/// <summary>Read binary relation data from file</summary>
/// <remarks>
/// The expected (sparse) line format is:
/// ENTITY_ID whitespace ENTITY_ID
/// for the relations that hold.
/// </remarks>
/// <param name="reader">a StreamReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the relation data</returns>
public static SparseBooleanMatrix Read(StreamReader reader, IEntityMapping mapping)
{
var matrix = new SparseBooleanMatrix();
char[] split_chars = new char[]{ '\t', ' ' };
string line;
while (!reader.EndOfStream)
{
line = reader.ReadLine();
// ignore empty lines
if (line.Length == 0)
continue;
string[] tokens = line.Split(split_chars);
if (tokens.Length != 2)
throw new IOException("Expected exactly two columns: " + line);
int entity1_id = mapping.ToInternalID(int.Parse(tokens[0]));
int entity2_id = mapping.ToInternalID(int.Parse(tokens[1]));
matrix[entity1_id, entity2_id] = true;
}
return matrix;
}
[Test()] public void TestCreateMatrix()
{
var matrix = new SparseBooleanMatrix();
var other_matrix = matrix.CreateMatrix(2, 2);
Assert.IsInstanceOf(matrix.GetType(), other_matrix);
}
public void TestCreate()
{
var sparse_boolean_matrix = new SparseBooleanMatrix();
sparse_boolean_matrix[0, 1] = true;
sparse_boolean_matrix[0, 4] = true;
sparse_boolean_matrix[1, 0] = true;
sparse_boolean_matrix[1, 2] = true;
sparse_boolean_matrix[1, 4] = true;
sparse_boolean_matrix[3, 1] = true;
sparse_boolean_matrix[3, 3] = true;
sparse_boolean_matrix[3, 4] = true;
var correlation_matrix = BinaryCosine.Create(sparse_boolean_matrix);
Assert.AreEqual(4, correlation_matrix.NumberOfRows);
Assert.IsTrue(correlation_matrix.IsSymmetric);
Assert.AreEqual(1 / Math.Sqrt(6), correlation_matrix[0, 1], delta);
Assert.AreEqual(1 / Math.Sqrt(6), correlation_matrix[1, 0], delta);
Assert.AreEqual(1 / 3d, correlation_matrix[1, 3], delta);
Assert.AreEqual(0f, correlation_matrix[2, 0]);
Assert.AreEqual(0f, correlation_matrix[2, 1]);
Assert.AreEqual(1f, correlation_matrix[2, 2]);
Assert.AreEqual(0f, correlation_matrix[2, 3]);
Assert.AreEqual(0f, correlation_matrix[0, 2]);
Assert.AreEqual(0f, correlation_matrix[1, 2]);
Assert.AreEqual(0f, correlation_matrix[3, 2]);
}
public void TestNumberOfColumns()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
{
matrix[i, 1]= true;
matrix[i, 4]= true;
}
Assert.AreEqual(5, matrix.NumberOfColumns);
}
public override void Train()
{
filtered_items_by_user = new Dictionary<int, ICollection<int>>[MaxUserID + 1];
items_by_attribute = (SparseBooleanMatrix) item_attributes.Transpose();
Console.Error.WriteLine("max_user_id {0} max_item_id {1}", MaxUserID, MaxItemID);
for (int u = 0; u < filtered_items_by_user.Count; u++)
filtered_items_by_user[u] = ItemsFiltered.GetFilteredItems(u, Feedback, ItemAttributes);
base.Train();
}
/// <summary>Get the transpose of the matrix, i.e. a matrix where rows and columns are interchanged</summary>
/// <returns>the transpose of the matrix (copy)</returns>
public IMatrix <bool> Transpose()
{
var transpose = new SparseBooleanMatrix();
for (int i = 0; i < row_list.Count; i++)
{
foreach (int j in this[i])
{
transpose[j, i] = true;
}
}
return(transpose);
}
public void TestNonEmptyRows()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2)
{
matrix[i, 1]= true;
matrix[i, 4]= true;
}
Assert.IsTrue(matrix[0, 1]);
IList<KeyValuePair<int, HashSet<int>>> nonEmptyRows = matrix.NonEmptyRows;
Assert.AreEqual(4, nonEmptyRows.Count);
// TODO test contents
}
/// <summary>Display dataset statistics</summary>
/// <param name="train">the training data</param>
/// <param name="test">the test data</param>
/// <param name="user_attributes">the user attributes</param>
/// <param name="item_attributes">the item attributes</param>
/// <param name="display_overlap">if set true, display the user/item overlap between train and test</param>
public static string Statistics(
this IRatings train, IRatings test = null,
SparseBooleanMatrix user_attributes = null, SparseBooleanMatrix item_attributes = null,
bool display_overlap = false)
{
// training data stats
int num_users = train.AllUsers.Count;
int num_items = train.AllItems.Count;
long matrix_size = (long) num_users * num_items;
long empty_size = (long) matrix_size - train.Count;
double sparsity = (double) 100L * empty_size / matrix_size;
string s = string.Format(CultureInfo.InvariantCulture, "training data: {0} users, {1} items, {2} ratings, sparsity {3,0:0.#####}\n", num_users, num_items, train.Count, sparsity);
if (train is ITimedRatings)
{
var time_train = train as ITimedRatings;
s += string.Format(CultureInfo.InvariantCulture, "rating period: {0} to {1}\n", time_train.EarliestTime, time_train.LatestTime);
}
// test data stats
if (test != null)
{
num_users = test.AllUsers.Count;
num_items = test.AllItems.Count;
matrix_size = (long) num_users * num_items;
empty_size = (long) matrix_size - test.Count; // TODO depends on the eval scheme whether this is correct
sparsity = (double) 100L * empty_size / matrix_size;
s += string.Format(CultureInfo.InvariantCulture, "test data: {0} users, {1} items, {2} ratings, sparsity {3,0:0.#####}\n", num_users, num_items, test.Count, sparsity);
if (test is ITimedRatings)
{
var time_test = test as ITimedRatings;
s += string.Format(CultureInfo.InvariantCulture, "rating period: {0} to {1}\n", time_test.EarliestTime, time_test.LatestTime);
}
}
// count and display the overlap between train and test
if (display_overlap && test != null)
{
int num_new_users = 0;
int num_new_items = 0;
TimeSpan seconds = Util.Wrap.MeasureTime(delegate() {
num_new_users = test.AllUsers.Except(train.AllUsers).Count();
num_new_items = test.AllItems.Except(train.AllItems).Count();
});
s += string.Format("{0} new users, {1} new items ({2} seconds)\n", num_new_users, num_new_items, seconds);
}
return s + Statistics(user_attributes, item_attributes);
}
[Test()] public void TestGetEntriesByRow()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2 && i !=3)
{
matrix[i, 1] = true;
matrix[i, 4] = true;
}
Assert.AreEqual(2, matrix.GetEntriesByRow(0).Count);
Assert.AreEqual(2, matrix.GetEntriesByRow(1).Count);
Assert.AreEqual(0, matrix.GetEntriesByRow(2).Count);
Assert.AreEqual(0, matrix.GetEntriesByRow(3).Count);
Assert.AreEqual(2, matrix.GetEntriesByRow(4).Count);
}
[Test()] public void TestIsSymmetric()
{
var matrix = new SparseBooleanMatrix();
Assert.IsTrue(matrix.IsSymmetric);
matrix[1, 1] = true;
Assert.IsTrue(matrix.IsSymmetric);
matrix[2, 1] = true;
Assert.IsFalse(matrix.IsSymmetric);
matrix[1, 2] = true;
Assert.IsTrue(matrix.IsSymmetric);
matrix[2, 1] = false;
Assert.IsFalse(matrix.IsSymmetric);
}
public void TestCreate()
{
// create test objects
var sparse_boolean_matrix = new SparseBooleanMatrix();
sparse_boolean_matrix[0, 1] = true;
sparse_boolean_matrix[0, 4] = true;
sparse_boolean_matrix[1, 0] = true;
sparse_boolean_matrix[1, 2] = true;
sparse_boolean_matrix[1, 4] = true;
sparse_boolean_matrix[3, 1] = true;
sparse_boolean_matrix[3, 3] = true;
sparse_boolean_matrix[3, 4] = true;
// test
var correlation_matrix = BinaryCosine.Create(sparse_boolean_matrix);
Assert.AreEqual(Math.Round(1 / Math.Sqrt(6), 4), Math.Round(correlation_matrix[0, 1], 4));
Assert.AreEqual(Math.Round(1 / Math.Sqrt(6), 4), Math.Round(correlation_matrix[1, 0], 4));
Assert.AreEqual(Math.Round(1 / 3d, 4), Math.Round(correlation_matrix[1, 3], 4));
}
public void TestComputeCorrelations()
{
var sparse_boolean_matrix = new SparseBooleanMatrix();
sparse_boolean_matrix[0, 1] = true;
sparse_boolean_matrix[0, 4] = true;
sparse_boolean_matrix[1, 0] = true;
sparse_boolean_matrix[1, 2] = true;
sparse_boolean_matrix[1, 4] = true;
sparse_boolean_matrix[3, 1] = true;
sparse_boolean_matrix[3, 3] = true;
sparse_boolean_matrix[3, 4] = true;
var correlation = new BinaryCosine(4);
correlation.ComputeCorrelations(sparse_boolean_matrix);
Assert.AreEqual(1 / Math.Sqrt(6), correlation[0, 1], delta);
Assert.AreEqual(1 / Math.Sqrt(6), correlation[1, 0], delta);
Assert.AreEqual(1 / 3d, correlation[1, 3], delta);
}
public void TestNonEmptyRowIDs()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2 && i !=3)
{
matrix[i, 1]= true;
matrix[i, 4]= true;
}
ICollection<int> rowIDs = matrix.NonEmptyRowIDs;
IEnumerator <int> rowIDsEnum = rowIDs.GetEnumerator();
rowIDsEnum.MoveNext();
Assert.AreEqual(0, rowIDsEnum.Current);
rowIDsEnum.MoveNext();
Assert.AreEqual(1, rowIDsEnum.Current);
rowIDsEnum.MoveNext();
rowIDsEnum.MoveNext();
Assert.AreEqual(4, rowIDsEnum.Current);
Assert.IsFalse(rowIDsEnum.MoveNext());
}
/// <summary>Read binary attribute data from a StreamReader</summary>
/// <remarks>
/// The expected (sparse) line format is:
/// ENTITY_ID tab/space/comma ATTRIBUTE_ID
/// for the relations that hold.
/// </remarks>
/// <param name="reader">a StreamReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the attribute data</returns>
public static SparseBooleanMatrix Read(StreamReader reader, IEntityMapping mapping)
{
var matrix = new SparseBooleanMatrix();
string line;
while ((line = reader.ReadLine()) != null)
{
// ignore empty lines
if (line.Length == 0)
continue;
string[] tokens = line.Split(Constants.SPLIT_CHARS);
if (tokens.Length != 2)
throw new FormatException("Expected exactly 2 columns: " + line);
int entity_id = mapping.ToInternalID(tokens[0]);
int attr_id = int.Parse(tokens[1]);
matrix[entity_id, attr_id] = true;
}
return matrix;
}
/// <summary>Evaluation for rankings of filtered items</summary>
/// <remarks>
/// </remarks>
/// <param name="recommender">item recommender</param>
/// <param name="test">test cases</param>
/// <param name="train">training data</param>
/// <param name="item_attributes">the item attributes to be used for filtering</param>
/// <param name="relevant_users">a collection of integers with all relevant users</param>
/// <param name="relevant_items">a collection of integers with all relevant items</param>
/// <returns>a dictionary containing the evaluation results</returns>
public static Dictionary<string, double> Evaluate(
IItemRecommender recommender,
IPosOnlyFeedback test,
IPosOnlyFeedback train,
SparseBooleanMatrix item_attributes,
ICollection<int> relevant_users,
ICollection<int> relevant_items)
{
if (train.Overlap(test) > 0)
Console.Error.WriteLine("WARNING: Overlapping train and test data");
SparseBooleanMatrix items_by_attribute = (SparseBooleanMatrix) item_attributes.Transpose();
// compute evaluation measures
double auc_sum = 0;
double map_sum = 0;
double prec_5_sum = 0;
double prec_10_sum = 0;
double prec_15_sum = 0;
double ndcg_sum = 0;
// for counting the users and the evaluation lists
int num_lists = 0;
int num_users = 0;
int last_user_id = -1;
foreach (int user_id in relevant_users)
{
var filtered_items = GetFilteredItems(user_id, test, item_attributes);
foreach (int attribute_id in filtered_items.Keys)
{
// TODO optimize this a bit, currently it is quite naive
var relevant_filtered_items = new HashSet<int>(items_by_attribute[attribute_id]);
relevant_filtered_items.IntersectWith(relevant_items);
var correct_items = new HashSet<int>(filtered_items[attribute_id]);
correct_items.IntersectWith(relevant_filtered_items);
// the number of items that are really relevant for this user
var relevant_items_in_train = new HashSet<int>(train.UserMatrix[user_id]);
relevant_items_in_train.IntersectWith(relevant_filtered_items);
int num_eval_items = relevant_filtered_items.Count - relevant_items_in_train.Count();
// skip all users that have 0 or #relevant_filtered_items test items
if (correct_items.Count == 0)
continue;
if (num_eval_items - correct_items.Count == 0)
continue;
// counting stats
num_lists++;
if (last_user_id != user_id)
{
last_user_id = user_id;
num_users++;
}
// evaluation
int[] prediction = Prediction.PredictItems(recommender, user_id, relevant_filtered_items);
auc_sum += Items.AUC(prediction, correct_items, train.UserMatrix[user_id]);
map_sum += Items.MAP(prediction, correct_items, train.UserMatrix[user_id]);
ndcg_sum += Items.NDCG(prediction, correct_items, train.UserMatrix[user_id]);
prec_5_sum += Items.PrecisionAt(prediction, correct_items, train.UserMatrix[user_id], 5);
prec_10_sum += Items.PrecisionAt(prediction, correct_items, train.UserMatrix[user_id], 10);
prec_15_sum += Items.PrecisionAt(prediction, correct_items, train.UserMatrix[user_id], 15);
if (prediction.Length != relevant_filtered_items.Count)
throw new Exception("Not all items have been ranked.");
if (num_lists % 1000 == 0)
Console.Error.Write(".");
if (num_lists % 20000 == 0)
Console.Error.WriteLine();
}
}
var result = new Dictionary<string, double>();
result.Add("AUC", auc_sum / num_lists);
result.Add("MAP", map_sum / num_lists);
result.Add("NDCG", ndcg_sum / num_lists);
result.Add("prec@5", prec_5_sum / num_lists);
result.Add("prec@10", prec_10_sum / num_lists);
result.Add("prec@15", prec_15_sum / num_lists);
result.Add("num_users", num_users);
result.Add("num_lists", num_lists);
result.Add("num_items", relevant_items.Count);
return result;
}
/// <summary>Get the transpose of the matrix, i.e. a matrix where rows and columns are interchanged</summary>
/// <returns>the transpose of the matrix (copy)</returns>
public IMatrix<bool> Transpose()
{
var transpose = new SparseBooleanMatrix();
for (int i = 0; i < row_list.Count; i++)
foreach (int j in this[i])
transpose[j, i] = true;
return transpose;
}
static void LoadData()
{
TimeSpan loading_time = Utils.MeasureTime(delegate() {
// training data
training_data = ItemRecommendation.Read(Path.Combine(data_dir, training_file), user_mapping, item_mapping);
// relevant users and items
if (relevant_users_file != null)
relevant_users = new HashSet<int>(user_mapping.ToInternalID(Utils.ReadIntegers(Path.Combine(data_dir, relevant_users_file))));
else
relevant_users = training_data.AllUsers;
if (relevant_items_file != null)
relevant_items = new HashSet<int>(item_mapping.ToInternalID(Utils.ReadIntegers(Path.Combine(data_dir, relevant_items_file))));
else
relevant_items = training_data.AllItems;
if (! (recommender is MyMediaLite.ItemRecommendation.Random))
((ItemRecommender)recommender).Feedback = training_data;
// user attributes
if (recommender is IUserAttributeAwareRecommender)
{
if (user_attributes_file == null)
Usage("Recommender expects --user-attributes=FILE.");
else
((IUserAttributeAwareRecommender)recommender).UserAttributes = AttributeData.Read(Path.Combine(data_dir, user_attributes_file), user_mapping);
}
// item attributes
if (recommender is IItemAttributeAwareRecommender)
{
if (item_attributes_file == null)
Usage("Recommender expects --item-attributes=FILE.");
else
((IItemAttributeAwareRecommender)recommender).ItemAttributes = AttributeData.Read(Path.Combine(data_dir, item_attributes_file), item_mapping);
}
if (filtered_eval)
{
if (item_attributes_file == null)
Usage("--filtered-evaluation expects --item-attributes=FILE.");
else
item_attributes = AttributeData.Read(Path.Combine(data_dir, item_attributes_file), item_mapping);
}
// user relation
if (recommender is IUserRelationAwareRecommender)
if (user_relations_file == null)
{
Usage("Recommender expects --user-relation=FILE.");
}
else
{
((IUserRelationAwareRecommender)recommender).UserRelation = RelationData.Read(Path.Combine(data_dir, user_relations_file), user_mapping);
Console.WriteLine("relation over {0} users", ((IUserRelationAwareRecommender)recommender).NumUsers); // TODO move to DisplayDataStats
}
// item relation
if (recommender is IItemRelationAwareRecommender)
if (user_relations_file == null)
{
Usage("Recommender expects --item-relation=FILE.");
}
else
{
((IItemRelationAwareRecommender)recommender).ItemRelation = RelationData.Read(Path.Combine(data_dir, item_relations_file), item_mapping);
Console.WriteLine("relation over {0} items", ((IItemRelationAwareRecommender)recommender).NumItems); // TODO move to DisplayDataStats
}
// test data
if (test_ratio == 0)
{
if (test_file != null)
test_data = ItemRecommendation.Read(Path.Combine(data_dir, test_file), user_mapping, item_mapping);
}
else
{
var split = new PosOnlyFeedbackSimpleSplit<PosOnlyFeedback<SparseBooleanMatrix>>(training_data, test_ratio);
training_data = split.Train[0];
test_data = split.Test[0];
}
});
Console.Error.WriteLine(string.Format(CultureInfo.InvariantCulture, "loading_time {0,0:0.##}", loading_time.TotalSeconds));
}
public void TestOverlapCount()
{
var row25 = new int[] { 2, 5 };
var row36 = new int[] { 3, 6 };
var row15 = new int[] { 1, 5 };
var matrix = new SparseBooleanMatrixStatic();
matrix[2] = row25;
matrix[4] = row36;
matrix[5] = row15;
var overlapMatrix = new SparseBooleanMatrix();
overlapMatrix[2, 1] = true;
overlapMatrix[2, 5] = true; // same entry
overlapMatrix[4, 4] = true;
overlapMatrix[4, 6] = true; // same entry
overlapMatrix[5, 2] = true;
overlapMatrix[5, 5] = true; // same entry
Assert.AreEqual(3, matrix.Overlap(overlapMatrix));
}
[Test()] public void TestNonEmptyColumnIDs()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2 && i !=3)
{
matrix[1, i] = true;
matrix[4, i] = true;
}
Assert.AreEqual(3, matrix.NonEmptyColumnIDs.Count);
ICollection<int> colIDs = matrix.NonEmptyColumnIDs;
var colIDsEnum = colIDs.GetEnumerator();
colIDsEnum.MoveNext();
Assert.AreEqual(0, colIDsEnum.Current);
colIDsEnum.MoveNext();
Assert.AreEqual(1, colIDsEnum.Current);
colIDsEnum.MoveNext();
Assert.AreEqual(4, colIDsEnum.Current);
Assert.IsFalse(colIDsEnum.MoveNext());
}
static void LoadData(bool static_data)
{
training_file = Path.Combine(data_dir, training_file);
TimeSpan loading_time = Wrap.MeasureTime(delegate() {
// 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, 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;
// user attributes
if (user_attributes_file != null)
user_attributes = AttributeData.Read(Path.Combine(data_dir, user_attributes_file), user_mapping);
if (recommender is IUserAttributeAwareRecommender)
((IUserAttributeAwareRecommender)recommender).UserAttributes = user_attributes;
// item attributes
if (item_attributes_file != null)
item_attributes = AttributeData.Read(Path.Combine(data_dir, item_attributes_file), item_mapping);
if (recommender is IItemAttributeAwareRecommender)
((IItemAttributeAwareRecommender)recommender).ItemAttributes = item_attributes;
// user relation
if (recommender is IUserRelationAwareRecommender)
{
((IUserRelationAwareRecommender)recommender).UserRelation = RelationData.Read(Path.Combine(data_dir, user_relations_file), user_mapping);
Console.WriteLine("relation over {0} users", ((IUserRelationAwareRecommender)recommender).NumUsers);
}
// item relation
if (recommender is IItemRelationAwareRecommender)
{
((IItemRelationAwareRecommender)recommender).ItemRelation = RelationData.Read(Path.Combine(data_dir, item_relations_file), item_mapping);
Console.WriteLine("relation over {0} items", ((IItemRelationAwareRecommender)recommender).NumItems);
}
// read test data
if (test_file != null)
{
test_file = Path.Combine(data_dir, test_file);
if (recommender is TimeAwareRatingPredictor && file_format != RatingFileFormat.MOVIELENS_1M)
test_data = TimedRatingData.Read(test_file, user_mapping, item_mapping);
else if (file_format == RatingFileFormat.MOVIELENS_1M)
test_data = MovieLensRatingData.Read(test_file, user_mapping, item_mapping);
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, file_format == RatingFileFormat.IGNORE_FIRST_LINE);
}
});
Console.Error.WriteLine(string.Format(CultureInfo.InvariantCulture, "loading_time {0:0.##}", loading_time.TotalSeconds));
Console.Error.WriteLine("memory {0}", Memory.Usage);
}
protected void Run(string[] args)
{
Console.WriteLine("WISER-RecSys começou");
options = new OptionSet() {
// string-valued options
{ "arquivo=", v => arquivo = v },
{ "measures=", v => measures = v },
{ "recommender-options=", v => recommender_options += " " + v },
{ "help", v => show_help = v != null },
};
eval_measures = ItemRecommendationEvaluationResults.DefaultMeasuresToShow;
IList<string> extra_args = options.Parse(args);
if (show_help)
Usage(0);
//eval
if (measures != null)
eval_measures = measures.Split(' ', ',');
//Rodar o de vocs
//
training_file = "training.data";
test_file = "test.data";
training_partial_file = "training.partial.data";
test_partial_file = "test.partial.data";
for (int i = 0; i < arquivos.Length; i++)
{
MyMediaLite.Random.Seed = 1;
item_attributes_file = "movie_" + arquivos[i] + ".dat_saida";
user_mapping.Add(new Mapping());
item_mapping.Add(new Mapping());
//Setup recommender
recommenders.Add("BPRMFAttr".CreateItemRecommender());
recommenders[i].Configure(recommender_options, (string msg) =>
{
Console.Error.WriteLine(msg); Environment.Exit(-1);
});
// item attributes
if (recommenders[i] is IItemAttributeAwareRecommender && item_attributes_file == null)
Abort("Recommender expects --item-attributes=FILE.");
if (item_attributes_file != null)
item_attributes.Add(AttributeData.Read(item_attributes_file, item_mapping[i]));
if (recommenders[i] is IItemAttributeAwareRecommender)
((IItemAttributeAwareRecommender)recommenders[i]).ItemAttributes = item_attributes[i];
IBooleanMatrix lista_vazia = new SparseBooleanMatrix();
if (recommenders[i] is IUserAttributeAwareRecommender)
((IUserAttributeAwareRecommender)recommenders[i]).UserAttributes = lista_vazia;
// training data
training_data.Add(ItemData.Read(training_file, user_mapping[i], item_mapping[i], false));
test_data.Add(ItemData.Read(test_file, user_mapping[i], item_mapping[i], false));
test_users.Add(test_data[i].AllUsers);
//Probe
training_probe_data.Add(ItemData.Read(training_partial_file, user_mapping[i], item_mapping[i], false));
test_probe_data.Add(ItemData.Read(test_partial_file, user_mapping[i], item_mapping[i], false));
if (recommenders[i] is MyMediaLite.ItemRecommendation.ItemRecommender)
((ItemRecommender)recommenders[i]).Feedback = training_probe_data[i];
//Trainar
Console.WriteLine("Vamos ao probe training");
var train_time_span = Wrap.MeasureTime(delegate () { recommenders[i].Train(); });
Console.WriteLine("training_time " + train_time_span + " ");
}
Evaluation evaluation = new Evaluation(recommenders, test_probe_data, training_probe_data);
//Probe learn
Console.WriteLine("Probe learn started");
TimeSpan time_span = Wrap.MeasureTime(delegate () { evaluation.EvaluateProbe(test_users, user_mapping, item_mapping); });
Console.WriteLine(" Probe learn time: " + time_span);
for (int i = 0; i < arquivos.Length; i++)
{
MyMediaLite.Random.Seed = 1;
item_attributes_file = "movie_" + arquivos[i] + ".dat_saida";
//Setup recommender
recommenders[i] = "BPRMFAttr".CreateItemRecommender();
recommenders[i].Configure(recommender_options, (string msg) => { Console.Error.WriteLine(msg); Environment.Exit(-1); });
// item attributes
if (recommenders[i] is IItemAttributeAwareRecommender && item_attributes_file == null)
Abort("Recommender expects --item-attributes=FILE.");
if (recommenders[i] is IItemAttributeAwareRecommender)
((IItemAttributeAwareRecommender)recommenders[i]).ItemAttributes = item_attributes[i];
IBooleanMatrix lista_vazia = new SparseBooleanMatrix();
if (recommenders[i] is IUserAttributeAwareRecommender)
((IUserAttributeAwareRecommender)recommenders[i]).UserAttributes = lista_vazia;
if (recommenders[i] is MyMediaLite.ItemRecommendation.ItemRecommender)
((ItemRecommender)recommenders[i]).Feedback = training_data[i];
//Trainar
Console.WriteLine("Agora ao treino normal");
var train_time_span = Wrap.MeasureTime(delegate () { recommenders[i].Train(); });
Console.WriteLine("training_time " + train_time_span + " ");
}
var results = evaluation.Evaluate(test_data, training_data, test_users, user_mapping, item_mapping);
foreach (EvaluationResults result in results)
{
Console.WriteLine(result.ToString());
}
Console.WriteLine("Press any key to continue...");
Console.ReadKey();
}
///
public override void LearnAttributeToFactorMapping()
{
random = Util.Random.GetInstance();
// create helper data structure
this.data_item = new SparseBooleanMatrix();
for (int i = 0; i < ratings.Count; i++)
data_item[ratings.Items[i], ratings.Users[i]] = true;
// create attribute-to-factor weight matrix
this.attribute_to_factor = new Matrix<double>(NumItemAttributes + 1, NumFactors + 1);
// account for regression bias term, and the item bias that we want to model
// store the results of the different runs in the following array
var old_attribute_to_factor = new Matrix<double>[num_init_mapping];
Console.Error.WriteLine("Will use {0} examples ...", num_iter_mapping * MaxItemID);
var old_rmse_per_factor = new double[num_init_mapping][];
for (int h = 0; h < num_init_mapping; h++)
{
MatrixUtils.InitNormal(attribute_to_factor, InitMean, InitStdev);
Console.Error.WriteLine("----");
for (int i = 0; i < num_iter_mapping * MaxItemID; i++)
IterateMapping();
old_attribute_to_factor[h] = new Matrix<double>(attribute_to_factor);
old_rmse_per_factor[h] = ComputeMappingFit();
}
var min_rmse_per_factor = new double[NumFactors + 1];
for (int i = 0; i <= NumFactors; i++)
min_rmse_per_factor[i] = Double.MaxValue;
var best_factor_init = new int[NumFactors + 1];
// find best factor mappings:
for (int i = 0; i < num_init_mapping; i++)
for (int j = 0; j <= NumFactors; j++)
if (old_rmse_per_factor[i][j] < min_rmse_per_factor[j])
{
min_rmse_per_factor[j] = old_rmse_per_factor[i][j];
best_factor_init[j] = i;
}
// set the best weight combinations for each factor mapping
for (int i = 0; i <= NumFactors; i++)
{
Console.Error.WriteLine("Factor {0}, pick {1}", i, best_factor_init[i]);
attribute_to_factor.SetColumn(i,
old_attribute_to_factor[best_factor_init[i]].GetColumn(i)
);
}
}
[Test()] public void TestTranspose()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 7; i++)
if(i != 2 && i != 4)
{
matrix[i, 1] = true;
matrix[i, 4] = true;
}
matrix[2, 2] = true;
matrix[2, 5] = true;
matrix[4, 3] = true;
// transpose the matrix
var transposed_matrix = (IBooleanMatrix) matrix.Transpose();
// test the transposed matrix
Assert.IsTrue(transposed_matrix[1,0]);
Assert.IsTrue(transposed_matrix[4, 6]);
Assert.IsFalse(transposed_matrix[3, 1]);
Assert.IsFalse(transposed_matrix[5, 4]);
}
[Test()] public void TestOverlapCount()
{
var matrix = new SparseBooleanMatrix();
matrix[2, 2] = true;
matrix[2, 5] = true;
matrix[4, 3] = true;
matrix[4, 6] = true;
matrix[5, 1] = true;
matrix[5, 5] = true;
var overlapMatrix = new SparseBooleanMatrix();
overlapMatrix[2, 1] = true;
overlapMatrix[2, 5] = true; // same entry
overlapMatrix[4, 4] = true;
overlapMatrix[4, 6] = true; // same entry
overlapMatrix[5, 2] = true;
overlapMatrix[5, 5] = true; // same entry
Assert.AreEqual(3, matrix.Overlap(overlapMatrix));
}
[Test()] public void TestNumEntriesByColumn()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2 && i !=3)
{
matrix[i, 1] = true;
matrix[i, 4] = true;
}
Assert.AreEqual(0, matrix.NumEntriesByColumn(0));
Assert.AreEqual(3, matrix.NumEntriesByColumn(1));
Assert.AreEqual(0, matrix.NumEntriesByColumn(2));
Assert.AreEqual(0, matrix.NumEntriesByColumn(3));
Assert.AreEqual(3, matrix.NumEntriesByColumn(4));
}
static void LoadData()
{
TimeSpan loading_time = Wrap.MeasureTime(delegate() {
// training data
training_file = Path.Combine(data_dir, training_file);
training_data = double.IsNaN(rating_threshold)
? ItemData.Read(training_file, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE)
: ItemDataRatingThreshold.Read(training_file, rating_threshold, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE);
// user attributes
if (user_attributes_file != null)
user_attributes = AttributeData.Read(Path.Combine(data_dir, user_attributes_file), user_mapping);
if (recommender is IUserAttributeAwareRecommender)
((IUserAttributeAwareRecommender)recommender).UserAttributes = user_attributes;
// item attributes
if (item_attributes_file != null)
item_attributes = AttributeData.Read(Path.Combine(data_dir, item_attributes_file), item_mapping);
if (recommender is IItemAttributeAwareRecommender)
((IItemAttributeAwareRecommender)recommender).ItemAttributes = item_attributes;
// user relation
if (recommender is IUserRelationAwareRecommender)
{
((IUserRelationAwareRecommender)recommender).UserRelation = RelationData.Read(Path.Combine(data_dir, user_relations_file), user_mapping);
Console.WriteLine("relation over {0} users", ((IUserRelationAwareRecommender)recommender).NumUsers);
}
// item relation
if (recommender is IItemRelationAwareRecommender)
{
((IItemRelationAwareRecommender)recommender).ItemRelation = RelationData.Read(Path.Combine(data_dir, item_relations_file), item_mapping);
Console.WriteLine("relation over {0} items", ((IItemRelationAwareRecommender)recommender).NumItems);
}
// user groups
if (user_groups_file != null)
{
group_to_user = RelationData.Read(Path.Combine(data_dir, user_groups_file), user_mapping); // assumption: user and user group IDs are disjoint
user_groups = group_to_user.NonEmptyRowIDs;
Console.WriteLine("{0} user groups", user_groups.Count);
}
// test data
if (test_ratio == 0)
{
if (test_file != null)
{
test_file = Path.Combine(data_dir, test_file);
test_data = double.IsNaN(rating_threshold)
? ItemData.Read(test_file, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE)
: ItemDataRatingThreshold.Read(test_file, rating_threshold, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE);
}
}
else
{
var split = new PosOnlyFeedbackSimpleSplit<PosOnlyFeedback<SparseBooleanMatrix>>(training_data, test_ratio);
training_data = split.Train[0];
test_data = split.Test[0];
}
if (group_method == "GroupsAsUsers")
{
Console.WriteLine("group recommendation strategy: {0}", group_method);
// TODO verify what is going on here
//var training_data_group = new PosOnlyFeedback<SparseBooleanMatrix>();
// transform groups to users
foreach (int group_id in group_to_user.NonEmptyRowIDs)
foreach (int user_id in group_to_user[group_id])
foreach (int item_id in training_data.UserMatrix.GetEntriesByRow(user_id))
training_data.Add(group_id, item_id);
// add the users that do not belong to groups
//training_data = training_data_group;
// transform groups to users
var test_data_group = new PosOnlyFeedback<SparseBooleanMatrix>();
foreach (int group_id in group_to_user.NonEmptyRowIDs)
foreach (int user_id in group_to_user[group_id])
foreach (int item_id in test_data.UserMatrix.GetEntriesByRow(user_id))
test_data_group.Add(group_id, item_id);
test_data = test_data_group;
group_method = null; // deactivate s.t. the normal eval routines are used
}
if (user_prediction)
{
// swap file names for test users and candidate items
var ruf = test_users_file;
var rif = candidate_items_file;
test_users_file = rif;
candidate_items_file = ruf;
// swap user and item mappings
var um = user_mapping;
var im = item_mapping;
user_mapping = im;
item_mapping = um;
// transpose training and test data
training_data = training_data.Transpose();
// transpose test data
if (test_data != null)
test_data = test_data.Transpose();
}
if (recommender is MyMediaLite.ItemRecommendation.ItemRecommender)
((ItemRecommender)recommender).Feedback = training_data;
// test users
if (test_users_file != null)
test_users = user_mapping.ToInternalID( File.ReadLines(Path.Combine(data_dir, test_users_file)).ToArray() );
else
test_users = test_data != null ? test_data.AllUsers : training_data.AllUsers;
// if necessary, perform user sampling
if (num_test_users > 0 && num_test_users < test_users.Count)
{
var old_test_users = new HashSet<int>(test_users);
var new_test_users = new int[num_test_users];
for (int i = 0; i < num_test_users; i++)
{
int random_index = MyMediaLite.Util.Random.GetInstance().Next(old_test_users.Count - 1);
new_test_users[i] = old_test_users.ElementAt(random_index);
old_test_users.Remove(new_test_users[i]);
}
test_users = new_test_users;
}
// candidate items
if (candidate_items_file != null)
candidate_items = item_mapping.ToInternalID( File.ReadLines(Path.Combine(data_dir, candidate_items_file)).ToArray() );
else if (all_items)
candidate_items = Enumerable.Range(0, item_mapping.InternalIDs.Max() + 1).ToArray();
if (candidate_items != null)
eval_item_mode = CandidateItems.EXPLICIT;
else if (in_training_items)
eval_item_mode = CandidateItems.TRAINING;
else if (in_test_items)
eval_item_mode = CandidateItems.TEST;
else if (overlap_items)
eval_item_mode = CandidateItems.OVERLAP;
else
eval_item_mode = CandidateItems.UNION;
});
Console.Error.WriteLine(string.Format(CultureInfo.InvariantCulture, "loading_time {0,0:0.##}", loading_time.TotalSeconds));
Console.Error.WriteLine("memory {0}", Memory.Usage);
}
/// <summary>Display data statistics for item recommendation datasets</summary>
/// <param name="training_data">the training dataset</param>
/// <param name="test_data">the test dataset</param>
/// <param name="user_attributes">the user attributes</param>
/// <param name="item_attributes">the item attributes</param>
public static string Statistics(
this IPosOnlyFeedback training_data, IPosOnlyFeedback test_data = null,
SparseBooleanMatrix user_attributes = null, SparseBooleanMatrix item_attributes = null)
{
// training data stats
int num_users = training_data.AllUsers.Count;
int num_items = training_data.AllItems.Count;
long matrix_size = (long) num_users * num_items;
long empty_size = (long) matrix_size - training_data.Count;
double sparsity = (double) 100L * empty_size / matrix_size;
string s = string.Format(CultureInfo.InvariantCulture, "training data: {0} users, {1} items, {2} events, sparsity {3,0:0.#####}\n", num_users, num_items, training_data.Count, sparsity);
// test data stats
if (test_data != null)
{
num_users = test_data.AllUsers.Count;
num_items = test_data.AllItems.Count;
matrix_size = (long) num_users * num_items;
empty_size = (long) matrix_size - test_data.Count;
sparsity = (double) 100L * empty_size / matrix_size; // TODO depends on the eval scheme whether this is correct
s += string.Format(CultureInfo.InvariantCulture, "test data: {0} users, {1} items, {2} events, sparsity {3,0:0.#####}\n", num_users, num_items, test_data.Count, sparsity);
}
return s + Statistics(user_attributes, item_attributes);
}
/// <summary>Evaluation for rankings of items recommended to groups</summary>
/// <remarks>
/// </remarks>
/// <param name="recommender">group recommender</param>
/// <param name="test">test cases</param>
/// <param name="train">training data</param>
/// <param name="group_to_user">group to user relation</param>
/// <param name="candidate_items">a collection of integers with all candidate items</param>
/// <param name="ignore_overlap">if true, ignore items that appear for a group in the training set when evaluating for that user</param>
/// <returns>a dictionary containing the evaluation results</returns>
public static ItemRecommendationEvaluationResults Evaluate(
this GroupRecommender recommender,
IPosOnlyFeedback test,
IPosOnlyFeedback train,
SparseBooleanMatrix group_to_user,
ICollection<int> candidate_items,
bool ignore_overlap = true)
{
var result = new ItemRecommendationEvaluationResults();
int num_groups = 0;
foreach (int group_id in group_to_user.NonEmptyRowIDs)
{
var users = group_to_user.GetEntriesByRow(group_id);
var correct_items = new HashSet<int>();
foreach (int user_id in users)
correct_items.UnionWith(test.UserMatrix[user_id]);
correct_items.IntersectWith(candidate_items);
var candidate_items_in_train = new HashSet<int>();
foreach (int user_id in users)
candidate_items_in_train.UnionWith(train.UserMatrix[user_id]);
candidate_items_in_train.IntersectWith(candidate_items);
int num_eval_items = candidate_items.Count - (ignore_overlap ? candidate_items_in_train.Count() : 0);
// skip all groups that have 0 or #candidate_items test items
if (correct_items.Count == 0)
continue;
if (num_eval_items - correct_items.Count == 0)
continue;
IList<int> prediction_list = recommender.RankItems(users, candidate_items);
if (prediction_list.Count != candidate_items.Count)
throw new Exception("Not all items have been ranked.");
var ignore_items = ignore_overlap ? candidate_items_in_train : new HashSet<int>();
double auc = AUC.Compute(prediction_list, correct_items, ignore_items);
double map = PrecisionAndRecall.AP(prediction_list, correct_items, ignore_items);
double ndcg = NDCG.Compute(prediction_list, correct_items, ignore_items);
double rr = ReciprocalRank.Compute(prediction_list, correct_items, ignore_items);
var positions = new int[] { 5, 10 };
var prec = PrecisionAndRecall.PrecisionAt(prediction_list, correct_items, ignore_items, positions);
var recall = PrecisionAndRecall.RecallAt(prediction_list, correct_items, ignore_items, positions);
// thread-safe incrementing
lock(result)
{
num_groups++;
result["AUC"] += (float) auc;
result["MAP"] += (float) map;
result["NDCG"] += (float) ndcg;
result["MRR"] += (float) rr;
result["prec@5"] += (float) prec[5];
result["prec@10"] += (float) prec[10];
result["recall@5"] += (float) recall[5];
result["recall@10"] += (float) recall[10];
}
if (num_groups % 1000 == 0)
Console.Error.Write(".");
if (num_groups % 60000 == 0)
Console.Error.WriteLine();
}
result["num_groups"] = num_groups;
result["num_lists"] = num_groups;
result["num_items"] = candidate_items.Count;
return result;
}
/// <summary>Display statistics for user and item attributes</summary>
/// <param name="user_attributes">the user attributes</param>
/// <param name="item_attributes">the item attributes</param>
public static string Statistics(SparseBooleanMatrix user_attributes, SparseBooleanMatrix item_attributes)
{
string s = string.Empty;
if (user_attributes != null)
{
s += string.Format(
"{0} user attributes for {1} users, {2} assignments, {3} users with attribute assignments\n",
user_attributes.NumberOfColumns, user_attributes.NumberOfRows,
user_attributes.NumberOfEntries, user_attributes.NonEmptyRowIDs.Count);
}
if (item_attributes != null)
s += string.Format(
"{0} item attributes for {1} items, {2} assignments, {3} items with attribute assignments\n",
item_attributes.NonEmptyColumnIDs.Count, item_attributes.NumberOfRows,
item_attributes.NumberOfEntries, item_attributes.NonEmptyRowIDs.Count);
return s;
}
/// <summary>Read binary attribute data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">an IDataReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the attribute data</returns>
public static SparseBooleanMatrix Read(IDataReader reader, IEntityMapping mapping)
{
if (reader.FieldCount < 2)
throw new Exception("Expected at least 2 columns.");
var matrix = new SparseBooleanMatrix();
while (!reader.Read())
{
int entity_id = mapping.ToInternalID(reader.GetString(0));
int attr_id = reader.GetInt32(1);
matrix[entity_id, attr_id] = true;
}
return matrix;
}
[Test()] public void TestNumberOfEntries()
{
var matrix = new SparseBooleanMatrix();
for (int i = 0; i < 5; i++)
if (i != 2 && i != 4)
{
matrix[i, 1] = true;
matrix[i, 4] = false;
}
Assert.AreEqual(3, matrix.NumberOfEntries);
}
