public static void Main(string[] args)
{
// load the data
var training_data = RatingData.Read(args[0]);
var test_data = RatingData.Read(args[1]);
// set up the recommender
var recommender = new UserItemBaseline();
recommender.Ratings = training_data;
recommender.Train();
// measure the accuracy on the test data set
var results = recommender.Evaluate(test_data);
Console.WriteLine("RMSE={0} MAE={1}", results["RMSE"], results["MAE"]);
Console.WriteLine(results);
// make a prediction for a certain user and item
Console.WriteLine(recommender.Predict(1, 1));
var bmf = new BiasedMatrixFactorization {
Ratings = training_data
};
Console.WriteLine(bmf.DoCrossValidation());
}
[Test()] public void TestComputeCorrelations2()
{
// load data from disk
var user_mapping = new Mapping();
var item_mapping = new Mapping();
var ratings = RatingData.Read("../../../../data/ml-100k/u1.base", user_mapping, item_mapping);
var p = new Pearson(ratings.AllUsers.Count, 200f);
Assert.AreEqual(-0.02788301f, p.ComputeCorrelation(ratings, EntityType.ITEM, 45, 311), 0.00001);
}
IFoldInRatingPredictor CreateRecommender()
{
var training_data = RatingData.Read("../../../../data/ml-100k/u.data");
var recommender = new MatrixFactorization();
recommender.Ratings = training_data;
recommender.NumFactors = 4;
recommender.NumIter = 5;
recommender.Train();
return(recommender);
}
private void CreateRecommender()
{
BiasedMatrixFactorization recommender = new BiasedMatrixFactorization();
Console.Error.Write("Reading in ratings ... ");
TimeSpan time = Wrap.MeasureTime(delegate() {
recommender.Ratings = RatingData.Read(ratings_file, user_mapping, item_mapping);
});
Console.Error.WriteLine("done ({0,0:0.##}).", time.TotalSeconds.ToString(CultureInfo.InvariantCulture));
//Console.Error.Write("Reading in additional ratings ... ");
//string[] rating_files = Directory.GetFiles("../../saved_data/", "user-ratings-*");
//Console.Error.WriteLine("done.");
foreach (var indices_for_item in recommender.Ratings.ByItem)
{
if (indices_for_item.Count > 0)
{
movies_by_frequency.Add(new Tuple <int, float>(recommender.Ratings.Items[indices_for_item[0]], indices_for_item.Count));
}
}
movies_by_frequency = movies_by_frequency.OrderByDescending(x => x.Item2).ToList();
for (int i = 0; i < n_movies; i++)
{
top_n_movies.Add(movies_by_frequency[i].Item1);
}
Console.Error.Write("Loading prediction model ... ");
recommender.UpdateUsers = true;
recommender.UpdateItems = false;
recommender.BiasReg = 0.001f;
recommender.Regularization = 0.045f;
recommender.NumIter = 60;
time = Wrap.MeasureTime(delegate() {
recommender.LoadModel(model_file);
});
Console.Error.WriteLine("done ({0,0:0.##}).", time.TotalSeconds.ToString(CultureInfo.InvariantCulture));
rating_predictor = recommender;
current_user_id = user_mapping.ToInternalID(current_user_external_id.ToString());
//rating_predictor.AddUser(current_user_id);
// add movies that were not in the training set
//rating_predictor.AddItem( item_mapping.InternalIDs.Count - 1 );
PredictAllRatings();
}
public void TestRead()
{
var reader = new StringReader(@"5951,50,5
5951,223,5
5951,260,5
5951,293,5
5951,356,4
5951,364,3
5951,457,3
");
IRatings data = RatingData.Read(reader);
Assert.AreEqual(7, data.Count);
}
public void TestReadIgnoreLine()
{
var reader = new StringReader(@"# first line
5951,50,5
5951,223,5
5951,260,5
5951,293,5
5951,356,4
5951,364,3
5951,457,3
");
IRatings data = RatingData.Read(reader, null, null, true);
Assert.AreEqual(7, data.Count);
}
public void TestCase()
{
string filename = "../../../../tests/example.test";
var mapping = new IdentityMapping();
var ratings = RatingData.Read(filename);
var recommender = new ExternalRatingPredictor()
{
PredictionFile = filename, UserMapping = mapping, ItemMapping = mapping
};
recommender.Train();
for (int i = 0; i < ratings.Count; i++)
{
Assert.AreEqual(ratings[i], recommender.Predict(ratings.Users[i], ratings.Items[i]));
}
}
void LoadRatings(string name)
{
// assumption: ratings, training data and model were reloaded
ratings.Clear();
using (var reader = new StreamReader("../../../../saved_data/user-ratings-" + name))
{
IRatings user_ratings = RatingData.Read(reader, user_mapping, item_mapping);
for (int i = 0; i < user_ratings.Count; i++)
{
ratings[user_ratings.Items[i]] = user_ratings[i];
current_user_id = user_ratings.Users[i]; // TODO check whether user ID is the same for all ratings
}
}
}
//*********** ItemKNN Recommender - most similar items
public List <int> getMostSimilarItems(string dataset, int itemid, int recs)
{
var mydata = RatingData.Read(dataset);
//Create the recommender
var recommenderItemKNN = new MyMediaLite.RatingPrediction.ItemKNN();
//Give it the dataset
recommenderItemKNN.Ratings = mydata;
//Train it
recommenderItemKNN.Train();
/////////////
var item_recs = recommenderItemKNN.GetMostSimilarItems(itemid, (uint)recs);
// Print similar items
foreach (var i in item_recs)
{
mylist.Add(i);
}
return(mylist);
}
//*********** GlobalAverage Recommender
public List <int> getBestItemsGlobalAverage(string dataset, int userid, int recs)
{
var mydata = RatingData.Read(dataset);
//Create the recommender
var recommenderGlobalAverage = new MyMediaLite.RatingPrediction.GlobalAverage();
//Give it the dataset
recommenderGlobalAverage.Ratings = mydata;
//Train it
recommenderGlobalAverage.Train();
/////////////
// Make the predictions
var user_recs = recommenderGlobalAverage.Recommend(userid, recs);
// get the recommendations
foreach (var i in user_recs)
{
mylist.Add(i.Item1);
}
return(mylist);
}
///
public override void Train()
{
external_scores = RatingData.Read(PredictionFile, UserMapping, ItemMapping);
// we dont use it locally but it should be initialized before entering the parallel code
IList <IList <int> > nonsense = external_scores.ByUser;
}
protected override void LoadData()
{
bool static_data = !online_eval;
TimeSpan loading_time = Wrap.MeasureTime(delegate() {
base.LoadData();
// read training data
if ((recommender is TimeAwareRatingPredictor || chronological_split != null) && file_format != RatingFileFormat.MOVIELENS_1M)
{
training_data = TimedRatingData.Read(training_file, user_mapping, item_mapping);
}
else
{
if (file_format == RatingFileFormat.DEFAULT)
{
training_data = static_data
? StaticRatingData.Read(training_file, user_mapping, item_mapping, rating_type)
: RatingData.Read(training_file, user_mapping, item_mapping);
}
else if (file_format == RatingFileFormat.IGNORE_FIRST_LINE)
{
training_data = static_data
? StaticRatingData.Read(training_file, user_mapping, item_mapping, rating_type, TestRatingFileFormat.WITH_RATINGS, true)
: RatingData.Read(training_file, user_mapping, item_mapping, true);
}
else if (file_format == RatingFileFormat.MOVIELENS_1M)
{
training_data = MovieLensRatingData.Read(training_file, user_mapping, item_mapping);
}
else if (file_format == RatingFileFormat.KDDCUP_2011)
{
training_data = MyMediaLite.IO.KDDCup2011.Ratings.Read(training_file);
}
}
recommender.Ratings = training_data;
// read test data
if (test_file != null)
{
TestRatingFileFormat test_format = test_no_ratings ? TestRatingFileFormat.WITHOUT_RATINGS : TestRatingFileFormat.WITH_RATINGS;
if (recommender is TimeAwareRatingPredictor && file_format != RatingFileFormat.MOVIELENS_1M)
{
test_data = TimedRatingData.Read(test_file, user_mapping, item_mapping, test_format);
}
else if (file_format == RatingFileFormat.MOVIELENS_1M)
{
test_data = MovieLensRatingData.Read(test_file, user_mapping, item_mapping, test_format);
}
else if (file_format == RatingFileFormat.KDDCUP_2011)
{
test_data = MyMediaLite.IO.KDDCup2011.Ratings.Read(test_file);
}
else
{
test_data = StaticRatingData.Read(test_file, user_mapping, item_mapping, rating_type, test_format, file_format == RatingFileFormat.IGNORE_FIRST_LINE);
}
if (recommender is ITransductiveRatingPredictor)
{
((ITransductiveRatingPredictor)recommender).AdditionalFeedback = test_data;
}
}
});
Console.Error.WriteLine(string.Format(CultureInfo.InvariantCulture, "loading_time {0:0.##}", loading_time.TotalSeconds));
Console.Error.WriteLine("memory {0}", Memory.Usage);
}
// default constructor
public EvaluationModels(string dataset)
{
mydata = RatingData.Read(dataset);
}
static void Main(string[] args)
{
String path_training_data = "user_ratedmovies.dat";
String path_user_data = "users.dat";
String path_atr_data = "movie_genres.dat";
String path_pred_data = "predict.dat";
var user_mapping = new Mapping();
var item_mapping = new Mapping();
//var user_mapping = new EntityMapping();
//var item_mapping = new EntityMapping();
//String path_training_data = "1.rec.train";
//String path_test_data = "1.rec.test";
//String path_training_data = "u1.base";
//String path_test_data = "u1.test";
//var training_data = ItemData.Read(path_training_data);
//var test_data = ItemData.Read(path_test_data);
var training_data = RatingData.Read(path_training_data, user_mapping, item_mapping);
var relevant_items = item_mapping.InternalIDs;
var atr_data = AttributeData.Read(path_atr_data, item_mapping);
var pred_data = RatingData.Read(path_pred_data, user_mapping, item_mapping);
//var user_data = ItemData.Read(path_user_data, user_mapping);
Console.WriteLine("I'm here");
//Console.WriteLine(String.Join(";", user_data.AllUsers));
//var test_data = RatingData.Read(path_test_data);
//var recommender = new ItemKNN();
//recommender.Feedback = training_data;
//recommender.Train();
//var recommender = new GSVDPlusPlus();
//var recommender = new MatrixFactorization();
//recommender.Ratings = training_data;
// recommender.MaxRating = 5;
// recommender.MinRating = 1;
//recommender.ItemAttributes = atr_data;
//recommender.NumFactors = 5;
//recommender.NumIter = 10;
//recommender.Train();
var recommender = new SVDPlusPlus();
recommender.Ratings = training_data;
//recommender.AdditionalFeedback = user_data;
Console.WriteLine("I'm here2");
Console.WriteLine(recommender.ToString());
//recommender.ItemAttributes = atr_data;
recommender.NumFactors = 10;
Console.WriteLine("I'm here3");
Console.WriteLine(recommender.ToString());
recommender.Train();
Console.WriteLine("I'm here4");
//var results = recommender.DoIterativeCrossValidation(recommdender, 10, 1, 1, true);
var results = recommender.DoCrossValidation(10, false, true);
////var results = recommender.Evaluate(test_data, training_data);
foreach (var key in results.Keys)
{
Console.WriteLine("{0}={1}", key, results[key]);
}
Console.WriteLine(results);
//recommender.Predict();
recommender.WritePredictions(pred_data, "test45.dat", user_mapping, item_mapping, "{0}|{1}|{2}");
Console.WriteLine(recommender.Predict(1, 1));
Console.ReadLine();
}
public static void Main(string[] args)
{
// TODO add random seed
// TODO report per-user times
string data_file = args[0];
string method = args[1];
string options = args[2];
int num_test_users = int.Parse(args[3]);
// load the data
var all_data = RatingData.Read(data_file);
// TODO randomize
var test_users = new HashSet <int>(Enumerable.Range(0, num_test_users));
var update_indices = new List <int>();
var eval_indices = new List <int>();
foreach (int user_id in test_users)
{
if (all_data.ByUser[user_id].Count > 1)
{
var user_indices = all_data.ByUser[user_id];
for (int i = 0; i < user_indices.Count - 1; i++)
{
update_indices.Add(user_indices[i]);
}
for (int i = user_indices.Count - 1; i < user_indices.Count; i++)
{
eval_indices.Add(user_indices[i]);
}
}
}
var training_indices = new List <int>();
for (int i = 0; i < all_data.Count; i++)
{
if (!test_users.Contains(all_data.Users[i]))
{
training_indices.Add(i);
}
}
var training_data = new MyMediaLite.Data.Ratings();
foreach (int i in training_indices)
{
training_data.Add(all_data.Users[i], all_data.Items[i], all_data[i]);
}
var update_data = new RatingsProxy(all_data, update_indices);
var eval_data = new RatingsProxy(all_data, eval_indices);
Console.Write(training_data.Statistics());
Console.Write(update_data.Statistics());
Console.Write(eval_data.Statistics());
// prepare recommender
RatingPredictor recommender = method.CreateRatingPredictor();
recommender.Configure(options);
recommender.Ratings = training_data;
Console.WriteLine(string.Format(CultureInfo.InvariantCulture, "ratings range: [{0}, {1}]", recommender.MinRating, recommender.MaxRating));
Console.WriteLine("recommender: {0}", recommender);
recommender.Train();
// I. complete retraining
Console.WriteLine(
"complete training: {0}",
recommender.EvaluateFoldInCompleteRetraining(update_data, eval_data));
// II. online updates
Console.WriteLine(
"incremental training: {0}",
((IncrementalRatingPredictor)recommender).EvaluateFoldInIncrementalTraining(update_data, eval_data));
// III. fold-in
Console.WriteLine(
"fold-in: {0}",
((IFoldInRatingPredictor)recommender).EvaluateFoldIn(update_data, eval_data));
}
///
public override void Train()
{
external_scores = RatingData.Read(PredictionFile, UserMapping, ItemMapping);
}