{
var relations = File.ReadAllLines(Paths.EpinionRelationsImplicit + scoreFile).ToCsvDictionary('\t')
.Select(i => new Relation()
{
UserId = i["UserId"],
ConnectedId = i["ConnectionId"],
ConnectionStrength = float.Parse(i["Strength"])
});
//.Where(r => r.ConnectionStrength > 1F);
string rmseValues = "", maeValues = "";
foreach (uint num in numFactors)
{
// step 2: recommender
var algorithm = new SocialMF();
algorithm.SocialRegularization = 1;
algorithm.NumFactors = num;
var recommender = new MediaLiteRatingPredictor(algorithm, relations);
// step3: evaluation
var context = new EvalutationContext <ItemRating>(recommender, dataset);
var ep = new EvaluationPipeline <ItemRating>(context);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
rmseValues += context["RMSE"] + "\t";
maeValues += context["MAE"] + "\t";
}
Console.WriteLine(scoreFile + "\t" + rmseValues + "\t" + maeValues);
}
}
public void TestMatrixInit()
{
var mf = new SocialMF()
{
Ratings = TestUtils.CreateRatings(), UserRelation = new SparseBooleanMatrix()
};
mf.InitModel();
Assert.IsNotNull(mf.user_factors);
Assert.IsNotNull(mf.item_factors);
Assert.IsNotNull(mf.user_bias);
Assert.IsNotNull(mf.item_bias);
}
public static void SocialMFTest()
{
List <Rating> baseRatings = Tools.GetRatings(BaseRatingFile, " ");
List <Rating> testRatings = Tools.GetRatings(TestRatingFile, " ");
List <Link> links = Tools.GetLinks(DefaultLinkFile, " ");
Tools.UpdateIndexesToZeroBased(baseRatings);
Tools.UpdateIndexesToZeroBased(testRatings);
Tools.UpdateIndexesToZeroBased(links);
SocialMF model = new SocialMF(MaxUserId, MaxItemId);
model.TrySGD(baseRatings, testRatings, links, 200, 0.02, 0.9, 0.01, 0.01, 0.01);
}
public void TestDecay()
{
var mf = new SocialMF()
{
LearnRate = 1.0f, Decay = 0.5f,
NumIter = 1, Ratings = TestUtils.CreateRatings(),
UserRelation = new SparseBooleanMatrix()
};
mf.Train();
Assert.AreEqual(0.5f, mf.current_learnrate);
mf.Iterate();
Assert.AreEqual(0.25f, mf.current_learnrate);
}
public void TestFoldIn()
{
var mf = new SocialMF()
{
Ratings = TestUtils.CreateRatings(), UserRelation = new SparseBooleanMatrix()
};
mf.Train();
var user_ratings = new List <Tuple <int, float> >();
user_ratings.Add(new Tuple <int, float>(0, 4.0f));
var candidate_items = new List <int> {
0, 1
}; // have a known and an unknown item
var results = mf.ScoreItems(user_ratings, candidate_items);
Assert.AreEqual(2, results.Count);
}
