public void TestFoldIn()
{
var mf = new BiasedMatrixFactorization() { Ratings = TestUtils.CreateRatings() };
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);
}
public void TestDecay()
{
var mf = new BiasedMatrixFactorization()
{
LearnRate = 1.0f, LearnRateDecay = 0.5f,
NumIter = 1, Ratings = TestUtils.CreateRatings()
};
mf.Train();
Assert.AreEqual(0.5f, mf.current_learnrate);
mf.Iterate();
Assert.AreEqual(0.25f, mf.current_learnrate);
}
static void Main(string[] args)
{
var t = new Stopwatch();
//Utils.Converter(@"D:\__testdata\lab10\train.csv");
//return;
t.Restart();
Console.WriteLine("RatingData.Read Begin");
var trainingData = RatingData.Read(TRAIN_DATA_FILE_NAME);
Console.WriteLine("RatingData.Read End {0}", t.Elapsed.TotalSeconds);
//t.Restart();
//Console.WriteLine("RatingData.Read Begin");
//var evalData = RatingData.Read(EVAL_DATA_FILE_NAME);
//Console.WriteLine("RatingData.Read End {0}", t.Elapsed.TotalSeconds);
//http://www.mymedialite.net/examples/datasets.html
// num_factors=120
// bias_reg=0.001
// regularization=0.055
// learn_rate=0.07
// num_iter=100
// bold_driver=true
var recommender = new BiasedMatrixFactorization
{
Ratings = trainingData,
NumIter = 10,
MaxRating = 5,
MinRating = 1,
};
t.Restart();
Console.WriteLine("Training begin");
recommender.Train();
Console.WriteLine("Training end {0}", t.Elapsed.TotalSeconds);
//t.Restart();
//Console.WriteLine("Evaluate begin");
//var resultsb = recommender.Evaluate(evalData);
//Console.WriteLine("Evaluate end {0}", t.Elapsed.TotalSeconds);
Console.WriteLine(recommender.DoCrossValidation());
//Console.WriteLine("RMSE={0} MAE={1}", resultsb["RMSE"], resultsb["MAE"]);
t.Restart();
Console.WriteLine("Result Begin");
var users = recommender.Ratings.AllUsers.ToArray();
var items = recommender.Ratings.AllItems.ToArray();
var ratingAvg = recommender.Ratings.Average;
using(var testIn = new StreamReader(TEST_FILE_NAME))
using (var resultOut = new StreamWriter(RESULTS_FILE_NAME))
{
var count = 0;
string line;
while ((line = testIn.ReadLine()) != null)
{
if (count > 0)
{
var parts = line.Split(new[] {","}, StringSplitOptions.RemoveEmptyEntries);
var userId = int.Parse(parts[0]);
var itemId = int.Parse(parts[1]);
var rating = !users.Contains(userId) || !items.Contains(itemId)
? ratingAvg
: recommender.Predict(userId, itemId);
resultOut.WriteLine("{0}, {1}, {2}", userId, itemId, rating);
}
if (count%10000 == 0)
{
resultOut.Flush();
Console.Write(".");
}
count++;
}
resultOut.Close();
testIn.Close();
}
Console.WriteLine();
Console.WriteLine("Result End {0}", t.Elapsed.TotalSeconds);
t.Stop();
Console.WriteLine("End");
Console.ReadLine();
}
public void TestDefaultBehaviorIsNoDecay()
{
var mf = new BiasedMatrixFactorization() { LearnRate = 1.1f, NumIter = 10, Ratings = TestUtils.CreateRatings() };
mf.Train();
Assert.AreEqual(1.1f, mf.current_learnrate);
}
public void TestIncrementalUpdates()
{
var mf = new BiasedMatrixFactorization() { Ratings = TestUtils.CreateRatings(), FrequencyRegularization = true };
mf.Train();
var new_ratings = new Ratings();
new_ratings.Add(mf.MaxUserID + 1, mf.MaxItemID + 1, 3f);
mf.AddRatings(new_ratings);
}
/// <summary>
/// Predict the rating of the item by users
/// </summary>
private static void PredictRating(string[] args)
{
Console.WriteLine("Predicting ratings for Users...");
String outputFile = Path.Combine(args[2], outputFileForRatings);
testingFile = Path.Combine(args[1], testingFile);
testingFileModified = Path.Combine(args[2], testingFileModified);
ModifyTestingFileForRating(testingFile, testingFileModified);
float minRating = 1;
float maxRating = 5;
var userMapping = new Mapping();
var itemMapping = new Mapping();
var trainingData = StaticRatingData.Read(trainingCompactFileForRatings, userMapping, itemMapping, RatingType.FLOAT, TestRatingFileFormat.WITH_RATINGS, false);
var testUsers = trainingData.AllUsers; // users that will be taken into account in the evaluation
var candidate_items = trainingData.AllItems; // items that will be taken into account in the evaluation
var testData = StaticRatingData.Read(testingFileModified, userMapping, itemMapping, RatingType.FLOAT, TestRatingFileFormat.WITH_RATINGS, false);
var recommender = new BiasedMatrixFactorization();
recommender.MinRating = minRating;
recommender.MaxRating = maxRating;
recommender.Ratings = trainingData;
recommender.NumFactors = 30;
recommender.NumIter = 100;
recommender.RegI = 0.04F;
recommender.RegU = 0.04F;
//recommender.BiasReg = 0.09F;
recommender.FrequencyRegularization = true;
recommender.BoldDriver = true;
recommender.LearnRate = 0.07F;
Stopwatch timeKeeper = new Stopwatch();
timeKeeper.Start();
recommender.Train();
timeKeeper.Stop();
Console.WriteLine("time passed for training rating prediction model: " + timeKeeper.ElapsedMilliseconds);
// measure the accuracy on the test data set
timeKeeper = new Stopwatch();
timeKeeper.Start();
var results = recommender.Evaluate(testData);
timeKeeper.Stop();
Console.WriteLine("time passed for rating prediction: " + timeKeeper.ElapsedMilliseconds);
Console.WriteLine("RMSE={0}", results["RMSE"]);
recommender.WritePredictions(testData, outputFile, userMapping, itemMapping, "{0}-{1},{2}", "userID-itemID,rating");
}